diff options
193 files changed, 7585 insertions, 8431 deletions
diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 2fea0120e..d82ff9111 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.28 + [debug] youtube-dl version 2020.03.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 6116acc79..04b350f76 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 79d1a7f3c..6f17ad7bc 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 9bda3d440..efb179ea5 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.28 + [debug] youtube-dl version 2020.03.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 581344917..cf4874bcc 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/.travis.yml b/.travis.yml index 6d16c2955..51afd469a 100644 --- a/.travis.yml +++ b/.travis.yml @@ -13,7 +13,7 @@ dist: trusty env: - YTDL_TEST_SET=core - YTDL_TEST_SET=download -matrix: +jobs: include: - python: 3.7 dist: xenial @@ -21,6 +21,12 @@ matrix: - python: 3.7 dist: xenial env: YTDL_TEST_SET=download + - python: 3.8 + dist: xenial + env: YTDL_TEST_SET=core + - python: 3.8 + dist: xenial + env: YTDL_TEST_SET=download - python: 3.8-dev dist: xenial env: YTDL_TEST_SET=core @@ -29,6 +35,11 @@ matrix: env: YTDL_TEST_SET=download - env: JYTHON=true; YTDL_TEST_SET=core - env: JYTHON=true; YTDL_TEST_SET=download + - name: flake8 + python: 3.8 + dist: xenial + install: pip install flake8 + script: flake8 . fast_finish: true allow_failures: - env: YTDL_TEST_SET=download @@ -1,3 +1,441 @@ +version 2020.03.08 + +Core ++ [utils] Add support for cookie files with spaces + +Extractors ++ [pornhub] Add support for pornhubpremium.com (#24288) +- [youtube] Remove outdated code and unnecessary requests +* [youtube] Improve extraction in 429 HTTP error conditions (#24283) +* [nhk] Update API version (#24270) + + +version 2020.03.06 + +Extractors +* [youtube] Fix age-gated videos support without login (#24248) +* [vimeo] Fix showcase password protected video extraction (#24224) +* [pornhub] Improve title extraction (#24184) +* [peertube] Improve extraction (#23657) ++ [servus] Add support for new URL schema (#23475, #23583, #24142) +* [vimeo] Fix subtitles URLs (#24209) + + +version 2020.03.01 + +Core +* [YoutubeDL] Force redirect URL to unicode on python 2 +- [options] Remove duplicate short option -v for --version (#24162) + +Extractors +* [xhamster] Fix extraction (#24205) +* [franceculture] Fix extraction (#24204) ++ [telecinco] Add support for article opening videos +* [telecinco] Fix extraction (#24195) +* [xtube] Fix metadata extraction (#21073, #22455) +* [youjizz] Fix extraction (#24181) +- Remove no longer needed compat_str around geturl +* [pornhd] Fix extraction (#24128) ++ [teachable] Add support for multiple videos per lecture (#24101) ++ [wistia] Add support for multiple generic embeds (#8347, 11385) +* [imdb] Fix extraction (#23443) +* [tv2dk:bornholm:play] Fix extraction (#24076) + + +version 2020.02.16 + +Core +* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591, + #10622) +* [update] Fix updating via symlinks (#23991) ++ [compat] Introduce compat_realpath (#23991) + +Extractors ++ [npr] Add support for streams (#24042) ++ [24video] Add support for porn.24video.net (#23779, #23784) +- [jpopsuki] Remove extractor (#23858) +* [nova] Improve extraction (#23690) +* [nova:embed] Improve (#23690) +* [nova:embed] Fix extraction (#23672) ++ [abc:iview] Add support for 720p (#22907, #22921) +* [nytimes] Improve format sorting (#24010) ++ [toggle] Add support for mewatch.sg (#23895, #23930) +* [thisoldhouse] Fix extraction (#23951) ++ [popcorntimes] Add support for popcorntimes.tv (#23949) +* [sportdeutschland] Update to new API +* [twitch:stream] Lowercase channel id for stream request (#23917) +* [tv5mondeplus] Fix extraction (#23907, #23911) +* [tva] Relax URL regular expression (#23903) +* [vimeo] Fix album extraction (#23864) +* [viewlift] Improve extraction + * Fix extraction (#23851) + + Add support for authentication + + Add support for more domains +* [svt] Fix series extraction (#22297) +* [svt] Fix article extraction (#22897, #22919) +* [soundcloud] Imporve private playlist/set tracks extraction (#3707) + + +version 2020.01.24 + +Extractors +* [youtube] Fix sigfunc name extraction (#23819) +* [stretchinternet] Fix extraction (#4319) +* [voicerepublic] Fix extraction +* [azmedien] Fix extraction (#23783) +* [businessinsider] Fix jwplatform id extraction (#22929, #22954) ++ [24video] Add support for 24video.vip (#23753) +* [ivi:compilation] Fix entries extraction (#23770) +* [ard] Improve extraction (#23761) + * Simplify extraction + + Extract age limit and series + * Bypass geo-restriction ++ [nbc] Add support for nbc multi network URLs (#23049) +* [americastestkitchen] Fix extraction +* [zype] Improve extraction + + Extract subtitles (#21258) + + Support URLs with alternative keys/tokens (#21258) + + Extract more metadata +* [orf:tvthek] Improve geo restricted videos detection (#23741) +* [soundcloud] Restore previews extraction (#23739) + + +version 2020.01.15 + +Extractors +* [yourporn] Fix extraction (#21645, #22255, #23459) ++ [canvas] Add support for new API endpoint (#17680, #18629) +* [ndr:base:embed] Improve thumbnails extraction (#23731) ++ [vodplatform] Add support for embed.kwikmotion.com domain ++ [twitter] Add support for promo_video_website cards (#23711) +* [orf:radio] Clean description and improve extraction +* [orf:fm4] Fix extraction (#23599) +* [safari] Fix kaltura session extraction (#23679, #23670) +* [lego] Fix extraction and extract subtitle (#23687) +* [cloudflarestream] Improve extraction + + Add support for bytehighway.net domain + + Add support for signed URLs + + Extract thumbnail +* [naver] Improve extraction + * Improve geo-restriction handling + + Extract automatic captions + + Extract uploader metadata + + Extract VLive HLS formats + * Improve metadata extraction +- [pandatv] Remove extractor (#23630) +* [dctp] Fix format extraction (#23656) ++ [scrippsnetworks] Add support for www.discovery.com videos +* [discovery] Fix anonymous token extraction (#23650) +* [nrktv:seriebase] Fix extraction (#23625, #23537) +* [wistia] Improve format extraction and extract subtitles (#22590) +* [vice] Improve extraction (#23631) +* [redtube] Detect private videos (#23518) + + +version 2020.01.01 + +Extractors +* [brightcove] Invalidate policy key cache on failing requests +* [pornhub] Improve locked videos detection (#22449, #22780) ++ [pornhub] Add support for m3u8 formats +* [pornhub] Fix extraction (#22749, #23082) +* [brightcove] Update policy key on failing requests +* [spankbang] Improve removed video detection (#23423) +* [spankbang] Fix extraction (#23307, #23423, #23444) +* [soundcloud] Automatically update client id on failing requests +* [prosiebensat1] Improve geo restriction handling (#23571) +* [brightcove] Cache brightcove player policy keys +* [teachable] Fail with error message if no video URL found +* [teachable] Improve locked lessons detection (#23528) ++ [scrippsnetworks] Add support for Scripps Networks sites (#19857, #22981) +* [mitele] Fix extraction (#21354, #23456) +* [soundcloud] Update client id (#23516) +* [mailru] Relax URL regular expressions (#23509) + + +version 2019.12.25 + +Core +* [utils] Improve str_to_int ++ [downloader/hls] Add ability to override AES decryption key URL (#17521) + +Extractors +* [mediaset] Fix parse formats (#23508) ++ [tv2dk:bornholm:play] Add support for play.tv2bornholm.dk (#23291) ++ [slideslive] Add support for url and vimeo service names (#23414) +* [slideslive] Fix extraction (#23413) +* [twitch:clips] Fix extraction (#23375) ++ [soundcloud] Add support for token protected embeds (#18954) +* [vk] Improve extraction + * Fix User Videos extraction (#23356) + * Extract all videos for lists with more than 1000 videos (#23356) + + Add support for video albums (#14327, #14492) +- [kontrtube] Remove extractor +- [videopremium] Remove extractor +- [musicplayon] Remove extractor (#9225) ++ [ufctv] Add support for ufcfightpass.imgdge.com and + ufcfightpass.imggaming.com (#23343) ++ [twitch] Extract m3u8 formats frame rate (#23333) ++ [imggaming] Add support for playlists and extract subtitles ++ [ufcarabia] Add support for UFC Arabia (#23312) +* [ufctv] Fix extraction +* [yahoo] Fix gyao brightcove player id (#23303) +* [vzaar] Override AES decryption key URL (#17521) ++ [vzaar] Add support for AES HLS manifests (#17521, #23299) +* [nrl] Fix extraction +* [teachingchannel] Fix extraction +* [nintendo] Fix extraction and partially add support for Nintendo Direct + videos (#4592) ++ [ooyala] Add better fallback values for domain and streams variables ++ [youtube] Add support youtubekids.com (#23272) +* [tv2] Detect DRM protection ++ [tv2] Add support for katsomo.fi and mtv.fi (#10543) +* [tv2] Fix tv2.no article extraction +* [msn] Improve extraction + + Add support for YouTube and NBCSports embeds + + Add support for articles with multiple videos + * Improve AOL embed support + * Improve format extraction +* [abcotvs] Relax URL regular expression and improve metadata extraction + (#18014) +* [channel9] Reduce response size +* [adobetv] Improve extaction + * Use OnDemandPagedList for list extractors + * Reduce show extraction requests + * Extract original video format and subtitles + + Add support for adobe tv embeds + + +version 2019.11.28 + +Core ++ [utils] Add generic caesar cipher and rot47 +* [utils] Handle rd-suffixed day parts in unified_strdate (#23199) + +Extractors +* [vimeo] Improve extraction + * Fix review extraction + * Fix ondemand extraction + * Make password protected player case as an expected error (#22896) + * Simplify channel based extractors code +- [openload] Remove extractor (#11999) +- [verystream] Remove extractor +- [streamango] Remove extractor (#15406) +* [dailymotion] Improve extraction + * Extract http formats included in m3u8 manifest + * Fix user extraction (#3553, #21415) + + Add suport for User Authentication (#11491) + * Fix password protected videos extraction (#23176) + * Respect age limit option and family filter cookie value (#18437) + * Handle video url playlist query param + * Report allowed countries for geo-restricted videos +* [corus] Improve extraction + + Add support for Series Plus, W Network, YTV, ABC Spark, disneychannel.com + and disneylachaine.ca (#20861) + + Add support for self hosted videos (#22075) + * Detect DRM protection (#14910, #9164) +* [vivo] Fix extraction (#22328, #22279) ++ [bitchute] Extract upload date (#22990, #23193) +* [soundcloud] Update client id (#23214) + + +version 2019.11.22 + +Core ++ [extractor/common] Clean jwplayer description HTML tags ++ [extractor/common] Add data, headers and query to all major extract formats + methods + +Extractors +* [chaturbate] Fix extraction (#23010, #23012) ++ [ntvru] Add support for non relative file URLs (#23140) +* [vk] Fix wall audio thumbnails extraction (#23135) +* [ivi] Fix format extraction (#21991) +- [comcarcoff] Remove extractor ++ [drtv] Add support for new URL schema (#23059) ++ [nexx] Add support for Multi Player JS Setup (#23052) ++ [teamcoco] Add support for new videos (#23054) +* [soundcloud] Check if the soundtrack has downloads left (#23045) +* [facebook] Fix posts video data extraction (#22473) +- [addanime] Remove extractor +- [minhateca] Remove extractor +- [daisuki] Remove extractor +* [seeker] Fix extraction +- [revision3] Remove extractors +* [twitch] Fix video comments URL (#18593, #15828) +* [twitter] Improve extraction + + Add support for generic embeds (#22168) + * Always extract http formats for native videos (#14934) + + Add support for Twitter Broadcasts (#21369) + + Extract more metadata + * Improve VMap format extraction + * Unify extraction code for both twitter statuses and cards ++ [twitch] Add support for Clip embed URLs +* [lnkgo] Fix extraction (#16834) +* [mixcloud] Improve extraction + * Improve metadata extraction (#11721) + * Fix playlist extraction (#22378) + * Fix user mixes extraction (#15197, #17865) ++ [kinja] Add support for Kinja embeds (#5756, #11282, #22237, #22384) +* [onionstudios] Fix extraction ++ [hotstar] Pass Referer header to format requests (#22836) +* [dplay] Minimize response size ++ [patreon] Extract uploader_id and filesize +* [patreon] Minimize response size +* [roosterteeth] Fix login request (#16094, #22689) + + +version 2019.11.05 + +Extractors ++ [scte] Add support for learning.scte.org (#22975) ++ [msn] Add support for Vidible and AOL embeds (#22195, #22227) +* [myspass] Fix video URL extraction and improve metadata extraction (#22448) +* [jamendo] Improve extraction + * Fix album extraction (#18564) + * Improve metadata extraction (#18565, #21379) +* [mediaset] Relax URL guid matching (#18352) ++ [mediaset] Extract unprotected M3U and MPD manifests (#17204) +* [telegraaf] Fix extraction ++ [bellmedia] Add support for marilyn.ca videos (#22193) +* [stv] Fix extraction (#22928) +- [iconosquare] Remove extractor +- [keek] Remove extractor +- [gameone] Remove extractor (#21778) +- [flipagram] Remove extractor +- [bambuser] Remove extractor +* [wistia] Reduce embed extraction false positives ++ [wistia] Add support for inline embeds (#22931) +- [go90] Remove extractor +* [kakao] Remove raw request ++ [kakao] Extract format total bitrate +* [daum] Fix VOD and Clip extracton (#15015) +* [kakao] Improve extraction + + Add support for embed URLs + + Add support for Kakao Legacy vid based embed URLs + * Only extract fields used for extraction + * Strip description and extract tags +* [mixcloud] Fix cloudcast data extraction (#22821) +* [yahoo] Improve extraction + + Add support for live streams (#3597, #3779, #22178) + * Bypass cookie consent page for european domains (#16948, #22576) + + Add generic support for embeds (#20332) +* [tv2] Fix and improve extraction (#22787) ++ [tv2dk] Add support for TV2 DK sites +* [onet] Improve extraction … + + Add support for onet100.vod.pl + + Extract m3u8 formats + * Correct audio only format info +* [fox9] Fix extraction + + +version 2019.10.29 + +Core +* [utils] Actualize major IPv4 address blocks per country + +Extractors ++ [go] Add support for abc.com and freeform.com (#22823, #22864) ++ [mtv] Add support for mtvjapan.com +* [mtv] Fix extraction for mtv.de (#22113) +* [videodetective] Fix extraction +* [internetvideoarchive] Fix extraction +* [nbcnews] Fix extraction (#12569, #12576, #21703, #21923) +- [hark] Remove extractor +- [tutv] Remove extractor +- [learnr] Remove extractor +- [macgamestore] Remove extractor +* [la7] Update Kaltura service URL (#22358) +* [thesun] Fix extraction (#16966) +- [makertv] Remove extractor ++ [tenplay] Add support for 10play.com.au (#21446) +* [soundcloud] Improve extraction + * Improve format extraction (#22123) + + Extract uploader_id and uploader_url (#21916) + + Extract all known thumbnails (#19071, #20659) + * Fix extration for private playlists (#20976) + + Add support for playlist embeds (#20976) + * Skip preview formats (#22806) +* [dplay] Improve extraction + + Add support for dplay.fi, dplay.jp and es.dplay.com (#16969) + * Fix it.dplay.com extraction (#22826) + + Extract creator, tags and thumbnails + * Handle playback API call errors ++ [discoverynetworks] Add support for dplay.co.uk +* [vk] Improve extraction + + Add support for Odnoklassniki embeds + + Extract more videos from user lists (#4470) + + Fix wall post audio extraction (#18332) + * Improve error detection (#22568) ++ [odnoklassniki] Add support for embeds +* [puhutv] Improve extraction + * Fix subtitles extraction + * Transform HLS URLs to HTTP URLs + * Improve metadata extraction +* [ceskatelevize] Skip DRM media ++ [facebook] Extract subtitles (#22777) +* [globo] Handle alternative hash signing method + + +version 2019.10.22 + +Core +* [utils] Improve subtitles_filename (#22753) + +Extractors +* [facebook] Bypass download rate limits (#21018) ++ [contv] Add support for contv.com +- [viewster] Remove extractor +* [xfileshare] Improve extractor (#17032, #17906, #18237, #18239) + * Update the list of domains + + Add support for aa-encoded video data + * Improve jwplayer format extraction + + Add support for Clappr sources +* [mangomolo] Fix video format extraction and add support for player URLs +* [audioboom] Improve metadata extraction +* [twitch] Update VOD URL matching (#22395, #22727) +- [mit] Remove support for video.mit.edu (#22403) +- [servingsys] Remove extractor (#22639) +* [dumpert] Fix extraction (#22428, #22564) +* [atresplayer] Fix extraction (#16277, #16716) + + +version 2019.10.16 + +Core +* [extractor/common] Make _is_valid_url more relaxed + +Extractors +* [vimeo] Improve album videos id extraction (#22599) ++ [globo] Extract subtitles (#22713) +* [bokecc] Improve player params extraction (#22638) +* [nexx] Handle result list (#22666) +* [vimeo] Fix VHX embed extraction +* [nbc] Switch to graphql API (#18581, #22693, #22701) +- [vessel] Remove extractor +- [promptfile] Remove extractor (#6239) +* [kaltura] Fix service URL extraction (#22658) +* [kaltura] Fix embed info strip (#22658) +* [globo] Fix format extraction (#20319) +* [redtube] Improve metadata extraction (#22492, #22615) +* [pornhub:uservideos:upload] Fix extraction (#22619) ++ [telequebec:squat] Add support for squat.telequebec.tv (#18503) +- [wimp] Remove extractor (#22088, #22091) ++ [gfycat] Extend URL regular expression (#22225) ++ [chaturbate] Extend URL regular expression (#22309) +* [peertube] Update instances (#22414) ++ [telequebec] Add support for coucou.telequebec.tv (#22482) ++ [xvideos] Extend URL regular expression (#22471) +- [youtube] Remove support for invidious.enkirton.net (#22543) ++ [openload] Add support for oload.monster (#22592) +* [nrktv:seriebase] Fix extraction (#22596) ++ [youtube] Add support for yt.lelux.fi (#22597) +* [orf:tvthek] Make manifest requests non fatal (#22578) +* [teachable] Skip login when already logged in (#22572) +* [viewlift] Improve extraction (#22545) +* [nonktube] Fix extraction (#22544) + + version 2019.09.28 Core @@ -353,7 +791,7 @@ Extractors version 2019.04.17 Extractors -* [openload] Randomize User-Agent (closes #20688) +* [openload] Randomize User-Agent (#20688) + [openload] Add support for oladblock domains (#20471) * [adn] Fix subtitle extraction (#12724) + [aol] Add support for localized websites @@ -918,7 +1356,7 @@ Extractors + [youtube] Extract channel meta fields (#9676, #12939) * [porntube] Fix extraction (#17541) * [asiancrush] Fix extraction (#15630) -+ [twitch:clips] Extend URL regular expression (closes #17559) ++ [twitch:clips] Extend URL regular expression (#17559) + [vzaar] Add support for HLS * [tube8] Fix metadata extraction (#17520) * [eporner] Extract JSON-LD (#17519) @@ -752,8 +752,8 @@ As a last resort, you can also uninstall the version installed by your package m Afterwards, simply follow [our manual installation instructions](https://ytdl-org.github.io/youtube-dl/download.html): ``` -sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl -sudo chmod a+x /usr/local/bin/youtube-dl +sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl +sudo chmod a+rx /usr/local/bin/youtube-dl hash -r ``` @@ -835,7 +835,9 @@ In February 2015, the new YouTube player contained a character sequence in a str ### HTTP Error 429: Too Many Requests or 402: Payment Required -These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. +These two error codes indicate that the service is blocking your IP address because of overuse. Usually this is a soft block meaning that you can gain access again after solving CAPTCHA. Just open a browser and solve a CAPTCHA the service suggests you and after that [pass cookies](#how-do-i-pass-cookies-to-youtube-dl) to youtube-dl. Note that if your machine has multiple external IPs then you should also pass exactly the same IP you've used for solving CAPTCHA with [`--source-address`](#network-options). Also you may need to pass a `User-Agent` HTTP header of your browser with [`--user-agent`](#workarounds). + +If this is not the case (no CAPTCHA suggested to solve by the service) then you can contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. ### SyntaxError: Non-ASCII character diff --git a/devscripts/create-github-release.py b/devscripts/create-github-release.py index 428111b3f..2ddfa1096 100644 --- a/devscripts/create-github-release.py +++ b/devscripts/create-github-release.py @@ -1,7 +1,6 @@ #!/usr/bin/env python from __future__ import unicode_literals -import base64 import io import json import mimetypes @@ -15,7 +14,6 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from youtube_dl.compat import ( compat_basestring, - compat_input, compat_getpass, compat_print, compat_urllib_request, @@ -40,28 +38,20 @@ class GitHubReleaser(object): try: info = netrc.netrc().authenticators(self._NETRC_MACHINE) if info is not None: - self._username = info[0] - self._password = info[2] + self._token = info[2] compat_print('Using GitHub credentials found in .netrc...') return else: compat_print('No GitHub credentials found in .netrc') except (IOError, netrc.NetrcParseError): compat_print('Unable to parse .netrc') - self._username = compat_input( - 'Type your GitHub username or email address and press [Return]: ') - self._password = compat_getpass( - 'Type your GitHub password and press [Return]: ') + self._token = compat_getpass( + 'Type your GitHub PAT (personal access token) and press [Return]: ') def _call(self, req): if isinstance(req, compat_basestring): req = sanitized_Request(req) - # Authorizing manually since GitHub does not response with 401 with - # WWW-Authenticate header set (see - # https://developer.github.com/v3/#basic-authentication) - b64 = base64.b64encode( - ('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii') - req.add_header('Authorization', 'Basic %s' % b64) + req.add_header('Authorization', 'token %s' % self._token) response = self._opener.open(req).read().decode('utf-8') return json.loads(response) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 35275278b..02bc088ab 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -26,13 +26,13 @@ - **AcademicEarth:Course** - **acast** - **acast:channel** - - **AddAnime** - **ADN**: Anime Digital Network - **AdobeConnect** - - **AdobeTV** - - **AdobeTVChannel** - - **AdobeTVShow** - - **AdobeTVVideo** + - **adobetv** + - **adobetv:channel** + - **adobetv:embed** + - **adobetv:show** + - **adobetv:video** - **AdultSwim** - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault - **afreecatv**: afreecatv.com @@ -76,8 +76,6 @@ - **awaan:video** - **AZMedien**: AZ Medien videos - **BaiduVideo**: 百度视频 - - **bambuser** - - **bambuser:channel** - **Bandcamp** - **Bandcamp:album** - **Bandcamp:weekly** @@ -177,12 +175,12 @@ - **CNN** - **CNNArticle** - **CNNBlogs** - - **ComCarCoff** - **ComedyCentral** - **ComedyCentralFullEpisodes** - **ComedyCentralShortname** - **ComedyCentralTV** - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED + - **CONtv** - **Corus** - **Coub** - **Cracked** @@ -204,8 +202,6 @@ - **dailymotion** - **dailymotion:playlist** - **dailymotion:user** - - **DaisukiMotto** - - **DaisukiMottoPlaylist** - **daum.net** - **daum.net:clip** - **daum.net:playlist** @@ -231,7 +227,6 @@ - **DouyuShow** - **DouyuTV**: 斗鱼 - **DPlay** - - **DPlayIt** - **DRBonanza** - **Dropbox** - **DrTuber** @@ -284,12 +279,12 @@ - **FiveThirtyEight** - **FiveTV** - **Flickr** - - **Flipagram** - **Folketinget**: Folketinget (ft.dk; Danish parliament) - **FootyRoom** - **Formula1** - **FOX** - **FOX9** + - **FOX9News** - **Foxgay** - **foxnews**: Fox News and Fox Business Video - **foxnews:article** @@ -315,8 +310,6 @@ - **FXNetworks** - **Gaia** - **GameInformer** - - **GameOne** - - **gameone:playlist** - **GameSpot** - **GameStar** - **Gaskrank** @@ -331,14 +324,12 @@ - **Globo** - **GloboArticle** - **Go** - - **Go90** - **GodTube** - **Golem** - **GoogleDrive** - **Goshgay** - **GPUTechConf** - **Groupon** - - **Hark** - **hbo** - **HearThisAt** - **Heise** @@ -367,7 +358,6 @@ - **Hungama** - **HungamaSong** - **Hypem** - - **Iconosquare** - **ign.com** - **imdb**: Internet Movie Database trailers - **imdb:list**: Internet Movie Database lists @@ -399,7 +389,6 @@ - **JeuxVideo** - **Joj** - **Jove** - - **jpopsuki.tv** - **JWPlatform** - **Kakao** - **Kaltura** @@ -407,14 +396,14 @@ - **Kankan** - **Karaoketv** - **KarriereVideos** - - **keek** + - **Katsomo** - **KeezMovies** - **Ketnet** - **KhanAcademy** - **KickStarter** + - **KinjaEmbed** - **KinoPoisk** - **KonserthusetPlay** - - **kontrtube**: KontrTube.ru - Труба зовёт - **KrasView**: Красвью - **Ku6** - **KUSI** @@ -431,7 +420,6 @@ - **Lcp** - **LcpPlay** - **Le**: 乐视网 - - **Learnr** - **Lecture2Go** - **Lecturio** - **LecturioCourse** @@ -465,11 +453,9 @@ - **lynda**: lynda.com videos - **lynda:course**: lynda.com online courses - **m6** - - **macgamestore**: MacGameStore trailers - **mailru**: Видео@Mail.Ru - **mailru:music**: Музыка@Mail.Ru - **mailru:music:search**: Музыка@Mail.Ru - - **MakerTV** - **MallTV** - **mangomolo:live** - **mangomolo:video** @@ -496,14 +482,12 @@ - **Mgoon** - **MGTV**: 芒果TV - **MiaoPai** - - **Minhateca** - **MinistryGrid** - **Minoto** - **miomio.tv** - **MiTele**: mitele.es - **mixcloud** - **mixcloud:playlist** - - **mixcloud:stream** - **mixcloud:user** - **Mixer:live** - **Mixer:vod** @@ -525,11 +509,10 @@ - **mtg**: MTG services - **mtv** - **mtv.de** - - **mtv81** - **mtv:video** + - **mtvjapan** - **mtvservices:embedded** - **MuenchenTV**: münchen.tv - - **MusicPlayOn** - **mva**: Microsoft Virtual Academy videos - **mva:course**: Microsoft Virtual Academy courses - **Mwave** @@ -634,7 +617,6 @@ - **OnionStudios** - **Ooyala** - **OoyalaExternal** - - **Openload** - **OraTV** - **orf:fm4**: radio FM4 - **orf:fm4:story**: fm4.orf.at stories @@ -645,7 +627,6 @@ - **OutsideTV** - **PacktPub** - **PacktPubCourse** - - **PandaTV**: 熊猫TV - **pandora.tv**: 판도라TV - **ParamountNetwork** - **parliamentlive.tv**: UK parliament videos @@ -681,6 +662,7 @@ - **Pokemon** - **PolskieRadio** - **PolskieRadioCategory** + - **Popcorntimes** - **PopcornTV** - **PornCom** - **PornerBros** @@ -694,7 +676,6 @@ - **PornoXO** - **PornTube** - **PressTV** - - **PromptFile** - **prosiebensat1**: ProSiebenSat.1 Digital - **puhutv** - **puhutv:serie** @@ -735,8 +716,6 @@ - **Restudy** - **Reuters** - **ReverbNation** - - **revision** - - **revision3:embed** - **RICE** - **RMCDecouverte** - **RockstarGames** @@ -781,11 +760,13 @@ - **screen.yahoo:search**: Yahoo screen search - **Screencast** - **ScreencastOMatic** + - **ScrippsNetworks** - **scrippsnetworks:watch** + - **SCTE** + - **SCTECourse** - **Seeker** - **SenateISVP** - **SendtoNews** - - **ServingSys** - **Servus** - **Sexu** - **SeznamZpravy** @@ -816,6 +797,7 @@ - **soundcloud:set** - **soundcloud:trackstation** - **soundcloud:user** + - **SoundcloudEmbed** - **soundgasm** - **soundgasm:profile** - **southpark.cc.com** @@ -842,7 +824,6 @@ - **Steam** - **Stitcher** - **Streamable** - - **Streamango** - **streamcloud.eu** - **StreamCZ** - **StreetVoice** @@ -884,9 +865,11 @@ - **TeleQuebec** - **TeleQuebecEmission** - **TeleQuebecLive** + - **TeleQuebecSquat** - **TeleTask** - **Telewebion** - **TennisTV** + - **TenPlay** - **TF1** - **TFO** - **TheIntercept** @@ -925,11 +908,12 @@ - **tunein:topic** - **TunePk** - **Turbo** - - **Tutv** - **tv.dfb.de** - **TV2** - **tv2.hu** - **TV2Article** + - **TV2DK** + - **TV2DKBornholmPlay** - **TV4**: tv4.se and tv4play.se - **TV5MondePlus**: TV5MONDE+ - **TVA** @@ -966,10 +950,12 @@ - **twitch:vod** - **twitter** - **twitter:amplify** + - **twitter:broadcast** - **twitter:card** - **udemy** - **udemy:course** - **UDNEmbed**: 聯合影音 + - **UFCArabia** - **UFCTV** - **UKTVPlay** - **umg:de**: Universal Music Deutschland @@ -990,8 +976,6 @@ - **Vbox7** - **VeeHD** - **Veoh** - - **verystream** - - **Vessel** - **Vesti**: Вести.Ru - **Vevo** - **VevoPlaylist** @@ -1006,13 +990,11 @@ - **Viddler** - **Videa** - **video.google:search**: Google Video search - - **video.mit.edu** - **VideoDetective** - **videofy.me** - **videomore** - **videomore:season** - **videomore:video** - - **VideoPremium** - **VideoPress** - **Vidio** - **VidLii** @@ -1022,9 +1004,8 @@ - **Vidzi** - **vier**: vier.be and vijf.be - **vier:videos** - - **ViewLift** - - **ViewLiftEmbed** - - **Viewster** + - **viewlift** + - **viewlift:embed** - **Viidea** - **viki** - **viki:channel** @@ -1090,7 +1071,6 @@ - **Weibo** - **WeiboMobile** - **WeiqiTV**: WQTV - - **Wimp** - **Wistia** - **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **WorldStarHipHop** @@ -1099,7 +1079,7 @@ - **WWE** - **XBef** - **XboxClips** - - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me + - **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing - **XHamster** - **XHamsterEmbed** - **XHamsterUser** diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index ce9666171..1e204e551 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -816,11 +816,15 @@ class TestYoutubeDL(unittest.TestCase): 'webpage_url': 'http://example.com', } - def get_ids(params): + def get_downloaded_info_dicts(params): ydl = YDL(params) - # make a copy because the dictionary can be modified - ydl.process_ie_result(playlist.copy()) - return [int(v['id']) for v in ydl.downloaded_info_dicts] + # make a deep copy because the dictionary and nested entries + # can be modified + ydl.process_ie_result(copy.deepcopy(playlist)) + return ydl.downloaded_info_dicts + + def get_ids(params): + return [int(v['id']) for v in get_downloaded_info_dicts(params)] result = get_ids({}) self.assertEqual(result, [1, 2, 3, 4]) @@ -852,6 +856,22 @@ class TestYoutubeDL(unittest.TestCase): result = get_ids({'playlist_items': '2-4,3-4,3'}) self.assertEqual(result, [2, 3, 4]) + # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591 + # @{ + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + self.assertEqual(result[2]['playlist_index'], 4) + + result = get_downloaded_info_dicts({'playlist_items': '4,2'}) + self.assertEqual(result[0]['playlist_index'], 4) + self.assertEqual(result[1]['playlist_index'], 2) + # @} + def test_urlopen_no_file_protocol(self): # see https://github.com/ytdl-org/youtube-dl/issues/8227 ydl = YDL() diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 465ce0050..81056a999 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -123,12 +123,6 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs']) self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs']) - def test_yahoo_https(self): - # https://github.com/ytdl-org/youtube-dl/issues/2701 - self.assertMatch( - 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', - ['Yahoo']) - def test_no_duplicated_ie_names(self): name_accu = collections.defaultdict(list) for ie in self.ies: diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 7d57a628e..17aaaf20d 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -26,7 +26,6 @@ from youtube_dl.extractor import ( ThePlatformIE, ThePlatformFeedIE, RTVEALaCartaIE, - FunnyOrDieIE, DemocracynowIE, ) @@ -322,18 +321,6 @@ class TestRtveSubtitles(BaseTestSubtitles): self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca') -class TestFunnyOrDieSubtitles(BaseTestSubtitles): - url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine' - IE = FunnyOrDieIE - - def test_allsubtitles(self): - self.DL.params['writesubtitles'] = True - self.DL.params['allsubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(set(subtitles.keys()), set(['en'])) - self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4') - - class TestDemocracynowSubtitles(BaseTestSubtitles): url = 'http://www.democracynow.org/shows/2015/7/3' IE = DemocracynowIE diff --git a/test/test_utils.py b/test/test_utils.py index 659c6ece5..0896f4150 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -19,6 +19,7 @@ from youtube_dl.utils import ( age_restricted, args_to_str, encode_base_n, + caesar, clean_html, date_from_str, DateRange, @@ -69,11 +70,13 @@ from youtube_dl.utils import ( remove_start, remove_end, remove_quotes, + rot47, shell_quote, smuggle_url, str_to_int, strip_jsonp, strip_or_none, + subtitles_filename, timeconvert, unescapeHTML, unified_strdate, @@ -261,6 +264,11 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_subtitles_filename(self): + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt') + def test_remove_start(self): self.assertEqual(remove_start(None, 'A - '), None) self.assertEqual(remove_start('A - B', 'A - '), 'B') @@ -334,6 +342,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_strdate('July 15th, 2013'), '20130715') self.assertEqual(unified_strdate('September 1st, 2013'), '20130901') self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902') + self.assertEqual(unified_strdate('November 3rd, 2019'), '20191103') + self.assertEqual(unified_strdate('October 23rd, 2005'), '20051023') def test_unified_timestamps(self): self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600) @@ -489,6 +499,12 @@ class TestUtil(unittest.TestCase): def test_str_to_int(self): self.assertEqual(str_to_int('123,456'), 123456) self.assertEqual(str_to_int('123.456'), 123456) + self.assertEqual(str_to_int(523), 523) + # Python 3 has no long + if sys.version_info < (3, 0): + eval('self.assertEqual(str_to_int(123456L), 123456)') + self.assertEqual(str_to_int('noninteger'), None) + self.assertEqual(str_to_int([]), None) def test_url_basename(self): self.assertEqual(url_basename('http://foo.de/'), '') @@ -1361,6 +1377,20 @@ Line 1 self.assertRaises(ValueError, encode_base_n, 0, 70) self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) + def test_caesar(self): + self.assertEqual(caesar('ace', 'abcdef', 2), 'cea') + self.assertEqual(caesar('cea', 'abcdef', -2), 'ace') + self.assertEqual(caesar('ace', 'abcdef', -2), 'eac') + self.assertEqual(caesar('eac', 'abcdef', 2), 'ace') + self.assertEqual(caesar('ace', 'abcdef', 0), 'ace') + self.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz') + self.assertEqual(caesar('abc', 'acegik', 2), 'ebg') + self.assertEqual(caesar('ebg', 'acegik', -2), 'abc') + + def test_rot47(self): + self.assertEqual(rot47('youtube-dl'), r'J@FEF36\5=') + self.assertEqual(rot47('YOUTUBE-DL'), r'*~&%&qt\s{') + def test_urshift(self): self.assertEqual(urshift(3, 1), 1) self.assertEqual(urshift(-3, 1), 2147483646) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index c3d1407f9..19370f62b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -92,6 +92,7 @@ from .utils import ( YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, + YoutubeDLRedirectHandler, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER @@ -990,7 +991,7 @@ class YoutubeDL(object): 'playlist_title': ie_result.get('title'), 'playlist_uploader': ie_result.get('uploader'), 'playlist_uploader_id': ie_result.get('uploader_id'), - 'playlist_index': i + playliststart, + 'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], 'webpage_url_basename': url_basename(ie_result['webpage_url']), @@ -1814,7 +1815,7 @@ class YoutubeDL(object): ie = self.get_info_extractor(info_dict['extractor_key']) for sub_lang, sub_info in subtitles.items(): sub_format = sub_info['ext'] - sub_filename = subtitles_filename(filename, sub_lang, sub_format) + sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext')) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format)) else: @@ -2343,6 +2344,7 @@ class YoutubeDL(object): debuglevel = 1 if self.params.get('debug_printtraffic') else 0 https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) + redirect_handler = YoutubeDLRedirectHandler() data_handler = compat_urllib_request_DataHandler() # When passing our own FileHandler instance, build_opener won't add the @@ -2356,7 +2358,7 @@ class YoutubeDL(object): file_handler.file_open = file_open opener = compat_urllib_request.build_opener( - proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler) + proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler) # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index c75ab131b..d1b86bd13 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2754,6 +2754,17 @@ else: compat_expanduser = os.path.expanduser +if compat_os_name == 'nt' and sys.version_info < (3, 8): + # os.path.realpath on Windows does not follow symbolic links + # prior to Python 3.8 (see https://bugs.python.org/issue9949) + def compat_realpath(path): + while os.path.islink(path): + path = os.path.abspath(os.readlink(path)) + return path +else: + compat_realpath = os.path.realpath + + if sys.version_info < (3, 0): def compat_print(s): from .utils import preferredencoding @@ -2998,6 +3009,7 @@ __all__ = [ 'compat_os_name', 'compat_parse_qs', 'compat_print', + 'compat_realpath', 'compat_setenv', 'compat_shlex_quote', 'compat_shlex_split', diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index b59aad73f..84bc34928 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -64,7 +64,7 @@ class HlsFD(FragmentFD): s = urlh.read().decode('utf-8', 'ignore') if not self.can_download(s, info_dict): - if info_dict.get('extra_param_to_segment_url'): + if info_dict.get('extra_param_to_segment_url') or info_dict.get('_decryption_key_url'): self.report_error('pycrypto not found. Please install it.') return False self.report_warning( @@ -169,7 +169,7 @@ class HlsFD(FragmentFD): if decrypt_info['METHOD'] == 'AES-128': iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence) decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen( - self._prepare_url(info_dict, decrypt_info['URI'])).read() + self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read() frag_content = AES.new( decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content) self._append_fragment(ctx, frag_content) diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 4ac323bf6..6637f4f35 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor): # ABC iview programs are normally available for 14 days only. _TESTS = [{ - 'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00', - 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', + 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00', + 'md5': '67715ce3c78426b11ba167d875ac6abf', 'info_dict': { - 'id': 'ZX9371A050S00', + 'id': 'LE1927H001S00', 'ext': 'mp4', - 'title': "Gaston's Birthday", - 'series': "Ben And Holly's Little Kingdom", - 'description': 'md5:f9de914d02f226968f598ac76f105bcf', - 'upload_date': '20180604', - 'uploader_id': 'abc4kids', - 'timestamp': 1528140219, + 'title': "Series 11 Ep 1", + 'series': "Gruen", + 'description': 'md5:52cc744ad35045baf6aded2ce7287f67', + 'upload_date': '20190925', + 'uploader_id': 'abc1', + 'timestamp': 1569445289, }, 'params': { 'skip_download': True, @@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor): 'hdnea': token, }) - for sd in ('sd', 'sd-low'): + for sd in ('720', 'sd', 'sd-low'): sd_url = try_get( stream, lambda x: x['streams']['hls'][sd], compat_str) if not sd_url: diff --git a/youtube_dl/extractor/abcotvs.py b/youtube_dl/extractor/abcotvs.py index 03b92a39c..0bc69a64f 100644 --- a/youtube_dl/extractor/abcotvs.py +++ b/youtube_dl/extractor/abcotvs.py @@ -4,29 +4,30 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( + dict_get, int_or_none, - parse_iso8601, + try_get, ) class ABCOTVSIE(InfoExtractor): IE_NAME = 'abcotvs' IE_DESC = 'ABC Owned Television Stations' - _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)' + _VALID_URL = r'https?://(?P<site>abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P<display_id>[^/]+))?/(?P<id>\d+)' _TESTS = [ { 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/', 'info_dict': { - 'id': '472581', + 'id': '472548', 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers', 'ext': 'mp4', - 'title': 'East Bay museum celebrates vintage synthesizers', + 'title': 'East Bay museum celebrates synthesized music', 'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3', 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1421123075, + 'timestamp': 1421118520, 'upload_date': '20150113', - 'uploader': 'Jonathan Bloom', }, 'params': { # m3u8 download @@ -37,39 +38,63 @@ class ABCOTVSIE(InfoExtractor): 'url': 'http://abc7news.com/472581', 'only_matching': True, }, + { + 'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/', + 'only_matching': True, + }, ] + _SITE_MAP = { + '6abc': 'wpvi', + 'abc11': 'wtvd', + 'abc13': 'ktrk', + 'abc30': 'kfsn', + 'abc7': 'kabc', + 'abc7chicago': 'wls', + 'abc7news': 'kgo', + 'abc7ny': 'wabc', + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') or video_id - - webpage = self._download_webpage(url, display_id) + site, display_id, video_id = re.match(self._VALID_URL, url).groups() + display_id = display_id or video_id + station = self._SITE_MAP[site] - m3u8 = self._html_search_meta( - 'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0] + data = self._download_json( + 'https://api.abcotvs.com/v2/content', display_id, query={ + 'id': video_id, + 'key': 'otv.web.%s.story' % station, + 'station': station, + })['data'] + video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data + video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id)) + title = video.get('title') or video['linkText'] - formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4') + formats = [] + m3u8_url = video.get('m3u8') + if m3u8_url: + formats = self._extract_m3u8_formats( + video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False) + mp4_url = video.get('mp4') + if mp4_url: + formats.append({ + 'abr': 128, + 'format_id': 'https', + 'height': 360, + 'url': mp4_url, + 'width': 640, + }) self._sort_formats(formats) - title = self._og_search_title(webpage).strip() - description = self._og_search_description(webpage).strip() - thumbnail = self._og_search_thumbnail(webpage) - timestamp = parse_iso8601(self._search_regex( - r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">', - webpage, 'upload date', fatal=False)) - uploader = self._search_regex( - r'rel="author">([^<]+)</a>', - webpage, 'uploader', default=None) + image = video.get('image') or {} return { 'id': video_id, 'display_id': display_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'uploader': uploader, + 'description': dict_get(video, ('description', 'caption'), try_get(video, lambda x: x['meta']['description'])), + 'thumbnail': dict_get(image, ('source', 'dynamicSource')), + 'timestamp': int_or_none(video.get('date')), + 'duration': int_or_none(video.get('length')), 'formats': formats, } diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py deleted file mode 100644 index 5e7c0724e..000000000 --- a/youtube_dl/extractor/addanime.py +++ /dev/null @@ -1,95 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, - compat_urllib_parse_urlencode, - compat_urllib_parse_urlparse, -) -from ..utils import ( - ExtractorError, - qualities, -) - - -class AddAnimeIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)' - _TESTS = [{ - 'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', - 'md5': '72954ea10bc979ab5e2eb288b21425a0', - 'info_dict': { - 'id': '24MR3YO5SAS9', - 'ext': 'mp4', - 'description': 'One Piece 606', - 'title': 'One Piece 606', - }, - 'skip': 'Video is gone', - }, { - 'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - try: - webpage = self._download_webpage(url, video_id) - except ExtractorError as ee: - if not isinstance(ee.cause, compat_HTTPError) or \ - ee.cause.code != 503: - raise - - redir_webpage = ee.cause.read().decode('utf-8') - action = self._search_regex( - r'<form id="challenge-form" action="([^"]+)"', - redir_webpage, 'Redirect form') - vc = self._search_regex( - r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>', - redir_webpage, 'redirect vc value') - av = re.search( - r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', - redir_webpage) - if av is None: - raise ExtractorError('Cannot find redirect math task') - av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3)) - - parsed_url = compat_urllib_parse_urlparse(url) - av_val = av_res + len(parsed_url.netloc) - confirm_url = ( - parsed_url.scheme + '://' + parsed_url.netloc - + action + '?' - + compat_urllib_parse_urlencode({ - 'jschl_vc': vc, 'jschl_answer': compat_str(av_val)})) - self._download_webpage( - confirm_url, video_id, - note='Confirming after redirect') - webpage = self._download_webpage(url, video_id) - - FORMATS = ('normal', 'hq') - quality = qualities(FORMATS) - formats = [] - for format_id in FORMATS: - rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id) - video_url = self._search_regex(rex, webpage, 'video file URLx', - fatal=False) - if not video_url: - continue - formats.append({ - 'format_id': format_id, - 'url': video_url, - 'quality': quality(format_id), - }) - self._sort_formats(formats) - video_title = self._og_search_title(webpage) - video_description = self._og_search_description(webpage) - - return { - '_type': 'video', - 'id': video_id, - 'formats': formats, - 'title': video_title, - 'description': video_description - } diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 008c98e51..80060f037 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -1,25 +1,119 @@ from __future__ import unicode_literals +import functools import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - parse_duration, - unified_strdate, - str_to_int, - int_or_none, float_or_none, + int_or_none, ISO639Utils, - determine_ext, + OnDemandPagedList, + parse_duration, + str_or_none, + str_to_int, + unified_strdate, ) class AdobeTVBaseIE(InfoExtractor): - _API_BASE_URL = 'http://tv.adobe.com/api/v4/' + def _call_api(self, path, video_id, query, note=None): + return self._download_json( + 'http://tv.adobe.com/api/v4/' + path, + video_id, note, query=query)['data'] + + def _parse_subtitles(self, video_data, url_key): + subtitles = {} + for translation in video_data.get('translations', []): + vtt_path = translation.get(url_key) + if not vtt_path: + continue + lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) + subtitles.setdefault(lang, []).append({ + 'ext': 'vtt', + 'url': vtt_path, + }) + return subtitles + + def _parse_video_data(self, video_data): + video_id = compat_str(video_data['id']) + title = video_data['title'] + + s3_extracted = False + formats = [] + for source in video_data.get('videos', []): + source_url = source.get('url') + if not source_url: + continue + f = { + 'format_id': source.get('quality_level'), + 'fps': int_or_none(source.get('frame_rate')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('video_data_rate')), + 'width': int_or_none(source.get('width')), + 'url': source_url, + } + original_filename = source.get('original_filename') + if original_filename: + if not (f.get('height') and f.get('width')): + mobj = re.search(r'_(\d+)x(\d+)', original_filename) + if mobj: + f.update({ + 'height': int(mobj.group(2)), + 'width': int(mobj.group(1)), + }) + if original_filename.startswith('s3://') and not s3_extracted: + formats.append({ + 'format_id': 'original', + 'preference': 1, + 'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'), + }) + s3_extracted = True + formats.append(f) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnail'), + 'upload_date': unified_strdate(video_data.get('start_date')), + 'duration': parse_duration(video_data.get('duration')), + 'view_count': str_to_int(video_data.get('playcount')), + 'formats': formats, + 'subtitles': self._parse_subtitles(video_data, 'vtt'), + } + + +class AdobeTVEmbedIE(AdobeTVBaseIE): + IE_NAME = 'adobetv:embed' + _VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)' + _TEST = { + 'url': 'https://tv.adobe.com/embed/22/4153', + 'md5': 'c8c0461bf04d54574fc2b4d07ac6783a', + 'info_dict': { + 'id': '4153', + 'ext': 'flv', + 'title': 'Creating Graphics Optimized for BlackBerry', + 'description': 'md5:eac6e8dced38bdaae51cd94447927459', + 'thumbnail': r're:https?://.*\.jpg$', + 'upload_date': '20091109', + 'duration': 377, + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + video_data = self._call_api( + 'episode/' + video_id, video_id, {'disclosure': 'standard'})[0] + return self._parse_video_data(video_data) class AdobeTVIE(AdobeTVBaseIE): + IE_NAME = 'adobetv' _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)' _TEST = { @@ -42,45 +136,33 @@ class AdobeTVIE(AdobeTVBaseIE): if not language: language = 'en' - video_data = self._download_json( - self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), - urlname)['data'][0] - - formats = [{ - 'url': source['url'], - 'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None, - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('video_data_rate')), - } for source in video_data['videos']] - self._sort_formats(formats) - - return { - 'id': compat_str(video_data['id']), - 'title': video_data['title'], - 'description': video_data.get('description'), - 'thumbnail': video_data.get('thumbnail'), - 'upload_date': unified_strdate(video_data.get('start_date')), - 'duration': parse_duration(video_data.get('duration')), - 'view_count': str_to_int(video_data.get('playcount')), - 'formats': formats, - } + video_data = self._call_api( + 'episode/get', urlname, { + 'disclosure': 'standard', + 'language': language, + 'show_urlname': show_urlname, + 'urlname': urlname, + })[0] + return self._parse_video_data(video_data) class AdobeTVPlaylistBaseIE(AdobeTVBaseIE): - def _parse_page_data(self, page_data): - return [self.url_result(self._get_element_url(element_data)) for element_data in page_data] + _PAGE_SIZE = 25 + + def _fetch_page(self, display_id, query, page): + page += 1 + query['page'] = page + for element_data in self._call_api( + self._RESOURCE, display_id, query, 'Download Page %d' % page): + yield self._process_data(element_data) - def _extract_playlist_entries(self, url, display_id): - page = self._download_json(url, display_id) - entries = self._parse_page_data(page['data']) - for page_num in range(2, page['paging']['pages'] + 1): - entries.extend(self._parse_page_data( - self._download_json(url + '&page=%d' % page_num, display_id)['data'])) - return entries + def _extract_playlist_entries(self, display_id, query): + return OnDemandPagedList(functools.partial( + self._fetch_page, display_id, query), self._PAGE_SIZE) class AdobeTVShowIE(AdobeTVPlaylistBaseIE): + IE_NAME = 'adobetv:show' _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)' _TEST = { @@ -92,26 +174,31 @@ class AdobeTVShowIE(AdobeTVPlaylistBaseIE): }, 'playlist_mincount': 136, } - - def _get_element_url(self, element_data): - return element_data['urls'][0] + _RESOURCE = 'episode' + _process_data = AdobeTVBaseIE._parse_video_data def _real_extract(self, url): language, show_urlname = re.match(self._VALID_URL, url).groups() if not language: language = 'en' - query = 'language=%s&show_urlname=%s' % (language, show_urlname) + query = { + 'disclosure': 'standard', + 'language': language, + 'show_urlname': show_urlname, + } - show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0] + show_data = self._call_api( + 'show/get', show_urlname, query)[0] return self.playlist_result( - self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname), - compat_str(show_data['id']), - show_data['show_name'], - show_data['show_description']) + self._extract_playlist_entries(show_urlname, query), + str_or_none(show_data.get('id')), + show_data.get('show_name'), + show_data.get('show_description')) class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): + IE_NAME = 'adobetv:channel' _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?' _TEST = { @@ -121,24 +208,30 @@ class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): }, 'playlist_mincount': 96, } + _RESOURCE = 'show' - def _get_element_url(self, element_data): - return element_data['url'] + def _process_data(self, show_data): + return self.url_result( + show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id'))) def _real_extract(self, url): language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups() if not language: language = 'en' - query = 'language=%s&channel_urlname=%s' % (language, channel_urlname) + query = { + 'channel_urlname': channel_urlname, + 'language': language, + } if category_urlname: - query += '&category_urlname=%s' % category_urlname + query['category_urlname'] = category_urlname return self.playlist_result( - self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname), + self._extract_playlist_entries(channel_urlname, query), channel_urlname) -class AdobeTVVideoIE(InfoExtractor): +class AdobeTVVideoIE(AdobeTVBaseIE): + IE_NAME = 'adobetv:video' _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)' _TEST = { @@ -160,38 +253,36 @@ class AdobeTVVideoIE(InfoExtractor): video_data = self._parse_json(self._search_regex( r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id) - - formats = [{ - 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), - 'url': source['src'], - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('bitrate')), - } for source in video_data['sources']] + title = video_data['title'] + + formats = [] + sources = video_data.get('sources') or [] + for source in sources: + source_src = source.get('src') + if not source_src: + continue + formats.append({ + 'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000), + 'format_id': '-'.join(filter(None, [source.get('format'), source.get('label')])), + 'height': int_or_none(source.get('height') or None), + 'tbr': int_or_none(source.get('bitrate') or None), + 'width': int_or_none(source.get('width') or None), + 'url': source_src, + }) self._sort_formats(formats) # For both metadata and downloaded files the duration varies among # formats. I just pick the max one duration = max(filter(None, [ float_or_none(source.get('duration'), scale=1000) - for source in video_data['sources']])) - - subtitles = {} - for translation in video_data.get('translations', []): - lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) - if lang_id not in subtitles: - subtitles[lang_id] = [] - subtitles[lang_id].append({ - 'url': translation['vttPath'], - 'ext': 'vtt', - }) + for source in sources])) return { 'id': video_id, 'formats': formats, - 'title': video_data['title'], + 'title': title, 'description': video_data.get('description'), - 'thumbnail': video_data['video'].get('poster'), + 'thumbnail': video_data.get('video', {}).get('poster'), 'duration': duration, - 'subtitles': subtitles, + 'subtitles': self._parse_subtitles(video_data, 'vttPath'), } diff --git a/youtube_dl/extractor/americastestkitchen.py b/youtube_dl/extractor/americastestkitchen.py index 8b32aa886..9c9d77ae1 100644 --- a/youtube_dl/extractor/americastestkitchen.py +++ b/youtube_dl/extractor/americastestkitchen.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..utils import ( clean_html, int_or_none, + js_to_json, try_get, unified_strdate, ) @@ -13,22 +14,21 @@ from ..utils import ( class AmericasTestKitchenIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)' _TESTS = [{ - 'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party', + 'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers', 'md5': 'b861c3e365ac38ad319cfd509c30577f', 'info_dict': { - 'id': '1_5g5zua6e', - 'title': 'Summer Dinner Party', + 'id': '5b400b9ee338f922cb06450c', + 'title': 'Weeknight Japanese Suppers', 'ext': 'mp4', - 'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec', - 'thumbnail': r're:^https?://.*\.jpg', - 'timestamp': 1497285541, - 'upload_date': '20170612', - 'uploader_id': 'roger.metcalf@americastestkitchen.com', - 'release_date': '20170617', + 'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8', + 'thumbnail': r're:^https?://', + 'timestamp': 1523664000, + 'upload_date': '20180414', + 'release_date': '20180414', 'series': "America's Test Kitchen", - 'season_number': 17, - 'episode': 'Summer Dinner Party', - 'episode_number': 24, + 'season_number': 18, + 'episode': 'Weeknight Japanese Suppers', + 'episode_number': 15, }, 'params': { 'skip_download': True, @@ -47,7 +47,7 @@ class AmericasTestKitchenIE(InfoExtractor): self._search_regex( r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>', webpage, 'initial context'), - video_id) + video_id, js_to_json) ep_data = try_get( video_data, @@ -55,17 +55,7 @@ class AmericasTestKitchenIE(InfoExtractor): lambda x: x['videoDetail']['content']['data']), dict) ep_meta = ep_data.get('full_video', {}) - zype_id = ep_meta.get('zype_id') - if zype_id: - embed_url = 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id - ie_key = 'Zype' - else: - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id') - external_id = ep_data.get('external_id') or ep_meta['external_id'] - embed_url = 'kaltura:%s:%s' % (partner_id, external_id) - ie_key = 'Kaltura' + zype_id = ep_data.get('zype_id') or ep_meta['zype_id'] title = ep_data.get('title') or ep_meta.get('title') description = clean_html(ep_meta.get('episode_description') or ep_data.get( @@ -79,8 +69,8 @@ class AmericasTestKitchenIE(InfoExtractor): return { '_type': 'url_transparent', - 'url': embed_url, - 'ie_key': ie_key, + 'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id, + 'ie_key': 'Zype', 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 8adae4644..2f47e21c3 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor @@ -22,66 +23,28 @@ from ..utils import ( from ..compat import compat_etree_fromstring -class ARDMediathekIE(InfoExtractor): - IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' - - _TESTS = [{ - # available till 26.07.2022 - 'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822', - 'info_dict': { - 'id': '44726822', - 'ext': 'mp4', - 'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?', - 'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5', - 'duration': 1740, - }, - 'params': { - # m3u8 download - 'skip_download': True, - } - }, { - 'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872', - 'only_matching': True, - }, { - # audio - 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', - 'only_matching': True, - }, { - 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', - 'only_matching': True, - }, { - # audio - 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', - 'only_matching': True, - }, { - 'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698', - 'only_matching': True, - }] - - @classmethod - def suitable(cls, url): - return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url) +class ARDMediathekBaseIE(InfoExtractor): + _GEO_COUNTRIES = ['DE'] def _extract_media_info(self, media_info_url, webpage, video_id): media_info = self._download_json( media_info_url, video_id, 'Downloading media JSON') + return self._parse_media_info(media_info, video_id, '"fsk"' in webpage) + def _parse_media_info(self, media_info, video_id, fsk): formats = self._extract_formats(media_info, video_id) if not formats: - if '"fsk"' in webpage: + if fsk: raise ExtractorError( 'This video is only available after 20:00', expected=True) elif media_info.get('_geoblocked'): - raise ExtractorError('This video is not available due to geo restriction', expected=True) + self.raise_geo_restricted( + 'This video is not available due to geoblocking', + countries=self._GEO_COUNTRIES) self._sort_formats(formats) - duration = int_or_none(media_info.get('_duration')) - thumbnail = media_info.get('_previewImage') - is_live = media_info.get('_isLive') is True - subtitles = {} subtitle_url = media_info.get('_subtitleUrl') if subtitle_url: @@ -92,9 +55,9 @@ class ARDMediathekIE(InfoExtractor): return { 'id': video_id, - 'duration': duration, - 'thumbnail': thumbnail, - 'is_live': is_live, + 'duration': int_or_none(media_info.get('_duration')), + 'thumbnail': media_info.get('_previewImage'), + 'is_live': media_info.get('_isLive') is True, 'formats': formats, 'subtitles': subtitles, } @@ -123,11 +86,11 @@ class ARDMediathekIE(InfoExtractor): update_url_query(stream_url, { 'hdcore': '3.1.1', 'plugin': 'aasp-3.1.1.69.124' - }), - video_id, f4m_id='hds', fatal=False)) + }), video_id, f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + stream_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) else: if server and server.startswith('rtmp'): f = { @@ -140,7 +103,9 @@ class ARDMediathekIE(InfoExtractor): 'url': stream_url, 'format_id': 'a%s-%s-%s' % (num, ext, quality) } - m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url) + m = re.search( + r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', + stream_url) if m: f.update({ 'width': int(m.group('width')), @@ -151,6 +116,48 @@ class ARDMediathekIE(InfoExtractor): formats.append(f) return formats + +class ARDMediathekIE(ARDMediathekBaseIE): + IE_NAME = 'ARD:mediathek' + _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + + _TESTS = [{ + # available till 26.07.2022 + 'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822', + 'info_dict': { + 'id': '44726822', + 'ext': 'mp4', + 'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?', + 'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5', + 'duration': 1740, + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + }, { + 'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872', + 'only_matching': True, + }, { + # audio + 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', + 'only_matching': True, + }, { + 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', + 'only_matching': True, + }, { + # audio + 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', + 'only_matching': True, + }, { + 'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url) + def _real_extract(self, url): # determine video id from url m = re.match(self._VALID_URL, url) @@ -302,19 +309,20 @@ class ARDIE(InfoExtractor): } -class ARDBetaMediathekIE(InfoExtractor): - _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?' +class ARDBetaMediathekIE(ARDMediathekBaseIE): + _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P<client>[^/]+)/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?' _TESTS = [{ 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', - 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', + 'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f', 'info_dict': { 'display_id': 'die-robuste-roswita', - 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', - 'title': 'Tatort: Die robuste Roswita', + 'id': '70153354', + 'title': 'Die robuste Roswita', 'description': r're:^Der Mord.*trüber ist als die Ilm.', 'duration': 5316, - 'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard', - 'upload_date': '20180826', + 'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard', + 'timestamp': 1577047500, + 'upload_date': '20191222', 'ext': 'mp4', }, }, { @@ -330,71 +338,69 @@ class ARDBetaMediathekIE(InfoExtractor): video_id = mobj.group('video_id') display_id = mobj.group('display_id') or video_id - webpage = self._download_webpage(url, display_id) - data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json') - data = self._parse_json(data_json, display_id) - - res = { - 'id': video_id, - 'display_id': display_id, + player_page = self._download_json( + 'https://api.ardmediathek.de/public-gateway', + display_id, data=json.dumps({ + 'query': '''{ + playerPage(client:"%s", clipId: "%s") { + blockedByFsk + broadcastedOn + maturityContentRating + mediaCollection { + _duration + _geoblocked + _isLive + _mediaArray { + _mediaStreamArray { + _quality + _server + _stream } - formats = [] - subtitles = {} - geoblocked = False - for widget in data.values(): - if widget.get('_geoblocked') is True: - geoblocked = True - if '_duration' in widget: - res['duration'] = int_or_none(widget['_duration']) - if 'clipTitle' in widget: - res['title'] = widget['clipTitle'] - if '_previewImage' in widget: - res['thumbnail'] = widget['_previewImage'] - if 'broadcastedOn' in widget: - res['timestamp'] = unified_timestamp(widget['broadcastedOn']) - if 'synopsis' in widget: - res['description'] = widget['synopsis'] - subtitle_url = url_or_none(widget.get('_subtitleUrl')) - if subtitle_url: - subtitles.setdefault('de', []).append({ - 'ext': 'ttml', - 'url': subtitle_url, - }) - if '_quality' in widget: - format_url = url_or_none(try_get( - widget, lambda x: x['_stream']['json'][0])) - if not format_url: - continue - ext = determine_ext(format_url) - if ext == 'f4m': - formats.extend(self._extract_f4m_formats( - format_url + '?hdcore=3.11.0', - video_id, f4m_id='hds', fatal=False)) - elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id='hls', - fatal=False)) - else: - # HTTP formats are not available when geoblocked is True, - # other formats are fine though - if geoblocked: - continue - quality = str_or_none(widget.get('_quality')) - formats.append({ - 'format_id': ('http-' + quality) if quality else 'http', - 'url': format_url, - 'preference': 10, # Plain HTTP, that's nice - }) - - if not formats and geoblocked: - self.raise_geo_restricted( - msg='This video is not available due to geoblocking', - countries=['DE']) - - self._sort_formats(formats) - res.update({ - 'subtitles': subtitles, - 'formats': formats, + } + _previewImage + _subtitleUrl + _type + } + show { + title + } + synopsis + title + tracking { + atiCustomVars { + contentId + } + } + } +}''' % (mobj.group('client'), video_id), + }).encode(), headers={ + 'Content-Type': 'application/json' + })['data']['playerPage'] + title = player_page['title'] + content_id = str_or_none(try_get( + player_page, lambda x: x['tracking']['atiCustomVars']['contentId'])) + media_collection = player_page.get('mediaCollection') or {} + if not media_collection and content_id: + media_collection = self._download_json( + 'https://www.ardmediathek.de/play/media/' + content_id, + content_id, fatal=False) or {} + info = self._parse_media_info( + media_collection, content_id or video_id, + player_page.get('blockedByFsk')) + age_limit = None + description = player_page.get('synopsis') + maturity_content_rating = player_page.get('maturityContentRating') + if maturity_content_rating: + age_limit = int_or_none(maturity_content_rating.lstrip('FSK')) + if not age_limit and description: + age_limit = int_or_none(self._search_regex( + r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None)) + info.update({ + 'age_limit': age_limit, + 'display_id': display_id, + 'title': title, + 'description': description, + 'timestamp': unified_timestamp(player_page.get('broadcastedOn')), + 'series': try_get(player_page, lambda x: x['show']['title']), }) - - return res + return info diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index ae1c09427..c2cec9845 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -1,202 +1,118 @@ +# coding: utf-8 from __future__ import unicode_literals -import time -import hmac -import hashlib import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, - float_or_none, int_or_none, - sanitized_Request, urlencode_postdata, - xpath_text, ) class AtresPlayerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html' + _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})' _NETRC_MACHINE = 'atresplayer' _TESTS = [ { - 'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html', - 'md5': 'efd56753cda1bb64df52a3074f62e38a', + 'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/', 'info_dict': { - 'id': 'capitulo-10-especial-solidario-nochebuena', + 'id': '5d4aa2c57ed1a88fc715a615', 'ext': 'mp4', - 'title': 'Especial Solidario de Nochebuena', - 'description': 'md5:e2d52ff12214fa937107d21064075bf1', - 'duration': 5527.6, - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': 'Capítulo 7: Asuntos pendientes', + 'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc', + 'duration': 3413, + }, + 'params': { + 'format': 'bestvideo', }, 'skip': 'This video is only available for registered users' }, { - 'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html', - 'md5': '6e52cbb513c405e403dbacb7aacf8747', - 'info_dict': { - 'id': 'capitulo-112-david-bustamante', - 'ext': 'flv', - 'title': 'David Bustamante', - 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6', - 'duration': 1439.0, - 'thumbnail': r're:^https?://.*\.jpg$', - }, + 'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/', + 'only_matching': True, }, { - 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', + 'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/', 'only_matching': True, }, ] - - _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J' - _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)' - _TIMESTAMP_SHIFT = 30000 - - _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json' - _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json' - _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s' - _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s' - - _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check' - - _ERRORS = { - 'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.', - 'DELETED': 'This video has expired and is no longer available for online streaming.', - 'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.', - # 'PREMIUM': 'PREMIUM', - } + _API_BASE = 'https://api.atresplayer.com/' def _real_initialize(self): self._login() + def _handle_error(self, e, code): + if isinstance(e.cause, compat_HTTPError) and e.cause.code == code: + error = self._parse_json(e.cause.read(), None) + if error.get('error') == 'required_registered': + self.raise_login_required() + raise ExtractorError(error['error_description'], expected=True) + raise + def _login(self): username, password = self._get_login_info() if username is None: return - login_form = { - 'j_username': username, - 'j_password': password, - } + self._request_webpage( + self._API_BASE + 'login', None, 'Downloading login page') - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') - response = self._download_webpage( - request, None, 'Logging in') + try: + target_url = self._download_json( + 'https://account.atresmedia.com/api/login', None, + 'Logging in', headers={ + 'Content-Type': 'application/x-www-form-urlencoded' + }, data=urlencode_postdata({ + 'username': username, + 'password': password, + }))['targetUrl'] + except ExtractorError as e: + self._handle_error(e, 400) - error = self._html_search_regex( - r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>', - response, 'error', default=None) - if error: - raise ExtractorError( - 'Unable to login: %s' % error, expected=True) + self._request_webpage(target_url, None, 'Following Target URL') def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) + display_id, video_id = re.match(self._VALID_URL, url).groups() - episode_id = self._search_regex( - r'episode="([^"]+)"', webpage, 'episode id') + try: + episode = self._download_json( + self._API_BASE + 'client/v1/player/episode/' + video_id, video_id) + except ExtractorError as e: + self._handle_error(e, 403) - request = sanitized_Request( - self._PLAYER_URL_TEMPLATE % episode_id, - headers={'User-Agent': self._USER_AGENT}) - player = self._download_json(request, episode_id, 'Downloading player JSON') - - episode_type = player.get('typeOfEpisode') - error_message = self._ERRORS.get(episode_type) - if error_message: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) + title = episode['titulo'] formats = [] - video_url = player.get('urlVideo') - if video_url: - format_info = { - 'url': video_url, - 'format_id': 'http', - } - mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url) - if mobj: - format_info.update({ - 'width': int_or_none(mobj.group('width')), - 'height': int_or_none(mobj.group('height')), - 'tbr': int_or_none(mobj.group('bitrate')), - }) - formats.append(format_info) - - timestamp = int_or_none(self._download_webpage( - self._TIME_API_URL, - video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) - timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) - token = hmac.new( - self._MAGIC.encode('ascii'), - (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5 - ).hexdigest() - - request = sanitized_Request( - self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token), - headers={'User-Agent': self._USER_AGENT}) - - fmt_json = self._download_json( - request, video_id, 'Downloading windows video JSON') - - result = fmt_json.get('resultDes') - if result.lower() != 'ok': - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, result), expected=True) - - for format_id, video_url in fmt_json['resultObject'].items(): - if format_id == 'token' or not video_url.startswith('http'): - continue - if 'geodeswowsmpra3player' in video_url: - # f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] - # f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) - # this videos are protected by DRM, the f4m downloader doesn't support them + for source in episode.get('sources', []): + src = source.get('src') + if not src: continue - video_url_hd = video_url.replace('free_es', 'es') - formats.extend(self._extract_f4m_formats( - video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds', - fatal=False)) - formats.extend(self._extract_mpd_formats( - video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash', - fatal=False)) + src_type = source.get('type') + if src_type == 'application/vnd.apple.mpegurl': + formats.extend(self._extract_m3u8_formats( + src, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif src_type == 'application/dash+xml': + formats.extend(self._extract_mpd_formats( + src, video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) - path_data = player.get('pathData') - - episode = self._download_xml( - self._EPISODE_URL_TEMPLATE % path_data, video_id, - 'Downloading episode XML') - - duration = float_or_none(xpath_text( - episode, './media/asset/info/technical/contentDuration', 'duration')) - - art = episode.find('./media/asset/info/art') - title = xpath_text(art, './name', 'title') - description = xpath_text(art, './description', 'description') - thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail') - - subtitles = {} - subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle') - if subtitle_url: - subtitles['es'] = [{ - 'ext': 'srt', - 'url': subtitle_url, - }] + heartbeat = episode.get('heartbeat') or {} + omniture = episode.get('omniture') or {} + get_meta = lambda x: heartbeat.get(x) or omniture.get(x) return { + 'display_id': display_id, 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, + 'description': episode.get('descripcion'), + 'thumbnail': episode.get('imgPoster'), + 'duration': int_or_none(episode.get('duration')), 'formats': formats, - 'subtitles': subtitles, + 'channel': get_meta('channel'), + 'season': get_meta('season'), + 'episode_number': int_or_none(get_meta('episodeNumber')), } diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py index 393f381c6..c51837b40 100644 --- a/youtube_dl/extractor/audioboom.py +++ b/youtube_dl/extractor/audioboom.py @@ -2,22 +2,25 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + clean_html, + float_or_none, +) class AudioBoomIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)' _TESTS = [{ - 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', - 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', + 'url': 'https://audioboom.com/posts/7398103-asim-chaudhry', + 'md5': '7b00192e593ff227e6a315486979a42d', 'info_dict': { - 'id': '4279833', + 'id': '7398103', 'ext': 'mp3', - 'title': '3/09/2016 Czaban Hour 3', - 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', - 'duration': 2245.72, - 'uploader': 'SB Nation A.M.', - 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', + 'title': 'Asim Chaudhry', + 'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc', + 'duration': 4000.99, + 'uploader': 'Sue Perkins: An hour or so with...', + 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins', } }, { 'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0', @@ -32,8 +35,8 @@ class AudioBoomIE(InfoExtractor): clip = None clip_store = self._parse_json( - self._search_regex( - r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id, + self._html_search_regex( + r'data-new-clip-store=(["\'])(?P<json>{.+?})\1', webpage, 'clip store', default='{}', group='json'), video_id, fatal=False) if clip_store: @@ -47,14 +50,15 @@ class AudioBoomIE(InfoExtractor): audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property( 'audio', webpage, 'audio url') - title = from_clip('title') or self._og_search_title(webpage) - description = from_clip('description') or self._og_search_description(webpage) + title = from_clip('title') or self._html_search_meta( + ['og:title', 'og:audio:title', 'audio_title'], webpage) + description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage) duration = float_or_none(from_clip('duration') or self._html_search_meta( 'weibo:audio:duration', webpage)) - uploader = from_clip('author') or self._og_search_property( - 'audio:artist', webpage, 'uploader', fatal=False) + uploader = from_clip('author') or self._html_search_meta( + ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader') uploader_url = from_clip('author_url') or self._html_search_meta( 'audioboo:channel', webpage, 'uploader url') diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index fcbdc71b9..b1e20def5 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -47,39 +47,19 @@ class AZMedienIE(InfoExtractor): 'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1', 'only_matching': True }] - + _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d' _PARTNER_ID = '1719221' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - host = mobj.group('host') - video_id = mobj.group('id') - entry_id = mobj.group('kaltura_id') + host, display_id, article_id, entry_id = re.match(self._VALID_URL, url).groups() if not entry_id: - api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0]) - payload = { - 'query': '''query VideoContext($articleId: ID!) { - article: node(id: $articleId) { - ... on Article { - mainAssetRelation { - asset { - ... on VideoAsset { - kalturaId - } - } - } - } - } - }''', - 'variables': {'articleId': 'Article:%s' % mobj.group('article_id')}, - } - json_data = self._download_json( - api_url, video_id, headers={ - 'Content-Type': 'application/json', - }, - data=json.dumps(payload).encode()) - entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId'] + entry_id = self._download_json( + self._API_TEMPL % (host, host.split('.')[0]), display_id, query={ + 'variables': json.dumps({ + 'contextId': 'NewsArticle:' + article_id, + }), + })['data']['context']['mainAsset']['video']['kaltura']['kalturaId'] return self.url_result( 'kaltura:%s:%s' % (self._PARTNER_ID, entry_id), diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py deleted file mode 100644 index 4400ff9c1..000000000 --- a/youtube_dl/extractor/bambuser.py +++ /dev/null @@ -1,142 +0,0 @@ -from __future__ import unicode_literals - -import re -import itertools - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - ExtractorError, - float_or_none, - int_or_none, - sanitized_Request, - urlencode_postdata, -) - - -class BambuserIE(InfoExtractor): - IE_NAME = 'bambuser' - _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)' - _API_KEY = '005f64509e19a868399060af746a00aa' - _LOGIN_URL = 'https://bambuser.com/user' - _NETRC_MACHINE = 'bambuser' - - _TEST = { - 'url': 'http://bambuser.com/v/4050584', - # MD5 seems to be flaky, see https://travis-ci.org/ytdl-org/youtube-dl/jobs/14051016#L388 - # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641', - 'info_dict': { - 'id': '4050584', - 'ext': 'flv', - 'title': 'Education engineering days - lightning talks', - 'duration': 3741, - 'uploader': 'pixelversity', - 'uploader_id': '344706', - 'timestamp': 1382976692, - 'upload_date': '20131028', - 'view_count': int, - }, - 'params': { - # It doesn't respect the 'Range' header, it would download the whole video - # caused the travis builds to fail: https://travis-ci.org/ytdl-org/youtube-dl/jobs/14493845#L59 - 'skip_download': True, - }, - } - - def _login(self): - username, password = self._get_login_info() - if username is None: - return - - login_form = { - 'form_id': 'user_login', - 'op': 'Log in', - 'name': username, - 'pass': password, - } - - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Referer', self._LOGIN_URL) - response = self._download_webpage( - request, None, 'Logging in') - - login_error = self._html_search_regex( - r'(?s)<div class="messages error">(.+?)</div>', - response, 'login error', default=None) - if login_error: - raise ExtractorError( - 'Unable to login: %s' % login_error, expected=True) - - def _real_initialize(self): - self._login() - - def _real_extract(self, url): - video_id = self._match_id(url) - - info = self._download_json( - 'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s' - % (self._API_KEY, video_id), video_id) - - error = info.get('error') - if error: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, error), expected=True) - - result = info['result'] - - return { - 'id': video_id, - 'title': result['title'], - 'url': result['url'], - 'thumbnail': result.get('preview'), - 'duration': int_or_none(result.get('length')), - 'uploader': result.get('username'), - 'uploader_id': compat_str(result.get('owner', {}).get('uid')), - 'timestamp': int_or_none(result.get('created')), - 'fps': float_or_none(result.get('framerate')), - 'view_count': int_or_none(result.get('views_total')), - 'comment_count': int_or_none(result.get('comment_count')), - } - - -class BambuserChannelIE(InfoExtractor): - IE_NAME = 'bambuser:channel' - _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)' - # The maximum number we can get with each request - _STEP = 50 - _TEST = { - 'url': 'http://bambuser.com/channel/pixelversity', - 'info_dict': { - 'title': 'pixelversity', - }, - 'playlist_mincount': 60, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user = mobj.group('user') - urls = [] - last_id = '' - for i in itertools.count(1): - req_url = ( - 'http://bambuser.com/xhr-api/index.php?username={user}' - '&sort=created&access_mode=0%2C1%2C2&limit={count}' - '&method=broadcast&format=json&vid_older_than={last}' - ).format(user=user, count=self._STEP, last=last_id) - req = sanitized_Request(req_url) - # Without setting this header, we wouldn't get any result - req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) - data = self._download_json( - req, user, 'Downloading page %d' % i) - results = data['result'] - if not results: - break - last_id = results[-1]['vid'] - urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) - - return { - '_type': 'playlist', - 'title': user, - 'entries': urls, - } diff --git a/youtube_dl/extractor/bellmedia.py b/youtube_dl/extractor/bellmedia.py index f36a2452d..485173774 100644 --- a/youtube_dl/extractor/bellmedia.py +++ b/youtube_dl/extractor/bellmedia.py @@ -22,7 +22,8 @@ class BellMediaIE(InfoExtractor): bravo| mtv| space| - etalk + etalk| + marilyn )\.ca| much\.com )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})''' @@ -70,6 +71,7 @@ class BellMediaIE(InfoExtractor): 'animalplanet': 'aniplan', 'etalk': 'ctv', 'bnnbloomberg': 'bnn', + 'marilyn': 'ctv_marilyn', } def _real_extract(self, url): diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 430663fbf..0c773e66e 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -7,6 +7,7 @@ import re from .common import InfoExtractor from ..utils import ( orderedSet, + unified_strdate, urlencode_postdata, ) @@ -23,6 +24,7 @@ class BitChuteIE(InfoExtractor): 'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a', 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Victoria X Rave', + 'upload_date': '20170813', }, }, { 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', @@ -74,12 +76,17 @@ class BitChuteIE(InfoExtractor): r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'), webpage, 'uploader', fatal=False) + upload_date = unified_strdate(self._search_regex( + r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.', + webpage, 'upload date', fatal=False)) + return { 'id': video_id, 'title': title, 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, + 'upload_date': upload_date, 'formats': formats, } diff --git a/youtube_dl/extractor/bokecc.py b/youtube_dl/extractor/bokecc.py index 86a7f4d7d..6017e8344 100644 --- a/youtube_dl/extractor/bokecc.py +++ b/youtube_dl/extractor/bokecc.py @@ -11,8 +11,8 @@ from ..utils import ExtractorError class BokeCCBaseIE(InfoExtractor): def _extract_bokecc_formats(self, webpage, video_id, format_id=None): player_params_str = self._html_search_regex( - r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', - webpage, 'player params') + r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)', + webpage, 'player params', group='query') player_params = compat_parse_qs(player_params_str) @@ -36,9 +36,9 @@ class BokeCCIE(BokeCCBaseIE): _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)' _TESTS = [{ - 'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B', + 'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A', 'info_dict': { - 'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30', + 'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461', 'ext': 'flv', 'title': 'BokeCC Video', }, diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 8e2f7217a..85001b3ad 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -586,45 +586,63 @@ class BrightcoveNewIE(AdobePassIE): account_id, player_id, embed, content_type, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage( - 'http://players.brightcove.net/%s/%s_%s/index.min.js' - % (account_id, player_id, embed), video_id) + policy_key_id = '%s_%s' % (account_id, player_id) + policy_key = self._downloader.cache.load('brightcove', policy_key_id) + policy_key_extracted = False + store_pk = lambda x: self._downloader.cache.store('brightcove', policy_key_id, x) - policy_key = None + def extract_policy_key(): + webpage = self._download_webpage( + 'http://players.brightcove.net/%s/%s_%s/index.min.js' + % (account_id, player_id, embed), video_id) - catalog = self._search_regex( - r'catalog\(({.+?})\);', webpage, 'catalog', default=None) - if catalog: - catalog = self._parse_json( - js_to_json(catalog), video_id, fatal=False) + policy_key = None + + catalog = self._search_regex( + r'catalog\(({.+?})\);', webpage, 'catalog', default=None) if catalog: - policy_key = catalog.get('policyKey') + catalog = self._parse_json( + js_to_json(catalog), video_id, fatal=False) + if catalog: + policy_key = catalog.get('policyKey') + + if not policy_key: + policy_key = self._search_regex( + r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1', + webpage, 'policy key', group='pk') - if not policy_key: - policy_key = self._search_regex( - r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1', - webpage, 'policy key', group='pk') + store_pk(policy_key) + return policy_key api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id) - headers = { - 'Accept': 'application/json;pk=%s' % policy_key, - } + headers = {} referrer = smuggled_data.get('referrer') if referrer: headers.update({ 'Referer': referrer, 'Origin': re.search(r'https?://[^/]+', referrer).group(0), }) - try: - json_data = self._download_json(api_url, video_id, headers=headers) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - json_data = self._parse_json(e.cause.read().decode(), video_id)[0] - message = json_data.get('message') or json_data['error_code'] - if json_data.get('error_subcode') == 'CLIENT_GEO': - self.raise_geo_restricted(msg=message) - raise ExtractorError(message, expected=True) - raise + + for _ in range(2): + if not policy_key: + policy_key = extract_policy_key() + policy_key_extracted = True + headers['Accept'] = 'application/json;pk=%s' % policy_key + try: + json_data = self._download_json(api_url, video_id, headers=headers) + break + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): + json_data = self._parse_json(e.cause.read().decode(), video_id)[0] + message = json_data.get('message') or json_data['error_code'] + if json_data.get('error_subcode') == 'CLIENT_GEO': + self.raise_geo_restricted(msg=message) + elif json_data.get('error_code') == 'INVALID_POLICY_KEY' and not policy_key_extracted: + policy_key = None + store_pk(None) + continue + raise ExtractorError(message, expected=True) + raise errors = json_data.get('errors') if errors and errors[0].get('error_subcode') == 'TVE_AUTH': diff --git a/youtube_dl/extractor/businessinsider.py b/youtube_dl/extractor/businessinsider.py index dfcf9bc6b..73a57b1e4 100644 --- a/youtube_dl/extractor/businessinsider.py +++ b/youtube_dl/extractor/businessinsider.py @@ -9,21 +9,26 @@ class BusinessInsiderIE(InfoExtractor): _VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6', - 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e', + 'md5': 'ffed3e1e12a6f950aa2f7d83851b497a', 'info_dict': { - 'id': 'hZRllCfw', + 'id': 'cjGDb0X9', 'ext': 'mp4', - 'title': "Here's how much radiation you're exposed to in everyday life", - 'description': 'md5:9a0d6e2c279948aadaa5e84d6d9b99bd', - 'upload_date': '20170709', - 'timestamp': 1499606400, - }, - 'params': { - 'skip_download': True, + 'title': "Bananas give you more radiation exposure than living next to a nuclear power plant", + 'description': 'md5:0175a3baf200dd8fa658f94cade841b3', + 'upload_date': '20160611', + 'timestamp': 1465675620, }, }, { 'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/', - 'only_matching': True, + 'md5': '43f438dbc6da0b89f5ac42f68529d84a', + 'info_dict': { + 'id': '5zJwd4FK', + 'ext': 'mp4', + 'title': 'Deze dingen zorgen ervoor dat je minder snel een date scoort', + 'description': 'md5:2af8975825d38a4fed24717bbe51db49', + 'upload_date': '20170705', + 'timestamp': 1499270528, + }, }, { 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T', 'only_matching': True, @@ -35,7 +40,8 @@ class BusinessInsiderIE(InfoExtractor): jwplatform_id = self._search_regex( (r'data-media-id=["\']([a-zA-Z0-9]{8})', r'id=["\']jwplayer_([a-zA-Z0-9]{8})', - r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})'), + r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})', + r'(?:jwplatform\.com/players/|jwplayer_)([a-zA-Z0-9]{8})'), webpage, 'jwplatform id') return self.url_result( 'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(), diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py index c506bc5dd..8667a0d04 100644 --- a/youtube_dl/extractor/canvas.py +++ b/youtube_dl/extractor/canvas.py @@ -13,6 +13,8 @@ from ..utils import ( int_or_none, merge_dicts, parse_iso8601, + str_or_none, + url_or_none, ) @@ -20,15 +22,15 @@ class CanvasIE(InfoExtractor): _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', - 'md5': '90139b746a0a9bd7bb631283f6e2a64e', + 'md5': '68993eda72ef62386a15ea2cf3c93107', 'info_dict': { 'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', 'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Nachtwacht: De Greystook', - 'description': 'md5:1db3f5dc4c7109c821261e7512975be7', + 'description': 'Nachtwacht: De Greystook', 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 1468.03, + 'duration': 1468.04, }, 'expected_warnings': ['is not a supported codec', 'Unknown MIME type'], }, { @@ -39,23 +41,45 @@ class CanvasIE(InfoExtractor): 'HLS': 'm3u8_native', 'HLS_AES': 'm3u8', } + _REST_API_BASE = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v1' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) site_id, video_id = mobj.group('site_id'), mobj.group('id') + # Old API endpoint, serves more formats but may fail for some videos data = self._download_json( 'https://mediazone.vrt.be/api/v1/%s/assets/%s' - % (site_id, video_id), video_id) + % (site_id, video_id), video_id, 'Downloading asset JSON', + 'Unable to download asset JSON', fatal=False) + + # New API endpoint + if not data: + token = self._download_json( + '%s/tokens' % self._REST_API_BASE, video_id, + 'Downloading token', data=b'', + headers={'Content-Type': 'application/json'})['vrtPlayerToken'] + data = self._download_json( + '%s/videos/%s' % (self._REST_API_BASE, video_id), + video_id, 'Downloading video JSON', fatal=False, query={ + 'vrtPlayerToken': token, + 'client': '%s@PROD' % site_id, + }, expected_status=400) + message = data.get('message') + if message and not data.get('title'): + if data.get('code') == 'AUTHENTICATION_REQUIRED': + self.raise_login_required(message) + raise ExtractorError(message, expected=True) title = data['title'] description = data.get('description') formats = [] for target in data['targetUrls']: - format_url, format_type = target.get('url'), target.get('type') + format_url, format_type = url_or_none(target.get('url')), str_or_none(target.get('type')) if not format_url or not format_type: continue + format_type = format_type.upper() if format_type in self._HLS_ENTRY_PROTOCOLS_MAP: formats.extend(self._extract_m3u8_formats( format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type], @@ -134,20 +158,20 @@ class CanvasEenIE(InfoExtractor): }, 'skip': 'Pagina niet gevonden', }, { - 'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles', + 'url': 'https://www.een.be/thuis/emma-pakt-thilly-aan', 'info_dict': { - 'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f', - 'display_id': 'herbekijk-sorry-voor-alles', + 'id': 'md-ast-3a24ced2-64d7-44fb-b4ed-ed1aafbf90b8', + 'display_id': 'emma-pakt-thilly-aan', 'ext': 'mp4', - 'title': 'Herbekijk Sorry voor alles', - 'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3', + 'title': 'Emma pakt Thilly aan', + 'description': 'md5:c5c9b572388a99b2690030afa3f3bad7', 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 3788.06, + 'duration': 118.24, }, 'params': { 'skip_download': True, }, - 'skip': 'Episode no longer available', + 'expected_warnings': ['is not a supported codec'], }, { 'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend', 'only_matching': True, @@ -183,19 +207,44 @@ class VrtNUIE(GigyaBaseIE): IE_DESC = 'VrtNU.be' _VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ + # Available via old API endpoint 'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/', 'info_dict': { 'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'De zwarte weduwe', - 'description': 'md5:d90c21dced7db869a85db89a623998d4', + 'description': 'md5:db1227b0f318c849ba5eab1fef895ee4', 'duration': 1457.04, 'thumbnail': r're:^https?://.*\.jpg$', - 'season': '1', + 'season': 'Season 1', 'season_number': 1, 'episode_number': 1, }, - 'skip': 'This video is only available for registered users' + 'skip': 'This video is only available for registered users', + 'params': { + 'username': '<snip>', + 'password': '<snip>', + }, + 'expected_warnings': ['is not a supported codec'], + }, { + # Only available via new API endpoint + 'url': 'https://www.vrt.be/vrtnu/a-z/kamp-waes/1/kamp-waes-s1a5/', + 'info_dict': { + 'id': 'pbs-pub-0763b56c-64fb-4d38-b95b-af60bf433c71$vid-ad36a73c-4735-4f1f-b2c0-a38e6e6aa7e1', + 'ext': 'mp4', + 'title': 'Aflevering 5', + 'description': 'Wie valt door de mand tijdens een missie?', + 'duration': 2967.06, + 'season': 'Season 1', + 'season_number': 1, + 'episode_number': 5, + }, + 'skip': 'This video is only available for registered users', + 'params': { + 'username': '<snip>', + 'password': '<snip>', + }, + 'expected_warnings': ['Unable to download asset JSON', 'is not a supported codec', 'Unknown MIME type'], }] _NETRC_MACHINE = 'vrtnu' _APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy' diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 1ec58f7d8..7cb4efb74 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -147,6 +147,8 @@ class CeskaTelevizeIE(InfoExtractor): is_live = item.get('type') == 'LIVE' formats = [] for format_id, stream_url in item.get('streamUrls', {}).items(): + if 'drmOnly=true' in stream_url: + continue if 'playerType=flash' in stream_url: stream_formats = self._extract_m3u8_formats( stream_url, playlist_id, 'mp4', 'm3u8_native', diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index 81108e704..09cacf6d3 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -32,7 +32,7 @@ class Channel9IE(InfoExtractor): 'upload_date': '20130828', 'session_code': 'KOS002', 'session_room': 'Arena 1A', - 'session_speakers': ['Andrew Coates', 'Brady Gaster', 'Mads Kristensen', 'Ed Blankenship', 'Patrick Klug'], + 'session_speakers': 'count:5', }, }, { 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', @@ -65,14 +65,14 @@ class Channel9IE(InfoExtractor): 'skip_download': True, }, }, { - 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS', + 'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS', 'info_dict': { - 'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b', - 'title': 'Channel 9', + 'id': 'Events/DEVintersection/DEVintersection-2016', + 'title': 'DEVintersection 2016 Orlando Sessions', }, - 'playlist_mincount': 100, + 'playlist_mincount': 14, }, { - 'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS', + 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS', 'only_matching': True, }, { 'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman', @@ -112,11 +112,11 @@ class Channel9IE(InfoExtractor): episode_data), content_path) content_id = episode_data['contentId'] is_session = '/Sessions(' in episode_data['api'] - content_url = 'https://channel9.msdn.com/odata' + episode_data['api'] + content_url = 'https://channel9.msdn.com/odata' + episode_data['api'] + '?$select=Captions,CommentCount,MediaLengthInSeconds,PublishedDate,Rating,RatingCount,Title,VideoMP4High,VideoMP4Low,VideoMP4Medium,VideoPlayerPreviewImage,VideoWMV,VideoWMVHQ,Views,' if is_session: - content_url += '?$expand=Speakers' + content_url += 'Code,Description,Room,Slides,Speakers,ZipFile&$expand=Speakers' else: - content_url += '?$expand=Authors' + content_url += 'Authors,Body&$expand=Authors' content_data = self._download_json(content_url, content_id) title = content_data['Title'] @@ -210,7 +210,7 @@ class Channel9IE(InfoExtractor): 'id': content_id, 'title': title, 'description': clean_html(content_data.get('Description') or content_data.get('Body')), - 'thumbnail': content_data.get('Thumbnail') or content_data.get('VideoPlayerPreviewImage'), + 'thumbnail': content_data.get('VideoPlayerPreviewImage'), 'duration': int_or_none(content_data.get('MediaLengthInSeconds')), 'timestamp': parse_iso8601(content_data.get('PublishedDate')), 'avg_rating': int_or_none(content_data.get('Rating')), diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 656e715ae..a459dcb8d 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -3,7 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + lowercase_escape, + url_or_none, +) class ChaturbateIE(InfoExtractor): @@ -38,12 +42,31 @@ class ChaturbateIE(InfoExtractor): 'https://chaturbate.com/%s/' % video_id, video_id, headers=self.geo_verification_headers()) - m3u8_urls = [] + found_m3u8_urls = [] + + data = self._parse_json( + self._search_regex( + r'initialRoomDossier\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', + webpage, 'data', default='{}', group='value'), + video_id, transform_source=lowercase_escape, fatal=False) + if data: + m3u8_url = url_or_none(data.get('hls_source')) + if m3u8_url: + found_m3u8_urls.append(m3u8_url) + + if not found_m3u8_urls: + for m in re.finditer( + r'(\\u002[27])(?P<url>http.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(lowercase_escape(m.group('url'))) - for m in re.finditer( - r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage): - m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group( - 'url').replace('_fast', '') + if not found_m3u8_urls: + for m in re.finditer( + r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(m.group('url')) + + m3u8_urls = [] + for found_m3u8_url in found_m3u8_urls: + m3u8_fast_url, m3u8_no_fast_url = found_m3u8_url, found_m3u8_url.replace('_fast', '') for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url): if m3u8_url not in m3u8_urls: m3u8_urls.append(m3u8_url) @@ -63,7 +86,12 @@ class ChaturbateIE(InfoExtractor): formats = [] for m3u8_url in m3u8_urls: - m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow' + for known_id in ('fast', 'slow'): + if '_%s' % known_id in m3u8_url: + m3u8_id = known_id + break + else: + m3u8_id = None formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, ext='mp4', # ffmpeg skips segments for fast m3u8 diff --git a/youtube_dl/extractor/cloudflarestream.py b/youtube_dl/extractor/cloudflarestream.py index 8ff2c6531..2fdcfbb3a 100644 --- a/youtube_dl/extractor/cloudflarestream.py +++ b/youtube_dl/extractor/cloudflarestream.py @@ -1,20 +1,24 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import re from .common import InfoExtractor class CloudflareStreamIE(InfoExtractor): + _DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)' + _EMBED_RE = r'embed\.%s/embed/[^/]+\.js\?.*?\bvideo=' % _DOMAIN_RE + _ID_RE = r'[\da-f]{32}|[\w-]+\.[\w-]+\.[\w-]+' _VALID_URL = r'''(?x) https?:// (?: - (?:watch\.)?(?:cloudflarestream\.com|videodelivery\.net)/| - embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo= + (?:watch\.)?%s/| + %s ) - (?P<id>[\da-f]+) - ''' + (?P<id>%s) + ''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE) _TESTS = [{ 'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717', 'info_dict': { @@ -41,23 +45,28 @@ class CloudflareStreamIE(InfoExtractor): return [ mobj.group('url') for mobj in re.finditer( - r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1', + r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s(?:%s).*?)\1' % (CloudflareStreamIE._EMBED_RE, CloudflareStreamIE._ID_RE), webpage)] def _real_extract(self, url): video_id = self._match_id(url) + domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net' + base_url = 'https://%s/%s/' % (domain, video_id) + if '.' in video_id: + video_id = self._parse_json(base64.urlsafe_b64decode( + video_id.split('.')[1]), video_id)['sub'] + manifest_base_url = base_url + 'manifest/video.' formats = self._extract_m3u8_formats( - 'https://cloudflarestream.com/%s/manifest/video.m3u8' % video_id, - video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', - fatal=False) + manifest_base_url + 'm3u8', video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) formats.extend(self._extract_mpd_formats( - 'https://cloudflarestream.com/%s/manifest/video.mpd' % video_id, - video_id, mpd_id='dash', fatal=False)) + manifest_base_url + 'mpd', video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) return { 'id': video_id, 'title': video_id, + 'thumbnail': base_url + 'thumbnails/thumbnail.jpg', 'formats': formats, } diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py deleted file mode 100644 index 588aad0d9..000000000 --- a/youtube_dl/extractor/comcarcoff.py +++ /dev/null @@ -1,74 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - parse_duration, - parse_iso8601, -) - - -class ComCarCoffIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)' - _TESTS = [{ - 'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/', - 'info_dict': { - 'id': '2494164', - 'ext': 'mp4', - 'upload_date': '20141127', - 'timestamp': 1417107600, - 'duration': 1232, - 'title': 'Happy Thanksgiving Miranda', - 'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.', - }, - 'params': { - 'skip_download': 'requires ffmpeg', - } - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - if not display_id: - display_id = 'comediansincarsgettingcoffee.com' - webpage = self._download_webpage(url, display_id) - - full_data = self._parse_json( - self._search_regex( - r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'), - display_id)['videoData'] - - display_id = full_data['activeVideo']['video'] - video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id] - - video_id = compat_str(video_data['mediaId']) - title = video_data['title'] - formats = self._extract_m3u8_formats( - video_data['mediaUrl'], video_id, 'mp4') - self._sort_formats(formats) - - thumbnails = [{ - 'url': video_data['images']['thumb'], - }, { - 'url': video_data['images']['poster'], - }] - - timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601( - video_data.get('pubDate')) - duration = int_or_none(video_data.get('durationSeconds')) or parse_duration( - video_data.get('duration')) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': video_data.get('description'), - 'timestamp': timestamp, - 'duration': duration, - 'thumbnails': thumbnails, - 'formats': formats, - 'season_number': int_or_none(video_data.get('season')), - 'episode_number': int_or_none(video_data.get('episode')), - 'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))), - } diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 50d48c40d..eaae5e484 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1455,14 +1455,14 @@ class InfoExtractor(object): def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True, m3u8_id=None): + fatal=True, m3u8_id=None, data=None, headers={}, query={}): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', 'Unable to download f4m manifest', # Some manifests may be malformed, e.g. prosiebensat1 generated manifests # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244) transform_source=transform_source, - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if manifest is False: return [] @@ -1586,12 +1586,13 @@ class InfoExtractor(object): def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, entry_protocol='m3u8', preference=None, m3u8_id=None, note=None, errnote=None, - fatal=True, live=False): + fatal=True, live=False, data=None, headers={}, + query={}): res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', errnote=errnote or 'Failed to download m3u8 information', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] @@ -1765,6 +1766,19 @@ class InfoExtractor(object): # the same GROUP-ID f['acodec'] = 'none' formats.append(f) + + # for DailyMotion + progressive_uri = last_stream_inf.get('PROGRESSIVE-URI') + if progressive_uri: + http_f = f.copy() + del http_f['manifest_url'] + http_f.update({ + 'format_id': f['format_id'].replace('hls-', 'http-'), + 'protocol': 'http', + 'url': progressive_uri, + }) + formats.append(http_f) + last_stream_inf = {} return formats @@ -2009,12 +2023,12 @@ class InfoExtractor(object): }) return entries - def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}): + def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}): res = self._download_xml_handle( mpd_url, video_id, note=note or 'Downloading MPD manifest', errnote=errnote or 'Failed to download MPD manifest', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] mpd_doc, urlh = res @@ -2317,12 +2331,12 @@ class InfoExtractor(object): self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) return formats - def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True): + def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}): res = self._download_xml_handle( ism_url, video_id, note=note or 'Downloading ISM manifest', errnote=errnote or 'Failed to download ISM manifest', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] ism_doc, urlh = res @@ -2689,7 +2703,7 @@ class InfoExtractor(object): entry = { 'id': this_video_id, 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')), - 'description': video_data.get('description'), + 'description': clean_html(video_data.get('description')), 'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))), 'timestamp': int_or_none(video_data.get('pubdate')), 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), diff --git a/youtube_dl/extractor/contv.py b/youtube_dl/extractor/contv.py new file mode 100644 index 000000000..84b462d40 --- /dev/null +++ b/youtube_dl/extractor/contv.py @@ -0,0 +1,118 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, +) + + +class CONtvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter', + 'info_dict': { + 'id': 'CEG10022949', + 'ext': 'mp4', + 'title': 'Days Of Thrills & Laughter', + 'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb', + 'upload_date': '20180703', + 'timestamp': 1530634789.61, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites', + 'info_dict': { + 'id': 'CLIP-show_fotld_bts', + 'title': 'Fight of the Living Dead: Behind the Scenes Bites', + }, + 'playlist_mincount': 7, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + details = self._download_json( + 'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id, + video_id, query={'device': 'web'}) + + if details.get('type') == 'episodic': + seasons = self._download_json( + 'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id, + video_id) + entries = [] + for season in seasons: + for episode in season.get('episodes', []): + episode_id = episode.get('id') + if not episode_id: + continue + entries.append(self.url_result( + 'https://www.contv.com/details-movie/' + episode_id, + CONtvIE.ie_key(), episode_id)) + return self.playlist_result(entries, video_id, details.get('title')) + + m_details = details['details'] + title = details['title'] + + formats = [] + + media_hls_url = m_details.get('media_hls_url') + if media_hls_url: + formats.extend(self._extract_m3u8_formats( + media_hls_url, video_id, 'mp4', + m3u8_id='hls', fatal=False)) + + media_mp4_url = m_details.get('media_mp4_url') + if media_mp4_url: + formats.append({ + 'format_id': 'http', + 'url': media_mp4_url, + }) + + self._sort_formats(formats) + + subtitles = {} + captions = m_details.get('captions') or {} + for caption_url in captions.values(): + subtitles.setdefault('en', []).append({ + 'url': caption_url + }) + + thumbnails = [] + for image in m_details.get('images', []): + image_url = image.get('url') + if not image_url: + continue + thumbnails.append({ + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + description = None + for p in ('large_', 'medium_', 'small_', ''): + d = m_details.get(p + 'description') + if d: + description = d + break + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': description, + 'timestamp': float_or_none(details.get('metax_added_on'), 1000), + 'subtitles': subtitles, + 'duration': float_or_none(m_details.get('duration'), 1000), + 'view_count': int_or_none(details.get('num_watched')), + 'like_count': int_or_none(details.get('num_fav')), + 'categories': details.get('category'), + 'tags': details.get('tags'), + 'season_number': int_or_none(details.get('season')), + 'episode_number': int_or_none(details.get('episode')), + 'release_year': int_or_none(details.get('pub_year')), + } diff --git a/youtube_dl/extractor/corus.py b/youtube_dl/extractor/corus.py index a1b251804..e11aadf14 100644 --- a/youtube_dl/extractor/corus.py +++ b/youtube_dl/extractor/corus.py @@ -4,7 +4,12 @@ from __future__ import unicode_literals import re from .theplatform import ThePlatformFeedIE -from ..utils import int_or_none +from ..utils import ( + dict_get, + ExtractorError, + float_or_none, + int_or_none, +) class CorusIE(ThePlatformFeedIE): @@ -12,24 +17,49 @@ class CorusIE(ThePlatformFeedIE): https?:// (?:www\.)? (?P<domain> - (?:globaltv|etcanada)\.com| - (?:hgtv|foodnetwork|slice|history|showcase|bigbrothercanada)\.ca + (?: + globaltv| + etcanada| + seriesplus| + wnetwork| + ytv + )\.com| + (?: + hgtv| + foodnetwork| + slice| + history| + showcase| + bigbrothercanada| + abcspark| + disney(?:channel|lachaine) + )\.ca + ) + /(?:[^/]+/)* + (?: + video\.html\?.*?\bv=| + videos?/(?:[^/]+/)*(?:[a-z0-9-]+-)? + ) + (?P<id> + [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}| + (?:[A-Z]{4})?\d{12,20} ) - /(?:video/(?:[^/]+/)?|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=)) - (?P<id>\d+) ''' _TESTS = [{ 'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/', - 'md5': '05dcbca777bf1e58c2acbb57168ad3a6', 'info_dict': { 'id': '870923331648', 'ext': 'mp4', 'title': 'Movie Night Popcorn with Bryan', 'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.', - 'uploader': 'SHWM-NEW', 'upload_date': '20170206', 'timestamp': 1486392197, }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + }, + 'expected_warnings': ['Failed to parse JSON'], }, { 'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753', 'only_matching': True, @@ -48,58 +78,83 @@ class CorusIE(ThePlatformFeedIE): }, { 'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/', 'only_matching': True + }, { + 'url': 'https://www.seriesplus.com/emissions/dre-mary-mort-sur-ordonnance/videos/deux-coeurs-battant/SERP0055626330000200/', + 'only_matching': True + }, { + 'url': 'https://www.disneychannel.ca/shows/gabby-duran-the-unsittables/video/crybaby-duran-clip/2f557eec-0588-11ea-ae2b-e2c6776b770e/', + 'only_matching': True }] - - _TP_FEEDS = { - 'globaltv': { - 'feed_id': 'ChQqrem0lNUp', - 'account_id': 2269680845, - }, - 'etcanada': { - 'feed_id': 'ChQqrem0lNUp', - 'account_id': 2269680845, - }, - 'hgtv': { - 'feed_id': 'L0BMHXi2no43', - 'account_id': 2414428465, - }, - 'foodnetwork': { - 'feed_id': 'ukK8o58zbRmJ', - 'account_id': 2414429569, - }, - 'slice': { - 'feed_id': '5tUJLgV2YNJ5', - 'account_id': 2414427935, - }, - 'history': { - 'feed_id': 'tQFx_TyyEq4J', - 'account_id': 2369613659, - }, - 'showcase': { - 'feed_id': '9H6qyshBZU3E', - 'account_id': 2414426607, - }, - 'bigbrothercanada': { - 'feed_id': 'ChQqrem0lNUp', - 'account_id': 2269680845, - }, + _GEO_BYPASS = False + _SITE_MAP = { + 'globaltv': 'series', + 'etcanada': 'series', + 'foodnetwork': 'food', + 'bigbrothercanada': 'series', + 'disneychannel': 'disneyen', + 'disneylachaine': 'disneyfr', } def _real_extract(self, url): domain, video_id = re.match(self._VALID_URL, url).groups() - feed_info = self._TP_FEEDS[domain.split('.')[0]] - return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: { - 'episode_number': int_or_none(e.get('pl1$episode')), - 'season_number': int_or_none(e.get('pl1$season')), - 'series': e.get('pl1$show'), - }, { - 'HLS': { - 'manifest': 'm3u', - }, - 'DesktopHLS Default': { - 'manifest': 'm3u', - }, - 'MP4 MBR': { - 'manifest': 'm3u', - }, - }, feed_info['account_id']) + site = domain.split('.')[0] + path = self._SITE_MAP.get(site, site) + if path != 'series': + path = 'migration/' + path + video = self._download_json( + 'https://globalcontent.corusappservices.com/templates/%s/playlist/' % path, + video_id, query={'byId': video_id}, + headers={'Accept': 'application/json'})[0] + title = video['title'] + + formats = [] + for source in video.get('sources', []): + smil_url = source.get('file') + if not smil_url: + continue + source_type = source.get('type') + note = 'Downloading%s smil file' % (' ' + source_type if source_type else '') + resp = self._download_webpage( + smil_url, video_id, note, fatal=False, + headers=self.geo_verification_headers()) + if not resp: + continue + error = self._parse_json(resp, video_id, fatal=False) + if error: + if error.get('exception') == 'GeoLocationBlocked': + self.raise_geo_restricted(countries=['CA']) + raise ExtractorError(error['description']) + smil = self._parse_xml(resp, video_id, fatal=False) + if smil is None: + continue + namespace = self._parse_smil_namespace(smil) + formats.extend(self._parse_smil_formats( + smil, smil_url, video_id, namespace)) + if not formats and video.get('drm'): + raise ExtractorError('This video is DRM protected.', expected=True) + self._sort_formats(formats) + + subtitles = {} + for track in video.get('tracks', []): + track_url = track.get('file') + if not track_url: + continue + lang = 'fr' if site in ('disneylachaine', 'seriesplus') else 'en' + subtitles.setdefault(lang, []).append({'url': track_url}) + + metadata = video.get('metadata') or {} + get_number = lambda x: int_or_none(video.get('pl1$' + x) or metadata.get(x + 'Number')) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': dict_get(video, ('defaultThumbnailUrl', 'thumbnail', 'image')), + 'description': video.get('description'), + 'timestamp': int_or_none(video.get('availableDate'), 1000), + 'subtitles': subtitles, + 'duration': float_or_none(metadata.get('duration')), + 'series': dict_get(video, ('show', 'pl1$show')), + 'season_number': get_number('season'), + 'episode_number': get_number('episode'), + } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 745971900..327fdb04a 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,50 +1,93 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import functools -import hashlib -import itertools import json -import random import re -import string from .common import InfoExtractor -from ..compat import compat_struct_pack +from ..compat import compat_HTTPError from ..utils import ( - determine_ext, - error_to_compat_str, + age_restricted, + clean_html, ExtractorError, int_or_none, - mimetype2ext, OnDemandPagedList, - parse_iso8601, - sanitized_Request, - str_to_int, try_get, unescapeHTML, - update_url_query, - url_or_none, urlencode_postdata, ) class DailymotionBaseInfoExtractor(InfoExtractor): - @staticmethod - def _build_request(url): - """Build a request with the family filter disabled""" - request = sanitized_Request(url) - request.add_header('Cookie', 'family_filter=off; ff=off') - return request + _FAMILY_FILTER = None + _HEADERS = { + 'Content-Type': 'application/json', + 'Origin': 'https://www.dailymotion.com', + } + _NETRC_MACHINE = 'dailymotion' - def _download_webpage_handle_no_ff(self, url, *args, **kwargs): - request = self._build_request(url) - return self._download_webpage_handle(request, *args, **kwargs) + def _get_dailymotion_cookies(self): + return self._get_cookies('https://www.dailymotion.com/') - def _download_webpage_no_ff(self, url, *args, **kwargs): - request = self._build_request(url) - return self._download_webpage(request, *args, **kwargs) + @staticmethod + def _get_cookie_value(cookies, name): + cookie = cookies.get('name') + if cookie: + return cookie.value + + def _set_dailymotion_cookie(self, name, value): + self._set_cookie('www.dailymotion.com', name, value) + + def _real_initialize(self): + cookies = self._get_dailymotion_cookies() + ff = self._get_cookie_value(cookies, 'ff') + self._FAMILY_FILTER = ff == 'on' if ff else age_restricted(18, self._downloader.params.get('age_limit')) + self._set_dailymotion_cookie('ff', 'on' if self._FAMILY_FILTER else 'off') + + def _call_api(self, object_type, xid, object_fields, note, filter_extra=None): + if not self._HEADERS.get('Authorization'): + cookies = self._get_dailymotion_cookies() + token = self._get_cookie_value(cookies, 'access_token') or self._get_cookie_value(cookies, 'client_token') + if not token: + data = { + 'client_id': 'f1a362d288c1b98099c7', + 'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5', + } + username, password = self._get_login_info() + if username: + data.update({ + 'grant_type': 'password', + 'password': password, + 'username': username, + }) + else: + data['grant_type'] = 'client_credentials' + try: + token = self._download_json( + 'https://graphql.api.dailymotion.com/oauth/token', + None, 'Downloading Access Token', + data=urlencode_postdata(data))['access_token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + raise ExtractorError(self._parse_json( + e.cause.read().decode(), xid)['error_description'], expected=True) + raise + self._set_dailymotion_cookie('access_token' if username else 'client_token', token) + self._HEADERS['Authorization'] = 'Bearer ' + token + + resp = self._download_json( + 'https://graphql.api.dailymotion.com/', xid, note, data=json.dumps({ + 'query': '''{ + %s(xid: "%s"%s) { + %s + } +}''' % (object_type, xid, ', ' + filter_extra if filter_extra else '', object_fields), + }).encode(), headers=self._HEADERS) + obj = resp['data'][object_type] + if not obj: + raise ExtractorError(resp['errors'][0]['message'], expected=True) + return obj class DailymotionIE(DailymotionBaseInfoExtractor): @@ -54,18 +97,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor): (?:(?:www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|\#)/)?video|swf)| (?:www\.)?lequipe\.fr/video ) - /(?P<id>[^/?_]+) + /(?P<id>[^/?_]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))? ''' IE_NAME = 'dailymotion' - - _FORMATS = [ - ('stream_h264_ld_url', 'ld'), - ('stream_h264_url', 'standard'), - ('stream_h264_hq_url', 'hq'), - ('stream_h264_hd_url', 'hd'), - ('stream_h264_hd1080_url', 'hd180'), - ] - _TESTS = [{ 'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news', 'md5': '074b95bdee76b9e3654137aee9c79dfe', @@ -74,7 +108,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'ext': 'mp4', 'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller', 'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller', - 'thumbnail': r're:^https?:.*\.(?:jpg|png)$', 'duration': 187, 'timestamp': 1493651285, 'upload_date': '20170501', @@ -146,7 +179,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor): }, { 'url': 'https://www.lequipe.fr/video/k7MtHciueyTcrFtFKA2', 'only_matching': True, + }, { + 'url': 'https://www.dailymotion.com/video/x3z49k?playlist=xv4bw', + 'only_matching': True, }] + _GEO_BYPASS = False + _COMMON_MEDIA_FIELDS = '''description + geoblockedCountries { + allowed + } + xid''' @staticmethod def _extract_urls(webpage): @@ -162,264 +204,140 @@ class DailymotionIE(DailymotionBaseInfoExtractor): return urls def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage_no_ff( - 'https://www.dailymotion.com/video/%s' % video_id, video_id) - - age_limit = self._rta_search(webpage) - - description = self._og_search_description( - webpage, default=None) or self._html_search_meta( - 'description', webpage, 'description') - - view_count_str = self._search_regex( - (r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"', - r'video_views_count[^>]+>\s+([\s\d\,.]+)'), - webpage, 'view count', default=None) - if view_count_str: - view_count_str = re.sub(r'\s', '', view_count_str) - view_count = str_to_int(view_count_str) - comment_count = int_or_none(self._search_regex( - r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"', - webpage, 'comment count', default=None)) - - player_v5 = self._search_regex( - [r'buildPlayer\(({.+?})\);\n', # See https://github.com/ytdl-org/youtube-dl/issues/7826 - r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', - r'buildPlayer\(({.+?})\);', - r'var\s+config\s*=\s*({.+?});', - # New layout regex (see https://github.com/ytdl-org/youtube-dl/issues/13580) - r'__PLAYER_CONFIG__\s*=\s*({.+?});'], - webpage, 'player v5', default=None) - if player_v5: - player = self._parse_json(player_v5, video_id, fatal=False) or {} - metadata = try_get(player, lambda x: x['metadata'], dict) - if not metadata: - metadata_url = url_or_none(try_get( - player, lambda x: x['context']['metadata_template_url1'])) - if metadata_url: - metadata_url = metadata_url.replace(':videoId', video_id) - else: - metadata_url = update_url_query( - 'https://www.dailymotion.com/player/metadata/video/%s' - % video_id, { - 'embedder': url, - 'integration': 'inline', - 'GK_PV5_NEON': '1', - }) - metadata = self._download_json( - metadata_url, video_id, 'Downloading metadata JSON') - - if try_get(metadata, lambda x: x['error']['type']) == 'password_protected': - password = self._downloader.params.get('videopassword') - if password: - r = int(metadata['id'][1:], 36) - us64e = lambda x: base64.urlsafe_b64encode(x).decode().strip('=') - t = ''.join(random.choice(string.ascii_letters) for i in range(10)) - n = us64e(compat_struct_pack('I', r)) - i = us64e(hashlib.md5(('%s%d%s' % (password, r, t)).encode()).digest()) - metadata = self._download_json( - 'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id) - - self._check_error(metadata) - - formats = [] - for quality, media_list in metadata['qualities'].items(): - for media in media_list: - media_url = media.get('url') - if not media_url: - continue - type_ = media.get('type') - if type_ == 'application/vnd.lumberjack.manifest': - continue - ext = mimetype2ext(type_) or determine_ext(media_url) - if ext == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - media_url, video_id, 'mp4', preference=-1, - m3u8_id='hls', fatal=False) - for f in m3u8_formats: - f['url'] = f['url'].split('#')[0] - formats.append(f) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - media_url, video_id, preference=-1, f4m_id='hds', fatal=False)) - else: - f = { - 'url': media_url, - 'format_id': 'http-%s' % quality, - 'ext': ext, - } - m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url) - if m: - f.update({ - 'width': int(m.group('width')), - 'height': int(m.group('height')), - }) - formats.append(f) - self._sort_formats(formats) - - title = metadata['title'] - duration = int_or_none(metadata.get('duration')) - timestamp = int_or_none(metadata.get('created_time')) - thumbnail = metadata.get('poster_url') - uploader = metadata.get('owner', {}).get('screenname') - uploader_id = metadata.get('owner', {}).get('id') - - subtitles = {} - subtitles_data = metadata.get('subtitles', {}).get('data', {}) - if subtitles_data and isinstance(subtitles_data, dict): - for subtitle_lang, subtitle in subtitles_data.items(): - subtitles[subtitle_lang] = [{ - 'ext': determine_ext(subtitle_url), - 'url': subtitle_url, - } for subtitle_url in subtitle.get('urls', [])] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'age_limit': age_limit, - 'view_count': view_count, - 'comment_count': comment_count, - 'formats': formats, - 'subtitles': subtitles, - } - - # vevo embed - vevo_id = self._search_regex( - r'<link rel="video_src" href="[^"]*?vevo\.com[^"]*?video=(?P<id>[\w]*)', - webpage, 'vevo embed', default=None) - if vevo_id: - return self.url_result('vevo:%s' % vevo_id, 'Vevo') - - # fallback old player - embed_page = self._download_webpage_no_ff( - 'https://www.dailymotion.com/embed/video/%s' % video_id, - video_id, 'Downloading embed page') - - timestamp = parse_iso8601(self._html_search_meta( - 'video:release_date', webpage, 'upload date')) - - info = self._parse_json( - self._search_regex( - r'var info = ({.*?}),$', embed_page, - 'video info', flags=re.MULTILINE), - video_id) - - self._check_error(info) + video_id, playlist_id = re.match(self._VALID_URL, url).groups() + + if playlist_id: + if not self._downloader.params.get('noplaylist'): + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id) + return self.url_result( + 'http://www.dailymotion.com/playlist/' + playlist_id, + 'DailymotionPlaylist', playlist_id) + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) + + password = self._downloader.params.get('videopassword') + media = self._call_api( + 'media', video_id, '''... on Video { + %s + stats { + likes { + total + } + views { + total + } + } + } + ... on Live { + %s + audienceCount + isOnAir + }''' % (self._COMMON_MEDIA_FIELDS, self._COMMON_MEDIA_FIELDS), 'Downloading media JSON metadata', + 'password: "%s"' % self._downloader.params.get('videopassword') if password else None) + xid = media['xid'] + + metadata = self._download_json( + 'https://www.dailymotion.com/player/metadata/video/' + xid, + xid, 'Downloading metadata JSON', + query={'app': 'com.dailymotion.neon'}) + + error = metadata.get('error') + if error: + title = error.get('title') or error['raw_message'] + # See https://developer.dailymotion.com/api#access-error + if error.get('code') == 'DM007': + allowed_countries = try_get(media, lambda x: x['geoblockedCountries']['allowed'], list) + self.raise_geo_restricted(msg=title, countries=allowed_countries) + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, title), expected=True) + title = metadata['title'] + is_live = media.get('isOnAir') formats = [] - for (key, format_id) in self._FORMATS: - video_url = info.get(key) - if video_url is not None: - m_size = re.search(r'H264-(\d+)x(\d+)', video_url) - if m_size is not None: - width, height = map(int_or_none, (m_size.group(1), m_size.group(2))) + for quality, media_list in metadata['qualities'].items(): + for m in media_list: + media_url = m.get('url') + media_type = m.get('type') + if not media_url or media_type == 'application/vnd.lumberjack.manifest': + continue + if media_type == 'application/x-mpegURL': + formats.extend(self._extract_m3u8_formats( + media_url, video_id, 'mp4', + 'm3u8' if is_live else 'm3u8_native', + m3u8_id='hls', fatal=False)) else: - width, height = None, None - formats.append({ - 'url': video_url, - 'ext': 'mp4', - 'format_id': format_id, - 'width': width, - 'height': height, - }) + f = { + 'url': media_url, + 'format_id': 'http-' + quality, + } + m = re.search(r'/H264-(\d+)x(\d+)(?:-(60)/)?', media_url) + if m: + width, height, fps = map(int_or_none, m.groups()) + f.update({ + 'fps': fps, + 'height': height, + 'width': width, + }) + formats.append(f) + for f in formats: + f['url'] = f['url'].split('#')[0] + if not f.get('fps') and f['format_id'].endswith('@60'): + f['fps'] = 60 self._sort_formats(formats) - # subtitles - video_subtitles = self.extract_subtitles(video_id, webpage) - - title = self._og_search_title(webpage, default=None) - if title is None: - title = self._html_search_regex( - r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage, - 'title') + subtitles = {} + subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {} + for subtitle_lang, subtitle in subtitles_data.items(): + subtitles[subtitle_lang] = [{ + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] + + thumbnails = [] + for height, poster_url in metadata.get('posters', {}).items(): + thumbnails.append({ + 'height': int_or_none(height), + 'id': height, + 'url': poster_url, + }) + + owner = metadata.get('owner') or {} + stats = media.get('stats') or {} + get_count = lambda x: int_or_none(try_get(stats, lambda y: y[x + 's']['total'])) return { 'id': video_id, + 'title': self._live_title(title) if is_live else title, + 'description': clean_html(media.get('description')), + 'thumbnails': thumbnails, + 'duration': int_or_none(metadata.get('duration')) or None, + 'timestamp': int_or_none(metadata.get('created_time')), + 'uploader': owner.get('screenname'), + 'uploader_id': owner.get('id') or metadata.get('screenname'), + 'age_limit': 18 if metadata.get('explicit') else 0, + 'tags': metadata.get('tags'), + 'view_count': get_count('view') or int_or_none(media.get('audienceCount')), + 'like_count': get_count('like'), 'formats': formats, - 'uploader': info['owner.screenname'], - 'timestamp': timestamp, - 'title': title, - 'description': description, - 'subtitles': video_subtitles, - 'thumbnail': info['thumbnail_url'], - 'age_limit': age_limit, - 'view_count': view_count, - 'duration': info['duration'] + 'subtitles': subtitles, + 'is_live': is_live, } - def _check_error(self, info): - error = info.get('error') - if error: - title = error.get('title') or error['message'] - # See https://developer.dailymotion.com/api#access-error - if error.get('code') == 'DM007': - self.raise_geo_restricted(msg=title) - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, title), expected=True) - - def _get_subtitles(self, video_id, webpage): - try: - sub_list = self._download_webpage( - 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, - video_id, note=False) - except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) - return {} - info = json.loads(sub_list) - if (info['total'] > 0): - sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list']) - return sub_lang_list - self._downloader.report_warning('video doesn\'t have subtitles') - return {} - -class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): - IE_NAME = 'dailymotion:playlist' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)' - _TESTS = [{ - 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', - 'info_dict': { - 'title': 'SPORT', - 'id': 'xv4bw', - }, - 'playlist_mincount': 20, - }] +class DailymotionPlaylistBaseIE(DailymotionBaseInfoExtractor): _PAGE_SIZE = 100 - def _fetch_page(self, playlist_id, authorizaion, page): + def _fetch_page(self, playlist_id, page): page += 1 - videos = self._download_json( - 'https://graphql.api.dailymotion.com', - playlist_id, 'Downloading page %d' % page, - data=json.dumps({ - 'query': '''{ - collection(xid: "%s") { - videos(first: %d, page: %d) { - pageInfo { - hasNextPage - nextPage - } + videos = self._call_api( + self._OBJECT_TYPE, playlist_id, + '''videos(allowExplicit: %s, first: %d, page: %d) { edges { node { xid url } } - } - } -}''' % (playlist_id, self._PAGE_SIZE, page) - }).encode(), headers={ - 'Authorization': authorizaion, - 'Origin': 'https://www.dailymotion.com', - })['data']['collection']['videos'] + }''' % ('false' if self._FAMILY_FILTER else 'true', self._PAGE_SIZE, page), + 'Downloading page %d' % page)['videos'] for edge in videos['edges']: node = edge['node'] yield self.url_result( @@ -427,86 +345,49 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): def _real_extract(self, url): playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - api = self._parse_json(self._search_regex( - r'__PLAYER_CONFIG__\s*=\s*({.+?});', - webpage, 'player config'), playlist_id)['context']['api'] - auth = self._download_json( - api.get('auth_url', 'https://graphql.api.dailymotion.com/oauth/token'), - playlist_id, data=urlencode_postdata({ - 'client_id': api.get('client_id', 'f1a362d288c1b98099c7'), - 'client_secret': api.get('client_secret', 'eea605b96e01c796ff369935357eca920c5da4c5'), - 'grant_type': 'client_credentials', - })) - authorizaion = '%s %s' % (auth.get('token_type', 'Bearer'), auth['access_token']) entries = OnDemandPagedList(functools.partial( - self._fetch_page, playlist_id, authorizaion), self._PAGE_SIZE) + self._fetch_page, playlist_id), self._PAGE_SIZE) return self.playlist_result( - entries, playlist_id, - self._og_search_title(webpage)) + entries, playlist_id) + + +class DailymotionPlaylistIE(DailymotionPlaylistBaseIE): + IE_NAME = 'dailymotion:playlist' + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)' + _TESTS = [{ + 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', + 'info_dict': { + 'id': 'xv4bw', + }, + 'playlist_mincount': 20, + }] + _OBJECT_TYPE = 'collection' -class DailymotionUserIE(DailymotionBaseInfoExtractor): +class DailymotionUserIE(DailymotionPlaylistBaseIE): IE_NAME = 'dailymotion:user' - _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)' - _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' - _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<id>[^/]+)' _TESTS = [{ 'url': 'https://www.dailymotion.com/user/nqtv', 'info_dict': { 'id': 'nqtv', - 'title': 'Rémi Gaillard', }, - 'playlist_mincount': 100, + 'playlist_mincount': 152, }, { 'url': 'http://www.dailymotion.com/user/UnderProject', 'info_dict': { 'id': 'UnderProject', - 'title': 'UnderProject', }, - 'playlist_mincount': 1800, - 'expected_warnings': [ - 'Stopped at duplicated page', - ], + 'playlist_mincount': 1000, 'skip': 'Takes too long time', + }, { + 'url': 'https://www.dailymotion.com/user/nqtv', + 'info_dict': { + 'id': 'nqtv', + }, + 'playlist_mincount': 148, + 'params': { + 'age_limit': 0, + }, }] - - def _extract_entries(self, id): - video_ids = set() - processed_urls = set() - for pagenum in itertools.count(1): - page_url = self._PAGE_TEMPLATE % (id, pagenum) - webpage, urlh = self._download_webpage_handle_no_ff( - page_url, id, 'Downloading page %s' % pagenum) - if urlh.geturl() in processed_urls: - self.report_warning('Stopped at duplicated page %s, which is the same as %s' % ( - page_url, urlh.geturl()), id) - break - - processed_urls.add(urlh.geturl()) - - for video_id in re.findall(r'data-xid="(.+?)"', webpage): - if video_id not in video_ids: - yield self.url_result( - 'http://www.dailymotion.com/video/%s' % video_id, - DailymotionIE.ie_key(), video_id) - video_ids.add(video_id) - - if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: - break - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user = mobj.group('user') - webpage = self._download_webpage( - 'https://www.dailymotion.com/user/%s' % user, user) - full_user = unescapeHTML(self._html_search_regex( - r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user), - webpage, 'user')) - - return { - '_type': 'playlist', - 'id': user, - 'title': full_user, - 'entries': self._extract_entries(user), - } + _OBJECT_TYPE = 'channel' diff --git a/youtube_dl/extractor/daisuki.py b/youtube_dl/extractor/daisuki.py deleted file mode 100644 index dbc1aa5d4..000000000 --- a/youtube_dl/extractor/daisuki.py +++ /dev/null @@ -1,154 +0,0 @@ -from __future__ import unicode_literals - -import base64 -import json -import random -import re - -from .common import InfoExtractor -from ..aes import ( - aes_cbc_decrypt, - aes_cbc_encrypt, -) -from ..compat import compat_b64decode -from ..utils import ( - bytes_to_intlist, - bytes_to_long, - extract_attributes, - ExtractorError, - intlist_to_bytes, - js_to_json, - int_or_none, - long_to_bytes, - pkcs1pad, -) - - -class DaisukiMottoIE(InfoExtractor): - _VALID_URL = r'https?://motto\.daisuki\.net/framewatch/embed/[^/]+/(?P<id>[0-9a-zA-Z]{3})' - - _TEST = { - 'url': 'http://motto.daisuki.net/framewatch/embed/embedDRAGONBALLSUPERUniverseSurvivalsaga/V2e/760/428', - 'info_dict': { - 'id': 'V2e', - 'ext': 'mp4', - 'title': '#117 SHOWDOWN OF LOVE! ANDROIDS VS UNIVERSE 2!!', - 'subtitles': { - 'mul': [{ - 'ext': 'ttml', - }], - }, - }, - 'params': { - 'skip_download': True, # AES-encrypted HLS stream - }, - } - - # The public key in PEM format can be found in clientlibs_anime_watch.min.js - _RSA_KEY = (0xc5524c25e8e14b366b3754940beeb6f96cb7e2feef0b932c7659a0c5c3bf173d602464c2df73d693b513ae06ff1be8f367529ab30bf969c5640522181f2a0c51ea546ae120d3d8d908595e4eff765b389cde080a1ef7f1bbfb07411cc568db73b7f521cedf270cbfbe0ddbc29b1ac9d0f2d8f4359098caffee6d07915020077d, 65537) - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - flashvars = self._parse_json(self._search_regex( - r'(?s)var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), - video_id, transform_source=js_to_json) - - iv = [0] * 16 - - data = {} - for key in ('device_cd', 'mv_id', 'ss1_prm', 'ss2_prm', 'ss3_prm', 'ss_id'): - data[key] = flashvars.get(key, '') - - encrypted_rtn = None - - # Some AES keys are rejected. Try it with different AES keys - for idx in range(5): - aes_key = [random.randint(0, 254) for _ in range(32)] - padded_aeskey = intlist_to_bytes(pkcs1pad(aes_key, 128)) - - n, e = self._RSA_KEY - encrypted_aeskey = long_to_bytes(pow(bytes_to_long(padded_aeskey), e, n)) - init_data = self._download_json( - 'http://motto.daisuki.net/fastAPI/bgn/init/', - video_id, query={ - 's': flashvars.get('s', ''), - 'c': flashvars.get('ss3_prm', ''), - 'e': url, - 'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt( - bytes_to_intlist(json.dumps(data)), - aes_key, iv))).decode('ascii'), - 'a': base64.b64encode(encrypted_aeskey).decode('ascii'), - }, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else '')) - - if 'rtn' in init_data: - encrypted_rtn = init_data['rtn'] - break - - self._sleep(5, video_id) - - if encrypted_rtn is None: - raise ExtractorError('Failed to fetch init data') - - rtn = self._parse_json( - intlist_to_bytes(aes_cbc_decrypt(bytes_to_intlist( - compat_b64decode(encrypted_rtn)), - aes_key, iv)).decode('utf-8').rstrip('\0'), - video_id) - - title = rtn['title_str'] - - formats = self._extract_m3u8_formats( - rtn['play_url'], video_id, ext='mp4', entry_protocol='m3u8_native') - - subtitles = {} - caption_url = rtn.get('caption_url') - if caption_url: - # mul: multiple languages - subtitles['mul'] = [{ - 'url': caption_url, - 'ext': 'ttml', - }] - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'subtitles': subtitles, - } - - -class DaisukiMottoPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://motto\.daisuki\.net/(?P<id>information)/' - - _TEST = { - 'url': 'http://motto.daisuki.net/information/', - 'info_dict': { - 'title': 'DRAGON BALL SUPER', - }, - 'playlist_mincount': 117, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - - webpage = self._download_webpage(url, playlist_id) - - entries = [] - for li in re.findall(r'(<li[^>]+?data-product_id="[a-zA-Z0-9]{3}"[^>]+>)', webpage): - attr = extract_attributes(li) - ad_id = attr.get('data-ad_id') - product_id = attr.get('data-product_id') - if ad_id and product_id: - episode_id = attr.get('data-chapter') - entries.append({ - '_type': 'url_transparent', - 'url': 'http://motto.daisuki.net/framewatch/embed/%s/%s/760/428' % (ad_id, product_id), - 'episode_id': episode_id, - 'episode_number': int_or_none(episode_id), - 'ie_key': 'DaisukiMotto', - }) - - return self.playlist_result(entries, playlist_title='DRAGON BALL SUPER') diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 76f021892..137095577 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -2,25 +2,21 @@ from __future__ import unicode_literals -import re import itertools from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urllib_parse_unquote, - compat_urllib_parse_urlencode, compat_urlparse, ) -from ..utils import ( - int_or_none, - str_to_int, - xpath_text, - unescapeHTML, -) -class DaumIE(InfoExtractor): +class DaumBaseIE(InfoExtractor): + _KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/' + + +class DaumIE(DaumBaseIE): _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)' IE_NAME = 'daum.net' @@ -36,6 +32,9 @@ class DaumIE(InfoExtractor): 'duration': 2117, 'view_count': int, 'comment_count': int, + 'uploader_id': 186139, + 'uploader': '콘간지', + 'timestamp': 1387310323, }, }, { 'url': 'http://m.tvpot.daum.net/v/65139429', @@ -44,11 +43,14 @@ class DaumIE(InfoExtractor): 'ext': 'mp4', 'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118', 'description': 'md5:79794514261164ff27e36a21ad229fc5', - 'upload_date': '20150604', + 'upload_date': '20150118', 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 154, 'view_count': int, 'comment_count': int, + 'uploader': 'MBC 예능', + 'uploader_id': 132251, + 'timestamp': 1421604228, }, }, { 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24', @@ -59,12 +61,15 @@ class DaumIE(InfoExtractor): 'id': 'vwIpVpCQsT8$', 'ext': 'flv', 'title': '01-Korean War ( Trouble on the horizon )', - 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름', + 'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름', 'upload_date': '20080223', 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 249, 'view_count': int, 'comment_count': int, + 'uploader': '까칠한 墮落始祖 황비홍님의', + 'uploader_id': 560824, + 'timestamp': 1203770745, }, }, { # Requires dte_type=WEB (#9972) @@ -73,60 +78,24 @@ class DaumIE(InfoExtractor): 'info_dict': { 'id': 's3794Uf1NZeZ1qMpGpeqeRU', 'ext': 'mp4', - 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611', - 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회', - 'upload_date': '20160611', + 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', + 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', + 'upload_date': '20170129', + 'uploader': '쇼! 음악중심', + 'uploader_id': 2653210, + 'timestamp': 1485684628, }, }] def _real_extract(self, url): video_id = compat_urllib_parse_unquote(self._match_id(url)) - movie_data = self._download_json( - 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json', - video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'}) - - # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid - if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id): - return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id) - - info = self._download_xml( - 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id, - 'Downloading video info', query={'vid': video_id}) - - formats = [] - for format_el in movie_data['output_list']['output_list']: - profile = format_el['profile'] - format_query = compat_urllib_parse_urlencode({ - 'vid': video_id, - 'profile': profile, - }) - url_doc = self._download_xml( - 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, - video_id, note='Downloading video data for %s format' % profile) - format_url = url_doc.find('result/url').text - formats.append({ - 'url': format_url, - 'format_id': profile, - 'width': int_or_none(format_el.get('width')), - 'height': int_or_none(format_el.get('height')), - 'filesize': int_or_none(format_el.get('filesize')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': info.find('TITLE').text, - 'formats': formats, - 'thumbnail': xpath_text(info, 'THUMB_URL'), - 'description': xpath_text(info, 'CONTENTS'), - 'duration': int_or_none(xpath_text(info, 'DURATION')), - 'upload_date': info.find('REGDTTM').text[:8], - 'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')), - 'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')), - } + if not video_id.isdigit(): + video_id += '@my' + return self.url_result( + self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id) -class DaumClipIE(InfoExtractor): +class DaumClipIE(DaumBaseIE): _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)' IE_NAME = 'daum.net:clip' _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s' @@ -142,6 +111,9 @@ class DaumClipIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 3868, 'view_count': int, + 'uploader': 'GOMeXP', + 'uploader_id': 6667, + 'timestamp': 1377911092, }, }, { 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425', @@ -154,22 +126,8 @@ class DaumClipIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - clip_info = self._download_json( - 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id, - video_id, 'Downloading clip info')['clip_bean'] - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'], - 'title': unescapeHTML(clip_info['title']), - 'thumbnail': clip_info.get('thumb_url'), - 'description': clip_info.get('contents'), - 'duration': int_or_none(clip_info.get('duration')), - 'upload_date': clip_info.get('up_date')[:8], - 'view_count': int_or_none(clip_info.get('play_count')), - 'ie_key': 'Daum', - } + return self.url_result( + self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id) class DaumListIE(InfoExtractor): diff --git a/youtube_dl/extractor/dctp.py b/youtube_dl/extractor/dctp.py index 04ff214f7..e700f8d86 100644 --- a/youtube_dl/extractor/dctp.py +++ b/youtube_dl/extractor/dctp.py @@ -16,10 +16,11 @@ class DctpTvIE(InfoExtractor): _TESTS = [{ # 4x3 'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/', + 'md5': '3ffbd1556c3fe210724d7088fad723e3', 'info_dict': { 'id': '95eaa4f33dad413aa17b4ee613cccc6c', 'display_id': 'videoinstallation-fuer-eine-kaufhausfassade', - 'ext': 'flv', + 'ext': 'm4v', 'title': 'Videoinstallation für eine Kaufhausfassade', 'description': 'Kurzfilm', 'thumbnail': r're:^https?://.*\.jpg$', @@ -27,10 +28,6 @@ class DctpTvIE(InfoExtractor): 'timestamp': 1302172322, 'upload_date': '20110407', }, - 'params': { - # rtmp download - 'skip_download': True, - }, }, { # 16x9 'url': 'http://www.dctp.tv/filme/sind-youtuber-die-besseren-lehrer/', @@ -59,33 +56,26 @@ class DctpTvIE(InfoExtractor): uuid = media['uuid'] title = media['title'] - ratio = '16x9' if media.get('is_wide') else '4x3' - play_path = 'mp4:%s_dctp_0500_%s.m4v' % (uuid, ratio) - - servers = self._download_json( - 'http://www.dctp.tv/streaming_servers/', display_id, - note='Downloading server list JSON', fatal=False) - - if servers: - endpoint = next( - server['endpoint'] - for server in servers - if url_or_none(server.get('endpoint')) - and 'cloudfront' in server['endpoint']) - else: - endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/' - - app = self._search_regex( - r'^rtmpe?://[^/]+/(?P<app>.*)$', endpoint, 'app') - - formats = [{ - 'url': endpoint, - 'app': app, - 'play_path': play_path, - 'page_url': url, - 'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-110.swf', - 'ext': 'flv', - }] + is_wide = media.get('is_wide') + formats = [] + + def add_formats(suffix): + templ = 'https://%%s/%s_dctp_%s.m4v' % (uuid, suffix) + formats.extend([{ + 'format_id': 'hls-' + suffix, + 'url': templ % 'cdn-segments.dctp.tv' + '/playlist.m3u8', + 'protocol': 'm3u8_native', + }, { + 'format_id': 's3-' + suffix, + 'url': templ % 'completed-media.s3.amazonaws.com', + }, { + 'format_id': 'http-' + suffix, + 'url': templ % 'cdn-media.dctp.tv', + }]) + + add_formats('0500_' + ('16x9' if is_wide else '4x3')) + if is_wide: + add_formats('720p') thumbnails = [] images = media.get('images') diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 6a2712cc5..e0139cc86 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -13,8 +13,8 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): _VALID_URL = r'''(?x)https?:// (?P<site> - (?:(?:www|go)\.)?discovery| - (?:www\.)? + go\.discovery| + www\. (?: investigationdiscovery| discoverylife| @@ -22,8 +22,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): ahctv| destinationamerica| sciencechannel| - tlc| - velocity + tlc )| watch\. (?: @@ -83,7 +82,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): 'authRel': 'authorization', 'client_id': '3020a40c2356a645b4b4', 'nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), - 'redirectUri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html?https://www.%s.com' % site, + 'redirectUri': 'https://www.discovery.com/', })['access_token'] headers = self.geo_verification_headers() diff --git a/youtube_dl/extractor/discoverynetworks.py b/youtube_dl/extractor/discoverynetworks.py index fba1ef221..607a54948 100644 --- a/youtube_dl/extractor/discoverynetworks.py +++ b/youtube_dl/extractor/discoverynetworks.py @@ -3,63 +3,38 @@ from __future__ import unicode_literals import re -from .brightcove import BrightcoveLegacyIE from .dplay import DPlayIE -from ..compat import ( - compat_parse_qs, - compat_urlparse, -) -from ..utils import smuggle_url class DiscoveryNetworksDeIE(DPlayIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/ - (?: - .*\#(?P<id>\d+)| - (?:[^/]+/)*videos/(?P<display_id>[^/?#]+)| - programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+) - )''' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)' _TESTS = [{ - 'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001', + 'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100', 'info_dict': { - 'id': '3235167922001', + 'id': '78867', 'ext': 'mp4', - 'title': 'Breaking Amish: Die Welt da draußen', - 'description': ( - 'Vier Amische und eine Mennonitin wagen in New York' - ' den Sprung in ein komplett anderes Leben. Begleitet sie auf' - ' ihrem spannenden Weg.'), - 'timestamp': 1396598084, - 'upload_date': '20140404', - 'uploader_id': '1659832546', + 'title': 'Die Welt da draußen', + 'description': 'md5:61033c12b73286e409d99a41742ef608', + 'timestamp': 1554069600, + 'upload_date': '20190331', + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, }, { - 'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/', + 'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316', 'only_matching': True, }, { - 'url': 'http://www.discovery.de/#5332316765001', + 'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B', 'only_matching': True, }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - alternate_id = mobj.group('alternate_id') - if alternate_id: - self._initialize_geo_bypass({ - 'countries': ['DE'], - }) - return self._get_disco_api_info( - url, '%s/%s' % (mobj.group('programme'), alternate_id), - 'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de') - brightcove_id = mobj.group('id') - if not brightcove_id: - title = mobj.group('title') - webpage = self._download_webpage(url, title) - brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - brightcove_id = compat_parse_qs(compat_urlparse.urlparse( - brightcove_legacy_url).query)['@videoPlayer'][0] - return self.url_result(smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}), - 'BrightcoveNew', brightcove_id) + domain, programme, alternate_id = re.match(self._VALID_URL, url).groups() + country = 'GB' if domain == 'dplay.co.uk' else 'DE' + realm = 'questuk' if country == 'GB' else domain.replace('.', '') + return self._get_disco_api_info( + url, '%s/%s' % (programme, alternate_id), + 'sonic-eu1-prod.disco-api.com', realm, country) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index ebf59512c..a7b9db568 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -1,74 +1,68 @@ # coding: utf-8 from __future__ import unicode_literals -import json import re -import time from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, - compat_urlparse, -) +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, float_or_none, int_or_none, - remove_end, - try_get, - unified_strdate, unified_timestamp, - update_url_query, - urljoin, - USER_AGENTS, ) class DPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)' + _VALID_URL = r'''(?x)https?:// + (?P<domain> + (?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))| + (?P<subdomain_country>es|it)\.dplay\.com + )/[^/]+/(?P<id>[^/]+/[^/?#]+)''' _TESTS = [{ # non geo restricted, via secure api, unsigned download hls URL - 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', + 'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101', 'info_dict': { - 'id': '3172', - 'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet', + 'id': '13628', + 'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101', 'ext': 'mp4', 'title': 'Svensken lär sig njuta av livet', 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8', - 'duration': 2650, - 'timestamp': 1365454320, + 'duration': 2649.856, + 'timestamp': 1365453720, 'upload_date': '20130408', - 'creator': 'Kanal 5 (Home)', + 'creator': 'Kanal 5', 'series': 'Nugammalt - 77 händelser som format Sverige', 'season_number': 1, 'episode_number': 1, - 'age_limit': 0, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, }, { # geo restricted, via secure api, unsigned download hls URL - 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/', + 'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster', 'info_dict': { - 'id': '70816', - 'display_id': 'mig-og-min-mor/season-6-episode-12', + 'id': '104465', + 'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster', 'ext': 'mp4', - 'title': 'Episode 12', - 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90', - 'duration': 2563, - 'timestamp': 1429696800, - 'upload_date': '20150422', - 'creator': 'Kanal 4 (Home)', - 'series': 'Mig og min mor', - 'season_number': 6, - 'episode_number': 12, - 'age_limit': 0, + 'title': 'Ted Bundy: Mind Of A Monster', + 'description': 'md5:8b780f6f18de4dae631668b8a9637995', + 'duration': 5290.027, + 'timestamp': 1570694400, + 'upload_date': '20191010', + 'creator': 'ID - Investigation Discovery', + 'series': 'Ted Bundy: Mind Of A Monster', + 'season_number': 1, + 'episode_number': 1, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, - }, { - # geo restricted, via direct unsigned hls URL - 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/', - 'only_matching': True, }, { # disco-api 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7', @@ -89,19 +83,59 @@ class DPlayIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, + 'skip': 'Available for Premium users', }, { - - 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3', + 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', + 'md5': '2b808ffb00fc47b884a172ca5d13053c', + 'info_dict': { + 'id': '6918', + 'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij', + 'ext': 'mp4', + 'title': 'Luigi Di Maio: la psicosi di Stanislawskij', + 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', + 'thumbnail': r're:^https?://.*\.jpe?g', + 'upload_date': '20160524', + 'timestamp': 1464076800, + 'series': 'Biografie imbarazzanti', + 'season_number': 1, + 'episode': 'Episode 1', + 'episode_number': 1, + }, + }, { + 'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/', + 'info_dict': { + 'id': '21652', + 'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1', + 'ext': 'mp4', + 'title': 'Episodio 1', + 'description': 'md5:b9dcff2071086e003737485210675f69', + 'thumbnail': r're:^https?://.*\.png', + 'upload_date': '20180709', + 'timestamp': 1531173540, + 'series': 'La fiebre del oro', + 'season_number': 8, + 'episode': 'Episode 1', + 'episode_number': 1, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16', 'only_matching': True, }, { - 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001', + 'url': 'https://www.dplay.jp/video/gold-rush/24086', 'only_matching': True, }] - def _get_disco_api_info(self, url, display_id, disco_host, realm): - disco_base = 'https://' + disco_host + def _get_disco_api_info(self, url, display_id, disco_host, realm, country): + geo_countries = [country.upper()] + self._initialize_geo_bypass({ + 'countries': geo_countries, + }) + disco_base = 'https://%s/' % disco_host token = self._download_json( - '%s/token' % disco_base, display_id, 'Downloading token', + disco_base + 'token', display_id, 'Downloading token', query={ 'realm': realm, })['data']['attributes']['token'] @@ -110,17 +144,35 @@ class DPlayIE(InfoExtractor): 'Authorization': 'Bearer ' + token, } video = self._download_json( - '%s/content/videos/%s' % (disco_base, display_id), display_id, + disco_base + 'content/videos/' + display_id, display_id, headers=headers, query={ - 'include': 'show' + 'fields[channel]': 'name', + 'fields[image]': 'height,src,width', + 'fields[show]': 'name', + 'fields[tag]': 'name', + 'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration', + 'include': 'images,primaryChannel,show,tags' }) video_id = video['data']['id'] info = video['data']['attributes'] - title = info['name'] + title = info['name'].strip() formats = [] - for format_id, format_dict in self._download_json( - '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), - display_id, headers=headers)['data']['attributes']['streaming'].items(): + try: + streaming = self._download_json( + disco_base + 'playback/videoPlaybackInfo/' + video_id, + display_id, headers=headers)['data']['attributes']['streaming'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + info = self._parse_json(e.cause.read().decode('utf-8'), display_id) + error = info['errors'][0] + error_code = error.get('code') + if error_code == 'access.denied.geoblocked': + self.raise_geo_restricted(countries=geo_countries) + elif error_code == 'access.denied.missingpackage': + self.raise_login_required() + raise ExtractorError(info['errors'][0]['detail'], expected=True) + raise + for format_id, format_dict in streaming.items(): if not isinstance(format_dict, dict): continue format_url = format_dict.get('url') @@ -142,235 +194,54 @@ class DPlayIE(InfoExtractor): }) self._sort_formats(formats) - series = None - try: - included = video.get('included') - if isinstance(included, list): - show = next(e for e in included if e.get('type') == 'show') - series = try_get( - show, lambda x: x['attributes']['name'], compat_str) - except StopIteration: - pass + creator = series = None + tags = [] + thumbnails = [] + included = video.get('included') or [] + if isinstance(included, list): + for e in included: + attributes = e.get('attributes') + if not attributes: + continue + e_type = e.get('type') + if e_type == 'channel': + creator = attributes.get('name') + elif e_type == 'image': + src = attributes.get('src') + if src: + thumbnails.append({ + 'url': src, + 'width': int_or_none(attributes.get('width')), + 'height': int_or_none(attributes.get('height')), + }) + if e_type == 'show': + series = attributes.get('name') + elif e_type == 'tag': + name = attributes.get('name') + if name: + tags.append(name) return { 'id': video_id, 'display_id': display_id, 'title': title, 'description': info.get('description'), - 'duration': float_or_none( - info.get('videoDuration'), scale=1000), + 'duration': float_or_none(info.get('videoDuration'), 1000), 'timestamp': unified_timestamp(info.get('publishStart')), 'series': series, 'season_number': int_or_none(info.get('seasonNumber')), 'episode_number': int_or_none(info.get('episodeNumber')), - 'age_limit': int_or_none(info.get('minimum_age')), + 'creator': creator, + 'tags': tags, + 'thumbnails': thumbnails, 'formats': formats, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') - domain = mobj.group('domain') - - self._initialize_geo_bypass({ - 'countries': [mobj.group('country').upper()], - }) - - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - r'data-video-id=["\'](\d+)', webpage, 'video id', default=None) - - if not video_id: - host = mobj.group('host') - return self._get_disco_api_info( - url, display_id, 'disco-api.' + host, host.replace('.', '')) - - info = self._download_json( - 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), - video_id)['data'][0] - - title = info['title'] - - PROTOCOLS = ('hls', 'hds') - formats = [] - - def extract_formats(protocol, manifest_url): - if protocol == 'hls': - m3u8_formats = self._extract_m3u8_formats( - manifest_url, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False) - # Sometimes final URLs inside m3u8 are unsigned, let's fix this - # ourselves. Also fragments' URLs are only served signed for - # Safari user agent. - query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query) - for m3u8_format in m3u8_formats: - m3u8_format.update({ - 'url': update_url_query(m3u8_format['url'], query), - 'http_headers': { - 'User-Agent': USER_AGENTS['Safari'], - }, - }) - formats.extend(m3u8_formats) - elif protocol == 'hds': - formats.extend(self._extract_f4m_formats( - manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0', - video_id, f4m_id=protocol, fatal=False)) - - domain_tld = domain.split('.')[-1] - if domain_tld in ('se', 'dk', 'no'): - for protocol in PROTOCOLS: - # Providing dsc-geo allows to bypass geo restriction in some cases - self._set_cookie( - 'secure.dplay.%s' % domain_tld, 'dsc-geo', - json.dumps({ - 'countryCode': domain_tld.upper(), - 'expiry': (time.time() + 20 * 60) * 1000, - })) - stream = self._download_json( - 'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s' - % (domain_tld, video_id, protocol), video_id, - 'Downloading %s stream JSON' % protocol, fatal=False) - if stream and stream.get(protocol): - extract_formats(protocol, stream[protocol]) - - # The last resort is to try direct unsigned hls/hds URLs from info dictionary. - # Sometimes this does work even when secure API with dsc-geo has failed (e.g. - # http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/). - if not formats: - for protocol in PROTOCOLS: - if info.get(protocol): - extract_formats(protocol, info[protocol]) - - self._sort_formats(formats) - - subtitles = {} - for lang in ('se', 'sv', 'da', 'nl', 'no'): - for format_id in ('web_vtt', 'vtt', 'srt'): - subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id)) - if subtitle_url: - subtitles.setdefault(lang, []).append({'url': subtitle_url}) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': info.get('video_metadata_longDescription'), - 'duration': int_or_none(info.get('video_metadata_length'), scale=1000), - 'timestamp': int_or_none(info.get('video_publish_date')), - 'creator': info.get('video_metadata_homeChannel'), - 'series': info.get('video_metadata_show'), - 'season_number': int_or_none(info.get('season')), - 'episode_number': int_or_none(info.get('episode')), - 'age_limit': int_or_none(info.get('minimum_age')), - 'formats': formats, - 'subtitles': subtitles, - } - - -class DPlayItIE(InfoExtractor): - _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)' - _GEO_COUNTRIES = ['IT'] - _TEST = { - 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', - 'md5': '2b808ffb00fc47b884a172ca5d13053c', - 'info_dict': { - 'id': '6918', - 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij', - 'ext': 'mp4', - 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij', - 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', - 'thumbnail': r're:^https?://.*\.jpe?g', - 'upload_date': '20160524', - 'series': 'Biografie imbarazzanti', - 'season_number': 1, - 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij', - 'episode_number': 1, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - title = remove_end(self._og_search_title(webpage), ' | Dplay') - - video_id = None - - info = self._search_regex( - r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")', - webpage, 'playback JSON', default=None) - if info: - for _ in range(2): - info = self._parse_json(info, display_id, fatal=False) - if not info: - break - else: - video_id = try_get(info, lambda x: x['data']['id']) - - if not info: - info_url = self._search_regex( - (r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', - r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'), - webpage, 'info url', group='url') - - info_url = urljoin(url, info_url) - video_id = info_url.rpartition('/')[-1] - - try: - info = self._download_json( - info_url, display_id, headers={ - 'Authorization': 'Bearer %s' % self._get_cookies(url).get( - 'dplayit_token').value, - 'Referer': url, - }) - if isinstance(info, compat_str): - info = self._parse_json(info, display_id) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): - info = self._parse_json(e.cause.read().decode('utf-8'), display_id) - error = info['errors'][0] - if error.get('code') == 'access.denied.geoblocked': - self.raise_geo_restricted( - msg=error.get('detail'), countries=self._GEO_COUNTRIES) - raise ExtractorError(info['errors'][0]['detail'], expected=True) - raise - - hls_url = info['data']['attributes']['streaming']['hls']['url'] - - formats = self._extract_m3u8_formats( - hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', - m3u8_id='hls') - self._sort_formats(formats) - - series = self._html_search_regex( - r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>', - webpage, 'series', fatal=False) - episode = self._search_regex( - r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)', - webpage, 'episode', fatal=False) - - mobj = re.search( - r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})', - webpage) - if mobj: - season_number = int(mobj.group('season_number')) - episode_number = int(mobj.group('episode_number')) - upload_date = unified_strdate(mobj.group('upload_date')) - else: - season_number = episode_number = upload_date = None - - return { - 'id': compat_str(video_id or display_id), - 'display_id': display_id, - 'title': title, - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - 'series': series, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - 'upload_date': upload_date, - 'formats': formats, - } + domain = mobj.group('domain').lstrip('www.') + country = mobj.group('country') or mobj.group('subdomain_country') + host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com' + return self._get_disco_api_info( + url, display_id, host, 'dplay' + country, country) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index 218f10209..390e79f8c 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -17,6 +17,7 @@ from ..utils import ( float_or_none, mimetype2ext, str_or_none, + try_get, unified_timestamp, update_url_query, url_or_none, @@ -24,7 +25,14 @@ from ..utils import ( class DRTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*| + (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode)/ + ) + (?P<id>[\da-z_-]+) + ''' _GEO_BYPASS = False _GEO_COUNTRIES = ['DK'] IE_NAME = 'drtv' @@ -83,6 +91,26 @@ class DRTVIE(InfoExtractor): }, { 'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9', 'only_matching': True, + }, { + 'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769', + 'info_dict': { + 'id': '00951930010', + 'ext': 'mp4', + 'title': 'Bonderøven (1:8)', + 'description': 'md5:3cf18fc0d3b205745d4505f896af8121', + 'timestamp': 1546542000, + 'upload_date': '20190103', + 'duration': 2576.6, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769', + 'only_matching': True, + }, { + 'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769', + 'only_matching': True, }] def _real_extract(self, url): @@ -100,13 +128,32 @@ class DRTVIE(InfoExtractor): webpage, 'video id', default=None) if not video_id: - video_id = compat_urllib_parse_unquote(self._search_regex( + video_id = self._search_regex( r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', - webpage, 'urn')) + webpage, 'urn', default=None) + if video_id: + video_id = compat_urllib_parse_unquote(video_id) + + _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard' + query = {'expanded': 'true'} + + if video_id: + programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id) + else: + programcard_url = _PROGRAMCARD_BASE + page = self._parse_json( + self._search_regex( + r'data\s*=\s*({.+?})\s*(?:;|</script)', webpage, + 'data'), '1')['cache']['page'] + page = page[list(page.keys())[0]] + item = try_get( + page, (lambda x: x['item'], lambda x: x['entries'][0]['item']), + dict) + video_id = item['customId'].split(':')[-1] + query['productionnumber'] = video_id data = self._download_json( - 'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, - video_id, 'Downloading video JSON', query={'expanded': 'true'}) + programcard_url, video_id, 'Downloading video JSON', query=query) title = str_or_none(data.get('Title')) or re.sub( r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '', diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py index be2e3d378..d9d9afdec 100644 --- a/youtube_dl/extractor/dumpert.py +++ b/youtube_dl/extractor/dumpert.py @@ -1,20 +1,17 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import compat_b64decode from ..utils import ( + int_or_none, qualities, - sanitized_Request, ) class DumpertIE(InfoExtractor): - _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)' + _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)' _TESTS = [{ - 'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/', + 'url': 'https://www.dumpert.nl/item/6646981_951bc60f', 'md5': '1b9318d7d5054e7dcb9dc7654f21d643', 'info_dict': { 'id': '6646981/951bc60f', @@ -24,46 +21,60 @@ class DumpertIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', } }, { - 'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/', + 'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7', + 'only_matching': True, + }, { + 'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f', + 'only_matching': True, + }, { + 'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - protocol = mobj.group('protocol') - - url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id) - req = sanitized_Request(url) - req.add_header('Cookie', 'nsfw=1; cpc=10') - webpage = self._download_webpage(req, video_id) - - files_base64 = self._search_regex( - r'data-files="([^"]+)"', webpage, 'data files') - - files = self._parse_json( - compat_b64decode(files_base64).decode('utf-8'), - video_id) + video_id = self._match_id(url).replace('_', '/') + item = self._download_json( + 'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'), + video_id)['items'][0] + title = item['title'] + media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO') quality = qualities(['flv', 'mobile', 'tablet', '720p']) - - formats = [{ - 'url': video_url, - 'format_id': format_id, - 'quality': quality(format_id), - } for format_id, video_url in files.items() if format_id != 'still'] + formats = [] + for variant in media.get('variants', []): + uri = variant.get('uri') + if not uri: + continue + version = variant.get('version') + formats.append({ + 'url': uri, + 'format_id': version, + 'quality': quality(version), + }) self._sort_formats(formats) - title = self._html_search_meta( - 'title', webpage) or self._og_search_title(webpage) - description = self._html_search_meta( - 'description', webpage) or self._og_search_description(webpage) - thumbnail = files.get('still') or self._og_search_thumbnail(webpage) + thumbnails = [] + stills = item.get('stills') or {} + for t in ('thumb', 'still'): + for s in ('', '-medium', '-large'): + still_id = t + s + still_url = stills.get(still_id) + if not still_url: + continue + thumbnails.append({ + 'id': still_id, + 'url': still_url, + }) + + stats = item.get('stats') or {} return { 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'formats': formats + 'description': item.get('description'), + 'thumbnails': thumbnails, + 'formats': formats, + 'duration': int_or_none(media.get('duration')), + 'like_count': int_or_none(stats.get('kudos_total')), + 'view_count': int_or_none(stats.get('views_total')), } diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index c050bf9df..fe42821c7 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( encode_base_n, ExtractorError, @@ -55,7 +54,7 @@ class EpornerIE(InfoExtractor): webpage, urlh = self._download_webpage_handle(url, display_id) - video_id = self._match_id(compat_str(urlh.geturl())) + video_id = self._match_id(urlh.geturl()) hash = self._search_regex( r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8d3e433c3..64d1fa251 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -18,10 +18,10 @@ from .acast import ( ACastIE, ACastChannelIE, ) -from .addanime import AddAnimeIE from .adn import ADNIE from .adobeconnect import AdobeConnectIE from .adobetv import ( + AdobeTVEmbedIE, AdobeTVIE, AdobeTVShowIE, AdobeTVChannelIE, @@ -80,7 +80,6 @@ from .awaan import ( ) from .azmedien import AZMedienIE from .baidu import BaiduVideoIE -from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE from .bbc import ( BBCCoUkIE, @@ -224,13 +223,13 @@ from .comedycentral import ( ComedyCentralTVIE, ToshIE, ) -from .comcarcoff import ComCarCoffIE from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .commonprotocols import ( MmsIE, RtmpIE, ) from .condenast import CondeNastIE +from .contv import CONtvIE from .corus import CorusIE from .cracked import CrackedIE from .crackle import CrackleIE @@ -254,10 +253,6 @@ from .dailymotion import ( DailymotionPlaylistIE, DailymotionUserIE, ) -from .daisuki import ( - DaisukiMottoIE, - DaisukiMottoPlaylistIE, -) from .daum import ( DaumIE, DaumClipIE, @@ -276,10 +271,7 @@ from .douyutv import ( DouyuShowIE, DouyuTVIE, ) -from .dplay import ( - DPlayIE, - DPlayItIE, -) +from .dplay import DPlayIE from .dreisat import DreiSatIE from .drbonanza import DRBonanzaIE from .drtuber import DrTuberIE @@ -358,7 +350,6 @@ from .firsttv import FirstTVIE from .fivemin import FiveMinIE from .fivetv import FiveTVIE from .flickr import FlickrIE -from .flipagram import FlipagramIE from .folketinget import FolketingetIE from .footyroom import FootyRoomIE from .formula1 import Formula1IE @@ -369,7 +360,10 @@ from .fourtube import ( FuxIE, ) from .fox import FOXIE -from .fox9 import FOX9IE +from .fox9 import ( + FOX9IE, + FOX9NewsIE, +) from .foxgay import FoxgayIE from .foxnews import ( FoxNewsIE, @@ -402,10 +396,6 @@ from .fusion import FusionIE from .fxnetworks import FXNetworksIE from .gaia import GaiaIE from .gameinformer import GameInformerIE -from .gameone import ( - GameOneIE, - GameOnePlaylistIE, -) from .gamespot import GameSpotIE from .gamestar import GameStarIE from .gaskrank import GaskrankIE @@ -421,7 +411,6 @@ from .globo import ( GloboArticleIE, ) from .go import GoIE -from .go90 import Go90IE from .godtube import GodTubeIE from .golem import GolemIE from .googledrive import GoogleDriveIE @@ -430,7 +419,6 @@ from .googlesearch import GoogleSearchIE from .goshgay import GoshgayIE from .gputechconf import GPUTechConfIE from .groupon import GrouponIE -from .hark import HarkIE from .hbo import HBOIE from .hearthisat import HearThisAtIE from .heise import HeiseIE @@ -462,7 +450,6 @@ from .hungama import ( HungamaSongIE, ) from .hypem import HypemIE -from .iconosquare import IconosquareIE from .ign import ( IGNIE, OneUPIE, @@ -510,7 +497,6 @@ from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .joj import JojIE from .jwplatform import JWPlatformIE -from .jpopsukitv import JpopsukiIE from .kakao import KakaoIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE @@ -521,10 +507,9 @@ from .keezmovies import KeezMoviesIE from .ketnet import KetnetIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE +from .kinja import KinjaEmbedIE from .kinopoisk import KinoPoiskIE -from .keek import KeekIE from .konserthusetplay import KonserthusetPlayIE -from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE from .kusi import KUSIIE @@ -548,7 +533,6 @@ from .lcp import ( LcpPlayIE, LcpIE, ) -from .learnr import LearnrIE from .lecture2go import Lecture2GoIE from .lecturio import ( LecturioIE, @@ -600,13 +584,11 @@ from .lynda import ( LyndaCourseIE ) from .m6 import M6IE -from .macgamestore import MacGameStoreIE from .mailru import ( MailRuIE, MailRuMusicIE, MailRuMusicSearchIE, ) -from .makertv import MakerTVIE from .malltv import MallTVIE from .mangomolo import ( MangomoloVideoIE, @@ -640,17 +622,15 @@ from .microsoftvirtualacademy import ( MicrosoftVirtualAcademyIE, MicrosoftVirtualAcademyCourseIE, ) -from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .minoto import MinotoIE from .miomio import MioMioIE -from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mit import TechTVMITIE, OCWMITIE from .mitele import MiTeleIE from .mixcloud import ( MixcloudIE, MixcloudUserIE, MixcloudPlaylistIE, - MixcloudStreamIE, ) from .mlb import MLBIE from .mnet import MnetIE @@ -672,10 +652,9 @@ from .mtv import ( MTVVideoIE, MTVServicesEmbeddedIE, MTVDEIE, - MTV81IE, + MTVJapanIE, ) from .muenchentv import MuenchenTVIE -from .musicplayon import MusicPlayOnIE from .mwave import MwaveIE, MwaveMeetGreetIE from .mychannels import MyChannelsIE from .myspace import MySpaceIE, MySpaceAlbumIE @@ -815,10 +794,6 @@ from .ooyala import ( OoyalaIE, OoyalaExternalIE, ) -from .openload import ( - OpenloadIE, - VerystreamIE, -) from .ora import OraTVIE from .orf import ( ORFTVthekIE, @@ -832,7 +807,6 @@ from .packtpub import ( PacktPubIE, PacktPubCourseIE, ) -from .pandatv import PandaTVIE from .pandoratv import PandoraTVIE from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE @@ -875,6 +849,7 @@ from .polskieradio import ( PolskieRadioIE, PolskieRadioCategoryIE, ) +from .popcorntimes import PopcorntimesIE from .popcorntv import PopcornTVIE from .porn91 import Porn91IE from .porncom import PornComIE @@ -893,7 +868,6 @@ from .puhutv import ( PuhuTVSerieIE, ) from .presstv import PressTVIE -from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .puls4 import Puls4IE from .pyvideo import PyvideoIE @@ -945,10 +919,6 @@ from .rentv import ( from .restudy import RestudyIE from .reuters import ReutersIE from .reverbnation import ReverbNationIE -from .revision3 import ( - Revision3EmbedIE, - Revision3IE, -) from .rice import RICEIE from .rmcdecouverte import RMCDecouverteIE from .ro220 import Ro220IE @@ -992,11 +962,17 @@ from .savefrom import SaveFromIE from .sbs import SBSIE from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE -from .scrippsnetworks import ScrippsNetworksWatchIE +from .scrippsnetworks import ( + ScrippsNetworksWatchIE, + ScrippsNetworksIE, +) +from .scte import ( + SCTEIE, + SCTECourseIE, +) from .seeker import SeekerIE from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE -from .servingsys import ServingSysIE from .servus import ServusIE from .sevenplus import SevenPlusIE from .sexu import SexuIE @@ -1037,6 +1013,7 @@ from .snotr import SnotrIE from .sohu import SohuIE from .sonyliv import SonyLIVIE from .soundcloud import ( + SoundcloudEmbedIE, SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE, @@ -1080,7 +1057,6 @@ from .srmediathek import SRMediathekIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamable import StreamableIE -from .streamango import StreamangoIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE @@ -1136,6 +1112,7 @@ from .telequebec import ( from .teletask import TeleTaskIE from .telewebion import TelewebionIE from .tennistv import TennisTVIE +from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE from .tfo import TFOIE @@ -1188,10 +1165,14 @@ from .tunein import ( ) from .tunepk import TunePkIE from .turbo import TurboIE -from .tutv import TutvIE from .tv2 import ( TV2IE, TV2ArticleIE, + KatsomoIE, +) +from .tv2dk import ( + TV2DKIE, + TV2DKBornholmPlayIE, ) from .tv2hu import TV2HuIE from .tv4 import TV4IE @@ -1249,13 +1230,17 @@ from .twitter import ( TwitterCardIE, TwitterIE, TwitterAmplifyIE, + TwitterBroadcastIE, ) from .udemy import ( UdemyIE, UdemyCourseIE ) from .udn import UDNEmbedIE -from .ufctv import UFCTVIE +from .ufctv import ( + UFCTVIE, + UFCArabiaIE, +) from .uktvplay import UKTVPlayIE from .digiteka import DigitekaIE from .dlive import ( @@ -1283,7 +1268,6 @@ from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE from .veoh import VeohIE -from .vessel import VesselIE from .vesti import VestiIE from .vevo import ( VevoIE, @@ -1310,7 +1294,6 @@ from .videomore import ( VideomoreVideoIE, VideomoreSeasonIE, ) -from .videopremium import VideoPremiumIE from .videopress import VideoPressIE from .vidio import VidioIE from .vidlii import VidLiiIE @@ -1325,7 +1308,6 @@ from .viewlift import ( ViewLiftIE, ViewLiftEmbedIE, ) -from .viewster import ViewsterIE from .viidea import ViideaIE from .vimeo import ( VimeoIE, diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index a3dcdca3e..ce64e2683 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -334,7 +334,7 @@ class FacebookIE(InfoExtractor): if not video_data: server_js_data = self._parse_json( self._search_regex( - r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)', + r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_\d+)', webpage, 'js data', default='{}'), video_id, transform_source=js_to_json, fatal=False) video_data = extract_from_jsmods_instances(server_js_data) @@ -379,6 +379,7 @@ class FacebookIE(InfoExtractor): if not video_data: raise ExtractorError('Cannot parse data') + subtitles = {} formats = [] for f in video_data: format_id = f['stream_type'] @@ -402,9 +403,17 @@ class FacebookIE(InfoExtractor): if dash_manifest: formats.extend(self._parse_mpd_formats( compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest)))) + subtitles_src = f[0].get('subtitles_src') + if subtitles_src: + subtitles.setdefault('en', []).append({'url': subtitles_src}) if not formats: raise ExtractorError('Cannot find video formats') + # Downloads with browser's User-Agent are rate limited. Working around + # with non-browser User-Agent. + for f in formats: + f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1' + self._sort_formats(formats) video_title = self._html_search_regex( @@ -442,6 +451,7 @@ class FacebookIE(InfoExtractor): 'timestamp': timestamp, 'thumbnail': thumbnail, 'view_count': view_count, + 'subtitles': subtitles, } return webpage, info_dict diff --git a/youtube_dl/extractor/flipagram.py b/youtube_dl/extractor/flipagram.py deleted file mode 100644 index b7be40f1b..000000000 --- a/youtube_dl/extractor/flipagram.py +++ /dev/null @@ -1,115 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - float_or_none, - try_get, - unified_timestamp, -) - - -class FlipagramIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?#&]+)' - _TEST = { - 'url': 'https://flipagram.com/f/nyvTSJMKId', - 'md5': '888dcf08b7ea671381f00fab74692755', - 'info_dict': { - 'id': 'nyvTSJMKId', - 'ext': 'mp4', - 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', - 'description': 'md5:d55e32edc55261cae96a41fa85ff630e', - 'duration': 35.571, - 'timestamp': 1461244995, - 'upload_date': '20160421', - 'uploader': 'kitty juria', - 'uploader_id': 'sjuria101', - 'creator': 'kitty juria', - 'view_count': int, - 'like_count': int, - 'repost_count': int, - 'comment_count': int, - 'comments': list, - 'formats': 'mincount:2', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_data = self._parse_json( - self._search_regex( - r'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'), - video_id) - - flipagram = video_data['flipagram'] - video = flipagram['video'] - - json_ld = self._search_json_ld(webpage, video_id, default={}) - title = json_ld.get('title') or flipagram['captionText'] - description = json_ld.get('description') or flipagram.get('captionText') - - formats = [{ - 'url': video['url'], - 'width': int_or_none(video.get('width')), - 'height': int_or_none(video.get('height')), - 'filesize': int_or_none(video_data.get('size')), - }] - - preview_url = try_get( - flipagram, lambda x: x['music']['track']['previewUrl'], compat_str) - if preview_url: - formats.append({ - 'url': preview_url, - 'ext': 'm4a', - 'vcodec': 'none', - }) - - self._sort_formats(formats) - - counts = flipagram.get('counts', {}) - user = flipagram.get('user', {}) - video_data = flipagram.get('video', {}) - - thumbnails = [{ - 'url': self._proto_relative_url(cover['url']), - 'width': int_or_none(cover.get('width')), - 'height': int_or_none(cover.get('height')), - 'filesize': int_or_none(cover.get('size')), - } for cover in flipagram.get('covers', []) if cover.get('url')] - - # Note that this only retrieves comments that are initially loaded. - # For videos with large amounts of comments, most won't be retrieved. - comments = [] - for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []): - text = comment.get('comment') - if not text or not isinstance(text, list): - continue - comments.append({ - 'author': comment.get('user', {}).get('name'), - 'author_id': comment.get('user', {}).get('username'), - 'id': comment.get('id'), - 'text': text[0], - 'timestamp': unified_timestamp(comment.get('created')), - }) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': float_or_none(flipagram.get('duration'), 1000), - 'thumbnails': thumbnails, - 'timestamp': unified_timestamp(flipagram.get('iso8601Created')), - 'uploader': user.get('name'), - 'uploader_id': user.get('username'), - 'creator': user.get('name'), - 'view_count': int_or_none(counts.get('plays')), - 'like_count': int_or_none(counts.get('likes')), - 'repost_count': int_or_none(counts.get('reflips')), - 'comment_count': int_or_none(counts.get('comments')), - 'comments': comments, - 'formats': formats, - } diff --git a/youtube_dl/extractor/fox9.py b/youtube_dl/extractor/fox9.py index 17dfffa7b..91f8f7b8a 100644 --- a/youtube_dl/extractor/fox9.py +++ b/youtube_dl/extractor/fox9.py @@ -1,13 +1,23 @@ # coding: utf-8 from __future__ import unicode_literals -from .anvato import AnvatoIE +from .common import InfoExtractor -class FOX9IE(AnvatoIE): - _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story' - _TESTS = [{ - 'url': 'http://www.fox9.com/news/215123287-story', +class FOX9IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P<id>\d+)' + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id, + 'Anvato', video_id) + + +class FOX9NewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P<id>[^/?&#]+)' + _TEST = { + 'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota', 'md5': 'd6e1b2572c3bab8a849c9103615dd243', 'info_dict': { 'id': '314473', @@ -21,22 +31,11 @@ class FOX9IE(AnvatoIE): 'categories': ['News', 'Sports'], 'tags': ['news', 'video'], }, - }, { - 'url': 'http://www.fox9.com/news/investigators/214070684-story', - 'only_matching': True, - }] + } def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_id = self._parse_json( - self._search_regex( - r"this\.videosJson\s*=\s*'(\[.+?\])';", - webpage, 'anvato playlist'), - video_id)[0]['video'] - - return self._get_anvato_videos( - 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b', - video_id) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + anvato_id = self._search_regex( + r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id') + return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9') diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index b8fa17588..306b45fc9 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -31,7 +31,13 @@ class FranceCultureIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_data = extract_attributes(self._search_regex( - r'(?s)<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(<button[^>]+data-asset-source="[^"]+"[^>]+>)', + r'''(?sx) + (?: + </h1>| + <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*> + ).*? + (<button[^>]+data-asset-source="[^"]+"[^>]+>) + ''', webpage, 'video data')) video_url = video_data['data-asset-source'] diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py deleted file mode 100644 index a07d69841..000000000 --- a/youtube_dl/extractor/gameone.py +++ /dev/null @@ -1,134 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - xpath_with_ns, - parse_iso8601, - float_or_none, - int_or_none, -) - -NAMESPACE_MAP = { - 'media': 'http://search.yahoo.com/mrss/', -} - -# URL prefix to download the mp4 files directly instead of streaming via rtmp -# Credits go to XBox-Maniac -# http://board.jdownloader.org/showpost.php?p=185835&postcount=31 -RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/' - - -class GameOneIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)' - _TESTS = [ - { - 'url': 'http://www.gameone.de/tv/288', - 'md5': '136656b7fb4c9cb4a8e2d500651c499b', - 'info_dict': { - 'id': '288', - 'ext': 'mp4', - 'title': 'Game One - Folge 288', - 'duration': 1238, - 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', - 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', - 'age_limit': 16, - 'upload_date': '20140513', - 'timestamp': 1399980122, - } - }, - { - 'url': 'http://gameone.de/tv/220', - 'md5': '5227ca74c4ae6b5f74c0510a7c48839e', - 'info_dict': { - 'id': '220', - 'ext': 'mp4', - 'upload_date': '20120918', - 'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker', - 'timestamp': 1347971451, - 'title': 'Game One - Folge 220', - 'duration': 896.62, - 'age_limit': 16, - } - } - - ] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - og_video = self._og_search_video_url(webpage, secure=False) - description = self._html_search_meta('description', webpage) - age_limit = int( - self._search_regex( - r'age=(\d+)', - self._html_search_meta( - 'age-de-meta-label', - webpage), - 'age_limit', - '0')) - mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss') - - mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss') - title = mrss.find('.//item/title').text - thumbnail = mrss.find('.//item/image').get('url') - timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ') - content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP)) - content_url = content.get('url') - - content = self._download_xml( - content_url, - video_id, - 'Downloading media:content') - rendition_items = content.findall('.//rendition') - duration = float_or_none(rendition_items[0].get('duration')) - formats = [ - { - 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text), - 'width': int_or_none(r.get('width')), - 'height': int_or_none(r.get('height')), - 'tbr': int_or_none(r.get('bitrate')), - } - for r in rendition_items - ] - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'description': description, - 'age_limit': age_limit, - 'timestamp': timestamp, - } - - -class GameOnePlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$' - IE_NAME = 'gameone:playlist' - _TEST = { - 'url': 'http://www.gameone.de/tv', - 'info_dict': { - 'title': 'GameOne', - }, - 'playlist_mincount': 294, - } - - def _real_extract(self, url): - webpage = self._download_webpage('http://www.gameone.de/tv', 'TV') - max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage))) - entries = [ - self.url_result('http://www.gameone.de/tv/%d' % - video_id, 'GameOne') - for video_id in range(max_id, 0, -1)] - - return { - '_type': 'playlist', - 'title': 'GameOne', - 'entries': entries, - } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d1725d98b..d1ec56be9 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -77,11 +77,10 @@ from .instagram import InstagramIE from .liveleak import LiveLeakIE from .threeqsdn import ThreeQSDNIE from .theplatform import ThePlatformIE -from .vessel import VesselIE from .kaltura import KalturaIE from .eagleplatform import EaglePlatformIE from .facebook import FacebookIE -from .soundcloud import SoundcloudIE +from .soundcloud import SoundcloudEmbedIE from .tunein import TuneInBaseIE from .vbox7 import Vbox7IE from .dbtv import DBTVIE @@ -89,10 +88,6 @@ from .piksel import PikselIE from .videa import VideaIE from .twentymin import TwentyMinutenIE from .ustream import UstreamIE -from .openload import ( - OpenloadIE, - VerystreamIE, -) from .videopress import VideoPressIE from .rutube import RutubeIE from .limelight import LimelightBaseIE @@ -119,6 +114,8 @@ from .foxnews import FoxNewsIE from .viqeo import ViqeoIE from .expressen import ExpressenIE from .zype import ZypeIE +from .odnoklassniki import OdnoklassnikiIE +from .kinja import KinjaEmbedIE class GenericIE(InfoExtractor): @@ -1487,16 +1484,18 @@ class GenericIE(InfoExtractor): 'timestamp': 1432570283, }, }, - # OnionStudios embed + # Kinja embed { 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', 'info_dict': { - 'id': '2855', + 'id': '106351', 'ext': 'mp4', 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You', + 'description': 'Migrated from OnionStudios', 'thumbnail': r're:^https?://.*\.jpe?g$', - 'uploader': 'ClickHole', - 'uploader_id': 'clickhole', + 'uploader': 'clickhole', + 'upload_date': '20150527', + 'timestamp': 1432744860, } }, # SnagFilms embed @@ -2099,6 +2098,9 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'Smoky Barbecue Favorites', 'thumbnail': r're:^https?://.*\.jpe?g', + 'description': 'md5:5ff01e76316bd8d46508af26dc86023b', + 'upload_date': '20170909', + 'timestamp': 1504915200, }, 'add_ie': [ZypeIE.ie_key()], 'params': { @@ -2285,7 +2287,7 @@ class GenericIE(InfoExtractor): if head_response is not False: # Check for redirect - new_url = compat_str(head_response.geturl()) + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) if force_videoid: @@ -2385,12 +2387,12 @@ class GenericIE(InfoExtractor): return self.playlist_result( self._parse_xspf( doc, video_id, xspf_url=url, - xspf_base_url=compat_str(full_response.geturl())), + xspf_base_url=full_response.geturl()), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( doc, - mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0], + mpd_base_url=full_response.geturl().rpartition('/')[0], mpd_url=url) self._sort_formats(info_dict['formats']) return info_dict @@ -2491,11 +2493,6 @@ class GenericIE(InfoExtractor): if tp_urls: return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform') - # Look for Vessel embeds - vessel_urls = VesselIE._extract_urls(webpage) - if vessel_urls: - return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key()) - # Look for embedded rtl.nl player matches = re.findall( r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"', @@ -2540,14 +2537,15 @@ class GenericIE(InfoExtractor): dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) # Look for embedded Wistia player - wistia_url = WistiaIE._extract_url(webpage) - if wistia_url: - return { - '_type': 'url_transparent', - 'url': self._proto_relative_url(wistia_url), - 'ie_key': WistiaIE.ie_key(), - 'uploader': video_uploader, - } + wistia_urls = WistiaIE._extract_urls(webpage) + if wistia_urls: + playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key()) + for entry in playlist['entries']: + entry.update({ + '_type': 'url_transparent', + 'uploader': video_uploader, + }) + return playlist # Look for SVT player svt_url = SVTIE._extract_url(webpage) @@ -2633,9 +2631,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'VK') # Look for embedded Odnoklassniki player - mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Odnoklassniki') + odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) # Look for embedded ivi player mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) @@ -2754,9 +2752,9 @@ class GenericIE(InfoExtractor): return self.url_result(myvi_url) # Look for embedded soundcloud player - soundcloud_urls = SoundcloudIE._extract_urls(webpage) + soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage) if soundcloud_urls: - return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key()) + return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML) # Look for tunein player tunein_urls = TuneInBaseIE._extract_urls(webpage) @@ -2899,6 +2897,12 @@ class GenericIE(InfoExtractor): if senate_isvp_url: return self.url_result(senate_isvp_url, 'SenateISVP') + # Look for Kinja embeds + kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url) + if kinja_embed_urls: + return self.playlist_from_matches( + kinja_embed_urls, video_id, video_title) + # Look for OnionStudios embeds onionstudios_url = OnionStudiosIE._extract_url(webpage) if onionstudios_url: @@ -2960,7 +2964,7 @@ class GenericIE(InfoExtractor): # Look for VODPlatform embeds mobj = re.search( - r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1', + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1', webpage) if mobj is not None: return self.url_result( @@ -2968,10 +2972,14 @@ class GenericIE(InfoExtractor): # Look for Mangomolo embeds mobj = re.search( - r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/ + r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?// + (?: + admin\.mangomolo\.com/analytics/index\.php/customers/embed| + player\.mangomolo\.com/v1 + )/ (?: video\?.*?\bid=(?P<video_id>\d+)| - index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) + (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) ).+?)\1''', webpage) if mobj is not None: info = { @@ -3040,18 +3048,6 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key()) - # Look for Openload embeds - openload_urls = OpenloadIE._extract_urls(webpage) - if openload_urls: - return self.playlist_from_matches( - openload_urls, video_id, video_title, ie=OpenloadIE.ie_key()) - - # Look for Verystream embeds - verystream_urls = VerystreamIE._extract_urls(webpage) - if verystream_urls: - return self.playlist_from_matches( - verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key()) - # Look for VideoPress embeds videopress_urls = VideoPressIE._extract_urls(webpage) if videopress_urls: diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index fb8f7679b..60d842d3a 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -96,21 +96,31 @@ class GloboIE(InfoExtractor): video = self._download_json( 'http://api.globovideos.com/videos/%s/playlist' % video_id, video_id)['videos'][0] + if video.get('encrypted') is True: + raise ExtractorError('This video is DRM protected.', expected=True) title = video['title'] formats = [] + subtitles = {} for resource in video['resources']: resource_id = resource.get('_id') resource_url = resource.get('url') - if not resource_id or not resource_url: + resource_type = resource.get('type') + if not resource_url or (resource_type == 'media' and not resource_id) or resource_type not in ('subtitle', 'media'): + continue + + if resource_type == 'subtitle': + subtitles.setdefault(resource.get('language') or 'por', []).append({ + 'url': resource_url, + }) continue security = self._download_json( 'http://security.video.globo.com/videos/%s/hash' % video_id, video_id, 'Downloading security hash for %s' % resource_id, query={ - 'player': 'flash', - 'version': '17.0.0.132', + 'player': 'desktop', + 'version': '5.19.1', 'resource_id': resource_id, }) @@ -123,18 +133,23 @@ class GloboIE(InfoExtractor): continue hash_code = security_hash[:2] - received_time = security_hash[2:12] - received_random = security_hash[12:22] - received_md5 = security_hash[22:] - - sign_time = compat_str(int(received_time) + 86400) padding = '%010d' % random.randint(1, 10000000000) - - md5_data = (received_md5 + sign_time + padding + '0xFF01DD').encode() + if hash_code in ('04', '14'): + received_time = security_hash[3:13] + received_md5 = security_hash[24:] + hash_prefix = security_hash[:23] + elif hash_code in ('02', '12', '03', '13'): + received_time = security_hash[2:12] + received_md5 = security_hash[22:] + padding += '1' + hash_prefix = '05' + security_hash[:22] + + padded_sign_time = compat_str(int(received_time) + 86400) + padding + md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode() signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=') - signed_hash = hash_code + received_time + received_random + sign_time + padding + signed_md5 + signed_hash = hash_prefix + padded_sign_time + signed_md5 + signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '') - signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash') if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'): formats.extend(self._extract_m3u8_formats( signed_url, resource_id, 'mp4', entry_protocol='m3u8_native', @@ -164,7 +179,8 @@ class GloboIE(InfoExtractor): 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'formats': formats + 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index 03e48f4ea..03cfba91f 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -40,8 +40,17 @@ class GoIE(AdobePassIE): 'resource_id': 'Disney', } } - _VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|(?P<sub_domain_2>disneynow))\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\ - % '|'.join(list(_SITE_INFO.keys()) + ['disneynow']) + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?P<sub_domain>%s)\.)?go| + (?P<sub_domain_2>abc|freeform|disneynow) + )\.com/ + (?: + (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)| + (?:[^/]+/)*(?P<display_id>[^/?\#]+) + ) + ''' % '|'.join(list(_SITE_INFO.keys())) _TESTS = [{ 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'info_dict': { @@ -54,6 +63,7 @@ class GoIE(AdobePassIE): # m3u8 download 'skip_download': True, }, + 'skip': 'This content is no longer available.', }, { 'url': 'http://watchdisneyxd.go.com/doraemon', 'info_dict': { @@ -62,6 +72,34 @@ class GoIE(AdobePassIE): }, 'playlist_mincount': 51, }, { + 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood', + 'info_dict': { + 'id': 'VDKA3609139', + 'ext': 'mp4', + 'title': 'This Guilty Blood', + 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292', + 'age_limit': 14, + }, + 'params': { + 'geo_bypass_ip_block': '3.244.239.0/24', + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet', + 'info_dict': { + 'id': 'VDKA13435179', + 'ext': 'mp4', + 'title': 'The Bet', + 'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404', + 'age_limit': 14, + }, + 'params': { + 'geo_bypass_ip_block': '3.244.239.0/24', + # m3u8 download + 'skip_download': True, + }, + }, { 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding', 'only_matching': True, }, { @@ -95,10 +133,13 @@ class GoIE(AdobePassIE): if not video_id or not site_info: webpage = self._download_webpage(url, display_id or video_id) video_id = self._search_regex( - # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" - # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood - r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', - default=video_id) + ( + # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" + # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood + r'data-video-id=["\']*(VDKA\w+)', + # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet + r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)' + ), webpage, 'video id', default=video_id) if not site_info: brand = self._search_regex( (r'data-brand=\s*["\']\s*(\d+)', diff --git a/youtube_dl/extractor/go90.py b/youtube_dl/extractor/go90.py deleted file mode 100644 index c3ea717bc..000000000 --- a/youtube_dl/extractor/go90.py +++ /dev/null @@ -1,149 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_HTTPError -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - parse_age_limit, - parse_iso8601, -) - - -class Go90IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)' - _TESTS = [{ - 'url': 'https://www.go90.com/videos/84BUqjLpf9D', - 'md5': 'efa7670dbbbf21a7b07b360652b24a32', - 'info_dict': { - 'id': '84BUqjLpf9D', - 'ext': 'mp4', - 'title': 'Daily VICE - Inside The Utah Coalition Against Pornography Convention', - 'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.', - 'timestamp': 1491868800, - 'upload_date': '20170411', - 'age_limit': 14, - } - }, { - 'url': 'https://www.go90.com/embed/261MflWkD3N', - 'only_matching': True, - }] - _GEO_BYPASS = False - - def _real_extract(self, url): - video_id = self._match_id(url) - - try: - headers = self.geo_verification_headers() - headers.update({ - 'Content-Type': 'application/json; charset=utf-8', - }) - video_data = self._download_json( - 'https://www.go90.com/api/view/items/' + video_id, video_id, - headers=headers, data=b'{"client":"web","device_type":"pc"}') - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: - message = self._parse_json(e.cause.read().decode(), None)['error']['message'] - if 'region unavailable' in message: - self.raise_geo_restricted(countries=['US']) - raise ExtractorError(message, expected=True) - raise - - if video_data.get('requires_drm'): - raise ExtractorError('This video is DRM protected.', expected=True) - main_video_asset = video_data['main_video_asset'] - - episode_number = int_or_none(video_data.get('episode_number')) - series = None - season = None - season_id = None - season_number = None - for metadata in video_data.get('__children', {}).get('Item', {}).values(): - if metadata.get('type') == 'show': - series = metadata.get('title') - elif metadata.get('type') == 'season': - season = metadata.get('title') - season_id = metadata.get('id') - season_number = int_or_none(metadata.get('season_number')) - - title = episode = video_data.get('title') or series - if series and series != title: - title = '%s - %s' % (series, title) - - thumbnails = [] - formats = [] - subtitles = {} - for asset in video_data.get('assets'): - if asset.get('id') == main_video_asset: - for source in asset.get('sources', []): - source_location = source.get('location') - if not source_location: - continue - source_type = source.get('type') - if source_type == 'hls': - m3u8_formats = self._extract_m3u8_formats( - source_location, video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False) - for f in m3u8_formats: - mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url']) - if mobj: - height, tbr = mobj.groups() - height = int_or_none(height) - f.update({ - 'height': f.get('height') or height, - 'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None), - 'tbr': f.get('tbr') or int_or_none(tbr), - }) - formats.extend(m3u8_formats) - elif source_type == 'dash': - formats.extend(self._extract_mpd_formats( - source_location, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': source.get('name'), - 'url': source_location, - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('bitrate')), - }) - - for caption in asset.get('caption_metadata', []): - caption_url = caption.get('source_url') - if not caption_url: - continue - subtitles.setdefault(caption.get('language', 'en'), []).append({ - 'url': caption_url, - 'ext': determine_ext(caption_url, 'vtt'), - }) - elif asset.get('type') == 'image': - asset_location = asset.get('location') - if not asset_location: - continue - thumbnails.append({ - 'url': asset_location, - 'width': int_or_none(asset.get('width')), - 'height': int_or_none(asset.get('height')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnails': thumbnails, - 'description': video_data.get('short_description'), - 'like_count': int_or_none(video_data.get('like_count')), - 'timestamp': parse_iso8601(video_data.get('released_at')), - 'series': series, - 'episode': episode, - 'season': season, - 'season_id': season_id, - 'season_number': season_number, - 'episode_number': episode_number, - 'subtitles': subtitles, - 'age_limit': parse_age_limit(video_data.get('rating')), - } diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py deleted file mode 100644 index 342a6130e..000000000 --- a/youtube_dl/extractor/hark.py +++ /dev/null @@ -1,33 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class HarkIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+' - _TEST = { - 'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', - 'md5': '6783a58491b47b92c7c1af5a77d4cbee', - 'info_dict': { - 'id': 'mmbzyhkgny', - 'ext': 'mp3', - 'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013', - 'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', - 'duration': 11, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - data = self._download_json( - 'http://www.hark.com/clips/%s.json' % video_id, video_id) - - return { - 'id': video_id, - 'url': data['url'], - 'title': data['name'], - 'description': data.get('description'), - 'thumbnail': data.get('image_original'), - 'duration': data.get('duration'), - } diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 0ee8ea712..fae425103 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -1,12 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - js_to_json, + int_or_none, + merge_dicts, remove_end, - determine_ext, + unified_timestamp, ) @@ -14,15 +13,21 @@ class HellPornoIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', - 'md5': '1fee339c610d2049699ef2aa699439f1', + 'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3', 'info_dict': { 'id': '149116', 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', 'ext': 'mp4', 'title': 'Dixie is posing with naked ass very erotic', + 'description': 'md5:9a72922749354edb1c4b6e540ad3d215', + 'categories': list, 'thumbnail': r're:https?://.*\.jpg$', + 'duration': 240, + 'timestamp': 1398762720, + 'upload_date': '20140429', + 'view_count': int, 'age_limit': 18, - } + }, }, { 'url': 'http://hellporno.net/v/186271/', 'only_matching': True, @@ -36,40 +41,36 @@ class HellPornoIE(InfoExtractor): title = remove_end(self._html_search_regex( r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno') - flashvars = self._parse_json(self._search_regex( - r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), - display_id, transform_source=js_to_json) - - video_id = flashvars.get('video_id') - thumbnail = flashvars.get('preview_url') - ext = determine_ext(flashvars.get('postfix'), 'mp4') - - formats = [] - for video_url_key in ['video_url', 'video_alt_url']: - video_url = flashvars.get(video_url_key) - if not video_url: - continue - video_text = flashvars.get('%s_text' % video_url_key) - fmt = { - 'url': video_url, - 'ext': ext, - 'format_id': video_text, - } - m = re.search(r'^(?P<height>\d+)[pP]', video_text) - if m: - fmt['height'] = int(m.group('height')) - formats.append(fmt) - self._sort_formats(formats) + info = self._parse_html5_media_entries(url, webpage, display_id)[0] + self._sort_formats(info['formats']) - categories = self._html_search_meta( - 'keywords', webpage, 'categories', default='').split(',') + video_id = self._search_regex( + (r'chs_object\s*=\s*["\'](\d+)', + r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id', + default=display_id) + description = self._search_regex( + r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage, + 'description', fatal=False) + categories = [ + c.strip() + for c in self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + if c.strip()] + duration = int_or_none(self._og_search_property( + 'video:duration', webpage, fatal=False)) + timestamp = unified_timestamp(self._og_search_property( + 'video:release_date', webpage, fatal=False)) + view_count = int_or_none(self._search_regex( + r'>Views\s+(\d+)', webpage, 'view count', fatal=False)) - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, - 'thumbnail': thumbnail, + 'description': description, 'categories': categories, + 'duration': duration, + 'timestamp': timestamp, + 'view_count': view_count, 'age_limit': 18, - 'formats': formats, - } + }) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index f9f7c5a64..f97eefa3d 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -118,6 +118,7 @@ class HotStarIE(HotStarBaseIE): if video_data.get('drmProtected'): raise ExtractorError('This video is DRM protected.', expected=True) + headers = {'Referer': url} formats = [] geo_restricted = False playback_sets = self._call_api_v2('h/v2/play', video_id)['playBackSets'] @@ -137,10 +138,11 @@ class HotStarIE(HotStarBaseIE): if 'package:hls' in tags or ext == 'm3u8': formats.extend(self._extract_m3u8_formats( format_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls')) + entry_protocol='m3u8_native', + m3u8_id='hls', headers=headers)) elif 'package:dash' in tags or ext == 'mpd': formats.extend(self._extract_mpd_formats( - format_url, video_id, mpd_id='dash')) + format_url, video_id, mpd_id='dash', headers=headers)) elif ext == 'f4m': # produce broken files pass @@ -158,6 +160,9 @@ class HotStarIE(HotStarBaseIE): self.raise_geo_restricted(countries=['IN']) self._sort_formats(formats) + for f in formats: + f.setdefault('http_headers', {}).update(headers) + return { 'id': video_id, 'title': title, diff --git a/youtube_dl/extractor/iconosquare.py b/youtube_dl/extractor/iconosquare.py deleted file mode 100644 index a39f422e9..000000000 --- a/youtube_dl/extractor/iconosquare.py +++ /dev/null @@ -1,85 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - get_element_by_id, - remove_end, -) - - -class IconosquareIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)' - _TEST = { - 'url': 'http://statigr.am/p/522207370455279102_24101272', - 'md5': '6eb93b882a3ded7c378ee1d6884b1814', - 'info_dict': { - 'id': '522207370455279102_24101272', - 'ext': 'mp4', - 'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)', - 'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d', - 'timestamp': 1376471991, - 'upload_date': '20130814', - 'uploader': 'aguynamedpatrick', - 'uploader_id': '24101272', - 'comment_count': int, - 'like_count': int, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - media = self._parse_json( - get_element_by_id('mediaJson', webpage), - video_id) - - formats = [{ - 'url': f['url'], - 'format_id': format_id, - 'width': int_or_none(f.get('width')), - 'height': int_or_none(f.get('height')) - } for format_id, f in media['videos'].items()] - self._sort_formats(formats) - - title = remove_end(self._og_search_title(webpage), ' - via Iconosquare') - - timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time')) - description = media.get('caption', {}).get('text') - - uploader = media.get('user', {}).get('username') - uploader_id = media.get('user', {}).get('id') - - comment_count = int_or_none(media.get('comments', {}).get('count')) - like_count = int_or_none(media.get('likes', {}).get('count')) - - thumbnails = [{ - 'url': t['url'], - 'id': thumbnail_id, - 'width': int_or_none(t.get('width')), - 'height': int_or_none(t.get('height')) - } for thumbnail_id, t in media.get('images', {}).items()] - - comments = [{ - 'id': comment.get('id'), - 'text': comment['text'], - 'timestamp': int_or_none(comment.get('created_time')), - 'author': comment.get('from', {}).get('full_name'), - 'author_id': comment.get('from', {}).get('username'), - } for comment in media.get('comments', {}).get('data', []) if 'text' in comment] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnails': thumbnails, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'comment_count': comment_count, - 'like_count': like_count, - 'formats': formats, - 'comments': comments, - } diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 436759da5..a31301985 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import base64 +import json import re from .common import InfoExtractor @@ -8,6 +10,7 @@ from ..utils import ( mimetype2ext, parse_duration, qualities, + try_get, url_or_none, ) @@ -15,15 +18,16 @@ from ..utils import ( class ImdbIE(InfoExtractor): IE_NAME = 'imdb' IE_DESC = 'Internet Movie Database trailers' - _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P<id>\d+)' + _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.imdb.com/video/imdb/vi2524815897', 'info_dict': { 'id': '2524815897', 'ext': 'mp4', - 'title': 'No. 2 from Ice Age: Continental Drift (2012)', + 'title': 'No. 2', 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7', + 'duration': 152, } }, { 'url': 'http://www.imdb.com/video/_/vi2524815897', @@ -47,21 +51,23 @@ class ImdbIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'https://www.imdb.com/videoplayer/vi' + video_id, video_id) - video_metadata = self._parse_json(self._search_regex( - r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage, - 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id] - title = self._html_search_meta( - ['og:title', 'twitter:title'], webpage) or self._html_search_regex( - r'<title>(.+?)</title>', webpage, 'title', fatal=False) or video_metadata['title'] + + data = self._download_json( + 'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id, + query={ + 'key': base64.b64encode(json.dumps({ + 'type': 'VIDEO_PLAYER', + 'subType': 'FORCE_LEGACY', + 'id': 'vi%s' % video_id, + }).encode()).decode(), + })[0] quality = qualities(('SD', '480p', '720p', '1080p')) formats = [] - for encoding in video_metadata.get('encodings', []): + for encoding in data['videoLegacyEncodings']: if not encoding or not isinstance(encoding, dict): continue - video_url = url_or_none(encoding.get('videoUrl')) + video_url = url_or_none(encoding.get('url')) if not video_url: continue ext = mimetype2ext(encoding.get( @@ -69,7 +75,7 @@ class ImdbIE(InfoExtractor): if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( video_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + preference=1, m3u8_id='hls', fatal=False)) continue format_id = encoding.get('definition') formats.append({ @@ -80,13 +86,33 @@ class ImdbIE(InfoExtractor): }) self._sort_formats(formats) + webpage = self._download_webpage( + 'https://www.imdb.com/video/vi' + video_id, video_id) + video_metadata = self._parse_json(self._search_regex( + r'args\.push\(\s*({.+?})\s*\)\s*;', webpage, + 'video metadata'), video_id) + + video_info = video_metadata.get('VIDEO_INFO') + if video_info and isinstance(video_info, dict): + info = try_get( + video_info, lambda x: x[list(video_info.keys())[0]][0], dict) + else: + info = {} + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage) or self._html_search_regex( + r'<title>(.+?)</title>', webpage, 'title', + default=None) or info['videoTitle'] + return { 'id': video_id, 'title': title, + 'alt_title': info.get('videoSubTitle'), 'formats': formats, - 'description': video_metadata.get('description'), - 'thumbnail': video_metadata.get('slate', {}).get('url'), - 'duration': parse_duration(video_metadata.get('duration')), + 'description': info.get('videoDescription'), + 'thumbnail': url_or_none(try_get( + video_metadata, lambda x: x['videoSlate']['source'])), + 'duration': parse_duration(info.get('videoRuntime')), } diff --git a/youtube_dl/extractor/imggaming.py b/youtube_dl/extractor/imggaming.py new file mode 100644 index 000000000..e11f92053 --- /dev/null +++ b/youtube_dl/extractor/imggaming.py @@ -0,0 +1,133 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + ExtractorError, + int_or_none, + str_or_none, + try_get, +) + + +class ImgGamingBaseIE(InfoExtractor): + _API_BASE = 'https://dce-frontoffice.imggaming.com/api/v2/' + _API_KEY = '857a1e5d-e35e-4fdf-805b-a87b6f8364bf' + _HEADERS = None + _MANIFEST_HEADERS = {'Accept-Encoding': 'identity'} + _REALM = None + _VALID_URL_TEMPL = r'https?://(?P<domain>%s)/(?P<type>live|playlist|video)/(?P<id>\d+)(?:\?.*?\bplaylistId=(?P<playlist_id>\d+))?' + + def _real_initialize(self): + self._HEADERS = { + 'Realm': 'dce.' + self._REALM, + 'x-api-key': self._API_KEY, + } + + email, password = self._get_login_info() + if email is None: + self.raise_login_required() + + p_headers = self._HEADERS.copy() + p_headers['Content-Type'] = 'application/json' + self._HEADERS['Authorization'] = 'Bearer ' + self._download_json( + self._API_BASE + 'login', + None, 'Logging in', data=json.dumps({ + 'id': email, + 'secret': password, + }).encode(), headers=p_headers)['authorisationToken'] + + def _call_api(self, path, media_id): + return self._download_json( + self._API_BASE + path + media_id, media_id, headers=self._HEADERS) + + def _extract_dve_api_url(self, media_id, media_type): + stream_path = 'stream' + if media_type == 'video': + stream_path += '/vod/' + else: + stream_path += '?eventId=' + try: + return self._call_api( + stream_path, media_id)['playerUrlCallback'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + raise ExtractorError( + self._parse_json(e.cause.read().decode(), media_id)['messages'][0], + expected=True) + raise + + def _real_extract(self, url): + domain, media_type, media_id, playlist_id = re.match(self._VALID_URL, url).groups() + + if playlist_id: + if self._downloader.params.get('noplaylist'): + self.to_screen('Downloading just video %s because of --no-playlist' % media_id) + else: + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id) + media_type, media_id = 'playlist', playlist_id + + if media_type == 'playlist': + playlist = self._call_api('vod/playlist/', media_id) + entries = [] + for video in try_get(playlist, lambda x: x['videos']['vods']) or []: + video_id = str_or_none(video.get('id')) + if not video_id: + continue + entries.append(self.url_result( + 'https://%s/video/%s' % (domain, video_id), + self.ie_key(), video_id)) + return self.playlist_result( + entries, media_id, playlist.get('title'), + playlist.get('description')) + + dve_api_url = self._extract_dve_api_url(media_id, media_type) + video_data = self._download_json(dve_api_url, media_id) + is_live = media_type == 'live' + if is_live: + title = self._live_title(self._call_api('event/', media_id)['title']) + else: + title = video_data['name'] + + formats = [] + for proto in ('hls', 'dash'): + media_url = video_data.get(proto + 'Url') or try_get(video_data, lambda x: x[proto]['url']) + if not media_url: + continue + if proto == 'hls': + m3u8_formats = self._extract_m3u8_formats( + media_url, media_id, 'mp4', 'm3u8' if is_live else 'm3u8_native', + m3u8_id='hls', fatal=False, headers=self._MANIFEST_HEADERS) + for f in m3u8_formats: + f.setdefault('http_headers', {}).update(self._MANIFEST_HEADERS) + formats.append(f) + else: + formats.extend(self._extract_mpd_formats( + media_url, media_id, mpd_id='dash', fatal=False, + headers=self._MANIFEST_HEADERS)) + self._sort_formats(formats) + + subtitles = {} + for subtitle in video_data.get('subtitles', []): + subtitle_url = subtitle.get('url') + if not subtitle_url: + continue + subtitles.setdefault(subtitle.get('lang', 'en_US'), []).append({ + 'url': subtitle_url, + }) + + return { + 'id': media_id, + 'title': title, + 'formats': formats, + 'thumbnail': video_data.get('thumbnailUrl'), + 'description': video_data.get('description'), + 'duration': int_or_none(video_data.get('duration')), + 'tags': video_data.get('tags'), + 'is_live': is_live, + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 76cc5ec3e..59b0a90c3 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,15 +1,13 @@ from __future__ import unicode_literals +import json +import re + from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urlparse, ) -from ..utils import ( - determine_ext, - int_or_none, - xpath_text, -) class InternetVideoArchiveIE(InfoExtractor): @@ -20,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor): 'info_dict': { 'id': '194487', 'ext': 'mp4', - 'title': 'KICK-ASS 2', + 'title': 'Kick-Ass 2', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', }, 'params': { @@ -33,68 +31,34 @@ class InternetVideoArchiveIE(InfoExtractor): def _build_json_url(query): return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query - @staticmethod - def _build_xml_url(query): - return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query - def _real_extract(self, url): - query = compat_urlparse.urlparse(url).query - query_dic = compat_parse_qs(query) - video_id = query_dic['publishedid'][0] - - if '/player/' in url: - configuration = self._download_json(url, video_id) - - # There are multiple videos in the playlist whlie only the first one - # matches the video played in browsers - video_info = configuration['playlist'][0] - title = video_info['title'] - - formats = [] - for source in video_info['sources']: - file_url = source['file'] - if determine_ext(file_url) == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) - file_url = m3u8_formats[0]['url'] - formats.extend(self._extract_f4m_formats( - file_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - formats.extend(self._extract_mpd_formats( - file_url.replace('.m3u8', '.mpd'), - video_id, mpd_id='dash', fatal=False)) - else: - a_format = { - 'url': file_url, - } - - if source.get('label') and source['label'][-4:] == ' kbs': - tbr = int_or_none(source['label'][:-4]) - a_format.update({ - 'tbr': tbr, - 'format_id': 'http-%d' % tbr, - }) - formats.append(a_format) - - self._sort_formats(formats) - - description = video_info.get('description') - thumbnail = video_info.get('image') - else: - configuration = self._download_xml(url, video_id) - formats = [{ - 'url': xpath_text(configuration, './file', 'file URL', fatal=True), - }] - thumbnail = xpath_text(configuration, './image', 'thumbnail') - title = 'InternetVideoArchive video %s' % video_id - description = None + query = compat_parse_qs(compat_urlparse.urlparse(url).query) + video_id = query['publishedid'][0] + data = self._download_json( + 'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx', + video_id, data=json.dumps({ + 'customerid': query['customerid'][0], + 'publishedid': video_id, + }).encode()) + title = data['Title'] + formats = self._extract_m3u8_formats( + data['VideoUrl'], video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + file_url = formats[0]['url'] + if '.ism/' in file_url: + replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url) + formats.extend(self._extract_f4m_formats( + replace_url('.f4m'), video_id, f4m_id='hds', fatal=False)) + formats.extend(self._extract_mpd_formats( + replace_url('.mpd'), video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_ism_formats( + replace_url('Manifest'), video_id, ism_id='mss', fatal=False)) + self._sort_formats(formats) return { 'id': video_id, 'title': title, 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, + 'thumbnail': data.get('PosterUrl'), + 'description': data.get('Description'), } diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 86c014b07..b5a740a01 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -1,8 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re import json +import re +import sys from .common import InfoExtractor from ..utils import ( @@ -18,6 +19,8 @@ class IviIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' _GEO_BYPASS = False _GEO_COUNTRIES = ['RU'] + _LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c' + _LIGHT_URL = 'https://api.ivi.ru/light/' _TESTS = [ # Single movie @@ -80,48 +83,96 @@ class IviIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - data = { + data = json.dumps({ 'method': 'da.content.get', 'params': [ video_id, { - 'site': 's183', + 'site': 's%d', 'referrer': 'http://www.ivi.ru/watch/%s' % video_id, 'contentid': video_id } ] - } + }) - video_json = self._download_json( - 'http://api.digitalaccess.ru/api/json/', video_id, - 'Downloading video JSON', data=json.dumps(data)) - - if 'error' in video_json: - error = video_json['error'] - origin = error['origin'] - if origin == 'NotAllowedForLocation': - self.raise_geo_restricted( - msg=error['message'], countries=self._GEO_COUNTRIES) - elif origin == 'NoRedisValidData': - raise ExtractorError('Video %s does not exist' % video_id, expected=True) - raise ExtractorError( - 'Unable to download video %s: %s' % (video_id, error['message']), - expected=True) + bundled = hasattr(sys, 'frozen') - result = video_json['result'] + for site in (353, 183): + content_data = (data % site).encode() + if site == 353: + if bundled: + continue + try: + from Cryptodome.Cipher import Blowfish + from Cryptodome.Hash import CMAC + pycryptodomex_found = True + except ImportError: + pycryptodomex_found = False + continue - quality = qualities(self._KNOWN_FORMATS) + timestamp = (self._download_json( + self._LIGHT_URL, video_id, + 'Downloading timestamp JSON', data=json.dumps({ + 'method': 'da.timestamp.get', + 'params': [] + }).encode(), fatal=False) or {}).get('result') + if not timestamp: + continue - formats = [{ - 'url': x['url'], - 'format_id': x.get('content_format'), - 'quality': quality(x.get('content_format')), - } for x in result['files'] if x.get('url')] + query = { + 'ts': timestamp, + 'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(), + } + else: + query = {} - self._sort_formats(formats) + video_json = self._download_json( + self._LIGHT_URL, video_id, + 'Downloading video JSON', data=content_data, query=query) + error = video_json.get('error') + if error: + origin = error.get('origin') + message = error.get('message') or error.get('user_message') + extractor_msg = 'Unable to download video %s' + if origin == 'NotAllowedForLocation': + self.raise_geo_restricted(message, self._GEO_COUNTRIES) + elif origin == 'NoRedisValidData': + extractor_msg = 'Video %s does not exist' + elif site == 353: + continue + elif bundled: + raise ExtractorError( + 'This feature does not work from bundled exe. Run youtube-dl from sources.', + expected=True) + elif not pycryptodomex_found: + raise ExtractorError( + 'pycryptodomex not found. Please install it.', + expected=True) + elif message: + extractor_msg += ': ' + message + raise ExtractorError(extractor_msg % video_id, expected=True) + else: + break + + result = video_json['result'] title = result['title'] - duration = int_or_none(result.get('duration')) + quality = qualities(self._KNOWN_FORMATS) + + formats = [] + for f in result.get('files', []): + f_url = f.get('url') + content_format = f.get('content_format') + if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format: + continue + formats.append({ + 'url': f_url, + 'format_id': content_format, + 'quality': quality(content_format), + 'filesize': int_or_none(f.get('size_in_bytes')), + }) + self._sort_formats(formats) + compilation = result.get('compilation') episode = title if compilation else None @@ -158,7 +209,7 @@ class IviIE(InfoExtractor): 'episode_number': episode_number, 'thumbnails': thumbnails, 'description': description, - 'duration': duration, + 'duration': int_or_none(result.get('duration')), 'formats': formats, } @@ -188,7 +239,7 @@ class IviCompilationIE(InfoExtractor): self.url_result( 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key()) for serie in re.findall( - r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)] + r'<a\b[^>]+\bhref=["\']/watch/%s/(\d+)["\']' % compilation_id, html)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py index c21827618..490efa8fb 100644 --- a/youtube_dl/extractor/jamendo.py +++ b/youtube_dl/extractor/jamendo.py @@ -1,38 +1,26 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import hashlib +import random -from ..compat import compat_urlparse +from ..compat import compat_str from .common import InfoExtractor -from ..utils import parse_duration - - -class JamendoBaseIE(InfoExtractor): - def _extract_meta(self, webpage, fatal=True): - title = self._og_search_title( - webpage, default=None) or self._search_regex( - r'<title>([^<]+)', webpage, - 'title', default=None) - if title: - title = self._search_regex( - r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None) - if not title: - title = self._html_search_meta( - 'name', webpage, 'title', fatal=fatal) - mobj = re.search(r'(.+) - (.+)', title or '') - artist, second = mobj.groups() if mobj else [None] * 2 - return title, artist, second - - -class JamendoIE(JamendoBaseIE): +from ..utils import ( + clean_html, + int_or_none, + try_get, +) + + +class JamendoIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: licensing\.jamendo\.com/[^/]+| (?:www\.)?jamendo\.com ) - /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+) + /track/(?P<id>[0-9]+)(?:/(?P<display_id>[^/?#&]+))? ''' _TESTS = [{ 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i', @@ -45,7 +33,9 @@ class JamendoIE(JamendoBaseIE): 'artist': 'Maya Filipič', 'track': 'Stories from Emona I', 'duration': 210, - 'thumbnail': r're:^https?://.*\.jpg' + 'thumbnail': r're:^https?://.*\.jpg', + 'timestamp': 1217438117, + 'upload_date': '20080730', } }, { 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock', @@ -53,15 +43,20 @@ class JamendoIE(JamendoBaseIE): }] def _real_extract(self, url): - mobj = self._VALID_URL_RE.match(url) - track_id = mobj.group('id') - display_id = mobj.group('display_id') - + track_id, display_id = self._VALID_URL_RE.match(url).groups() webpage = self._download_webpage( - 'https://www.jamendo.com/track/%s/%s' % (track_id, display_id), - display_id) - - title, artist, track = self._extract_meta(webpage) + 'https://www.jamendo.com/track/' + track_id, track_id) + models = self._parse_json(self._html_search_regex( + r"data-bundled-models='([^']+)", + webpage, 'bundled models'), track_id) + track = models['track']['models'][0] + title = track_name = track['name'] + get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {} + artist = get_model('artist') + artist_name = artist.get('name') + if artist_name: + title = '%s - %s' % (artist_name, title) + album = get_model('album') formats = [{ 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294' @@ -77,31 +72,58 @@ class JamendoIE(JamendoBaseIE): ))] self._sort_formats(formats) - thumbnail = self._html_search_meta( - 'image', webpage, 'thumbnail', fatal=False) - duration = parse_duration(self._search_regex( - r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']', - webpage, 'duration', fatal=False)) + urls = [] + thumbnails = [] + for _, covers in track.get('cover', {}).items(): + for cover_id, cover_url in covers.items(): + if not cover_url or cover_url in urls: + continue + urls.append(cover_url) + size = int_or_none(cover_id.lstrip('size')) + thumbnails.append({ + 'id': cover_id, + 'url': cover_url, + 'width': size, + 'height': size, + }) + + tags = [] + for tag in track.get('tags', []): + tag_name = tag.get('name') + if not tag_name: + continue + tags.append(tag_name) + + stats = track.get('stats') or {} return { 'id': track_id, 'display_id': display_id, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, 'title': title, - 'duration': duration, - 'artist': artist, - 'track': track, - 'formats': formats + 'description': track.get('description'), + 'duration': int_or_none(track.get('duration')), + 'artist': artist_name, + 'track': track_name, + 'album': album.get('name'), + 'formats': formats, + 'license': '-'.join(track.get('licenseCC', [])) or None, + 'timestamp': int_or_none(track.get('dateCreated')), + 'view_count': int_or_none(stats.get('listenedAll')), + 'like_count': int_or_none(stats.get('favorited')), + 'average_rating': int_or_none(stats.get('averageNote')), + 'tags': tags, } -class JamendoAlbumIE(JamendoBaseIE): - _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)' +class JamendoAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)' _TEST = { 'url': 'https://www.jamendo.com/album/121486/duck-on-cover', 'info_dict': { 'id': '121486', - 'title': 'Shearer - Duck On Cover' + 'title': 'Duck On Cover', + 'description': 'md5:c2920eaeef07d7af5b96d7c64daf1239', }, 'playlist': [{ 'md5': 'e1a2fcb42bda30dfac990212924149a8', @@ -111,6 +133,8 @@ class JamendoAlbumIE(JamendoBaseIE): 'title': 'Shearer - Warmachine', 'artist': 'Shearer', 'track': 'Warmachine', + 'timestamp': 1368089771, + 'upload_date': '20130509', } }, { 'md5': '1f358d7b2f98edfe90fd55dac0799d50', @@ -120,6 +144,8 @@ class JamendoAlbumIE(JamendoBaseIE): 'title': 'Shearer - Without Your Ghost', 'artist': 'Shearer', 'track': 'Without Your Ghost', + 'timestamp': 1368089771, + 'upload_date': '20130509', } }], 'params': { @@ -127,24 +153,35 @@ class JamendoAlbumIE(JamendoBaseIE): } } + def _call_api(self, resource, resource_id): + path = '/api/%ss' % resource + rand = compat_str(random.random()) + return self._download_json( + 'https://www.jamendo.com' + path, resource_id, query={ + 'id[]': resource_id, + }, headers={ + 'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand) + })[0] + def _real_extract(self, url): - mobj = self._VALID_URL_RE.match(url) - album_id = mobj.group('id') - - webpage = self._download_webpage(url, mobj.group('display_id')) - - title, artist, album = self._extract_meta(webpage, fatal=False) - - entries = [{ - '_type': 'url_transparent', - 'url': compat_urlparse.urljoin(url, m.group('path')), - 'ie_key': JamendoIE.ie_key(), - 'id': self._search_regex( - r'/track/(\d+)', m.group('path'), 'track id', default=None), - 'artist': artist, - 'album': album, - } for m in re.finditer( - r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link', - webpage)] - - return self.playlist_result(entries, album_id, title) + album_id = self._match_id(url) + album = self._call_api('album', album_id) + album_name = album.get('name') + + entries = [] + for track in album.get('tracks', []): + track_id = track.get('id') + if not track_id: + continue + track_id = compat_str(track_id) + entries.append({ + '_type': 'url_transparent', + 'url': 'https://www.jamendo.com/track/' + track_id, + 'ie_key': JamendoIE.ie_key(), + 'id': track_id, + 'album': album_name, + }) + + return self.playlist_result( + entries, album_id, album_name, + clean_html(try_get(album, lambda x: x['description']['en'], compat_str))) diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py deleted file mode 100644 index 4b5f346d1..000000000 --- a/youtube_dl/extractor/jpopsukitv.py +++ /dev/null @@ -1,68 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - unified_strdate, -) - - -class JpopsukiIE(InfoExtractor): - IE_NAME = 'jpopsuki.tv' - _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P<id>\S+)' - - _TEST = { - 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', - 'md5': '88018c0c1a9b1387940e90ec9e7e198e', - 'info_dict': { - 'id': '00be659d23b0b40508169cdee4545771', - 'ext': 'mp4', - 'title': 'ayumi hamasaki - evolution', - 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', - 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', - 'uploader': 'plama_chan', - 'uploader_id': '404', - 'upload_date': '20121101' - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_url = 'http://www.jpopsuki.tv' + self._html_search_regex( - r'<source src="(.*?)" type', webpage, 'video url') - - video_title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - uploader = self._html_search_regex( - r'<li>from: <a href="/user/view/user/(.*?)/uid/', - webpage, 'video uploader', fatal=False) - uploader_id = self._html_search_regex( - r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', - webpage, 'video uploader_id', fatal=False) - upload_date = unified_strdate(self._html_search_regex( - r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date', - fatal=False)) - view_count_str = self._html_search_regex( - r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count', - fatal=False) - comment_count_str = self._html_search_regex( - r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count', - fatal=False) - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - 'view_count': int_or_none(view_count_str), - 'comment_count': int_or_none(comment_count_str), - } diff --git a/youtube_dl/extractor/kakao.py b/youtube_dl/extractor/kakao.py index 7fa140b0c..32935bb28 100644 --- a/youtube_dl/extractor/kakao.py +++ b/youtube_dl/extractor/kakao.py @@ -6,14 +6,15 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( int_or_none, + strip_or_none, unified_timestamp, update_url_query, ) class KakaoIE(InfoExtractor): - _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P<channel>\d+)/cliplink/(?P<id>\d+)' - _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks' + _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)' + _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/' _TESTS = [{ 'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083', @@ -36,7 +37,7 @@ class KakaoIE(InfoExtractor): 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', 'uploader_id': 2653210, - 'uploader': '쇼 음악중심', + 'uploader': '쇼! 음악중심', 'timestamp': 1485684628, 'upload_date': '20170129', } @@ -44,6 +45,8 @@ class KakaoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + display_id = video_id.rstrip('@my') + api_base = self._API_BASE_TMPL % video_id player_header = { 'Referer': update_url_query( @@ -55,20 +58,23 @@ class KakaoIE(InfoExtractor): }) } - QUERY_COMMON = { + query = { 'player': 'monet_html5', 'referer': url, 'uuid': '', 'service': 'kakao_tv', 'section': '', 'dteType': 'PC', + 'fields': ','.join([ + '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title', + 'description', 'channelId', 'createTime', 'duration', 'playCount', + 'likeCount', 'commentCount', 'tagList', 'channel', 'name', + 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault', + 'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label']) } - query = QUERY_COMMON.copy() - query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList' impress = self._download_json( - '%s/%s/impress' % (self._API_BASE, video_id), - video_id, 'Downloading video info', + api_base + 'impress', display_id, 'Downloading video info', query=query, headers=player_header) clip_link = impress['clipLink'] @@ -76,32 +82,22 @@ class KakaoIE(InfoExtractor): title = clip.get('title') or clip_link.get('displayTitle') - tid = impress.get('tid', '') - - query = QUERY_COMMON.copy() - query.update({ - 'tid': tid, - 'profile': 'HIGH', - }) - raw = self._download_json( - '%s/%s/raw' % (self._API_BASE, video_id), - video_id, 'Downloading video formats info', - query=query, headers=player_header) + query['tid'] = impress.get('tid', '') formats = [] - for fmt in raw.get('outputList', []): + for fmt in clip.get('videoOutputList', []): try: profile_name = fmt['profile'] + if profile_name == 'AUDIO': + continue + query.update({ + 'profile': profile_name, + 'fields': '-*,url', + }) fmt_url_json = self._download_json( - '%s/%s/raw/videolocation' % (self._API_BASE, video_id), - video_id, + api_base + 'raw/videolocation', display_id, 'Downloading video URL for profile %s' % profile_name, - query={ - 'service': 'kakao_tv', - 'section': '', - 'tid': tid, - 'profile': profile_name - }, headers=player_header, fatal=False) + query=query, headers=player_header, fatal=False) if fmt_url_json is None: continue @@ -113,7 +109,8 @@ class KakaoIE(InfoExtractor): 'width': int_or_none(fmt.get('width')), 'height': int_or_none(fmt.get('height')), 'format_note': fmt.get('label'), - 'filesize': int_or_none(fmt.get('filesize')) + 'filesize': int_or_none(fmt.get('filesize')), + 'tbr': int_or_none(fmt.get('kbps')), }) except KeyError: pass @@ -134,9 +131,9 @@ class KakaoIE(InfoExtractor): }) return { - 'id': video_id, + 'id': display_id, 'title': title, - 'description': clip.get('description'), + 'description': strip_or_none(clip.get('description')), 'uploader': clip_link.get('channel', {}).get('name'), 'uploader_id': clip_link.get('channelId'), 'thumbnails': thumbs, @@ -146,4 +143,5 @@ class KakaoIE(InfoExtractor): 'like_count': int_or_none(clip.get('likeCount')), 'comment_count': int_or_none(clip.get('commentCount')), 'formats': formats, + 'tags': clip.get('tagList'), } diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 0a733424c..2d38b758b 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -151,14 +151,15 @@ class KalturaIE(InfoExtractor): if mobj: embed_info = mobj.groupdict() for k, v in embed_info.items(): - embed_info[k] = v.strip() + if v: + embed_info[k] = v.strip() url = 'kaltura:%(partner_id)s:%(id)s' % embed_info escaped_pid = re.escape(embed_info['partner_id']) - service_url = re.search( - r'<script[^>]+src=["\']((?:https?:)?//.+?)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid), + service_mobj = re.search( + r'<script[^>]+src=(["\'])(?P<id>(?:https?:)?//(?:(?!\1).)+)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid), webpage) - if service_url: - url = smuggle_url(url, {'service_url': service_url.group(1)}) + if service_mobj: + url = smuggle_url(url, {'service_url': service_mobj.group('id')}) return url def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs): diff --git a/youtube_dl/extractor/keek.py b/youtube_dl/extractor/keek.py deleted file mode 100644 index 94a03d277..000000000 --- a/youtube_dl/extractor/keek.py +++ /dev/null @@ -1,39 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class KeekIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P<id>\w+)' - IE_NAME = 'keek' - _TEST = { - 'url': 'https://www.keek.com/keek/NODfbab', - 'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83', - 'info_dict': { - 'id': 'NODfbab', - 'ext': 'mp4', - 'title': 'md5:35d42050a3ece241d5ddd7fdcc6fd896', - 'uploader': 'ytdl', - 'uploader_id': 'eGT5bab', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - return { - 'id': video_id, - 'url': self._og_search_video_url(webpage), - 'ext': 'mp4', - 'title': self._og_search_description(webpage).strip(), - 'thumbnail': self._og_search_thumbnail(webpage), - 'uploader': self._search_regex( - r'data-username=(["\'])(?P<uploader>.+?)\1', webpage, - 'uploader', fatal=False, group='uploader'), - 'uploader_id': self._search_regex( - r'data-user-id=(["\'])(?P<uploader_id>.+?)\1', webpage, - 'uploader id', fatal=False, group='uploader_id'), - } diff --git a/youtube_dl/extractor/kinja.py b/youtube_dl/extractor/kinja.py new file mode 100644 index 000000000..79e3026d2 --- /dev/null +++ b/youtube_dl/extractor/kinja.py @@ -0,0 +1,221 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse_unquote, +) +from ..utils import ( + int_or_none, + parse_iso8601, + strip_or_none, + try_get, + unescapeHTML, + urljoin, +) + + +class KinjaEmbedIE(InfoExtractor): + IENAME = 'kinja:embed' + _DOMAIN_REGEX = r'''(?:[^.]+\.)? + (?: + avclub| + clickhole| + deadspin| + gizmodo| + jalopnik| + jezebel| + kinja| + kotaku| + lifehacker| + splinternews| + the(?:inventory|onion|root|takeout) + )\.com''' + _COMMON_REGEX = r'''/ + (?: + ajax/inset| + embed/video + )/iframe\?.*?\bid=''' + _VALID_URL = r'''(?x)https?://%s%s + (?P<type> + fb| + imgur| + instagram| + jwp(?:layer)?-video| + kinjavideo| + mcp| + megaphone| + ooyala| + soundcloud(?:-playlist)?| + tumblr-post| + twitch-stream| + twitter| + ustream-channel| + vimeo| + vine| + youtube-(?:list|video) + )-(?P<id>[^&]+)''' % (_DOMAIN_REGEX, _COMMON_REGEX) + _TESTS = [{ + 'url': 'https://kinja.com/ajax/inset/iframe?id=fb-10103303356633621', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=kinjavideo-100313', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=megaphone-PPY1300931075', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=ooyala-xzMXhleDpopuT0u1ijt_qZj3Va-34pEX%2FZTIxYmJjZDM2NWYzZDViZGRiOWJjYzc5', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=soundcloud-128574047', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=soundcloud-playlist-317413750', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=tumblr-post-160130699814-daydreams-at-midnight', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=twitch-stream-libratus_extra', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=twitter-1068875942473404422', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=ustream-channel-10414700', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=vimeo-120153502', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=vine-5BlvV5qqPrD', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-list-BCQ3KyrPjgA/PLE6509247C270A72E', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-video-00QyL0AgPAE', + 'only_matching': True, + }] + _JWPLATFORM_PROVIDER = ('cdn.jwplayer.com/v2/media/', 'JWPlatform') + _PROVIDER_MAP = { + 'fb': ('facebook.com/video.php?v=', 'Facebook'), + 'imgur': ('imgur.com/', 'Imgur'), + 'instagram': ('instagram.com/p/', 'Instagram'), + 'jwplayer-video': _JWPLATFORM_PROVIDER, + 'jwp-video': _JWPLATFORM_PROVIDER, + 'megaphone': ('player.megaphone.fm/', 'Generic'), + 'ooyala': ('player.ooyala.com/player.js?embedCode=', 'Ooyala'), + 'soundcloud': ('api.soundcloud.com/tracks/', 'Soundcloud'), + 'soundcloud-playlist': ('api.soundcloud.com/playlists/', 'SoundcloudPlaylist'), + 'tumblr-post': ('%s.tumblr.com/post/%s', 'Tumblr'), + 'twitch-stream': ('twitch.tv/', 'TwitchStream'), + 'twitter': ('twitter.com/i/cards/tfw/v1/', 'TwitterCard'), + 'ustream-channel': ('ustream.tv/embed/', 'Ustream'), + 'vimeo': ('vimeo.com/', 'Vimeo'), + 'vine': ('vine.co/v/', 'Vine'), + 'youtube-list': ('youtube.com/embed/%s?list=%s', 'YoutubePlaylist'), + 'youtube-video': ('youtube.com/embed/', 'Youtube'), + } + + @staticmethod + def _extract_urls(webpage, url): + return [urljoin(url, unescapeHTML(mobj.group('url'))) for mobj in re.finditer( + r'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//%s)?%s(?:(?!\1).)+)\1' % (KinjaEmbedIE._DOMAIN_REGEX, KinjaEmbedIE._COMMON_REGEX), + webpage)] + + def _real_extract(self, url): + video_type, video_id = re.match(self._VALID_URL, url).groups() + + provider = self._PROVIDER_MAP.get(video_type) + if provider: + video_id = compat_urllib_parse_unquote(video_id) + if video_type == 'tumblr-post': + video_id, blog = video_id.split('-', 1) + result_url = provider[0] % (blog, video_id) + elif video_type == 'youtube-list': + video_id, playlist_id = video_id.split('/') + result_url = provider[0] % (video_id, playlist_id) + else: + if video_type == 'ooyala': + video_id = video_id.split('/')[0] + result_url = provider[0] + video_id + return self.url_result('http://' + result_url, provider[1]) + + if video_type == 'kinjavideo': + data = self._download_json( + 'https://kinja.com/api/core/video/views/videoById', + video_id, query={'videoId': video_id})['data'] + title = data['title'] + + formats = [] + for k in ('signedPlaylist', 'streaming'): + m3u8_url = data.get(k + 'Url') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + self._sort_formats(formats) + + thumbnail = None + poster = data.get('poster') or {} + poster_id = poster.get('id') + if poster_id: + thumbnail = 'https://i.kinja-img.com/gawker-media/image/upload/%s.%s' % (poster_id, poster.get('format') or 'jpg') + + return { + 'id': video_id, + 'title': title, + 'description': strip_or_none(data.get('description')), + 'formats': formats, + 'tags': data.get('tags'), + 'timestamp': int_or_none(try_get( + data, lambda x: x['postInfo']['publishTimeMillis']), 1000), + 'thumbnail': thumbnail, + 'uploader': data.get('network'), + } + else: + video_data = self._download_json( + 'https://api.vmh.univision.com/metadata/v1/content/' + video_id, + video_id)['videoMetadata'] + iptc = video_data['photoVideoMetadataIPTC'] + title = iptc['title']['en'] + fmg = video_data.get('photoVideoMetadata_fmg') or {} + tvss_domain = fmg.get('tvssDomain') or 'https://auth.univision.com' + data = self._download_json( + tvss_domain + '/api/v3/video-auth/url-signature-tokens', + video_id, query={'mcpids': video_id})['data'][0] + formats = [] + + rendition_url = data.get('renditionUrl') + if rendition_url: + formats = self._extract_m3u8_formats( + rendition_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + + fallback_rendition_url = data.get('fallbackRenditionUrl') + if fallback_rendition_url: + formats.append({ + 'format_id': 'fallback', + 'tbr': int_or_none(self._search_regex( + r'_(\d+)\.mp4', fallback_rendition_url, + 'bitrate', default=None)), + 'url': fallback_rendition_url, + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': try_get(iptc, lambda x: x['cloudinaryLink']['link'], compat_str), + 'uploader': fmg.get('network'), + 'duration': int_or_none(iptc.get('fileDuration')), + 'formats': formats, + 'description': try_get(iptc, lambda x: x['description']['en'], compat_str), + 'timestamp': parse_iso8601(iptc.get('dateReleased')), + } diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py deleted file mode 100644 index 1fda45107..000000000 --- a/youtube_dl/extractor/kontrtube.py +++ /dev/null @@ -1,73 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - parse_duration, -) - - -class KontrTubeIE(InfoExtractor): - IE_NAME = 'kontrtube' - IE_DESC = 'KontrTube.ru - Труба зовёт' - _VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/' - - _TEST = { - 'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/', - 'md5': '975a991a4926c9a85f383a736a2e6b80', - 'info_dict': { - 'id': '2678', - 'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag', - 'ext': 'mp4', - 'title': 'Над олимпийской деревней в Сочи поднят российский флаг', - 'description': 'md5:80edc4c613d5887ae8ccf1d59432be41', - 'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg', - 'duration': 270, - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') - - webpage = self._download_webpage( - url, display_id, 'Downloading page') - - video_url = self._search_regex( - r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL') - thumbnail = self._search_regex( - r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False) - title = self._html_search_regex( - r'(?s)<h2>(.+?)</h2>', webpage, 'title') - description = self._html_search_meta( - 'description', webpage, 'description') - - duration = self._search_regex( - r'Длительность: <em>([^<]+)</em>', webpage, 'duration', fatal=False) - if duration: - duration = parse_duration(duration.replace('мин', 'min').replace('сек', 'sec')) - - view_count = self._search_regex( - r'Просмотров: <em>([^<]+)</em>', - webpage, 'view count', fatal=False) - if view_count: - view_count = int_or_none(view_count.replace(' ', '')) - - comment_count = int_or_none(self._search_regex( - r'Комментарии \((\d+)\)<', webpage, ' comment count', fatal=False)) - - return { - 'id': video_id, - 'display_id': display_id, - 'url': video_url, - 'thumbnail': thumbnail, - 'title': title, - 'description': description, - 'duration': duration, - 'view_count': int_or_none(view_count), - 'comment_count': int_or_none(comment_count), - } diff --git a/youtube_dl/extractor/la7.py b/youtube_dl/extractor/la7.py index 6373268c4..c3b4ffa7e 100644 --- a/youtube_dl/extractor/la7.py +++ b/youtube_dl/extractor/la7.py @@ -20,7 +20,7 @@ class LA7IE(InfoExtractor): 'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722', 'md5': '8b613ffc0c4bf9b9e377169fc19c214c', 'info_dict': { - 'id': 'inccool8-02-10-2015-163722', + 'id': '0_42j6wd36', 'ext': 'mp4', 'title': 'Inc.Cool8', 'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto atletico', @@ -57,7 +57,7 @@ class LA7IE(InfoExtractor): return { '_type': 'url_transparent', 'url': smuggle_url('kaltura:103:%s' % player_data['vid'], { - 'service_url': 'http://kdam.iltrovatore.it', + 'service_url': 'http://nkdam.iltrovatore.it', }), 'id': video_id, 'title': player_data['title'], diff --git a/youtube_dl/extractor/learnr.py b/youtube_dl/extractor/learnr.py deleted file mode 100644 index 1435e090e..000000000 --- a/youtube_dl/extractor/learnr.py +++ /dev/null @@ -1,33 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class LearnrIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?learnr\.pro/view/video/(?P<id>[0-9]+)' - _TEST = { - 'url': 'http://www.learnr.pro/view/video/51624-web-development-tutorial-for-beginners-1-how-to-build-webpages-with-html-css-javascript', - 'md5': '3719fdf0a68397f49899e82c308a89de', - 'info_dict': { - 'id': '51624', - 'ext': 'mp4', - 'title': 'Web Development Tutorial for Beginners (#1) - How to build webpages with HTML, CSS, Javascript', - 'description': 'md5:b36dbfa92350176cdf12b4d388485503', - 'uploader': 'LearnCode.academy', - 'uploader_id': 'learncodeacademy', - 'upload_date': '20131021', - }, - 'add_ie': ['Youtube'], - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - return { - '_type': 'url_transparent', - 'url': self._search_regex( - r"videoId\s*:\s*'([^']+)'", webpage, 'youtube id'), - 'id': video_id, - } diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 6ed7da4ab..1b2dcef46 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( clean_html, determine_ext, @@ -36,7 +35,7 @@ class LecturioBaseIE(InfoExtractor): self._LOGIN_URL, None, 'Downloading login popup') def is_logged(url_handle): - return self._LOGIN_URL not in compat_str(url_handle.geturl()) + return self._LOGIN_URL not in url_handle.geturl() # Already logged in if is_logged(urlh): diff --git a/youtube_dl/extractor/lego.py b/youtube_dl/extractor/lego.py index b312e77f1..1e3c19dfd 100644 --- a/youtube_dl/extractor/lego.py +++ b/youtube_dl/extractor/lego.py @@ -2,23 +2,24 @@ from __future__ import unicode_literals import re +import uuid from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( - unescapeHTML, - parse_duration, - get_element_by_class, + ExtractorError, + int_or_none, + qualities, ) class LEGOIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)' + _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[a-z]{2}-[a-z]{2})/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]{32})' _TESTS = [{ 'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1', 'md5': 'f34468f176cfd76488767fc162c405fa', 'info_dict': { - 'id': '55492d823b1b4d5e985787fa8c2973b1', + 'id': '55492d82-3b1b-4d5e-9857-87fa8c2973b1_en-US', 'ext': 'mp4', 'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi', 'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi', @@ -26,103 +27,123 @@ class LEGOIE(InfoExtractor): }, { # geo-restricted but the contentUrl contain a valid url 'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399', - 'md5': '4c3fec48a12e40c6e5995abc3d36cc2e', + 'md5': 'c7420221f7ffd03ff056f9db7f8d807c', 'info_dict': { - 'id': '13bdc2299ab24d9685701a915b3d71e7', + 'id': '13bdc229-9ab2-4d96-8570-1a915b3d71e7_nl-NL', 'ext': 'mp4', - 'title': 'Aflevering 20 - Helden van het koninkrijk', + 'title': 'Aflevering 20: Helden van het koninkrijk', 'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941', + 'age_limit': 5, }, }, { - # special characters in title - 'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d', + # with subtitle + 'url': 'https://www.lego.com/nl-nl/kids/videos/classic/creative-storytelling-the-little-puppy-aa24f27c7d5242bc86102ebdc0f24cba', 'info_dict': { - 'id': '9685ee9d12e84ff38e84b4e3d0db533d', + 'id': 'aa24f27c-7d52-42bc-8610-2ebdc0f24cba_nl-NL', 'ext': 'mp4', - 'title': 'Force Surprise – LEGO® Star Wars™ Microfighters', - 'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3', + 'title': 'De kleine puppy', + 'description': 'md5:5b725471f849348ac73f2e12cfb4be06', + 'age_limit': 1, + 'subtitles': { + 'nl': [{ + 'ext': 'srt', + 'url': r're:^https://.+\.srt$', + }], + }, }, 'params': { 'skip_download': True, }, }] - _BITRATES = [256, 512, 1024, 1536, 2560] + _QUALITIES = { + 'Lowest': (64, 180, 320), + 'Low': (64, 270, 480), + 'Medium': (96, 360, 640), + 'High': (128, 540, 960), + 'Highest': (128, 720, 1280), + } def _real_extract(self, url): locale, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) - title = get_element_by_class('video-header', webpage).strip() - progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/' - streaming_base = 'http://legoprod-f.akamaihd.net/' - content_url = self._html_search_meta('contentUrl', webpage) - path = self._search_regex( - r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)', - content_url, 'video path', default=None) - if not path: - player_url = self._proto_relative_url(self._search_regex( - r'<iframe[^>]+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)', - webpage, 'player url', default=None)) - if not player_url: - base_url = self._proto_relative_url(self._search_regex( - r'data-baseurl="([^"]+)"', webpage, 'base url', - default='http://www.lego.com/%s/mediaplayer/video/' % locale)) - player_url = base_url + video_id - player_webpage = self._download_webpage(player_url, video_id) - video_data = self._parse_json(unescapeHTML(self._search_regex( - r"video='([^']+)'", player_webpage, 'video data')), video_id) - progressive_base = self._search_regex( - r'data-video-progressive-url="([^"]+)"', - player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/') - streaming_base = self._search_regex( - r'data-video-streaming-url="([^"]+)"', - player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/') - item_id = video_data['ItemId'] + countries = [locale.split('-')[1].upper()] + self._initialize_geo_bypass({ + 'countries': countries, + }) - net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]]) - base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])]) - path = '/'.join([net_storage_path, base_path]) - streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES)) + try: + item = self._download_json( + # https://contentfeed.services.lego.com/api/v2/item/[VIDEO_ID]?culture=[LOCALE]&contentType=Video + 'https://services.slingshot.lego.com/mediaplayer/v2', + video_id, query={ + 'videoId': '%s_%s' % (uuid.UUID(video_id), locale), + }, headers=self.geo_verification_headers()) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 451: + self.raise_geo_restricted(countries=countries) + raise - formats = self._extract_akamai_formats( - '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id) - m3u8_formats = list(filter( - lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none', - formats)) - if len(m3u8_formats) == len(self._BITRATES): - self._sort_formats(m3u8_formats) - for bitrate, m3u8_format in zip(self._BITRATES, m3u8_formats): - progressive_base_url = '%spublic/%s_%d.' % (progressive_base, path, bitrate) - mp4_f = m3u8_format.copy() - mp4_f.update({ - 'url': progressive_base_url + 'mp4', - 'format_id': m3u8_format['format_id'].replace('hls', 'mp4'), - 'protocol': 'http', - }) - web_f = { - 'url': progressive_base_url + 'webm', - 'format_id': m3u8_format['format_id'].replace('hls', 'webm'), - 'width': m3u8_format['width'], - 'height': m3u8_format['height'], - 'tbr': m3u8_format.get('tbr'), - 'ext': 'webm', + video = item['Video'] + video_id = video['Id'] + title = video['Title'] + + q = qualities(['Lowest', 'Low', 'Medium', 'High', 'Highest']) + formats = [] + for video_source in item.get('VideoFormats', []): + video_source_url = video_source.get('Url') + if not video_source_url: + continue + video_source_format = video_source.get('Format') + if video_source_format == 'F4M': + formats.extend(self._extract_f4m_formats( + video_source_url, video_id, + f4m_id=video_source_format, fatal=False)) + elif video_source_format == 'M3U8': + formats.extend(self._extract_m3u8_formats( + video_source_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=video_source_format, fatal=False)) + else: + video_source_quality = video_source.get('Quality') + format_id = [] + for v in (video_source_format, video_source_quality): + if v: + format_id.append(v) + f = { + 'format_id': '-'.join(format_id), + 'quality': q(video_source_quality), + 'url': video_source_url, } - formats.extend([web_f, mp4_f]) - else: - for bitrate in self._BITRATES: - for ext in ('web', 'mp4'): - formats.append({ - 'format_id': '%s-%s' % (ext, bitrate), - 'url': '%spublic/%s_%d.%s' % (progressive_base, path, bitrate, ext), - 'tbr': bitrate, - 'ext': ext, - }) + quality = self._QUALITIES.get(video_source_quality) + if quality: + f.update({ + 'abr': quality[0], + 'height': quality[1], + 'width': quality[2], + }), + formats.append(f) self._sort_formats(formats) + subtitles = {} + sub_file_id = video.get('SubFileId') + if sub_file_id and sub_file_id != '00000000-0000-0000-0000-000000000000': + net_storage_path = video.get('NetstoragePath') + invariant_id = video.get('InvariantId') + video_file_id = video.get('VideoFileId') + video_version = video.get('VideoVersion') + if net_storage_path and invariant_id and video_file_id and video_version: + subtitles.setdefault(locale[:2], []).append({ + 'url': 'https://lc-mediaplayerns-live-s.legocdn.com/public/%s/%s_%s_%s_%s_sub.srt' % (net_storage_path, invariant_id, video_file_id, locale, video_version), + }) + return { 'id': video_id, 'title': title, - 'description': self._html_search_meta('description', webpage), - 'thumbnail': self._html_search_meta('thumbnail', webpage), - 'duration': parse_duration(self._html_search_meta('duration', webpage)), + 'description': video.get('Description'), + 'thumbnail': video.get('GeneratedCoverImage') or video.get('GeneratedThumbnail'), + 'duration': int_or_none(video.get('Length')), 'formats': formats, + 'subtitles': subtitles, + 'age_limit': int_or_none(video.get('AgeFrom')), + 'season': video.get('SeasonTitle'), + 'season_number': int_or_none(video.get('Season')) or None, + 'episode_number': int_or_none(video.get('Episode')) or None, } diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py index a78c6556e..23ca965d9 100644 --- a/youtube_dl/extractor/linuxacademy.py +++ b/youtube_dl/extractor/linuxacademy.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_b64decode, compat_HTTPError, - compat_str, ) from ..utils import ( ExtractorError, @@ -99,7 +98,7 @@ class LinuxAcademyIE(InfoExtractor): 'sso': 'true', }) - login_state_url = compat_str(urlh.geturl()) + login_state_url = urlh.geturl() try: login_page = self._download_webpage( @@ -129,7 +128,7 @@ class LinuxAcademyIE(InfoExtractor): }) access_token = self._search_regex( - r'access_token=([^=&]+)', compat_str(urlh.geturl()), + r'access_token=([^=&]+)', urlh.geturl(), 'access token') self._download_webpage( diff --git a/youtube_dl/extractor/lnkgo.py b/youtube_dl/extractor/lnkgo.py index cfec0d3d0..3e71852aa 100644 --- a/youtube_dl/extractor/lnkgo.py +++ b/youtube_dl/extractor/lnkgo.py @@ -5,24 +5,27 @@ import re from .common import InfoExtractor from ..utils import ( + clean_html, + compat_str, int_or_none, - unified_strdate, + parse_iso8601, ) class LnkGoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?lnkgo\.(?:alfa\.)?lt/visi-video/(?P<show>[^/]+)/ziurek-(?P<id>[A-Za-z0-9-]+)' + _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P<id>[A-Za-z0-9-]+)(?:/(?P<episode_id>\d+))?' _TESTS = [{ - 'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162', + 'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai', 'info_dict': { - 'id': '46712', + 'id': '10809', 'ext': 'mp4', - 'title': 'Yra kaip yra', - 'upload_date': '20150107', - 'description': 'md5:d82a5e36b775b7048617f263a0e3475e', - 'age_limit': 7, - 'duration': 3019, - 'thumbnail': r're:^https?://.*\.jpg$' + 'title': "Put'ka: Trys Klausimai", + 'upload_date': '20161216', + 'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.', + 'age_limit': 18, + 'duration': 117, + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1481904000, }, 'params': { 'skip_download': True, # HLS download @@ -30,20 +33,21 @@ class LnkGoIE(InfoExtractor): }, { 'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2', 'info_dict': { - 'id': '47289', + 'id': '10467', 'ext': 'mp4', 'title': 'Nėrdas: Kompiuterio Valymas', 'upload_date': '20150113', 'description': 'md5:7352d113a242a808676ff17e69db6a69', 'age_limit': 18, 'duration': 346, - 'thumbnail': r're:^https?://.*\.jpg$' + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1421164800, }, 'params': { 'skip_download': True, # HLS download }, }, { - 'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai', + 'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413', 'only_matching': True, }] _AGE_LIMITS = { @@ -51,66 +55,34 @@ class LnkGoIE(InfoExtractor): 'N-14': 14, 'S': 18, } + _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s' def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage( - url, display_id, 'Downloading player webpage') - - video_id = self._search_regex( - r'data-ep="([^"]+)"', webpage, 'video ID') - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - upload_date = unified_strdate(self._search_regex( - r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False)) - - thumbnail_w = int_or_none( - self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False)) - thumbnail_h = int_or_none( - self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False)) - thumbnail = { - 'url': self._og_search_thumbnail(webpage), - } - if thumbnail_w and thumbnail_h: - thumbnail.update({ - 'width': thumbnail_w, - 'height': thumbnail_h, - }) - - config = self._parse_json(self._search_regex( - r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id) - - if config.get('pGeo'): - self.report_warning( - 'This content might not be available in your country due to copyright reasons') + display_id, video_id = re.match(self._VALID_URL, url).groups() - formats = [{ - 'format_id': 'hls', - 'ext': 'mp4', - 'url': config['EpisodeVideoLink_HLS'], - }] - - m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink']) - if m: - formats.append({ - 'format_id': 'rtmp', - 'ext': 'flv', - 'url': m.group('url'), - 'play_path': m.group('play_path'), - 'page_url': url, - }) + video_info = self._download_json( + 'https://lnk.lt/api/main/video-page/%s/%s/false' % (display_id, video_id or '0'), + display_id)['videoConfig']['videoInfo'] + video_id = compat_str(video_info['id']) + title = video_info['title'] + prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4' + formats = self._extract_m3u8_formats( + self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''), + video_id, 'mp4', 'm3u8_native') self._sort_formats(formats) + poster_image = video_info.get('posterImage') + return { 'id': video_id, 'display_id': display_id, 'title': title, 'formats': formats, - 'thumbnails': [thumbnail], - 'duration': int_or_none(config.get('VideoTime')), - 'description': description, - 'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0), - 'upload_date': upload_date, + 'thumbnail': 'https://lnk.lt/all-images/' + poster_image if poster_image else None, + 'duration': int_or_none(video_info.get('duration')), + 'description': clean_html(video_info.get('htmlDescription')), + 'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0), + 'timestamp': parse_iso8601(video_info.get('airDate')), + 'view_count': int_or_none(video_info.get('viewsCount')), } diff --git a/youtube_dl/extractor/macgamestore.py b/youtube_dl/extractor/macgamestore.py deleted file mode 100644 index 43db9929c..000000000 --- a/youtube_dl/extractor/macgamestore.py +++ /dev/null @@ -1,42 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ExtractorError - - -class MacGameStoreIE(InfoExtractor): - IE_NAME = 'macgamestore' - IE_DESC = 'MacGameStore trailers' - _VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)' - - _TEST = { - 'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450', - 'md5': '8649b8ea684b6666b4c5be736ecddc61', - 'info_dict': { - 'id': '2450', - 'ext': 'm4v', - 'title': 'Crow', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, 'Downloading trailer page') - - if '>Missing Media<' in webpage: - raise ExtractorError( - 'Trailer %s does not exist' % video_id, expected=True) - - video_title = self._html_search_regex( - r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title') - - video_url = self._html_search_regex( - r'(?s)<div\s+id="video-player".*?href="([^"]+)"\s*>', - webpage, 'video URL') - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title - } diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index 6b0e64b7f..50234798b 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -20,10 +20,10 @@ class MailRuIE(InfoExtractor): IE_DESC = 'Видео@Mail.Ru' _VALID_URL = r'''(?x) https?:// - (?:(?:www|m)\.)?my\.mail\.ru/ + (?:(?:www|m)\.)?my\.mail\.ru/+ (?: video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)| - (?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html| + (?:(?P<idv2prefix>(?:[^/]+/+){2})video/(?P<idv2suffix>[^/]+/\d+))\.html| (?:video/embed|\+/video/meta)/(?P<metaid>\d+) ) ''' @@ -85,6 +85,14 @@ class MailRuIE(InfoExtractor): { 'url': 'http://my.mail.ru/+/video/meta/7949340477499637815', 'only_matching': True, + }, + { + 'url': 'https://my.mail.ru//list/sinyutin10/video/_myvideo/4.html', + 'only_matching': True, + }, + { + 'url': 'https://my.mail.ru//list//sinyutin10/video/_myvideo/4.html', + 'only_matching': True, } ] @@ -237,7 +245,7 @@ class MailRuMusicSearchBaseIE(InfoExtractor): class MailRuMusicIE(MailRuMusicSearchBaseIE): IE_NAME = 'mailru:music' IE_DESC = 'Музыка@Mail.Ru' - _VALID_URL = r'https?://my\.mail\.ru/music/songs/[^/?#&]+-(?P<id>[\da-f]+)' + _VALID_URL = r'https?://my\.mail\.ru/+music/+songs/+[^/?#&]+-(?P<id>[\da-f]+)' _TESTS = [{ 'url': 'https://my.mail.ru/music/songs/%D0%BC8%D0%BB8%D1%82%D1%85-l-a-h-luciferian-aesthetics-of-herrschaft-single-2017-4e31f7125d0dfaef505d947642366893', 'md5': '0f8c22ef8c5d665b13ac709e63025610', @@ -273,7 +281,7 @@ class MailRuMusicIE(MailRuMusicSearchBaseIE): class MailRuMusicSearchIE(MailRuMusicSearchBaseIE): IE_NAME = 'mailru:music:search' IE_DESC = 'Музыка@Mail.Ru' - _VALID_URL = r'https?://my\.mail\.ru/music/search/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://my\.mail\.ru/+music/+search/+(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://my.mail.ru/music/search/black%20shadow', 'info_dict': { diff --git a/youtube_dl/extractor/makertv.py b/youtube_dl/extractor/makertv.py deleted file mode 100644 index 8eda69cfc..000000000 --- a/youtube_dl/extractor/makertv.py +++ /dev/null @@ -1,32 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class MakerTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer\.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})' - _TEST = { - 'url': 'http://www.maker.tv/video/Fh3QgymL9gsc', - 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e', - 'info_dict': { - 'id': 'Fh3QgymL9gsc', - 'ext': 'mp4', - 'title': 'Maze Runner: The Scorch Trials Official Movie Review', - 'description': 'md5:11ff3362d7ef1d679fdb649f6413975a', - 'upload_date': '20150918', - 'timestamp': 1442549540, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id') - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'jwplatform:%s' % jwplatform_id, - 'ie_key': 'JWPlatform', - } diff --git a/youtube_dl/extractor/mangomolo.py b/youtube_dl/extractor/mangomolo.py index 482175a34..acee370e9 100644 --- a/youtube_dl/extractor/mangomolo.py +++ b/youtube_dl/extractor/mangomolo.py @@ -10,18 +10,21 @@ from ..utils import int_or_none class MangomoloBaseIE(InfoExtractor): + _BASE_REGEX = r'https?://(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)' + def _get_real_id(self, page_id): return page_id def _real_extract(self, url): page_id = self._get_real_id(self._match_id(url)) - webpage = self._download_webpage(url, page_id) + webpage = self._download_webpage( + 'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id) hidden_inputs = self._hidden_inputs(webpage) m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native' format_url = self._html_search_regex( [ - r'file\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', + r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', r'<a[^>]+href="(rtsp://[^"]+)"' ], webpage, 'format url') formats = self._extract_wowza_formats( @@ -39,14 +42,16 @@ class MangomoloBaseIE(InfoExtractor): class MangomoloVideoIE(MangomoloBaseIE): - IE_NAME = 'mangomolo:video' - _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)' + _TYPE = 'video' + IE_NAME = 'mangomolo:' + _TYPE + _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'video\?.*?\bid=(?P<id>\d+)' _IS_LIVE = False class MangomoloLiveIE(MangomoloBaseIE): - IE_NAME = 'mangomolo:live' - _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' + _TYPE = 'live' + IE_NAME = 'mangomolo:' + _TYPE + _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'(live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' _IS_LIVE = True def _get_real_id(self, page_id): diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index df3748798..933df1495 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -6,7 +6,6 @@ import re from .theplatform import ThePlatformBaseIE from ..compat import ( compat_parse_qs, - compat_str, compat_urllib_parse_urlparse, ) from ..utils import ( @@ -27,7 +26,7 @@ class MediasetIE(ThePlatformBaseIE): (?:video|on-demand)/(?:[^/]+/)+[^/]+_| player/index\.html\?.*?\bprogramGuid= ) - )(?P<id>[0-9A-Z]{16}) + )(?P<id>[0-9A-Z]{16,}) ''' _TESTS = [{ # full episode @@ -62,7 +61,6 @@ class MediasetIE(ThePlatformBaseIE): 'uploader': 'Canale 5', 'uploader_id': 'C5', }, - 'expected_warnings': ['HTTP Error 403: Forbidden'], }, { # clip 'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680', @@ -78,6 +76,18 @@ class MediasetIE(ThePlatformBaseIE): }, { 'url': 'mediaset:FAFU000000665924', 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295', + 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02', + 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01', + 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135', + 'only_matching': True, }] @staticmethod @@ -103,12 +113,17 @@ class MediasetIE(ThePlatformBaseIE): continue urlh = ie._request_webpage( embed_url, video_id, note='Following embed URL redirect') - embed_url = compat_str(urlh.geturl()) + embed_url = urlh.geturl() program_guid = _program_guid(_qs(embed_url)) if program_guid: entries.append(embed_url) return entries + def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None): + for video in smil.findall(self._xpath_ns('.//video', namespace)): + video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src']) + return super(MediasetIE, self)._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url) + def _real_extract(self, url): guid = self._match_id(url) tp_path = 'PR1GhC/media/guid/2702976343/' + guid @@ -118,14 +133,15 @@ class MediasetIE(ThePlatformBaseIE): subtitles = {} first_e = None for asset_type in ('SD', 'HD'): - for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'): + # TODO: fixup ISM+none manifest URLs + for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'): try: tp_formats, tp_subtitles = self._extract_theplatform_smil( update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), { 'mbr': 'true', 'formats': f, 'assetTypes': asset_type, - }), guid, 'Downloading %s %s SMIL data' % (f, asset_type)) + }), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type)) except ExtractorError as e: if not first_e: first_e = e diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 694a264d6..d6eb15740 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -129,7 +129,7 @@ class MediasiteIE(InfoExtractor): query = mobj.group('query') webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() # XXX: might have also extracted UrlReferrer and QueryString from the html service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( diff --git a/youtube_dl/extractor/minhateca.py b/youtube_dl/extractor/minhateca.py deleted file mode 100644 index dccc54249..000000000 --- a/youtube_dl/extractor/minhateca.py +++ /dev/null @@ -1,70 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - parse_duration, - parse_filesize, - sanitized_Request, - urlencode_postdata, -) - - -class MinhatecaIE(InfoExtractor): - _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.' - _TEST = { - 'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)', - 'info_dict': { - 'id': '125848331', - 'ext': 'mp4', - 'title': 'youtube-dl test video', - 'thumbnail': r're:^https?://.*\.jpg$', - 'filesize_approx': 1530000, - 'duration': 9, - 'view_count': int, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - token = self._html_search_regex( - r'<input name="__RequestVerificationToken".*?value="([^"]+)"', - webpage, 'request token') - token_data = [ - ('fileId', video_id), - ('__RequestVerificationToken', token), - ] - req = sanitized_Request( - 'http://minhateca.com.br/action/License/Download', - data=urlencode_postdata(token_data)) - req.add_header('Content-Type', 'application/x-www-form-urlencoded') - data = self._download_json( - req, video_id, note='Downloading metadata') - - video_url = data['redirectUrl'] - title_str = self._html_search_regex( - r'<h1.*?>(.*?)</h1>', webpage, 'title') - title, _, ext = title_str.rpartition('.') - filesize_approx = parse_filesize(self._html_search_regex( - r'<p class="fileSize">(.*?)</p>', - webpage, 'file size approximation', fatal=False)) - duration = parse_duration(self._html_search_regex( - r'(?s)<p class="fileLeng[ht][th]">.*?class="bold">(.*?)<', - webpage, 'duration', fatal=False)) - view_count = int_or_none(self._html_search_regex( - r'<p class="downloadsCounter">([0-9]+)</p>', - webpage, 'view count', fatal=False)) - - return { - 'id': video_id, - 'url': video_url, - 'title': title, - 'ext': ext, - 'filesize_approx': filesize_approx, - 'duration': duration, - 'view_count': view_count, - 'thumbnail': self._og_search_thumbnail(webpage), - } diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 1aea78d11..e1506a745 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -65,30 +65,6 @@ class TechTVMITIE(InfoExtractor): } -class MITIE(TechTVMITIE): - IE_NAME = 'video.mit.edu' - _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)' - - _TEST = { - 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', - 'md5': '7db01d5ccc1895fc5010e9c9e13648da', - 'info_dict': { - 'id': '21783', - 'ext': 'mp4', - 'title': 'The Government is Profiling You', - 'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd', - }, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_title = mobj.group('title') - webpage = self._download_webpage(url, page_title) - embed_url = self._search_regex( - r'<iframe .*?src="(.+?)"', webpage, 'embed url') - return self.url_result(embed_url) - - class OCWMITIE(InfoExtractor): IE_NAME = 'ocw.mit.edu' _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)' diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 40f214a87..ad9da9612 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -4,8 +4,8 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( int_or_none, + parse_iso8601, smuggle_url, - parse_duration, ) @@ -18,16 +18,18 @@ class MiTeleIE(InfoExtractor): 'info_dict': { 'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg', 'ext': 'mp4', - 'title': 'Tor, la web invisible', - 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', + 'title': 'Diario de La redacción Programa 144', + 'description': 'md5:07c35a7b11abb05876a6a79185b58d27', 'series': 'Diario de', - 'season': 'La redacción', + 'season': 'Season 14', 'season_number': 14, - 'season_id': 'diario_de_t14_11981', - 'episode': 'Programa 144', + 'episode': 'Tor, la web invisible', 'episode_number': 3, 'thumbnail': r're:(?i)^https?://.*\.jpg$', 'duration': 2913, + 'age_limit': 16, + 'timestamp': 1471209401, + 'upload_date': '20160814', }, 'add_ie': ['Ooyala'], }, { @@ -39,13 +41,15 @@ class MiTeleIE(InfoExtractor): 'title': 'Cuarto Milenio Temporada 6 Programa 226', 'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f', 'series': 'Cuarto Milenio', - 'season': 'Temporada 6', + 'season': 'Season 6', 'season_number': 6, - 'season_id': 'cuarto_milenio_t06_12715', - 'episode': 'Programa 226', + 'episode': 'Episode 24', 'episode_number': 24, 'thumbnail': r're:(?i)^https?://.*\.jpg$', 'duration': 7313, + 'age_limit': 12, + 'timestamp': 1471209021, + 'upload_date': '20160814', }, 'params': { 'skip_download': True, @@ -54,67 +58,36 @@ class MiTeleIE(InfoExtractor): }, { 'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player', 'only_matching': True, + }, { + 'url': 'https://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144-40_1006364575251/player/', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) - - paths = self._download_json( - 'https://www.mitele.es/amd/agp/web/metadata/general_configuration', - video_id, 'Downloading paths JSON') - - ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search'] - base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com') - full_path = ooyala_s.get('full_path', '/search/v1/full/providers/') - source = self._download_json( - '%s://%s%s%s/docs/%s' % ( - ooyala_s.get('protocol', 'https'), base_url, full_path, - ooyala_s.get('provider_id', '104951'), video_id), - video_id, 'Downloading data JSON', query={ - 'include_titles': 'Series,Season', - 'product_name': ooyala_s.get('product_name', 'test'), - 'format': 'full', - })['hits']['hits'][0]['_source'] - - embedCode = source['offers'][0]['embed_codes'][0] - titles = source['localizable_titles'][0] - - title = titles.get('title_medium') or titles['title_long'] - - description = titles.get('summary_long') or titles.get('summary_medium') - - def get(key1, key2): - value1 = source.get(key1) - if not value1 or not isinstance(value1, list): - return - if not isinstance(value1[0], dict): - return - return value1[0].get(key2) - - series = get('localizable_titles_series', 'title_medium') - - season = get('localizable_titles_season', 'title_medium') - season_number = int_or_none(source.get('season_number')) - season_id = source.get('season_id') - - episode = titles.get('title_sort_name') - episode_number = int_or_none(source.get('episode_number')) - - duration = parse_duration(get('videos', 'duration')) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + pre_player = self._parse_json(self._search_regex( + r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})', + webpage, 'Pre Player'), display_id)['prePlayer'] + title = pre_player['title'] + video = pre_player['video'] + video_id = video['dataMediaId'] + content = pre_player.get('content') or {} + info = content.get('info') or {} return { '_type': 'url_transparent', # for some reason only HLS is supported - 'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}), + 'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}), 'id': video_id, 'title': title, - 'description': description, - 'series': series, - 'season': season, - 'season_number': season_number, - 'season_id': season_id, - 'episode': episode, - 'episode_number': episode_number, - 'duration': duration, - 'thumbnail': get('images', 'url'), + 'description': info.get('synopsis'), + 'series': content.get('title'), + 'season_number': int_or_none(info.get('season_number')), + 'episode': content.get('subtitle'), + 'episode_number': int_or_none(info.get('episode_number')), + 'duration': int_or_none(info.get('duration')), + 'thumbnail': video.get('dataPoster'), + 'age_limit': int_or_none(info.get('rating')), + 'timestamp': parse_iso8601(pre_player.get('publishedTime')), } diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index bf5353ef9..9759560f1 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import functools import itertools import re @@ -11,28 +10,37 @@ from ..compat import ( compat_ord, compat_str, compat_urllib_parse_unquote, - compat_urlparse, compat_zip ) from ..utils import ( - clean_html, - ExtractorError, int_or_none, - OnDemandPagedList, - str_to_int, + parse_iso8601, + strip_or_none, try_get, - urljoin, ) -class MixcloudIE(InfoExtractor): +class MixcloudBaseIE(InfoExtractor): + def _call_api(self, object_type, object_fields, display_id, username, slug=None): + lookup_key = object_type + 'Lookup' + return self._download_json( + 'https://www.mixcloud.com/graphql', display_id, query={ + 'query': '''{ + %s(lookup: {username: "%s"%s}) { + %s + } +}''' % (lookup_key, username, ', slug: "%s"' % slug if slug else '', object_fields) + })['data'][lookup_key] + + +class MixcloudIE(MixcloudBaseIE): _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)' IE_NAME = 'mixcloud' _TESTS = [{ 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', 'info_dict': { - 'id': 'dholbach-cryptkeeper', + 'id': 'dholbach_cryptkeeper', 'ext': 'm4a', 'title': 'Cryptkeeper', 'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', @@ -40,11 +48,13 @@ class MixcloudIE(InfoExtractor): 'uploader_id': 'dholbach', 'thumbnail': r're:https?://.*\.jpg', 'view_count': int, + 'timestamp': 1321359578, + 'upload_date': '20111115', }, }, { 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', 'info_dict': { - 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat', + 'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat', 'ext': 'mp3', 'title': 'Caribou 7 inch Vinyl Mix & Chat', 'description': 'md5:2b8aec6adce69f9d41724647c65875e8', @@ -52,11 +62,14 @@ class MixcloudIE(InfoExtractor): 'uploader_id': 'gillespeterson', 'thumbnail': 're:https?://.*', 'view_count': int, + 'timestamp': 1422987057, + 'upload_date': '20150203', }, }, { 'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/', 'only_matching': True, }] + _DECRYPTION_KEY = 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD' @staticmethod def _decrypt_xor_cipher(key, ciphertext): @@ -66,176 +79,193 @@ class MixcloudIE(InfoExtractor): for ch, k in compat_zip(ciphertext, itertools.cycle(key))]) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - uploader = mobj.group(1) - cloudcast_name = mobj.group(2) - track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name))) + username, slug = re.match(self._VALID_URL, url).groups() + username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug) + track_id = '%s_%s' % (username, slug) + + cloudcast = self._call_api('cloudcast', '''audioLength + comments(first: 100) { + edges { + node { + comment + created + user { + displayName + username + } + } + } + totalCount + } + description + favorites { + totalCount + } + featuringArtistList + isExclusive + name + owner { + displayName + url + username + } + picture(width: 1024, height: 1024) { + url + } + plays + publishDate + reposts { + totalCount + } + streamInfo { + dashUrl + hlsUrl + url + } + tags { + tag { + name + } + }''', track_id, username, slug) - webpage = self._download_webpage(url, track_id) + title = cloudcast['name'] - # Legacy path - encrypted_play_info = self._search_regex( - r'm-play-info="([^"]+)"', webpage, 'play info', default=None) + stream_info = cloudcast['streamInfo'] + formats = [] - if encrypted_play_info is not None: - # Decode - encrypted_play_info = compat_b64decode(encrypted_play_info) - else: - # New path - full_info_json = self._parse_json(self._html_search_regex( - r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>', - webpage, 'play info'), 'play info') - for item in full_info_json: - item_data = try_get( - item, lambda x: x['cloudcast']['data']['cloudcastLookup'], - dict) - if try_get(item_data, lambda x: x['streamInfo']['url']): - info_json = item_data - break - else: - raise ExtractorError('Failed to extract matching stream info') - - message = self._html_search_regex( - r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)', - webpage, 'error message', default=None) - - js_url = self._search_regex( - r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)', - webpage, 'js url') - js = self._download_webpage(js_url, track_id, 'Downloading JS') - # Known plaintext attack - if encrypted_play_info: - kps = ['{"stream_url":'] - kpa_target = encrypted_play_info - else: - kps = ['https://', 'http://'] - kpa_target = compat_b64decode(info_json['streamInfo']['url']) - for kp in kps: - partial_key = self._decrypt_xor_cipher(kpa_target, kp) - for quote in ["'", '"']: - key = self._search_regex( - r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)), - js, 'encryption key', default=None) - if key is not None: - break + for url_key in ('url', 'hlsUrl', 'dashUrl'): + format_url = stream_info.get(url_key) + if not format_url: + continue + decrypted = self._decrypt_xor_cipher( + self._DECRYPTION_KEY, compat_b64decode(format_url)) + if url_key == 'hlsUrl': + formats.extend(self._extract_m3u8_formats( + decrypted, track_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif url_key == 'dashUrl': + formats.extend(self._extract_mpd_formats( + decrypted, track_id, mpd_id='dash', fatal=False)) else: + formats.append({ + 'format_id': 'http', + 'url': decrypted, + 'downloader_options': { + # Mixcloud starts throttling at >~5M + 'http_chunk_size': 5242880, + }, + }) + + if not formats and cloudcast.get('isExclusive'): + self.raise_login_required() + + self._sort_formats(formats) + + comments = [] + for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []): + node = edge.get('node') or {} + text = strip_or_none(node.get('comment')) + if not text: continue - break - else: - raise ExtractorError('Failed to extract encryption key') - - if encrypted_play_info is not None: - play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info') - if message and 'stream_url' not in play_info: - raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) - song_url = play_info['stream_url'] - formats = [{ - 'format_id': 'normal', - 'url': song_url - }] - - title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title') - thumbnail = self._proto_relative_url(self._html_search_regex( - r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False)) - uploader = self._html_search_regex( - r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False) - uploader_id = self._search_regex( - r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) - description = self._og_search_description(webpage) - view_count = str_to_int(self._search_regex( - [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', - r'/listeners/?">([0-9,.]+)</a>', - r'(?:m|data)-tooltip=["\']([\d,.]+) plays'], - webpage, 'play count', default=None)) + user = node.get('user') or {} + comments.append({ + 'author': user.get('displayName'), + 'author_id': user.get('username'), + 'text': text, + 'timestamp': parse_iso8601(node.get('created')), + }) - else: - title = info_json['name'] - thumbnail = urljoin( - 'https://thumbnailer.mixcloud.com/unsafe/600x600/', - try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str)) - uploader = try_get(info_json, lambda x: x['owner']['displayName']) - uploader_id = try_get(info_json, lambda x: x['owner']['username']) - description = try_get(info_json, lambda x: x['description']) - view_count = int_or_none(try_get(info_json, lambda x: x['plays'])) - - stream_info = info_json['streamInfo'] - formats = [] - - def decrypt_url(f_url): - for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'): - decrypted_url = self._decrypt_xor_cipher(k, f_url) - if re.search(r'^https?://[0-9A-Za-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): - return decrypted_url - - for url_key in ('url', 'hlsUrl', 'dashUrl'): - format_url = stream_info.get(url_key) - if not format_url: - continue - decrypted = decrypt_url(compat_b64decode(format_url)) - if not decrypted: - continue - if url_key == 'hlsUrl': - formats.extend(self._extract_m3u8_formats( - decrypted, track_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - elif url_key == 'dashUrl': - formats.extend(self._extract_mpd_formats( - decrypted, track_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': 'http', - 'url': decrypted, - 'downloader_options': { - # Mixcloud starts throttling at >~5M - 'http_chunk_size': 5242880, - }, - }) - self._sort_formats(formats) + tags = [] + for t in cloudcast.get('tags'): + tag = try_get(t, lambda x: x['tag']['name'], compat_str) + if not tag: + tags.append(tag) + + get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount'])) + + owner = cloudcast.get('owner') or {} return { 'id': track_id, 'title': title, 'formats': formats, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'view_count': view_count, + 'description': cloudcast.get('description'), + 'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], compat_str), + 'uploader': owner.get('displayName'), + 'timestamp': parse_iso8601(cloudcast.get('publishDate')), + 'uploader_id': owner.get('username'), + 'uploader_url': owner.get('url'), + 'duration': int_or_none(cloudcast.get('audioLength')), + 'view_count': int_or_none(cloudcast.get('plays')), + 'like_count': get_count('favorites'), + 'repost_count': get_count('reposts'), + 'comment_count': get_count('comments'), + 'comments': comments, + 'tags': tags, + 'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None, } -class MixcloudPlaylistBaseIE(InfoExtractor): - _PAGE_SIZE = 24 +class MixcloudPlaylistBaseIE(MixcloudBaseIE): + def _get_cloudcast(self, node): + return node - def _find_urls_in_page(self, page): - for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page): - yield self.url_result( - compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)), - MixcloudIE.ie_key()) + def _get_playlist_title(self, title, slug): + return title + + def _real_extract(self, url): + username, slug = re.match(self._VALID_URL, url).groups() + username = compat_urllib_parse_unquote(username) + if not slug: + slug = 'uploads' + else: + slug = compat_urllib_parse_unquote(slug) + playlist_id = '%s_%s' % (username, slug) - def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None): - real_page_number = real_page_number or current_page + 1 - return self._download_webpage( - 'https://www.mixcloud.com/%s/' % path, video_id, - note='Download %s (page %d)' % (page_name, current_page + 1), - errnote='Unable to download %s' % page_name, - query={'page': real_page_number, 'list': 'main', '_ajax': '1'}, - headers={'X-Requested-With': 'XMLHttpRequest'}) + is_playlist_type = self._ROOT_TYPE == 'playlist' + playlist_type = 'items' if is_playlist_type else slug + list_filter = '' - def _tracks_page_func(self, page, video_id, page_name, current_page): - resp = self._fetch_tracks_page(page, video_id, page_name, current_page) + has_next_page = True + entries = [] + while has_next_page: + playlist = self._call_api( + self._ROOT_TYPE, '''%s + %s + %s(first: 100%s) { + edges { + node { + %s + } + } + pageInfo { + endCursor + hasNextPage + } + }''' % (self._TITLE_KEY, self._DESCRIPTION_KEY, playlist_type, list_filter, self._NODE_TEMPLATE), + playlist_id, username, slug if is_playlist_type else None) + + items = playlist.get(playlist_type) or {} + for edge in items.get('edges', []): + cloudcast = self._get_cloudcast(edge.get('node') or {}) + cloudcast_url = cloudcast.get('url') + if not cloudcast_url: + continue + entries.append(self.url_result( + cloudcast_url, MixcloudIE.ie_key(), cloudcast.get('slug'))) - for item in self._find_urls_in_page(resp): - yield item + page_info = items['pageInfo'] + has_next_page = page_info['hasNextPage'] + list_filter = ', after: "%s"' % page_info['endCursor'] - def _get_user_description(self, page_content): - return self._html_search_regex( - r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>', - page_content, 'user description', fatal=False) + return self.playlist_result( + entries, playlist_id, + self._get_playlist_title(playlist[self._TITLE_KEY], slug), + playlist.get(self._DESCRIPTION_KEY)) class MixcloudUserIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$' + _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/(?P<type>uploads|favorites|listens|stream)?/?$' IE_NAME = 'mixcloud:user' _TESTS = [{ @@ -243,68 +273,58 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE): 'info_dict': { 'id': 'dholbach_uploads', 'title': 'Daniel Holbach (uploads)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 11, + 'playlist_mincount': 36, }, { 'url': 'http://www.mixcloud.com/dholbach/uploads/', 'info_dict': { 'id': 'dholbach_uploads', 'title': 'Daniel Holbach (uploads)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 11, + 'playlist_mincount': 36, }, { 'url': 'http://www.mixcloud.com/dholbach/favorites/', 'info_dict': { 'id': 'dholbach_favorites', 'title': 'Daniel Holbach (favorites)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', - }, - 'params': { - 'playlist_items': '1-100', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 100, + # 'params': { + # 'playlist_items': '1-100', + # }, + 'playlist_mincount': 396, }, { 'url': 'http://www.mixcloud.com/dholbach/listens/', 'info_dict': { 'id': 'dholbach_listens', 'title': 'Daniel Holbach (listens)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'params': { - 'playlist_items': '1-100', + # 'params': { + # 'playlist_items': '1-100', + # }, + 'playlist_mincount': 1623, + 'skip': 'Large list', + }, { + 'url': 'https://www.mixcloud.com/FirstEar/stream/', + 'info_dict': { + 'id': 'FirstEar_stream', + 'title': 'First Ear (stream)', + 'description': 'Curators of good music\r\n\r\nfirstearmusic.com', }, - 'playlist_mincount': 100, + 'playlist_mincount': 271, }] - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user') - list_type = mobj.group('type') - - # if only a profile URL was supplied, default to download all uploads - if list_type is None: - list_type = 'uploads' - - video_id = '%s_%s' % (user_id, list_type) + _TITLE_KEY = 'displayName' + _DESCRIPTION_KEY = 'biog' + _ROOT_TYPE = 'user' + _NODE_TEMPLATE = '''slug + url''' - profile = self._download_webpage( - 'https://www.mixcloud.com/%s/' % user_id, video_id, - note='Downloading user profile', - errnote='Unable to download user profile') - - username = self._og_search_title(profile) - description = self._get_user_description(profile) - - entries = OnDemandPagedList( - functools.partial( - self._tracks_page_func, - '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type), - self._PAGE_SIZE) - - return self.playlist_result( - entries, video_id, '%s (%s)' % (username, list_type), description) + def _get_playlist_title(self, title, slug): + return '%s (%s)' % (title, slug) class MixcloudPlaylistIE(MixcloudPlaylistBaseIE): @@ -312,87 +332,20 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE): IE_NAME = 'mixcloud:playlist' _TESTS = [{ - 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/', - 'info_dict': { - 'id': 'RedBullThre3style_tokyo-finalists-2015', - 'title': 'National Champions 2015', - 'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3', - }, - 'playlist_mincount': 16, - }, { 'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user') - playlist_id = mobj.group('playlist') - video_id = '%s_%s' % (user_id, playlist_id) - - webpage = self._download_webpage( - url, user_id, - note='Downloading playlist page', - errnote='Unable to download playlist page') - - title = self._html_search_regex( - r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)', - webpage, 'playlist title', - default=None) or self._og_search_title(webpage, fatal=False) - description = self._get_user_description(webpage) - - entries = OnDemandPagedList( - functools.partial( - self._tracks_page_func, - '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'), - self._PAGE_SIZE) - - return self.playlist_result(entries, video_id, title, description) - - -class MixcloudStreamIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$' - IE_NAME = 'mixcloud:stream' - - _TEST = { - 'url': 'https://www.mixcloud.com/FirstEar/stream/', 'info_dict': { - 'id': 'FirstEar', - 'title': 'First Ear', - 'description': 'Curators of good music\nfirstearmusic.com', + 'id': 'maxvibes_jazzcat-on-ness-radio', + 'title': 'Ness Radio sessions', }, - 'playlist_mincount': 192, - } - - def _real_extract(self, url): - user_id = self._match_id(url) - - webpage = self._download_webpage(url, user_id) - - entries = [] - prev_page_url = None - - def _handle_page(page): - entries.extend(self._find_urls_in_page(page)) - return self._search_regex( - r'm-next-page-url="([^"]+)"', page, - 'next page URL', default=None) - - next_page_url = _handle_page(webpage) - - for idx in itertools.count(0): - if not next_page_url or prev_page_url == next_page_url: - break - - prev_page_url = next_page_url - current_page = int(self._search_regex( - r'\?page=(\d+)', next_page_url, 'next page number')) - - next_page_url = _handle_page(self._fetch_tracks_page( - '%s/stream' % user_id, user_id, 'stream', idx, - real_page_number=current_page)) - - username = self._og_search_title(webpage) - description = self._get_user_description(webpage) - - return self.playlist_result(entries, user_id, username, description) + 'playlist_mincount': 59, + }] + _TITLE_KEY = 'name' + _DESCRIPTION_KEY = 'description' + _ROOT_TYPE = 'playlist' + _NODE_TEMPLATE = '''cloudcast { + slug + url + }''' + + def _get_cloudcast(self, node): + return node.get('cloudcast') or {} diff --git a/youtube_dl/extractor/msn.py b/youtube_dl/extractor/msn.py index 0460cf4d5..e59b0b7b0 100644 --- a/youtube_dl/extractor/msn.py +++ b/youtube_dl/extractor/msn.py @@ -14,21 +14,28 @@ from ..utils import ( class MSNIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)' + _VALID_URL = r'https?://(?:(?:www|preview)\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)' _TESTS = [{ - 'url': 'http://www.msn.com/en-ae/foodanddrink/joinourtable/criminal-minds-shemar-moore-shares-a-touching-goodbye-message/vp-BBqQYNE', - 'md5': '8442f66c116cbab1ff7098f986983458', + 'url': 'https://www.msn.com/en-in/money/video/7-ways-to-get-rid-of-chest-congestion/vi-BBPxU6d', + 'md5': '087548191d273c5c55d05028f8d2cbcd', 'info_dict': { - 'id': 'BBqQYNE', - 'display_id': 'criminal-minds-shemar-moore-shares-a-touching-goodbye-message', + 'id': 'BBPxU6d', + 'display_id': '7-ways-to-get-rid-of-chest-congestion', 'ext': 'mp4', - 'title': 'Criminal Minds - Shemar Moore Shares A Touching Goodbye Message', - 'description': 'md5:e8e89b897b222eb33a6b5067a8f1bc25', - 'duration': 104, - 'uploader': 'CBS Entertainment', - 'uploader_id': 'IT0X5aoJ6bJgYerJXSDCgFmYPB1__54v', + 'title': 'Seven ways to get rid of chest congestion', + 'description': '7 Ways to Get Rid of Chest Congestion', + 'duration': 88, + 'uploader': 'Health', + 'uploader_id': 'BBPrMqa', }, }, { + # Article, multiple Dailymotion Embeds + 'url': 'https://www.msn.com/en-in/money/sports/hottest-football-wags-greatest-footballers-turned-managers-and-more/ar-BBpc7Nl', + 'info_dict': { + 'id': 'BBpc7Nl', + }, + 'playlist_mincount': 4, + }, { 'url': 'http://www.msn.com/en-ae/news/offbeat/meet-the-nine-year-old-self-made-millionaire/ar-BBt6ZKf', 'only_matching': True, }, { @@ -41,75 +48,124 @@ class MSNIE(InfoExtractor): }, { 'url': 'http://www.msn.com/en-ae/entertainment/bollywood/watch-how-salman-khan-reacted-when-asked-if-he-would-apologize-for-his-‘raped-woman’-comment/vi-AAhvzW6', 'only_matching': True, + }, { + # Vidible(AOL) Embed + 'url': 'https://www.msn.com/en-us/money/other/jupiter-is-about-to-come-so-close-you-can-see-its-moons-with-binoculars/vi-AACqsHR', + 'only_matching': True, + }, { + # Dailymotion Embed + 'url': 'https://www.msn.com/es-ve/entretenimiento/watch/winston-salem-paire-refait-des-siennes-en-perdant-sa-raquette-au-service/vp-AAG704L', + 'only_matching': True, + }, { + # YouTube Embed + 'url': 'https://www.msn.com/en-in/money/news/meet-vikram-%E2%80%94-chandrayaan-2s-lander/vi-AAGUr0v', + 'only_matching': True, + }, { + # NBCSports Embed + 'url': 'https://www.msn.com/en-us/money/football_nfl/week-13-preview-redskins-vs-panthers/vi-BBXsCDb', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id, display_id = mobj.group('id', 'display_id') + display_id, page_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) - video = self._parse_json( - self._search_regex( - r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1', - webpage, 'video data', default='{}', group='data'), - display_id, transform_source=unescapeHTML) + entries = [] + for _, metadata in re.findall(r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1', webpage): + video = self._parse_json(unescapeHTML(metadata), display_id) + + provider_id = video.get('providerId') + player_name = video.get('playerName') + if player_name and provider_id: + entry = None + if player_name == 'AOL': + if provider_id.startswith('http'): + provider_id = self._search_regex( + r'https?://delivery\.vidible\.tv/video/redirect/([0-9a-f]{24})', + provider_id, 'vidible id') + entry = self.url_result( + 'aol-video:' + provider_id, 'Aol', provider_id) + elif player_name == 'Dailymotion': + entry = self.url_result( + 'https://www.dailymotion.com/video/' + provider_id, + 'Dailymotion', provider_id) + elif player_name == 'YouTube': + entry = self.url_result( + provider_id, 'Youtube', provider_id) + elif player_name == 'NBCSports': + entry = self.url_result( + 'http://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/' + provider_id, + 'NBCSportsVPlayer', provider_id) + if entry: + entries.append(entry) + continue + + video_id = video['uuid'] + title = video['title'] + + formats = [] + for file_ in video.get('videoFiles', []): + format_url = file_.get('url') + if not format_url: + continue + if 'format=m3u8-aapl' in format_url: + # m3u8_native should not be used here until + # https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed + formats.extend(self._extract_m3u8_formats( + format_url, display_id, 'mp4', + m3u8_id='hls', fatal=False)) + elif 'format=mpd-time-csf' in format_url: + formats.extend(self._extract_mpd_formats( + format_url, display_id, 'dash', fatal=False)) + elif '.ism' in format_url: + if format_url.endswith('.ism'): + format_url += '/manifest' + formats.extend(self._extract_ism_formats( + format_url, display_id, 'mss', fatal=False)) + else: + format_id = file_.get('formatCode') + formats.append({ + 'url': format_url, + 'ext': 'mp4', + 'format_id': format_id, + 'width': int_or_none(file_.get('width')), + 'height': int_or_none(file_.get('height')), + 'vbr': int_or_none(self._search_regex(r'_(\d+)\.mp4', format_url, 'vbr', default=None)), + 'preference': 1 if format_id == '1001' else None, + }) + self._sort_formats(formats) + + subtitles = {} + for file_ in video.get('files', []): + format_url = file_.get('url') + format_code = file_.get('formatCode') + if not format_url or not format_code: + continue + if compat_str(format_code) == '3100': + subtitles.setdefault(file_.get('culture', 'en'), []).append({ + 'ext': determine_ext(format_url, 'ttml'), + 'url': format_url, + }) - if not video: + entries.append({ + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': video.get('description'), + 'thumbnail': video.get('headlineImage', {}).get('url'), + 'duration': int_or_none(video.get('durationSecs')), + 'uploader': video.get('sourceFriendly'), + 'uploader_id': video.get('providerId'), + 'creator': video.get('creator'), + 'subtitles': subtitles, + 'formats': formats, + }) + + if not entries: error = unescapeHTML(self._search_regex( r'data-error=(["\'])(?P<error>.+?)\1', webpage, 'error', group='error')) raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) - title = video['title'] - - formats = [] - for file_ in video.get('videoFiles', []): - format_url = file_.get('url') - if not format_url: - continue - if 'm3u8' in format_url: - # m3u8_native should not be used here until - # https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed - m3u8_formats = self._extract_m3u8_formats( - format_url, display_id, 'mp4', - m3u8_id='hls', fatal=False) - formats.extend(m3u8_formats) - elif determine_ext(format_url) == 'ism': - formats.extend(self._extract_ism_formats( - format_url + '/Manifest', display_id, 'mss', fatal=False)) - else: - formats.append({ - 'url': format_url, - 'ext': 'mp4', - 'format_id': 'http', - 'width': int_or_none(file_.get('width')), - 'height': int_or_none(file_.get('height')), - }) - self._sort_formats(formats) - - subtitles = {} - for file_ in video.get('files', []): - format_url = file_.get('url') - format_code = file_.get('formatCode') - if not format_url or not format_code: - continue - if compat_str(format_code) == '3100': - subtitles.setdefault(file_.get('culture', 'en'), []).append({ - 'ext': determine_ext(format_url, 'ttml'), - 'url': format_url, - }) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': video.get('description'), - 'thumbnail': video.get('headlineImage', {}).get('url'), - 'duration': int_or_none(video.get('durationSecs')), - 'uploader': video.get('sourceFriendly'), - 'uploader_id': video.get('providerId'), - 'creator': video.get('creator'), - 'subtitles': subtitles, - 'formats': formats, - } + return self.playlist_result(entries, page_id) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 7a3b57abd..fedd5f46b 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -349,33 +350,29 @@ class MTVIE(MTVServicesInfoExtractor): }] -class MTV81IE(InfoExtractor): - IE_NAME = 'mtv81' - _VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P<id>[^/?#.]+)' +class MTVJapanIE(MTVServicesInfoExtractor): + IE_NAME = 'mtvjapan' + _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)' _TEST = { - 'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/', - 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b', + 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade', 'info_dict': { - 'id': '5e14040d-18a4-47c4-a582-43ff602de88e', + 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5', 'ext': 'mp4', - 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer', - 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.', - 'timestamp': 1468846800, - 'upload_date': '20160718', + 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition', + }, + 'params': { + 'skip_download': True, }, } + _GEO_COUNTRIES = ['JP'] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' - def _extract_mgid(self, webpage): - return self._search_regex( - r'getTheVideo\((["\'])(?P<id>mgid:.+?)\1', webpage, - 'mgid', group='id') - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - mgid = self._extract_mgid(webpage) - return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid) + def _get_feed_query(self, uri): + return { + 'arcEp': 'mtvjapan.com', + 'mgid': uri, + } class MTVVideoIE(MTVServicesInfoExtractor): @@ -425,14 +422,14 @@ class MTVVideoIE(MTVServicesInfoExtractor): class MTVDEIE(MTVServicesInfoExtractor): IE_NAME = 'mtv.de' - _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$' + _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)' _TESTS = [{ - 'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum', + 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum', 'info_dict': { - 'id': 'music_video-a50bc5f0b3aa4b3190aa', - 'ext': 'flv', - 'title': 'MusicVideo_cro-traum', - 'description': 'Cro - Traum', + 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5', + 'ext': 'mp4', + 'title': 'Traum', + 'description': 'Traum', }, 'params': { # rtmp download @@ -441,11 +438,12 @@ class MTVDEIE(MTVServicesInfoExtractor): 'skip': 'Blocked at Travis CI', }, { # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) - 'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen', + 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1', 'info_dict': { - 'id': 'local_playlist-f5ae778b9832cc837189', - 'ext': 'flv', - 'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1', + 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285', + 'ext': 'mp4', + 'title': 'Teen Mom 2', + 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7', }, 'params': { # rtmp download @@ -453,7 +451,7 @@ class MTVDEIE(MTVServicesInfoExtractor): }, 'skip': 'Blocked at Travis CI', }, { - 'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3', + 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3', 'info_dict': { 'id': 'local_playlist-4e760566473c4c8c5344', 'ext': 'mp4', @@ -466,25 +464,11 @@ class MTVDEIE(MTVServicesInfoExtractor): }, 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.', }] + _GEO_COUNTRIES = ['DE'] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - playlist = self._parse_json( - self._search_regex( - r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'), - video_id) - - def _mrss_url(item): - return item['mrss'] + item.get('mrssvars', '') - - # news pages contain single video in playlist with different id - if len(playlist) == 1: - return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id) - - for item in playlist: - item_id = item.get('id') - if item_id and compat_str(item_id) == video_id: - return self._get_videos_info_from_url(_mrss_url(item), video_id) + def _get_feed_query(self, uri): + return { + 'arcEp': 'mtv.de', + 'mgid': uri, + } diff --git a/youtube_dl/extractor/musicplayon.py b/youtube_dl/extractor/musicplayon.py deleted file mode 100644 index 1854d59a5..000000000 --- a/youtube_dl/extractor/musicplayon.py +++ /dev/null @@ -1,66 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_urlparse -from ..utils import ( - int_or_none, - js_to_json, - mimetype2ext, -) - - -class MusicPlayOnIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=\d+&play)=(?P<id>\d+)' - - _TESTS = [{ - 'url': 'http://en.musicplayon.com/play?v=433377', - 'md5': '00cdcdea1726abdf500d1e7fd6dd59bb', - 'info_dict': { - 'id': '433377', - 'ext': 'mp4', - 'title': 'Rick Ross - Interview On Chelsea Lately (2014)', - 'description': 'Rick Ross Interview On Chelsea Lately', - 'duration': 342, - 'uploader': 'ultrafish', - }, - }, { - 'url': 'http://en.musicplayon.com/play?pl=102&play=442629', - 'only_matching': True, - }] - - _URL_TEMPLATE = 'http://en.musicplayon.com/play?v=%s' - - def _real_extract(self, url): - video_id = self._match_id(url) - url = self._URL_TEMPLATE % video_id - - page = self._download_webpage(url, video_id) - - title = self._og_search_title(page) - description = self._og_search_description(page) - thumbnail = self._og_search_thumbnail(page) - duration = self._html_search_meta('video:duration', page, 'duration', fatal=False) - view_count = self._og_search_property('count', page, fatal=False) - uploader = self._html_search_regex( - r'<div>by <a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False) - - sources = self._parse_json( - self._search_regex(r'setup\[\'_sources\'\]\s*=\s*([^;]+);', page, 'video sources'), - video_id, transform_source=js_to_json) - formats = [{ - 'url': compat_urlparse.urljoin(url, source['src']), - 'ext': mimetype2ext(source.get('type')), - 'format_note': source.get('data-res'), - } for source in sources] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'duration': int_or_none(duration), - 'view_count': int_or_none(view_count), - 'formats': formats, - } diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py index 2afe535b5..db7ebc94c 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -1,73 +1,56 @@ +# coding: utf-8 from __future__ import unicode_literals -import os.path + +import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, -) +from ..compat import compat_str from ..utils import ( - ExtractorError, + int_or_none, + parse_duration, + xpath_text, ) class MySpassIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?myspass\.de/.*' + _VALID_URL = r'https?://(?:www\.)?myspass\.de/([^/]+/)*(?P<id>\d+)' _TEST = { 'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/', 'md5': '0b49f4844a068f8b33f4b7c88405862b', 'info_dict': { 'id': '11741', 'ext': 'mp4', - 'description': 'Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?', - 'title': 'Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2', + 'description': 'Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?', + 'title': '17.02.2013 - Die Highlights, Teil 2', }, } def _real_extract(self, url): - META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' + video_id = self._match_id(url) - # video id is the last path element of the URL - # usually there is a trailing slash, so also try the second but last - url_path = compat_urllib_parse_urlparse(url).path - url_parent_path, video_id = os.path.split(url_path) - if not video_id: - _, video_id = os.path.split(url_parent_path) - - # get metadata - metadata_url = META_DATA_URL_TEMPLATE % video_id metadata = self._download_xml( - metadata_url, video_id, transform_source=lambda s: s.strip()) - - # extract values from metadata - url_flv_el = metadata.find('url_flv') - if url_flv_el is None: - raise ExtractorError('Unable to extract download url') - video_url = url_flv_el.text - title_el = metadata.find('title') - if title_el is None: - raise ExtractorError('Unable to extract title') - title = title_el.text - format_id_el = metadata.find('format_id') - if format_id_el is None: - format = 'mp4' - else: - format = format_id_el.text - description_el = metadata.find('description') - if description_el is not None: - description = description_el.text - else: - description = None - imagePreview_el = metadata.find('imagePreview') - if imagePreview_el is not None: - thumbnail = imagePreview_el.text - else: - thumbnail = None + 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=' + video_id, + video_id) + + title = xpath_text(metadata, 'title', fatal=True) + video_url = xpath_text(metadata, 'url_flv', 'download url', True) + video_id_int = int(video_id) + for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups(): + group_int = int(group) + if group_int > video_id_int: + video_url = video_url.replace( + group, compat_str(group_int // video_id_int)) return { 'id': video_id, 'url': video_url, 'title': title, - 'format': format, - 'thumbnail': thumbnail, - 'description': description, + 'thumbnail': xpath_text(metadata, 'imagePreview'), + 'description': xpath_text(metadata, 'description'), + 'duration': parse_duration(xpath_text(metadata, 'duration')), + 'series': xpath_text(metadata, 'format'), + 'season_number': int_or_none(xpath_text(metadata, 'season')), + 'season_id': xpath_text(metadata, 'season_id'), + 'episode': title, + 'episode_number': int_or_none(xpath_text(metadata, 'episode')), } diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index bb3d94413..61fc59126 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -1,68 +1,33 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( + clean_html, + dict_get, ExtractorError, int_or_none, + parse_duration, + try_get, update_url_query, ) -class NaverIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P<id>\d+)' +class NaverBaseIE(InfoExtractor): + _CAPTION_EXT_RE = r'\.(?:ttml|vtt)' - _TESTS = [{ - 'url': 'http://tv.naver.com/v/81652', - 'info_dict': { - 'id': '81652', - 'ext': 'mp4', - 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', - 'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', - 'upload_date': '20130903', - }, - }, { - 'url': 'http://tv.naver.com/v/395837', - 'md5': '638ed4c12012c458fefcddfd01f173cd', - 'info_dict': { - 'id': '395837', - 'ext': 'mp4', - 'title': '9년이 지나도 아픈 기억, 전효성의 아버지', - 'description': 'md5:5bf200dcbf4b66eb1b350d1eb9c753f7', - 'upload_date': '20150519', - }, - 'skip': 'Georestricted', - }, { - 'url': 'http://tvcast.naver.com/v/81652', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - vid = self._search_regex( - r'videoId["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, - 'video id', fatal=None, group='value') - in_key = self._search_regex( - r'inKey["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, - 'key', default=None, group='value') - - if not vid or not in_key: - error = self._html_search_regex( - r'(?s)<div class="(?:nation_error|nation_box|error_box)">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>', - webpage, 'error', default=None) - if error: - raise ExtractorError(error, expected=True) - raise ExtractorError('couldn\'t extract vid and key') + def _extract_video_info(self, video_id, vid, key): video_data = self._download_json( 'http://play.rmcnmv.naver.com/vod/play/v2.0/' + vid, video_id, query={ - 'key': in_key, + 'key': key, }) meta = video_data['meta'] title = meta['subject'] formats = [] + get_list = lambda x: try_get(video_data, lambda y: y[x + 's']['list'], list) or [] def extract_formats(streams, stream_type, query={}): for stream in streams: @@ -73,7 +38,7 @@ class NaverIE(InfoExtractor): encoding_option = stream.get('encodingOption', {}) bitrate = stream.get('bitrate', {}) formats.append({ - 'format_id': '%s_%s' % (stream.get('type') or stream_type, encoding_option.get('id') or encoding_option.get('name')), + 'format_id': '%s_%s' % (stream.get('type') or stream_type, dict_get(encoding_option, ('name', 'id'))), 'url': stream_url, 'width': int_or_none(encoding_option.get('width')), 'height': int_or_none(encoding_option.get('height')), @@ -83,7 +48,7 @@ class NaverIE(InfoExtractor): 'protocol': 'm3u8_native' if stream_type == 'HLS' else None, }) - extract_formats(video_data.get('videos', {}).get('list', []), 'H264') + extract_formats(get_list('video'), 'H264') for stream_set in video_data.get('streams', []): query = {} for param in stream_set.get('keys', []): @@ -101,28 +66,101 @@ class NaverIE(InfoExtractor): 'mp4', 'm3u8_native', m3u8_id=stream_type, fatal=False)) self._sort_formats(formats) + replace_ext = lambda x, y: re.sub(self._CAPTION_EXT_RE, '.' + y, x) + + def get_subs(caption_url): + if re.search(self._CAPTION_EXT_RE, caption_url): + return [{ + 'url': replace_ext(caption_url, 'ttml'), + }, { + 'url': replace_ext(caption_url, 'vtt'), + }] + else: + return [{'url': caption_url}] + + automatic_captions = {} subtitles = {} - for caption in video_data.get('captions', {}).get('list', []): + for caption in get_list('caption'): caption_url = caption.get('source') if not caption_url: continue - subtitles.setdefault(caption.get('language') or caption.get('locale'), []).append({ - 'url': caption_url, - }) + sub_dict = automatic_captions if caption.get('type') == 'auto' else subtitles + sub_dict.setdefault(dict_get(caption, ('locale', 'language')), []).extend(get_subs(caption_url)) - upload_date = self._search_regex( - r'<span[^>]+class="date".*?(\d{4}\.\d{2}\.\d{2})', - webpage, 'upload date', fatal=False) - if upload_date: - upload_date = upload_date.replace('.', '') + user = meta.get('user', {}) return { 'id': video_id, 'title': title, 'formats': formats, 'subtitles': subtitles, - 'description': self._og_search_description(webpage), - 'thumbnail': meta.get('cover', {}).get('source') or self._og_search_thumbnail(webpage), + 'automatic_captions': automatic_captions, + 'thumbnail': try_get(meta, lambda x: x['cover']['source']), 'view_count': int_or_none(meta.get('count')), - 'upload_date': upload_date, + 'uploader_id': user.get('id'), + 'uploader': user.get('name'), + 'uploader_url': user.get('url'), } + + +class NaverIE(NaverBaseIE): + _VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/(?:v|embed)/(?P<id>\d+)' + _GEO_BYPASS = False + _TESTS = [{ + 'url': 'http://tv.naver.com/v/81652', + 'info_dict': { + 'id': '81652', + 'ext': 'mp4', + 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', + 'description': '메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', + 'timestamp': 1378200754, + 'upload_date': '20130903', + 'uploader': '메가스터디, 합격불변의 법칙', + 'uploader_id': 'megastudy', + }, + }, { + 'url': 'http://tv.naver.com/v/395837', + 'md5': '8a38e35354d26a17f73f4e90094febd3', + 'info_dict': { + 'id': '395837', + 'ext': 'mp4', + 'title': '9년이 지나도 아픈 기억, 전효성의 아버지', + 'description': 'md5:eb6aca9d457b922e43860a2a2b1984d3', + 'timestamp': 1432030253, + 'upload_date': '20150519', + 'uploader': '4가지쇼 시즌2', + 'uploader_id': 'wrappinguser29', + }, + 'skip': 'Georestricted', + }, { + 'url': 'http://tvcast.naver.com/v/81652', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + content = self._download_json( + 'https://tv.naver.com/api/json/v/' + video_id, + video_id, headers=self.geo_verification_headers()) + player_info_json = content.get('playerInfoJson') or {} + current_clip = player_info_json.get('currentClip') or {} + + vid = current_clip.get('videoId') + in_key = current_clip.get('inKey') + + if not vid or not in_key: + player_auth = try_get(player_info_json, lambda x: x['playerOption']['auth']) + if player_auth == 'notCountry': + self.raise_geo_restricted(countries=['KR']) + elif player_auth == 'notLogin': + self.raise_login_required() + raise ExtractorError('couldn\'t extract vid and key') + info = self._extract_video_info(video_id, vid, in_key) + info.update({ + 'description': clean_html(current_clip.get('description')), + 'timestamp': int_or_none(current_clip.get('firstExposureTime'), 1000), + 'duration': parse_duration(current_clip.get('displayPlayTime')), + 'like_count': int_or_none(current_clip.get('recommendPoint')), + 'age_limit': 19 if current_clip.get('adult') else None, + }) + return info diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 3282f84ee..6f3cb3003 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -9,10 +9,13 @@ from .theplatform import ThePlatformIE from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( + int_or_none, + js_to_json, + parse_duration, smuggle_url, try_get, + unified_timestamp, update_url_query, - int_or_none, ) @@ -84,28 +87,61 @@ class NBCIE(AdobePassIE): def _real_extract(self, url): permalink, video_id = re.match(self._VALID_URL, url).groups() permalink = 'http' + compat_urllib_parse_unquote(permalink) - response = self._download_json( - 'https://api.nbc.com/v3/videos', video_id, query={ - 'filter[permalink]': permalink, - 'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating', - 'fields[shows]': 'shortTitle', - 'include': 'show.shortTitle', - }) - video_data = response['data'][0]['attributes'] + video_data = self._download_json( + 'https://friendship.nbc.co/v2/graphql', video_id, query={ + 'query': '''query bonanzaPage( + $app: NBCUBrands! = nbc + $name: String! + $oneApp: Boolean + $platform: SupportedPlatforms! = web + $type: EntityPageType! = VIDEO + $userId: String! +) { + bonanzaPage( + app: $app + name: $name + oneApp: $oneApp + platform: $platform + type: $type + userId: $userId + ) { + metadata { + ... on VideoPageData { + description + episodeNumber + keywords + locked + mpxAccountId + mpxGuid + rating + resourceId + seasonNumber + secondaryTitle + seriesShortTitle + } + } + } +}''', + 'variables': json.dumps({ + 'name': permalink, + 'oneApp': True, + 'userId': '0', + }), + })['data']['bonanzaPage']['metadata'] query = { 'mbr': 'true', 'manifest': 'm3u', } - video_id = video_data['guid'] - title = video_data['title'] - if video_data.get('entitlement') == 'auth': + video_id = video_data['mpxGuid'] + title = video_data['secondaryTitle'] + if video_data.get('locked'): resource = self._get_mvpd_resource( - 'nbcentertainment', title, video_id, - video_data.get('vChipRating')) + video_data.get('resourceId') or 'nbcentertainment', + title, video_id, video_data.get('rating')) query['auth'] = self._extract_mvpd_auth( url, video_id, 'nbcentertainment', resource) theplatform_url = smuggle_url(update_url_query( - 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id, + 'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id), query), {'force_smil_url': True}) return { '_type': 'url_transparent', @@ -117,7 +153,7 @@ class NBCIE(AdobePassIE): 'season_number': int_or_none(video_data.get('seasonNumber')), 'episode_number': int_or_none(video_data.get('episodeNumber')), 'episode': title, - 'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']), + 'series': video_data.get('seriesShortTitle'), 'ie_key': 'ThePlatform', } @@ -272,13 +308,12 @@ class NBCNewsIE(ThePlatformIE): _TESTS = [ { 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880', - 'md5': 'af1adfa51312291a017720403826bb64', + 'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf', 'info_dict': { 'id': '269389891880', 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', - 'uploader': 'NBCU-NEWS', 'timestamp': 1401363060, 'upload_date': '20140529', }, @@ -296,28 +331,26 @@ class NBCNewsIE(ThePlatformIE): }, { 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844', - 'md5': '73135a2e0ef819107bbb55a5a9b2a802', + 'md5': '8eb831eca25bfa7d25ddd83e85946548', 'info_dict': { 'id': '394064451844', 'ext': 'mp4', 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)', 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5', 'timestamp': 1423104900, - 'uploader': 'NBCU-NEWS', 'upload_date': '20150205', }, }, { 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456', - 'md5': 'a49e173825e5fcd15c13fc297fced39d', + 'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0', 'info_dict': { - 'id': '529953347624', + 'id': 'n431456', 'ext': 'mp4', - 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up', - 'description': 'md5:c8be487b2d80ff0594c005add88d8351', + 'title': "Volkswagen U.S. Chief: We 'Totally Screwed Up'", + 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301', 'upload_date': '20150922', 'timestamp': 1442917800, - 'uploader': 'NBCU-NEWS', }, }, { @@ -330,7 +363,6 @@ class NBCNewsIE(ThePlatformIE): 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1', 'upload_date': '20160420', 'timestamp': 1461152093, - 'uploader': 'NBCU-NEWS', }, }, { @@ -344,7 +376,6 @@ class NBCNewsIE(ThePlatformIE): 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1406937606, 'upload_date': '20140802', - 'uploader': 'NBCU-NEWS', }, }, { @@ -360,20 +391,61 @@ class NBCNewsIE(ThePlatformIE): def _real_extract(self, url): video_id = self._match_id(url) - if not video_id.isdigit(): - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) - data = self._parse_json(self._search_regex( - r'window\.__data\s*=\s*({.+});', webpage, - 'bootstrap json'), video_id) - video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id'] + data = self._parse_json(self._search_regex( + r'window\.__data\s*=\s*({.+});', webpage, + 'bootstrap json'), video_id, js_to_json) + video_data = try_get(data, lambda x: x['video']['current'], dict) + if not video_data: + video_data = data['article']['content'][0]['primaryMedia']['video'] + title = video_data['headline']['primary'] + + formats = [] + for va in video_data.get('videoAssets', []): + public_url = va.get('publicUrl') + if not public_url: + continue + if '://link.theplatform.com/' in public_url: + public_url = update_url_query(public_url, {'format': 'redirect'}) + format_id = va.get('format') + if format_id == 'M3U': + formats.extend(self._extract_m3u8_formats( + public_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=format_id, fatal=False)) + continue + tbr = int_or_none(va.get('bitrate'), 1000) + if tbr: + format_id += '-%d' % tbr + formats.append({ + 'format_id': format_id, + 'url': public_url, + 'width': int_or_none(va.get('width')), + 'height': int_or_none(va.get('height')), + 'tbr': tbr, + 'ext': 'mp4', + }) + self._sort_formats(formats) + + subtitles = {} + closed_captioning = video_data.get('closedCaptioning') + if closed_captioning: + for cc_url in closed_captioning.values(): + if not cc_url: + continue + subtitles.setdefault('en', []).append({ + 'url': cc_url, + }) return { - '_type': 'url_transparent', 'id': video_id, - # http://feed.theplatform.com/f/2E2eJC/nbcnews also works - 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}), - 'ie_key': 'ThePlatformFeed', + 'title': title, + 'description': try_get(video_data, lambda x: x['description']['primary']), + 'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']), + 'duration': parse_duration(video_data.get('duration')), + 'timestamp': unified_timestamp(video_data.get('datePublished')), + 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index aec2ea133..2447c812e 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -7,8 +7,11 @@ from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, + merge_dicts, parse_iso8601, qualities, + try_get, + urljoin, ) @@ -85,21 +88,25 @@ class NDRIE(NDRBaseIE): def _extract_embed(self, webpage, display_id): embed_url = self._html_search_meta( - 'embedURL', webpage, 'embed URL', fatal=True) + 'embedURL', webpage, 'embed URL', + default=None) or self._search_regex( + r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'embed URL', group='url') description = self._search_regex( r'<p[^>]+itemprop="description">([^<]+)</p>', webpage, 'description', default=None) or self._og_search_description(webpage) timestamp = parse_iso8601( self._search_regex( r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', - webpage, 'upload date', fatal=False)) - return { + webpage, 'upload date', default=None)) + info = self._search_json_ld(webpage, display_id, default={}) + return merge_dicts({ '_type': 'url_transparent', 'url': embed_url, 'display_id': display_id, 'description': description, 'timestamp': timestamp, - } + }, info) class NJoyIE(NDRBaseIE): @@ -220,11 +227,17 @@ class NDREmbedBaseIE(InfoExtractor): upload_date = ppjson.get('config', {}).get('publicationDate') duration = int_or_none(config.get('duration')) - thumbnails = [{ - 'id': thumbnail.get('quality') or thumbnail_id, - 'url': thumbnail['src'], - 'preference': quality_key(thumbnail.get('quality')), - } for thumbnail_id, thumbnail in config.get('poster', {}).items() if thumbnail.get('src')] + thumbnails = [] + poster = try_get(config, lambda x: x['poster'], dict) or {} + for thumbnail_id, thumbnail in poster.items(): + thumbnail_url = urljoin(url, thumbnail.get('src')) + if not thumbnail_url: + continue + thumbnails.append({ + 'id': thumbnail.get('quality') or thumbnail_id, + 'url': thumbnail_url, + 'preference': quality_key(thumbnail.get('quality')), + }) return { 'id': video_id, diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py index 82d526c22..586c1b7eb 100644 --- a/youtube_dl/extractor/nexx.py +++ b/youtube_dl/extractor/nexx.py @@ -108,7 +108,7 @@ class NexxIE(InfoExtractor): @staticmethod def _extract_domain_id(webpage): mobj = re.search( - r'<script\b[^>]+\bsrc=["\'](?:https?:)?//require\.nexx(?:\.cloud|cdn\.com)/(?P<id>\d+)', + r'<script\b[^>]+\bsrc=["\'](?:https?:)?//(?:require|arc)\.nexx(?:\.cloud|cdn\.com)/(?:sdk/)?(?P<id>\d+)', webpage) return mobj.group('id') if mobj else None @@ -123,7 +123,7 @@ class NexxIE(InfoExtractor): domain_id = NexxIE._extract_domain_id(webpage) if domain_id: for video_id in re.findall( - r'(?is)onPLAYReady.+?_play\.init\s*\(.+?\s*,\s*["\']?(\d+)', + r'(?is)onPLAYReady.+?_play\.(?:init|(?:control\.)?addPlayer)\s*\(.+?\s*,\s*["\']?(\d+)', webpage): entries.append( 'https://api.nexx.cloud/v3/%s/videos/byid/%s' @@ -295,13 +295,23 @@ class NexxIE(InfoExtractor): video = None + def find_video(result): + if isinstance(result, dict): + return result + elif isinstance(result, list): + vid = int(video_id) + for v in result: + if try_get(v, lambda x: x['general']['ID'], int) == vid: + return v + return None + response = self._download_json( 'https://arc.nexx.cloud/api/video/%s.json' % video_id, video_id, fatal=False) if response and isinstance(response, dict): result = response.get('result') - if result and isinstance(result, dict): - video = result + if result: + video = find_video(result) # not all videos work via arc, e.g. nexx:741:1269984 if not video: @@ -348,7 +358,7 @@ class NexxIE(InfoExtractor): request_token = hashlib.md5( ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest() - video = self._call_api( + result = self._call_api( domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={ 'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description', 'addInteractionOptions': '1', @@ -363,6 +373,7 @@ class NexxIE(InfoExtractor): 'X-Request-CID': cid, 'X-Request-Token': request_token, }) + video = find_video(result) general = video['general'] title = general['title'] @@ -399,8 +410,8 @@ class NexxIE(InfoExtractor): class NexxEmbedIE(InfoExtractor): - _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?P<id>[^/?#&]+)' - _TEST = { + _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:video/)?(?P<id>[^/?#&]+)' + _TESTS = [{ 'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1', 'md5': '16746bfc28c42049492385c989b26c4a', 'info_dict': { @@ -409,7 +420,6 @@ class NexxEmbedIE(InfoExtractor): 'title': 'Nervenkitzel Achterbahn', 'alt_title': 'Karussellbauer in Deutschland', 'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc', - 'release_year': 2005, 'creator': 'SPIEGEL TV', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 2761, @@ -420,7 +430,10 @@ class NexxEmbedIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, - } + }, { + 'url': 'https://embed.nexx.cloud/11888/video/DSRTO7UVOX06S7', + 'only_matching': True, + }] @staticmethod def _extract_urls(webpage): diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 6a2c6cb7b..de6a707c4 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class NhkVodIE(InfoExtractor): - _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)' + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)' # Content available only for a limited period of time. Visit # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples. _TESTS = [{ @@ -30,8 +30,11 @@ class NhkVodIE(InfoExtractor): }, { 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/', 'only_matching': True, + }, { + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/', + 'only_matching': True, }] - _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json' + _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json' def _real_extract(self, url): lang, m_type, episode_id = re.match(self._VALID_URL, url).groups() @@ -82,15 +85,9 @@ class NhkVodIE(InfoExtractor): audio = episode['audio'] audio_path = audio['audio'] info['formats'] = self._extract_m3u8_formats( - 'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path, - episode_id, 'm4a', m3u8_id='hls', fatal=False) - for proto in ('rtmpt', 'rtmp'): - info['formats'].append({ - 'ext': 'flv', - 'format_id': proto, - 'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path), - 'vcodec': 'none', - }) + 'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path, + episode_id, 'm4a', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False) for f in info['formats']: f['language'] = lang return info diff --git a/youtube_dl/extractor/nintendo.py b/youtube_dl/extractor/nintendo.py index 4b4e66b05..ff8f70ba6 100644 --- a/youtube_dl/extractor/nintendo.py +++ b/youtube_dl/extractor/nintendo.py @@ -5,13 +5,12 @@ import re from .common import InfoExtractor from .ooyala import OoyalaIE -from ..utils import unescapeHTML class NintendoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nintendo\.com/games/detail/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?nintendo\.com/(?:games/detail|nintendo-direct)/(?P<id>[^/?#&]+)' _TESTS = [{ - 'url': 'http://www.nintendo.com/games/detail/yEiAzhU2eQI1KZ7wOHhngFoAHc1FpHwj', + 'url': 'https://www.nintendo.com/games/detail/duck-hunt-wii-u/', 'info_dict': { 'id': 'MzMmticjp0VPzO3CCj4rmFOuohEuEWoW', 'ext': 'flv', @@ -28,7 +27,19 @@ class NintendoIE(InfoExtractor): 'id': 'tokyo-mirage-sessions-fe-wii-u', 'title': 'Tokyo Mirage Sessions ♯FE', }, - 'playlist_count': 3, + 'playlist_count': 4, + }, { + 'url': 'https://www.nintendo.com/nintendo-direct/09-04-2019/', + 'info_dict': { + 'id': 'J2bXdmaTE6fe3dWJTPcc7m23FNbc_A1V', + 'ext': 'mp4', + 'title': 'Switch_ROS_ND0904-H264.mov', + 'duration': 2324.758, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Ooyala'], }] def _real_extract(self, url): @@ -39,8 +50,11 @@ class NintendoIE(InfoExtractor): entries = [ OoyalaIE._build_url_result(m.group('code')) for m in re.finditer( - r'class=(["\'])embed-video\1[^>]+data-video-code=(["\'])(?P<code>(?:(?!\2).)+)\2', - webpage)] + r'data-(?:video-id|directVideoId)=(["\'])(?P<code>(?:(?!\1).)+)\1', webpage)] + + title = self._html_search_regex( + r'(?s)<(?:span|div)[^>]+class="(?:title|wrapper)"[^>]*>.*?<h1>(.+?)</h1>', + webpage, 'title', fatal=False) return self.playlist_result( - entries, page_id, unescapeHTML(self._og_search_title(webpage, fatal=False))) + entries, page_id, title) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 901f44b54..2850af5db 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -18,7 +18,7 @@ class NovaEmbedIE(InfoExtractor): _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)' _TEST = { 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', - 'md5': 'b3834f6de5401baabf31ed57456463f7', + 'md5': 'ee009bafcc794541570edd44b71cbea3', 'info_dict': { 'id': '8o0n0r', 'ext': 'mp4', @@ -44,11 +44,17 @@ class NovaEmbedIE(InfoExtractor): formats = [] for format_id, format_list in bitrates.items(): if not isinstance(format_list, list): - continue + format_list = [format_list] for format_url in format_list: format_url = url_or_none(format_url) if not format_url: continue + if format_id == 'hls': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + continue f = { 'url': format_url, } @@ -91,7 +97,7 @@ class NovaIE(InfoExtractor): _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)' _TESTS = [{ 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', - 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', + 'md5': '249baab7d0104e186e78b0899c7d5f28', 'info_dict': { 'id': '1757139', 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', @@ -113,7 +119,8 @@ class NovaIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'gone', }, { # media.cms.nova.cz embed 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', @@ -128,6 +135,7 @@ class NovaIE(InfoExtractor): 'skip_download': True, }, 'add_ie': [NovaEmbedIE.ie_key()], + 'skip': 'CHYBA 404: STRÁNKA NENALEZENA', }, { 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'only_matching': True, @@ -152,14 +160,29 @@ class NovaIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + description = clean_html(self._og_search_description(webpage, default=None)) + if site == 'novaplus': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) + elif site == 'fanda': + upload_date = unified_strdate(self._search_regex( + r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) + else: + upload_date = None + # novaplus embed_id = self._search_regex( r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', webpage, 'embed url', default=None) if embed_id: - return self.url_result( - 'https://media.cms.nova.cz/embed/%s' % embed_id, - ie=NovaEmbedIE.ie_key(), video_id=embed_id) + return { + '_type': 'url_transparent', + 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id, + 'ie_key': NovaEmbedIE.ie_key(), + 'id': embed_id, + 'description': description, + 'upload_date': upload_date + } video_id = self._search_regex( [r"(?:media|video_id)\s*:\s*'(\d+)'", @@ -233,18 +256,8 @@ class NovaIE(InfoExtractor): self._sort_formats(formats) title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) - description = clean_html(self._og_search_description(webpage, default=None)) thumbnail = config.get('poster') - if site == 'novaplus': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) - elif site == 'fanda': - upload_date = unified_strdate(self._search_regex( - r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) - else: - upload_date = None - return { 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/npr.py b/youtube_dl/extractor/npr.py index a5e8baa7e..53acc6e57 100644 --- a/youtube_dl/extractor/npr.py +++ b/youtube_dl/extractor/npr.py @@ -4,6 +4,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, qualities, + url_or_none, ) @@ -48,6 +49,10 @@ class NprIE(InfoExtractor): }, }], 'expected_warnings': ['Failed to download m3u8 information'], + }, { + # multimedia, no formats, stream + 'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert', + 'only_matching': True, }] def _real_extract(self, url): @@ -95,6 +100,17 @@ class NprIE(InfoExtractor): 'format_id': format_id, 'quality': quality(format_id), }) + for stream_id, stream_entry in media.get('stream', {}).items(): + if not isinstance(stream_entry, dict): + continue + if stream_id != 'hlsUrl': + continue + stream_url = url_or_none(stream_entry.get('$text')) + if not stream_url: + continue + formats.extend(self._extract_m3u8_formats( + stream_url, stream_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) self._sort_formats(formats) entries.append({ diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 60933f069..94115534b 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -12,6 +12,7 @@ from ..utils import ( ExtractorError, int_or_none, JSON_LD_RE, + js_to_json, NO_DEFAULT, parse_age_limit, parse_duration, @@ -105,6 +106,7 @@ class NRKBaseIE(InfoExtractor): MESSAGES = { 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', 'ProgramRightsHasExpired': 'Programmet har gått ut', + 'NoProgramRights': 'Ikke tilgjengelig', 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', } message_type = data.get('messageType', '') @@ -255,6 +257,17 @@ class NRKTVIE(NRKBaseIE): ''' % _EPISODE_RE _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') _TESTS = [{ + 'url': 'https://tv.nrk.no/program/MDDP12000117', + 'md5': '8270824df46ec629b66aeaa5796b36fb', + 'info_dict': { + 'id': 'MDDP12000117AA', + 'ext': 'mp4', + 'title': 'Alarm Trolltunga', + 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce', + 'duration': 2223, + 'age_limit': 6, + }, + }, { 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', 'md5': '9a167e54d04671eb6317a37b7bc8a280', 'info_dict': { @@ -266,6 +279,7 @@ class NRKTVIE(NRKBaseIE): 'series': '20 spørsmål', 'episode': '23.05.2014', }, + 'skip': 'NoProgramRights', }, { 'url': 'https://tv.nrk.no/program/mdfp15000514', 'info_dict': { @@ -370,7 +384,24 @@ class NRKTVIE(NRKBaseIE): class NRKTVEpisodeIE(InfoExtractor): _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)' - _TEST = { + _TESTS = [{ + 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2', + 'info_dict': { + 'id': 'MUHH36005220BA', + 'ext': 'mp4', + 'title': 'Kro, krig og kjærlighet 2:6', + 'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350', + 'duration': 1563, + 'series': 'Hellums kro', + 'season_number': 1, + 'episode_number': 2, + 'episode': '2:6', + 'age_limit': 6, + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', 'info_dict': { 'id': 'MSUI14000816AA', @@ -386,7 +417,8 @@ class NRKTVEpisodeIE(InfoExtractor): 'params': { 'skip_download': True, }, - } + 'skip': 'ProgramRightsHasExpired', + }] def _real_extract(self, url): display_id = self._match_id(url) @@ -409,7 +441,7 @@ class NRKTVSerieBaseIE(InfoExtractor): (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;', r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'), webpage, 'config', default='{}' if not fatal else NO_DEFAULT), - display_id, fatal=False) + display_id, fatal=False, transform_source=js_to_json) if not config: return return try_get( @@ -479,6 +511,14 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)' _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)' _TESTS = [{ + 'url': 'https://tv.nrk.no/serie/blank', + 'info_dict': { + 'id': 'blank', + 'title': 'Blank', + 'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e', + }, + 'playlist_mincount': 30, + }, { # new layout, seasons 'url': 'https://tv.nrk.no/serie/backstage', 'info_dict': { @@ -648,7 +688,7 @@ class NRKSkoleIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099', - 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6', + 'md5': '18c12c3d071953c3bf8d54ef6b2587b7', 'info_dict': { 'id': '6021', 'ext': 'mp4', diff --git a/youtube_dl/extractor/nrl.py b/youtube_dl/extractor/nrl.py index 798b91e04..22a2df8d3 100644 --- a/youtube_dl/extractor/nrl.py +++ b/youtube_dl/extractor/nrl.py @@ -23,8 +23,8 @@ class NRLTVIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - q_data = self._parse_json(self._search_regex( - r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id) + q_data = self._parse_json(self._html_search_regex( + r'(?s)q-data="({.+?})"', webpage, 'player data'), display_id) ooyala_id = q_data['videoId'] return self.url_result( 'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title')) diff --git a/youtube_dl/extractor/ntvru.py b/youtube_dl/extractor/ntvru.py index 4f9cedb84..c47d1dfa4 100644 --- a/youtube_dl/extractor/ntvru.py +++ b/youtube_dl/extractor/ntvru.py @@ -3,9 +3,10 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - clean_html, - xpath_text, int_or_none, + strip_or_none, + unescapeHTML, + xpath_text, ) @@ -47,10 +48,10 @@ class NTVRuIE(InfoExtractor): 'duration': 1496, }, }, { - 'url': 'http://www.ntv.ru/kino/Koma_film', - 'md5': 'f825770930937aa7e5aca0dc0d29319a', + 'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/', + 'md5': 'e9c7cde24d9d3eaed545911a04e6d4f4', 'info_dict': { - 'id': '1007609', + 'id': '1126480', 'ext': 'mp4', 'title': 'Остросюжетный фильм «Кома»', 'description': 'Остросюжетный фильм «Кома»', @@ -68,6 +69,10 @@ class NTVRuIE(InfoExtractor): 'thumbnail': r're:^http://.*\.jpg', 'duration': 2590, }, + }, { + # Schemeless file URL + 'url': 'https://www.ntv.ru/video/1797442', + 'only_matching': True, }] _VIDEO_ID_REGEXES = [ @@ -96,37 +101,31 @@ class NTVRuIE(InfoExtractor): 'http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML') - title = clean_html(xpath_text(player, './data/title', 'title', fatal=True)) - description = clean_html(xpath_text(player, './data/description', 'description')) + title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True))) video = player.find('./data/video') - video_id = xpath_text(video, './id', 'video id') - thumbnail = xpath_text(video, './splash', 'thumbnail') - duration = int_or_none(xpath_text(video, './totaltime', 'duration')) - view_count = int_or_none(xpath_text(video, './views', 'view count')) - - token = self._download_webpage( - 'http://stat.ntv.ru/services/access/token', - video_id, 'Downloading access token') formats = [] for format_id in ['', 'hi', 'webm']: - file_ = video.find('./%sfile' % format_id) - if file_ is None: + file_ = xpath_text(video, './%sfile' % format_id) + if not file_: continue - size = video.find('./%ssize' % format_id) + if file_.startswith('//'): + file_ = self._proto_relative_url(file_) + elif not file_.startswith('http'): + file_ = 'http://media.ntv.ru/vod/' + file_ formats.append({ - 'url': 'http://media2.ntv.ru/vod/%s&tok=%s' % (file_.text, token), - 'filesize': int_or_none(size.text if size is not None else None), + 'url': file_, + 'filesize': int_or_none(xpath_text(video, './%ssize' % format_id)), }) self._sort_formats(formats) return { - 'id': video_id, + 'id': xpath_text(video, './id'), 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'view_count': view_count, + 'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))), + 'thumbnail': xpath_text(video, './splash'), + 'duration': int_or_none(xpath_text(video, './totaltime')), + 'view_count': int_or_none(xpath_text(video, './views')), 'formats': formats, } diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 2bb77ab24..fc78ca56c 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor): 'width': int_or_none(video.get('width')), 'height': int_or_none(video.get('height')), 'filesize': get_file_size(video.get('file_size') or video.get('fileSize')), - 'tbr': int_or_none(video.get('bitrate'), 1000), + 'tbr': int_or_none(video.get('bitrate'), 1000) or None, 'ext': ext, }) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id')) thumbnails = [] for image in video_data.get('images', []): diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 114b93c07..7ed9fac55 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_etree_fromstring, @@ -121,6 +123,13 @@ class OdnoklassnikiIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) + if mobj: + return mobj.group('url') + def _real_extract(self, url): start_time = int_or_none(compat_parse_qs( compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0]) diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py index 58da1bc27..e55b2ac89 100644 --- a/youtube_dl/extractor/onet.py +++ b/youtube_dl/extractor/onet.py @@ -20,6 +20,8 @@ from ..utils import ( class OnetBaseIE(InfoExtractor): + _URL_BASE_RE = r'https?://(?:(?:www\.)?onet\.tv|onet100\.vod\.pl)/[a-z]/' + def _search_mvp_id(self, webpage): return self._search_regex( r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id') @@ -45,7 +47,7 @@ class OnetBaseIE(InfoExtractor): video = response['result'].get('0') formats = [] - for _, formats_dict in video['formats'].items(): + for format_type, formats_dict in video['formats'].items(): if not isinstance(formats_dict, dict): continue for format_id, format_list in formats_dict.items(): @@ -56,21 +58,31 @@ class OnetBaseIE(InfoExtractor): if not video_url: continue ext = determine_ext(video_url) - if format_id == 'ism': + if format_id.startswith('ism'): formats.extend(self._extract_ism_formats( video_url, video_id, 'mss', fatal=False)) elif ext == 'mpd': formats.extend(self._extract_mpd_formats( video_url, video_id, mpd_id='dash', fatal=False)) + elif format_id.startswith('hls'): + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) else: - formats.append({ + http_f = { 'url': video_url, 'format_id': format_id, - 'height': int_or_none(f.get('vertical_resolution')), - 'width': int_or_none(f.get('horizontal_resolution')), 'abr': float_or_none(f.get('audio_bitrate')), - 'vbr': float_or_none(f.get('video_bitrate')), - }) + } + if format_type == 'audio': + http_f['vcodec'] = 'none' + else: + http_f.update({ + 'height': int_or_none(f.get('vertical_resolution')), + 'width': int_or_none(f.get('horizontal_resolution')), + 'vbr': float_or_none(f.get('video_bitrate')), + }) + formats.append(http_f) self._sort_formats(formats) meta = video.get('meta', {}) @@ -105,12 +117,12 @@ class OnetMVPIE(OnetBaseIE): class OnetIE(OnetBaseIE): - _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)' + _VALID_URL = OnetBaseIE._URL_BASE_RE + r'[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)' IE_NAME = 'onet.tv' - _TEST = { + _TESTS = [{ 'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc', - 'md5': 'e3ffbf47590032ac3f27249204173d50', + 'md5': '436102770fb095c75b8bb0392d3da9ff', 'info_dict': { 'id': 'qbpyqc', 'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd', @@ -120,7 +132,10 @@ class OnetIE(OnetBaseIE): 'upload_date': '20160705', 'timestamp': 1467721580, }, - } + }, { + 'url': 'https://onet100.vod.pl/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -140,18 +155,21 @@ class OnetIE(OnetBaseIE): class OnetChannelIE(OnetBaseIE): - _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P<id>[a-z]+)(?:[?#]|$)' + _VALID_URL = OnetBaseIE._URL_BASE_RE + r'(?P<id>[a-z]+)(?:[?#]|$)' IE_NAME = 'onet.tv:channel' - _TEST = { + _TESTS = [{ 'url': 'http://onet.tv/k/openerfestival', 'info_dict': { 'id': 'openerfestival', - 'title': 'Open\'er Festival Live', - 'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.', + 'title': "Open'er Festival", + 'description': "Tak było na Open'er Festival 2016! Oglądaj nasze reportaże i wywiady z artystami.", }, - 'playlist_mincount': 46, - } + 'playlist_mincount': 35, + }, { + 'url': 'https://onet100.vod.pl/k/openerfestival', + 'only_matching': True, + }] def _real_extract(self, url): channel_id = self._match_id(url) @@ -173,7 +191,7 @@ class OnetChannelIE(OnetBaseIE): 'Downloading channel %s - add --no-playlist to just download video %s' % ( channel_id, video_name)) matches = re.findall( - r'<a[^>]+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)', + r'<a[^>]+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE, webpage) entries = [ self.url_result(video_link, OnetIE.ie_key()) diff --git a/youtube_dl/extractor/onionstudios.py b/youtube_dl/extractor/onionstudios.py index c6e3d5640..cf5c39e66 100644 --- a/youtube_dl/extractor/onionstudios.py +++ b/youtube_dl/extractor/onionstudios.py @@ -4,12 +4,8 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - determine_ext, - int_or_none, - float_or_none, - mimetype2ext, -) +from ..compat import compat_str +from ..utils import js_to_json class OnionStudiosIE(InfoExtractor): @@ -17,14 +13,16 @@ class OnionStudiosIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937', - 'md5': '719d1f8c32094b8c33902c17bcae5e34', + 'md5': '5a118d466d62b5cd03647cf2c593977f', 'info_dict': { - 'id': '2937', + 'id': '3459881', 'ext': 'mp4', 'title': 'Hannibal charges forward, stops for a cocktail', + 'description': 'md5:545299bda6abf87e5ec666548c6a9448', 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'The A.V. Club', - 'uploader_id': 'the-av-club', + 'uploader': 'a.v. club', + 'upload_date': '20150619', + 'timestamp': 1434728546, }, }, { 'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true', @@ -44,38 +42,12 @@ class OnionStudiosIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json( - 'http://www.onionstudios.com/video/%s.json' % video_id, video_id) - - title = video_data['title'] - - formats = [] - for source in video_data.get('sources', []): - source_url = source.get('url') - if not source_url: - continue - ext = mimetype2ext(source.get('content_type')) or determine_ext(source_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - source_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - else: - tbr = int_or_none(source.get('bitrate')) - formats.append({ - 'format_id': ext + ('-%d' % tbr if tbr else ''), - 'url': source_url, - 'width': int_or_none(source.get('width')), - 'tbr': tbr, - 'ext': ext, - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': video_data.get('poster_url'), - 'uploader': video_data.get('channel_name'), - 'uploader_id': video_data.get('channel_slug'), - 'duration': float_or_none(video_data.get('duration', 1000)), - 'tags': video_data.get('tags'), - 'formats': formats, - } + webpage = self._download_webpage( + 'http://onionstudios.com/embed/dc94dc2899fe644c0e7241fa04c1b732.js', + video_id) + mcp_id = compat_str(self._parse_json(self._search_regex( + r'window\.mcpMapping\s*=\s*({.+?});', webpage, + 'MCP Mapping'), video_id, js_to_json)[video_id]['mcp_id']) + return self.url_result( + 'http://kinja.com/ajax/inset/iframe?id=mcp-' + mcp_id, + 'KinjaEmbed', mcp_id) diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 995b24d1b..eb957b8fe 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -1,12 +1,12 @@ from __future__ import unicode_literals +import base64 import re from .common import InfoExtractor from ..compat import ( compat_b64decode, compat_str, - compat_urllib_parse_urlencode, ) from ..utils import ( determine_ext, @@ -21,9 +21,9 @@ from ..utils import ( class OoyalaBaseIE(InfoExtractor): _PLAYER_BASE = 'http://player.ooyala.com/' _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/' - _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?' + _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s' - def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None, embed_token=None): + def _extract(self, content_tree_url, video_id, domain=None, supportedformats=None, embed_token=None): content_tree = self._download_json(content_tree_url, video_id)['content_tree'] metadata = content_tree[list(content_tree)[0]] embed_code = metadata['embed_code'] @@ -31,59 +31,62 @@ class OoyalaBaseIE(InfoExtractor): title = metadata['title'] auth_data = self._download_json( - self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) - + compat_urllib_parse_urlencode({ - 'domain': domain, + self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code), + video_id, headers=self.geo_verification_headers(), query={ + 'domain': domain or 'player.ooyala.com', 'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth', 'embedToken': embed_token, - }), video_id, headers=self.geo_verification_headers()) - - cur_auth_data = auth_data['authorization_data'][embed_code] + })['authorization_data'][embed_code] urls = [] formats = [] - if cur_auth_data['authorized']: - for stream in cur_auth_data['streams']: - url_data = try_get(stream, lambda x: x['url']['data'], compat_str) - if not url_data: - continue - s_url = compat_b64decode(url_data).decode('utf-8') - if not s_url or s_url in urls: - continue - urls.append(s_url) - ext = determine_ext(s_url, None) - delivery_type = stream.get('delivery_type') - if delivery_type == 'hls' or ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - re.sub(r'/ip(?:ad|hone)/', '/all/', s_url), embed_code, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - elif delivery_type == 'hds' or ext == 'f4m': - formats.extend(self._extract_f4m_formats( - s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False)) - elif delivery_type == 'dash' or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - s_url, embed_code, mpd_id='dash', fatal=False)) - elif delivery_type == 'smooth': - self._extract_ism_formats( - s_url, embed_code, ism_id='mss', fatal=False) - elif ext == 'smil': - formats.extend(self._extract_smil_formats( - s_url, embed_code, fatal=False)) - else: - formats.append({ - 'url': s_url, - 'ext': ext or delivery_type, - 'vcodec': stream.get('video_codec'), - 'format_id': delivery_type, - 'width': int_or_none(stream.get('width')), - 'height': int_or_none(stream.get('height')), - 'abr': int_or_none(stream.get('audio_bitrate')), - 'vbr': int_or_none(stream.get('video_bitrate')), - 'fps': float_or_none(stream.get('framerate')), - }) - else: + streams = auth_data.get('streams') or [{ + 'delivery_type': 'hls', + 'url': { + 'data': base64.b64encode(('http://player.ooyala.com/hls/player/all/%s.m3u8' % embed_code).encode()).decode(), + } + }] + for stream in streams: + url_data = try_get(stream, lambda x: x['url']['data'], compat_str) + if not url_data: + continue + s_url = compat_b64decode(url_data).decode('utf-8') + if not s_url or s_url in urls: + continue + urls.append(s_url) + ext = determine_ext(s_url, None) + delivery_type = stream.get('delivery_type') + if delivery_type == 'hls' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + re.sub(r'/ip(?:ad|hone)/', '/all/', s_url), embed_code, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif delivery_type == 'hds' or ext == 'f4m': + formats.extend(self._extract_f4m_formats( + s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False)) + elif delivery_type == 'dash' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + s_url, embed_code, mpd_id='dash', fatal=False)) + elif delivery_type == 'smooth': + self._extract_ism_formats( + s_url, embed_code, ism_id='mss', fatal=False) + elif ext == 'smil': + formats.extend(self._extract_smil_formats( + s_url, embed_code, fatal=False)) + else: + formats.append({ + 'url': s_url, + 'ext': ext or delivery_type, + 'vcodec': stream.get('video_codec'), + 'format_id': delivery_type, + 'width': int_or_none(stream.get('width')), + 'height': int_or_none(stream.get('height')), + 'abr': int_or_none(stream.get('audio_bitrate')), + 'vbr': int_or_none(stream.get('video_bitrate')), + 'fps': float_or_none(stream.get('framerate')), + }) + if not formats and not auth_data.get('authorized'): raise ExtractorError('%s said: %s' % ( - self.IE_NAME, cur_auth_data['message']), expected=True) + self.IE_NAME, auth_data['message']), expected=True) self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 66e38cdb4..0c20d0177 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -3,21 +3,17 @@ from __future__ import unicode_literals import json import os -import re import subprocess import tempfile -from .common import InfoExtractor from ..compat import ( compat_urlparse, compat_kwargs, ) from ..utils import ( check_executable, - determine_ext, encodeArgument, ExtractorError, - get_element_by_id, get_exe_version, is_outdated_version, std_headers, @@ -240,262 +236,3 @@ class PhantomJSwrapper(object): self._load_cookies() return (html, encodeArgument(out)) - - -class OpenloadIE(InfoExtractor): - _DOMAINS = r''' - (?: - openload\.(?:co|io|link|pw)| - oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|online|monster|press|pw|life|live|space|services|website|vip)| - oladblock\.(?:services|xyz|me)|openloed\.co - ) - ''' - _VALID_URL = r'''(?x) - https?:// - (?P<host> - (?:www\.)? - %s - )/ - (?:f|embed)/ - (?P<id>[a-zA-Z0-9-_]+) - ''' % _DOMAINS - _EMBED_WORD = 'embed' - _STREAM_WORD = 'f' - _REDIR_WORD = 'stream' - _URL_IDS = ('streamurl', 'streamuri', 'streamurj') - _TESTS = [{ - 'url': 'https://openload.co/f/kUEfGclsU9o', - 'md5': 'bf1c059b004ebc7a256f89408e65c36e', - 'info_dict': { - 'id': 'kUEfGclsU9o', - 'ext': 'mp4', - 'title': 'skyrim_no-audio_1080.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - }, - }, { - 'url': 'https://openload.co/embed/rjC09fkPLYs', - 'info_dict': { - 'id': 'rjC09fkPLYs', - 'ext': 'mp4', - 'title': 'movie.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - 'subtitles': { - 'en': [{ - 'ext': 'vtt', - }], - }, - }, - 'params': { - 'skip_download': True, # test subtitles only - }, - }, { - 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4', - 'only_matching': True, - }, { - 'url': 'https://openload.io/f/ZAn6oz-VZGE/', - 'only_matching': True, - }, { - 'url': 'https://openload.co/f/_-ztPaZtMhM/', - 'only_matching': True, - }, { - # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout - # for title and ext - 'url': 'https://openload.co/embed/Sxz5sADo82g/', - 'only_matching': True, - }, { - # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available - # via https://openload.co/f/e-Ixz9ZR5L0/ - 'url': 'https://openload.co/f/e-Ixz9ZR5L0/', - 'only_matching': True, - }, { - 'url': 'https://oload.tv/embed/KnG-kKZdcfY/', - 'only_matching': True, - }, { - 'url': 'http://www.openload.link/f/KnG-kKZdcfY', - 'only_matching': True, - }, { - 'url': 'https://oload.stream/f/KnG-kKZdcfY', - 'only_matching': True, - }, { - 'url': 'https://oload.xyz/f/WwRBpzW8Wtk', - 'only_matching': True, - }, { - 'url': 'https://oload.win/f/kUEfGclsU9o', - 'only_matching': True, - }, { - 'url': 'https://oload.download/f/kUEfGclsU9o', - 'only_matching': True, - }, { - 'url': 'https://oload.cloud/f/4ZDnBXRWiB8', - 'only_matching': True, - }, { - # Its title has not got its extension but url has it - 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4', - 'only_matching': True, - }, { - 'url': 'https://oload.cc/embed/5NEAbI2BDSk', - 'only_matching': True, - }, { - 'url': 'https://oload.icu/f/-_i4y_F_Hs8', - 'only_matching': True, - }, { - 'url': 'https://oload.fun/f/gb6G1H4sHXY', - 'only_matching': True, - }, { - 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', - 'only_matching': True, - }, { - 'url': 'https://oload.info/f/5NEAbI2BDSk', - 'only_matching': True, - }, { - 'url': 'https://openload.pw/f/WyKgK8s94N0', - 'only_matching': True, - }, { - 'url': 'https://oload.pw/f/WyKgK8s94N0', - 'only_matching': True, - }, { - 'url': 'https://oload.live/f/-Z58UZ-GR4M', - 'only_matching': True, - }, { - 'url': 'https://oload.space/f/IY4eZSst3u8/', - 'only_matching': True, - }, { - 'url': 'https://oload.services/embed/bs1NWj1dCag/', - 'only_matching': True, - }, { - 'url': 'https://oload.online/f/W8o2UfN1vNY/', - 'only_matching': True, - }, { - 'url': 'https://oload.monster/f/W8o2UfN1vNY/', - 'only_matching': True, - }, { - 'url': 'https://oload.press/embed/drTBl1aOTvk/', - 'only_matching': True, - }, { - 'url': 'https://oload.website/embed/drTBl1aOTvk/', - 'only_matching': True, - }, { - 'url': 'https://oload.life/embed/oOzZjNPw9Dc/', - 'only_matching': True, - }, { - 'url': 'https://oload.biz/f/bEk3Gp8ARr4/', - 'only_matching': True, - }, { - 'url': 'https://oload.best/embed/kkz9JgVZeWc/', - 'only_matching': True, - }, { - 'url': 'https://oladblock.services/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://oladblock.xyz/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://oladblock.me/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://openloed.co/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://oload.vip/f/kUEfGclsU9o', - 'only_matching': True, - }] - - @classmethod - def _extract_urls(cls, webpage): - return re.findall( - r'(?x)<iframe[^>]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)' - % (cls._DOMAINS, cls._EMBED_WORD), webpage) - - def _extract_decrypted_page(self, page_url, webpage, video_id): - phantom = PhantomJSwrapper(self, required_version='2.0') - webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id) - return webpage - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - host = mobj.group('host') - video_id = mobj.group('id') - - url_pattern = 'https://%s/%%s/%s/' % (host, video_id) - - for path in (self._EMBED_WORD, self._STREAM_WORD): - page_url = url_pattern % path - last = path == self._STREAM_WORD - webpage = self._download_webpage( - page_url, video_id, 'Downloading %s webpage' % path, - fatal=last) - if not webpage: - continue - if 'File not found' in webpage or 'deleted by the owner' in webpage: - if not last: - continue - raise ExtractorError('File not found', expected=True, video_id=video_id) - break - - webpage = self._extract_decrypted_page(page_url, webpage, video_id) - for element_id in self._URL_IDS: - decoded_id = get_element_by_id(element_id, webpage) - if decoded_id: - break - if not decoded_id: - decoded_id = self._search_regex( - (r'>\s*([\w-]+~\d{10,}~\d+\.\d+\.0\.0~[\w-]+)\s*<', - r'>\s*([\w~-]+~\d+\.\d+\.\d+\.\d+~[\w~-]+)', - r'>\s*([\w-]+~\d{10,}~(?:[a-f\d]+:){2}:~[\w-]+)\s*<', - r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)\s*<', - r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage, - 'stream URL') - video_url = 'https://%s/%s/%s?mime=true' % (host, self._REDIR_WORD, decoded_id) - - title = self._og_search_title(webpage, default=None) or self._search_regex( - r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage, - 'title', default=None) or self._html_search_meta( - 'description', webpage, 'title', fatal=True) - - entries = self._parse_html5_media_entries(page_url, webpage, video_id) - entry = entries[0] if entries else {} - subtitles = entry.get('subtitles') - - return { - 'id': video_id, - 'title': title, - 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), - 'url': video_url, - 'ext': determine_ext(title, None) or determine_ext(url, 'mp4'), - 'subtitles': subtitles, - } - - -class VerystreamIE(OpenloadIE): - IE_NAME = 'verystream' - - _DOMAINS = r'(?:verystream\.com|woof\.tube)' - _VALID_URL = r'''(?x) - https?:// - (?P<host> - (?:www\.)? - %s - )/ - (?:stream|e)/ - (?P<id>[a-zA-Z0-9-_]+) - ''' % _DOMAINS - _EMBED_WORD = 'e' - _STREAM_WORD = 'stream' - _REDIR_WORD = 'gettoken' - _URL_IDS = ('videolink', ) - _TESTS = [{ - 'url': 'https://verystream.com/stream/c1GWQ9ngBBx/', - 'md5': 'd3e8c5628ccb9970b65fd65269886795', - 'info_dict': { - 'id': 'c1GWQ9ngBBx', - 'ext': 'mp4', - 'title': 'Big Buck Bunny.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - }, - }, { - 'url': 'https://verystream.com/e/c1GWQ9ngBBx/', - 'only_matching': True, - }] - - def _extract_decrypted_page(self, page_url, webpage, video_id): - return webpage # for Verystream, the webpage is already decrypted diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 3425f7602..d54b8ace6 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -6,12 +6,14 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + clean_html, determine_ext, float_or_none, HEADRequest, int_or_none, orderedSet, remove_end, + str_or_none, strip_jsonp, unescapeHTML, unified_strdate, @@ -88,8 +90,11 @@ class ORFTVthekIE(InfoExtractor): format_id = '-'.join(format_id_list) ext = determine_ext(src) if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id=format_id, fatal=False)) + m3u8_formats = self._extract_m3u8_formats( + src, video_id, 'mp4', m3u8_id=format_id, fatal=False) + if any('/geoprotection' in f['url'] for f in m3u8_formats): + self.raise_geo_restricted() + formats.extend(m3u8_formats) elif ext == 'f4m': formats.extend(self._extract_f4m_formats( src, video_id, f4m_id=format_id, fatal=False)) @@ -161,44 +166,48 @@ class ORFRadioIE(InfoExtractor): show_date = mobj.group('date') show_id = mobj.group('show') - if station == 'fm4': - show_id = '4%s' % show_id - data = self._download_json( - 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date), - show_id - ) - - def extract_entry_dict(info, title, subtitle): - return { - 'id': info['loopStreamId'].replace('.mp3', ''), - 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']), + 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' + % (station, show_id, show_date), show_id) + + entries = [] + for info in data['streams']: + loop_stream_id = str_or_none(info.get('loopStreamId')) + if not loop_stream_id: + continue + title = str_or_none(data.get('title')) + if not title: + continue + start = int_or_none(info.get('start'), scale=1000) + end = int_or_none(info.get('end'), scale=1000) + duration = end - start if end and start else None + entries.append({ + 'id': loop_stream_id.replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id), 'title': title, - 'description': subtitle, - 'duration': (info['end'] - info['start']) / 1000, - 'timestamp': info['start'] / 1000, + 'description': clean_html(data.get('subtitle')), + 'duration': duration, + 'timestamp': start, 'ext': 'mp3', - 'series': data.get('programTitle') - } - - entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + 'series': data.get('programTitle'), + }) return { '_type': 'playlist', 'id': show_id, - 'title': data['title'], - 'description': data['subtitle'], - 'entries': entries + 'title': data.get('title'), + 'description': clean_html(data.get('subtitle')), + 'entries': entries, } class ORFFM4IE(ORFRadioIE): IE_NAME = 'orf:fm4' IE_DESC = 'radio FM4' - _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)' + _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)' _TEST = { - 'url': 'http://fm4.orf.at/player/20170107/CC', + 'url': 'http://fm4.orf.at/player/20170107/4CC', 'md5': '2b0be47375432a7ef104453432a19212', 'info_dict': { 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295', @@ -209,7 +218,8 @@ class ORFFM4IE(ORFRadioIE): 'timestamp': 1483819257, 'upload_date': '20170107', }, - 'skip': 'Shows from ORF radios are only available for 7 days.' + 'skip': 'Shows from ORF radios are only available for 7 days.', + 'only_matching': True, } diff --git a/youtube_dl/extractor/pandatv.py b/youtube_dl/extractor/pandatv.py deleted file mode 100644 index 4219802d5..000000000 --- a/youtube_dl/extractor/pandatv.py +++ /dev/null @@ -1,99 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - qualities, -) - - -class PandaTVIE(InfoExtractor): - IE_DESC = '熊猫TV' - _VALID_URL = r'https?://(?:www\.)?panda\.tv/(?P<id>[0-9]+)' - _TESTS = [{ - 'url': 'http://www.panda.tv/66666', - 'info_dict': { - 'id': '66666', - 'title': 're:.+', - 'uploader': '刘杀鸡', - 'ext': 'flv', - 'is_live': True, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Live stream is offline', - }, { - 'url': 'https://www.panda.tv/66666', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - config = self._download_json( - 'https://www.panda.tv/api_room_v2?roomid=%s' % video_id, video_id) - - error_code = config.get('errno', 0) - if error_code != 0: - raise ExtractorError( - '%s returned error %s: %s' - % (self.IE_NAME, error_code, config['errmsg']), - expected=True) - - data = config['data'] - video_info = data['videoinfo'] - - # 2 = live, 3 = offline - if video_info.get('status') != '2': - raise ExtractorError( - 'Live stream is offline', expected=True) - - title = data['roominfo']['name'] - uploader = data.get('hostinfo', {}).get('name') - room_key = video_info['room_key'] - stream_addr = video_info.get( - 'stream_addr', {'OD': '1', 'HD': '1', 'SD': '1'}) - - # Reverse engineered from web player swf - # (http://s6.pdim.gs/static/07153e425f581151.swf at the moment of - # writing). - plflag0, plflag1 = video_info['plflag'].split('_') - plflag0 = int(plflag0) - 1 - if plflag1 == '21': - plflag0 = 10 - plflag1 = '4' - live_panda = 'live_panda' if plflag0 < 1 else '' - - plflag_auth = self._parse_json(video_info['plflag_list'], video_id) - sign = plflag_auth['auth']['sign'] - ts = plflag_auth['auth']['time'] - rid = plflag_auth['auth']['rid'] - - quality_key = qualities(['OD', 'HD', 'SD']) - suffix = ['_small', '_mid', ''] - formats = [] - for k, v in stream_addr.items(): - if v != '1': - continue - quality = quality_key(k) - if quality <= 0: - continue - for pref, (ext, pl) in enumerate((('m3u8', '-hls'), ('flv', ''))): - formats.append({ - 'url': 'https://pl%s%s.live.panda.tv/live_panda/%s%s%s.%s?sign=%s&ts=%s&rid=%s' - % (pl, plflag1, room_key, live_panda, suffix[quality], ext, sign, ts, rid), - 'format_id': '%s-%s' % (k, ext), - 'quality': quality, - 'source_preference': pref, - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': self._live_title(title), - 'uploader': uploader, - 'formats': formats, - 'is_live': True, - } diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index 426dd8121..761a4b1de 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -6,7 +6,11 @@ from ..utils import ( clean_html, determine_ext, int_or_none, + KNOWN_EXTENSIONS, + mimetype2ext, parse_iso8601, + str_or_none, + try_get, ) @@ -24,6 +28,7 @@ class PatreonIE(InfoExtractor): 'thumbnail': 're:^https?://.*$', 'timestamp': 1406473987, 'upload_date': '20140727', + 'uploader_id': '87145', }, }, { 'url': 'http://www.patreon.com/creation?hid=754133', @@ -90,7 +95,13 @@ class PatreonIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) post = self._download_json( - 'https://www.patreon.com/api/posts/' + video_id, video_id) + 'https://www.patreon.com/api/posts/' + video_id, video_id, query={ + 'fields[media]': 'download_url,mimetype,size_bytes', + 'fields[post]': 'comment_count,content,embed,image,like_count,post_file,published_at,title', + 'fields[user]': 'full_name,url', + 'json-api-use-default-includes': 'false', + 'include': 'media,user', + }) attributes = post['data']['attributes'] title = attributes['title'].strip() image = attributes.get('image') or {} @@ -104,33 +115,42 @@ class PatreonIE(InfoExtractor): 'comment_count': int_or_none(attributes.get('comment_count')), } - def add_file(file_data): - file_url = file_data.get('url') - if file_url: - info.update({ - 'url': file_url, - 'ext': determine_ext(file_data.get('name'), 'mp3'), - }) - for i in post.get('included', []): i_type = i.get('type') - if i_type == 'attachment': - add_file(i.get('attributes') or {}) + if i_type == 'media': + media_attributes = i.get('attributes') or {} + download_url = media_attributes.get('download_url') + ext = mimetype2ext(media_attributes.get('mimetype')) + if download_url and ext in KNOWN_EXTENSIONS: + info.update({ + 'ext': ext, + 'filesize': int_or_none(media_attributes.get('size_bytes')), + 'url': download_url, + }) elif i_type == 'user': user_attributes = i.get('attributes') if user_attributes: info.update({ 'uploader': user_attributes.get('full_name'), + 'uploader_id': str_or_none(i.get('id')), 'uploader_url': user_attributes.get('url'), }) if not info.get('url'): - add_file(attributes.get('post_file') or {}) + embed_url = try_get(attributes, lambda x: x['embed']['url']) + if embed_url: + info.update({ + '_type': 'url', + 'url': embed_url, + }) if not info.get('url'): - info.update({ - '_type': 'url', - 'url': attributes['embed']['url'], - }) + post_file = attributes['post_file'] + ext = determine_ext(post_file.get('name')) + if ext in KNOWN_EXTENSIONS: + info.update({ + 'ext': ext, + 'url': post_file['url'], + }) return info diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index d3a83ea2b..48fb95416 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -8,6 +8,7 @@ from ..compat import compat_str from ..utils import ( int_or_none, parse_resolution, + str_or_none, try_get, unified_timestamp, url_or_none, @@ -415,6 +416,7 @@ class PeerTubeIE(InfoExtractor): peertube\.cpy\.re )''' _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}' + _API_BASE = 'https://%s/api/v1/videos/%s/%s' _VALID_URL = r'''(?x) (?: peertube:(?P<host>[^:]+):| @@ -423,26 +425,30 @@ class PeerTubeIE(InfoExtractor): (?P<id>%s) ''' % (_INSTANCES_RE, _UUID_RE) _TESTS = [{ - 'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', - 'md5': '80f24ff364cc9d333529506a263e7feb', + 'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d', + 'md5': '9bed8c0137913e17b86334e5885aacff', 'info_dict': { - 'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c', + 'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d', 'ext': 'mp4', - 'title': 'wow', - 'description': 'wow such video, so gif', + 'title': 'What is PeerTube?', + 'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10', 'thumbnail': r're:https?://.*\.(?:jpg|png)', - 'timestamp': 1519297480, - 'upload_date': '20180222', - 'uploader': 'Luclu7', - 'uploader_id': '7fc42640-efdb-4505-a45d-a15b1a5496f1', - 'uploder_url': 'https://peertube.nsa.ovh/accounts/luclu7', - 'license': 'Unknown', - 'duration': 3, + 'timestamp': 1538391166, + 'upload_date': '20181001', + 'uploader': 'Framasoft', + 'uploader_id': '3', + 'uploader_url': 'https://framatube.org/accounts/framasoft', + 'channel': 'Les vidéos de Framasoft', + 'channel_id': '2', + 'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8', + 'language': 'en', + 'license': 'Attribution - Share Alike', + 'duration': 113, 'view_count': int, 'like_count': int, 'dislike_count': int, - 'tags': list, - 'categories': list, + 'tags': ['framasoft', 'peertube'], + 'categories': ['Science & Technology'], } }, { 'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44', @@ -484,13 +490,38 @@ class PeerTubeIE(InfoExtractor): entries = [peertube_url] return entries + def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True): + return self._download_json( + self._API_BASE % (host, video_id, path), video_id, + note=note, errnote=errnote, fatal=fatal) + + def _get_subtitles(self, host, video_id): + captions = self._call_api( + host, video_id, 'captions', note='Downloading captions JSON', + fatal=False) + if not isinstance(captions, dict): + return + data = captions.get('data') + if not isinstance(data, list): + return + subtitles = {} + for e in data: + language_id = try_get(e, lambda x: x['language']['id'], compat_str) + caption_url = urljoin('https://%s' % host, e.get('captionPath')) + if not caption_url: + continue + subtitles.setdefault(language_id or 'en', []).append({ + 'url': caption_url, + }) + return subtitles + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) host = mobj.group('host') or mobj.group('host_2') video_id = mobj.group('id') - video = self._download_json( - 'https://%s/api/v1/videos/%s' % (host, video_id), video_id) + video = self._call_api( + host, video_id, '', note='Downloading video JSON') title = video['name'] @@ -513,10 +544,28 @@ class PeerTubeIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - def account_data(field): - return try_get(video, lambda x: x['account'][field], compat_str) + full_description = self._call_api( + host, video_id, 'description', note='Downloading description JSON', + fatal=False) + + description = None + if isinstance(full_description, dict): + description = str_or_none(full_description.get('description')) + if not description: + description = video.get('description') + + subtitles = self.extract_subtitles(host, video_id) + + def data(section, field, type_): + return try_get(video, lambda x: x[section][field], type_) + + def account_data(field, type_): + return data('account', field, type_) + + def channel_data(field, type_): + return data('channel', field, type_) - category = try_get(video, lambda x: x['category']['label'], compat_str) + category = data('category', 'label', compat_str) categories = [category] if category else None nsfw = video.get('nsfw') @@ -528,14 +577,17 @@ class PeerTubeIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'description': video.get('description'), + 'description': description, 'thumbnail': urljoin(url, video.get('thumbnailPath')), 'timestamp': unified_timestamp(video.get('publishedAt')), - 'uploader': account_data('displayName'), - 'uploader_id': account_data('uuid'), - 'uploder_url': account_data('url'), - 'license': try_get( - video, lambda x: x['licence']['label'], compat_str), + 'uploader': account_data('displayName', compat_str), + 'uploader_id': str_or_none(account_data('id', int)), + 'uploader_url': url_or_none(account_data('url', compat_str)), + 'channel': channel_data('displayName', compat_str), + 'channel_id': str_or_none(channel_data('id', int)), + 'channel_url': url_or_none(channel_data('url', compat_str)), + 'language': data('language', 'id', compat_str), + 'license': data('licence', 'label', compat_str), 'duration': int_or_none(video.get('duration')), 'view_count': int_or_none(video.get('views')), 'like_count': int_or_none(video.get('likes')), @@ -544,4 +596,5 @@ class PeerTubeIE(InfoExtractor): 'tags': try_get(video, lambda x: x['tags'], list), 'categories': categories, 'formats': formats, + 'subtitles': subtitles } diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py index b337a56c0..c02e34aba 100644 --- a/youtube_dl/extractor/periscope.py +++ b/youtube_dl/extractor/periscope.py @@ -17,12 +17,54 @@ class PeriscopeBaseIE(InfoExtractor): 'https://api.periscope.tv/api/v2/%s' % method, item_id, query=query) + def _parse_broadcast_data(self, broadcast, video_id): + title = broadcast['status'] + uploader = broadcast.get('user_display_name') or broadcast.get('username') + title = '%s - %s' % (uploader, title) if uploader else title + is_live = broadcast.get('state').lower() == 'running' + + thumbnails = [{ + 'url': broadcast[image], + } for image in ('image_url', 'image_url_small') if broadcast.get(image)] + + return { + 'id': broadcast.get('id') or video_id, + 'title': self._live_title(title) if is_live else title, + 'timestamp': parse_iso8601(broadcast.get('created_at')), + 'uploader': uploader, + 'uploader_id': broadcast.get('user_id') or broadcast.get('username'), + 'thumbnails': thumbnails, + 'view_count': int_or_none(broadcast.get('total_watched')), + 'tags': broadcast.get('tags'), + 'is_live': is_live, + } + + @staticmethod + def _extract_common_format_info(broadcast): + return broadcast.get('state').lower(), int_or_none(broadcast.get('width')), int_or_none(broadcast.get('height')) + + @staticmethod + def _add_width_and_height(f, width, height): + for key, val in (('width', width), ('height', height)): + if not f.get(key): + f[key] = val + + def _extract_pscp_m3u8_formats(self, m3u8_url, video_id, format_id, state, width, height, fatal=True): + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', + entry_protocol='m3u8_native' + if state in ('ended', 'timed_out') else 'm3u8', + m3u8_id=format_id, fatal=fatal) + if len(m3u8_formats) == 1: + self._add_width_and_height(m3u8_formats[0], width, height) + return m3u8_formats + class PeriscopeIE(PeriscopeBaseIE): IE_DESC = 'Periscope' IE_NAME = 'periscope' _VALID_URL = r'https?://(?:www\.)?(?:periscope|pscp)\.tv/[^/]+/(?P<id>[^/?#]+)' - # Alive example URLs can be found here http://onperiscope.com/ + # Alive example URLs can be found here https://www.periscope.tv/ _TESTS = [{ 'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==', 'md5': '65b57957972e503fcbbaeed8f4fa04ca', @@ -61,21 +103,9 @@ class PeriscopeIE(PeriscopeBaseIE): 'accessVideoPublic', {'broadcast_id': token}, token) broadcast = stream['broadcast'] - title = broadcast['status'] - - uploader = broadcast.get('user_display_name') or broadcast.get('username') - uploader_id = (broadcast.get('user_id') or broadcast.get('username')) + info = self._parse_broadcast_data(broadcast, token) - title = '%s - %s' % (uploader, title) if uploader else title state = broadcast.get('state').lower() - if state == 'running': - title = self._live_title(title) - timestamp = parse_iso8601(broadcast.get('created_at')) - - thumbnails = [{ - 'url': broadcast[image], - } for image in ('image_url', 'image_url_small') if broadcast.get(image)] - width = int_or_none(broadcast.get('width')) height = int_or_none(broadcast.get('height')) @@ -92,32 +122,20 @@ class PeriscopeIE(PeriscopeBaseIE): continue video_urls.add(video_url) if format_id != 'rtmp': - m3u8_formats = self._extract_m3u8_formats( - video_url, token, 'mp4', - entry_protocol='m3u8_native' - if state in ('ended', 'timed_out') else 'm3u8', - m3u8_id=format_id, fatal=False) - if len(m3u8_formats) == 1: - add_width_and_height(m3u8_formats[0]) + m3u8_formats = self._extract_pscp_m3u8_formats( + video_url, token, format_id, state, width, height, False) formats.extend(m3u8_formats) continue rtmp_format = { 'url': video_url, 'ext': 'flv' if format_id == 'rtmp' else 'mp4', } - add_width_and_height(rtmp_format) + self._add_width_and_height(rtmp_format) formats.append(rtmp_format) self._sort_formats(formats) - return { - 'id': broadcast.get('id') or token, - 'title': title, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'thumbnails': thumbnails, - 'formats': formats, - } + info['formats'] = formats + return info class PeriscopeUserIE(PeriscopeBaseIE): diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py index 602207beb..23c8256b5 100644 --- a/youtube_dl/extractor/platzi.py +++ b/youtube_dl/extractor/platzi.py @@ -46,7 +46,7 @@ class PlatziBaseIE(InfoExtractor): headers={'Referer': self._LOGIN_URL}) # login succeeded - if 'platzi.com/login' not in compat_str(urlh.geturl()): + if 'platzi.com/login' not in urlh.geturl(): return login_error = self._webpage_read_content( diff --git a/youtube_dl/extractor/popcorntimes.py b/youtube_dl/extractor/popcorntimes.py new file mode 100644 index 000000000..7bf7f9858 --- /dev/null +++ b/youtube_dl/extractor/popcorntimes.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_chr, +) +from ..utils import int_or_none + + +class PopcorntimesIE(InfoExtractor): + _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)' + _TEST = { + 'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy', + 'md5': '93f210991ad94ba8c3485950a2453257', + 'info_dict': { + 'id': 'A1XCFvz', + 'display_id': 'haensel-und-gretel-opera-fantasy', + 'ext': 'mp4', + 'title': 'Hänsel und Gretel', + 'description': 'md5:1b8146791726342e7b22ce8125cf6945', + 'thumbnail': r're:^https?://.*\.jpg$', + 'creator': 'John Paul', + 'release_date': '19541009', + 'duration': 4260, + 'tbr': 5380, + 'width': 720, + 'height': 540, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._search_regex( + r'<h1>([^<]+)', webpage, 'title', + default=None) or self._html_search_meta( + 'ya:ovs:original_name', webpage, 'title', fatal=True) + + loc = self._search_regex( + r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc', + group='value') + + loc_b64 = '' + for c in loc: + c_ord = ord(c) + if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'): + upper = ord('Z') if c_ord <= ord('Z') else ord('z') + c_ord += 13 + if upper < c_ord: + c_ord -= 26 + loc_b64 += compat_chr(c_ord) + + video_url = compat_b64decode(loc_b64).decode('utf-8') + + description = self._html_search_regex( + r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage, + 'description', fatal=False) + + thumbnail = self._search_regex( + r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1', + webpage, 'thumbnail', default=None, + group='value') or self._og_search_thumbnail(webpage) + + creator = self._html_search_meta( + 'video:director', webpage, 'creator', default=None) + + release_date = self._html_search_meta( + 'video:release_date', webpage, default=None) + if release_date: + release_date = release_date.replace('-', '') + + def int_meta(name): + return int_or_none(self._html_search_meta( + name, webpage, default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'creator': creator, + 'release_date': release_date, + 'duration': int_meta('video:duration'), + 'tbr': int_meta('ya:ovs:bitrate'), + 'width': int_meta('og:video:width'), + 'height': int_meta('og:video:height'), + 'http_headers': { + 'Referer': url, + }, + } diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 27d65d4b9..c6052ac9f 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -8,6 +8,7 @@ from ..utils import ( ExtractorError, int_or_none, js_to_json, + merge_dicts, urljoin, ) @@ -27,23 +28,22 @@ class PornHdIE(InfoExtractor): 'view_count': int, 'like_count': int, 'age_limit': 18, - } + }, + 'skip': 'HTTP Error 404: Not Found', }, { - # removed video 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'md5': '956b8ca569f7f4d8ec563e2c41598441', + 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de', 'info_dict': { 'id': '1962', 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', - 'title': 'Sierra loves doing laundry', + 'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, 'like_count': int, 'age_limit': 18, }, - 'skip': 'Not available anymore', }] def _real_extract(self, url): @@ -61,7 +61,13 @@ class PornHdIE(InfoExtractor): r"(?s)sources'?\s*[:=]\s*(\{.+?\})", webpage, 'sources', default='{}')), video_id) + info = {} if not sources: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info = entries[0] + + if not sources and not info: message = self._html_search_regex( r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1', webpage, 'error message', group='value') @@ -80,23 +86,29 @@ class PornHdIE(InfoExtractor): 'format_id': format_id, 'height': height, }) - self._sort_formats(formats) + if formats: + info['formats'] = formats + self._sort_formats(info['formats']) description = self._html_search_regex( - r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1', - webpage, 'description', fatal=False, group='value') + (r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>', + r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'), + webpage, 'description', fatal=False, + group='value') or self._html_search_meta( + 'description', webpage, default=None) or self._og_search_description(webpage) view_count = int_or_none(self._html_search_regex( r'(\d+) views\s*<', webpage, 'view count', fatal=False)) thumbnail = self._search_regex( r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage, - 'thumbnail', fatal=False, group='url') + 'thumbnail', default=None, group='url') like_count = int_or_none(self._search_regex( - (r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes', + (r'(\d+)</span>\s*likes', + r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes', r'class=["\']save-count["\'][^>]*>\s*(\d+)'), webpage, 'like count', fatal=False)) - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -106,4 +118,4 @@ class PornHdIE(InfoExtractor): 'like_count': like_count, 'formats': formats, 'age_limit': 18, - } + }) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index ba0ad7da2..3567a3283 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -17,6 +17,7 @@ from ..utils import ( determine_ext, ExtractorError, int_or_none, + NO_DEFAULT, orderedSet, remove_quotes, str_to_int, @@ -51,7 +52,7 @@ class PornHubIE(PornHubBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P<id>[\da-z]+) @@ -148,6 +149,9 @@ class PornHubIE(PornHubBaseIE): }, { 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', 'only_matching': True, + }, { + 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82', + 'only_matching': True, }] @staticmethod @@ -165,6 +169,13 @@ class PornHubIE(PornHubBaseIE): host = mobj.group('host') or 'pornhub.com' video_id = mobj.group('id') + if 'premium' in host: + if not self._downloader.params.get('cookiefile'): + raise ExtractorError( + 'PornHub Premium requires authentication.' + ' You may want to use --cookies.', + expected=True) + self._set_cookie(host, 'age_verified', '1') def dl_webpage(platform): @@ -188,10 +199,10 @@ class PornHubIE(PornHubBaseIE): # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. title = self._html_search_meta( - 'twitter:title', webpage, default=None) or self._search_regex( - (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', - r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', - r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), + 'twitter:title', webpage, default=None) or self._html_search_regex( + (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>', + r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1', + r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'), webpage, 'title', group='title') video_urls = [] @@ -227,12 +238,13 @@ class PornHubIE(PornHubBaseIE): else: thumbnail, duration = [None] * 2 - if not video_urls: - tv_webpage = dl_webpage('tv') - + def extract_js_vars(webpage, pattern, default=NO_DEFAULT): assignments = self._search_regex( - r'(var.+?mediastring.+?)</script>', tv_webpage, - 'encoded url').split(';') + pattern, webpage, 'encoded url', default=default) + if not assignments: + return {} + + assignments = assignments.split(';') js_vars = {} @@ -254,11 +266,35 @@ class PornHubIE(PornHubBaseIE): assn = re.sub(r'var\s+', '', assn) vname, value = assn.split('=', 1) js_vars[vname] = parse_js_value(value) + return js_vars - video_url = js_vars['mediastring'] - if video_url not in video_urls_set: - video_urls.append((video_url, None)) - video_urls_set.add(video_url) + def add_video_url(video_url): + v_url = url_or_none(video_url) + if not v_url: + return + if v_url in video_urls_set: + return + video_urls.append((v_url, None)) + video_urls_set.add(v_url) + + if not video_urls: + FORMAT_PREFIXES = ('media', 'quality') + js_vars = extract_js_vars( + webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES), + default=None) + if js_vars: + for key, format_url in js_vars.items(): + if any(key.startswith(p) for p in FORMAT_PREFIXES): + add_video_url(format_url) + if not video_urls and re.search( + r'<[^>]+\bid=["\']lockedPlayer', webpage): + raise ExtractorError( + 'Video %s is locked' % video_id, expected=True) + + if not video_urls: + js_vars = extract_js_vars( + dl_webpage('tv'), r'(var.+?mediastring.+?)</script>') + add_video_url(js_vars['mediastring']) for mobj in re.finditer( r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1', @@ -276,10 +312,16 @@ class PornHubIE(PornHubBaseIE): r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None) if upload_date: upload_date = upload_date.replace('/', '') - if determine_ext(video_url) == 'mpd': + ext = determine_ext(video_url) + if ext == 'mpd': formats.extend(self._extract_mpd_formats( video_url, video_id, mpd_id='dash', fatal=False)) continue + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + continue tbr = None mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url) if mobj: @@ -373,7 +415,7 @@ class PornHubPlaylistBaseIE(PornHubBaseIE): class PornHubUserIE(PornHubPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph', 'playlist_mincount': 118, @@ -441,7 +483,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph/videos', 'only_matching': True, @@ -556,7 +598,7 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' _TESTS = [{ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'info_dict': { diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py deleted file mode 100644 index 23ac93d7e..000000000 --- a/youtube_dl/extractor/promptfile.py +++ /dev/null @@ -1,70 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - determine_ext, - ExtractorError, - urlencode_postdata, -) - - -class PromptFileIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' - _TEST = { - 'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416', - 'md5': '5a7e285a26e0d66d9a263fae91bc92ce', - 'info_dict': { - 'id': '86D1CE8462-576CAAE416', - 'ext': 'mp4', - 'title': 'oceans.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None: - raise ExtractorError('Video %s does not exist' % video_id, - expected=True) - - chash = self._search_regex( - r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash') - fields = self._hidden_inputs(webpage) - keys = list(fields.keys()) - chash_key = keys[0] if len(keys) == 1 else next( - key for key in keys if key.startswith('cha')) - fields[chash_key] = chash + fields[chash_key] - - webpage = self._download_webpage( - url, video_id, 'Downloading video page', - data=urlencode_postdata(fields), - headers={'Content-type': 'application/x-www-form-urlencoded'}) - - video_url = self._search_regex( - (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File', - r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'), - webpage, 'video url', group='url') - title = self._html_search_regex( - r'<span.+title="([^"]+)">', webpage, 'title') - thumbnail = self._html_search_regex( - r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"', - webpage, 'thumbnail', fatal=False, flags=re.DOTALL) - - formats = [{ - 'format_id': 'sd', - 'url': video_url, - 'ext': determine_ext(title), - }] - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'formats': formats, - } diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index e19a470a5..1bc4f9b6b 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -16,7 +16,7 @@ from ..utils import ( class ProSiebenSat1BaseIE(InfoExtractor): - _GEO_COUNTRIES = ['DE'] + _GEO_BYPASS = False _ACCESS_ID = None _SUPPORTED_PROTOCOLS = 'dash:clear,hls:clear,progressive:clear' _V4_BASE_URL = 'https://vas-v4.p7s1video.net/4.0/get' @@ -39,14 +39,18 @@ class ProSiebenSat1BaseIE(InfoExtractor): formats = [] if self._ACCESS_ID: raw_ct = self._ENCRYPTION_KEY + clip_id + self._IV + self._ACCESS_ID - server_token = (self._download_json( + protocols = self._download_json( self._V4_BASE_URL + 'protocols', clip_id, 'Downloading protocols JSON', headers=self.geo_verification_headers(), query={ 'access_id': self._ACCESS_ID, 'client_token': sha1((raw_ct).encode()).hexdigest(), 'video_id': clip_id, - }, fatal=False) or {}).get('server_token') + }, fatal=False, expected_status=(403,)) or {} + error = protocols.get('error') or {} + if error.get('title') == 'Geo check failed': + self.raise_geo_restricted(countries=['AT', 'CH', 'DE']) + server_token = protocols.get('server_token') if server_token: urls = (self._download_json( self._V4_BASE_URL + 'urls', clip_id, 'Downloading urls JSON', query={ diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py index 5465e8ab7..fb704a3c4 100644 --- a/youtube_dl/extractor/puhutv.py +++ b/youtube_dl/extractor/puhutv.py @@ -25,21 +25,21 @@ class PuhuTVIE(InfoExtractor): _TESTS = [{ # film 'url': 'https://puhutv.com/sut-kardesler-izle', - 'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7', + 'md5': 'a347470371d56e1585d1b2c8dab01c96', 'info_dict': { 'id': '5085', 'display_id': 'sut-kardesler', 'ext': 'mp4', 'title': 'Süt Kardeşler', - 'description': 'md5:405fd024df916ca16731114eb18e511a', + 'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 4832.44, 'creator': 'Arzu Film', - 'timestamp': 1469778212, - 'upload_date': '20160729', + 'timestamp': 1561062602, + 'upload_date': '20190620', 'release_year': 1976, 'view_count': int, - 'tags': ['Aile', 'Komedi', 'Klasikler'], + 'tags': list, }, }, { # episode, geo restricted, bypassable with --geo-verification-proxy @@ -64,9 +64,10 @@ class PuhuTVIE(InfoExtractor): display_id)['data'] video_id = compat_str(info['id']) - title = info.get('name') or info['title']['name'] + show = info.get('title') or {} + title = info.get('name') or show['name'] if info.get('display_name'): - title = '%s %s' % (title, info.get('display_name')) + title = '%s %s' % (title, info['display_name']) try: videos = self._download_json( @@ -78,17 +79,36 @@ class PuhuTVIE(InfoExtractor): self.raise_geo_restricted() raise + urls = [] formats = [] + + def add_http_from_hls(m3u8_f): + http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4') + if http_url != m3u8_f['url']: + f = m3u8_f.copy() + f.update({ + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + 'url': http_url, + }) + formats.append(f) + for video in videos['data']['videos']: media_url = url_or_none(video.get('url')) - if not media_url: + if not media_url or media_url in urls: continue + urls.append(media_url) + playlist = video.get('is_playlist') - if video.get('stream_type') == 'hls' and playlist is True: - formats.extend(self._extract_m3u8_formats( + if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url: + m3u8_formats = self._extract_m3u8_formats( media_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + m3u8_id='hls', fatal=False) + for m3u8_f in m3u8_formats: + formats.append(m3u8_f) + add_http_from_hls(m3u8_f) continue + quality = int_or_none(video.get('quality')) f = { 'url': media_url, @@ -96,34 +116,29 @@ class PuhuTVIE(InfoExtractor): 'height': quality } video_format = video.get('video_format') - if video_format == 'hls' and playlist is False: + is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False + if is_hls: format_id = 'hls' f['protocol'] = 'm3u8_native' elif video_format == 'mp4': format_id = 'http' - else: continue if quality: format_id += '-%sp' % quality f['format_id'] = format_id formats.append(f) + if is_hls: + add_http_from_hls(f) self._sort_formats(formats) - description = try_get( - info, lambda x: x['title']['description'], - compat_str) or info.get('description') - timestamp = unified_timestamp(info.get('created_at')) creator = try_get( - info, lambda x: x['title']['producer']['name'], compat_str) + show, lambda x: x['producer']['name'], compat_str) - duration = float_or_none( - try_get(info, lambda x: x['content']['duration_in_ms'], int), - scale=1000) - view_count = try_get(info, lambda x: x['content']['watch_count'], int) + content = info.get('content') or {} images = try_get( - info, lambda x: x['content']['images']['wide'], dict) or {} + content, lambda x: x['images']['wide'], dict) or {} thumbnails = [] for image_id, image_url in images.items(): if not isinstance(image_url, compat_str): @@ -137,14 +152,8 @@ class PuhuTVIE(InfoExtractor): }) thumbnails.append(t) - release_year = try_get(info, lambda x: x['title']['released_at'], int) - - season_number = int_or_none(info.get('season_number')) - season_id = str_or_none(info.get('season_id')) - episode_number = int_or_none(info.get('episode_number')) - tags = [] - for genre in try_get(info, lambda x: x['title']['genres'], list) or []: + for genre in show.get('genres') or []: if not isinstance(genre, dict): continue genre_name = genre.get('name') @@ -152,12 +161,11 @@ class PuhuTVIE(InfoExtractor): tags.append(genre_name) subtitles = {} - for subtitle in try_get( - info, lambda x: x['content']['subtitles'], list) or []: + for subtitle in content.get('subtitles') or []: if not isinstance(subtitle, dict): continue lang = subtitle.get('language') - sub_url = url_or_none(subtitle.get('url')) + sub_url = url_or_none(subtitle.get('url') or subtitle.get('file')) if not lang or not isinstance(lang, compat_str) or not sub_url: continue subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ @@ -168,15 +176,15 @@ class PuhuTVIE(InfoExtractor): 'id': video_id, 'display_id': display_id, 'title': title, - 'description': description, - 'season_id': season_id, - 'season_number': season_number, - 'episode_number': episode_number, - 'release_year': release_year, - 'timestamp': timestamp, + 'description': info.get('description') or show.get('description'), + 'season_id': str_or_none(info.get('season_id')), + 'season_number': int_or_none(info.get('season_number')), + 'episode_number': int_or_none(info.get('episode_number')), + 'release_year': int_or_none(show.get('released_at')), + 'timestamp': unified_timestamp(info.get('created_at')), 'creator': creator, - 'view_count': view_count, - 'duration': duration, + 'view_count': int_or_none(content.get('watch_count')), + 'duration': float_or_none(content.get('duration_in_ms'), 1000), 'tags': tags, 'subtitles': subtitles, 'thumbnails': thumbnails, diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 5c84028ef..b1bde1e81 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -43,8 +43,15 @@ class RedTubeIE(InfoExtractor): webpage = self._download_webpage( 'http://www.redtube.com/%s' % video_id, video_id) - if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']): - raise ExtractorError('Video %s has been removed' % video_id, expected=True) + ERRORS = ( + (('video-deleted-info', '>This video has been removed'), 'has been removed'), + (('private_video_text', '>This video is private', '>Send a friend request to its owner to be able to view it'), 'is private'), + ) + + for patterns, message in ERRORS: + if any(p in webpage for p in patterns): + raise ExtractorError( + 'Video %s %s' % (video_id, message), expected=True) info = self._search_json_ld(webpage, video_id, default={}) diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py deleted file mode 100644 index 833d8a2f0..000000000 --- a/youtube_dl/extractor/revision3.py +++ /dev/null @@ -1,170 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - parse_iso8601, - unescapeHTML, - qualities, -) - - -class Revision3EmbedIE(InfoExtractor): - IE_NAME = 'revision3:embed' - _VALID_URL = r'(?:revision3:(?:(?P<playlist_type>[^:]+):)?|https?://(?:(?:(?:www|embed)\.)?(?:revision3|animalist)|(?:(?:api|embed)\.)?seekernetwork)\.com/player/embed\?videoId=)(?P<playlist_id>\d+)' - _TEST = { - 'url': 'http://api.seekernetwork.com/player/embed?videoId=67558', - 'md5': '83bcd157cab89ad7318dd7b8c9cf1306', - 'info_dict': { - 'id': '67558', - 'ext': 'mp4', - 'title': 'The Pros & Cons Of Zoos', - 'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?', - 'uploader_id': 'dnews', - 'uploader': 'DNews', - } - } - _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('playlist_id') - playlist_type = mobj.group('playlist_type') or 'video_id' - video_data = self._download_json( - 'http://revision3.com/api/getPlaylist.json', playlist_id, query={ - 'api_key': self._API_KEY, - 'codecs': 'h264,vp8,theora', - playlist_type: playlist_id, - })['items'][0] - - formats = [] - for vcodec, media in video_data['media'].items(): - for quality_id, quality in media.items(): - if quality_id == 'hls': - formats.extend(self._extract_m3u8_formats( - quality['url'], playlist_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - else: - formats.append({ - 'url': quality['url'], - 'format_id': '%s-%s' % (vcodec, quality_id), - 'tbr': int_or_none(quality.get('bitrate')), - 'vcodec': vcodec, - }) - self._sort_formats(formats) - - return { - 'id': playlist_id, - 'title': unescapeHTML(video_data['title']), - 'description': unescapeHTML(video_data.get('summary')), - 'uploader': video_data.get('show', {}).get('name'), - 'uploader_id': video_data.get('show', {}).get('slug'), - 'duration': int_or_none(video_data.get('duration')), - 'formats': formats, - } - - -class Revision3IE(InfoExtractor): - IE_NAME = 'revision' - _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:revision3|animalist)\.com)/(?P<id>[^/]+(?:/[^/?#]+)?)' - _TESTS = [{ - 'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016', - 'md5': 'd94a72d85d0a829766de4deb8daaf7df', - 'info_dict': { - 'id': '71089', - 'display_id': 'technobuffalo/5-google-predictions-for-2016', - 'ext': 'webm', - 'title': '5 Google Predictions for 2016', - 'description': 'Google had a great 2015, but it\'s already time to look ahead. Here are our five predictions for 2016.', - 'upload_date': '20151228', - 'timestamp': 1451325600, - 'duration': 187, - 'uploader': 'TechnoBuffalo', - 'uploader_id': 'technobuffalo', - } - }, { - # Show - 'url': 'http://revision3.com/variant', - 'only_matching': True, - }, { - # Tag - 'url': 'http://revision3.com/vr', - 'only_matching': True, - }] - _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s' - - def _real_extract(self, url): - domain, display_id = re.match(self._VALID_URL, url).groups() - site = domain.split('.')[0] - page_info = self._download_json( - self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id) - - page_data = page_info['data'] - page_type = page_data['type'] - if page_type in ('episode', 'embed'): - show_data = page_data['show']['data'] - page_id = compat_str(page_data['id']) - video_id = compat_str(page_data['video']['data']['id']) - - preference = qualities(['mini', 'small', 'medium', 'large']) - thumbnails = [{ - 'url': image_url, - 'id': image_id, - 'preference': preference(image_id) - } for image_id, image_url in page_data.get('images', {}).items()] - - info = { - 'id': page_id, - 'display_id': display_id, - 'title': unescapeHTML(page_data['name']), - 'description': unescapeHTML(page_data.get('summary')), - 'timestamp': parse_iso8601(page_data.get('publishTime'), ' '), - 'author': page_data.get('author'), - 'uploader': show_data.get('name'), - 'uploader_id': show_data.get('slug'), - 'thumbnails': thumbnails, - 'extractor_key': site, - } - - if page_type == 'embed': - info.update({ - '_type': 'url_transparent', - 'url': page_data['video']['data']['embed'], - }) - return info - - info.update({ - '_type': 'url_transparent', - 'url': 'revision3:%s' % video_id, - }) - return info - else: - list_data = page_info[page_type]['data'] - episodes_data = page_info['episodes']['data'] - num_episodes = page_info['meta']['totalEpisodes'] - processed_episodes = 0 - entries = [] - page_num = 1 - while True: - entries.extend([{ - '_type': 'url', - 'url': 'http://%s%s' % (domain, episode['path']), - 'id': compat_str(episode['id']), - 'ie_key': 'Revision3', - 'extractor_key': site, - } for episode in episodes_data]) - processed_episodes += len(episodes_data) - if processed_episodes == num_episodes: - break - page_num += 1 - episodes_data = self._download_json(self._PAGE_DATA_TEMPLATE % ( - domain, display_id + '/' + compat_str(page_num), domain), - display_id)['episodes']['data'] - - return self.playlist_result( - entries, compat_str(list_data['id']), - list_data.get('name'), list_data.get('summary')) diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py index 8d88ee499..8883639b2 100644 --- a/youtube_dl/extractor/roosterteeth.py +++ b/youtube_dl/extractor/roosterteeth.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..compat import ( compat_HTTPError, @@ -18,7 +16,6 @@ from ..utils import ( class RoosterTeethIE(InfoExtractor): _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)' - _LOGIN_URL = 'https://roosterteeth.com/login' _NETRC_MACHINE = 'roosterteeth' _TESTS = [{ 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement', @@ -53,48 +50,40 @@ class RoosterTeethIE(InfoExtractor): 'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement', 'only_matching': True, }] + _EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/episodes/' def _login(self): username, password = self._get_login_info() if username is None: return - login_page = self._download_webpage( - self._LOGIN_URL, None, - note='Downloading login page', - errnote='Unable to download login page') - - login_form = self._hidden_inputs(login_page) - - login_form.update({ - 'username': username, - 'password': password, - }) - - login_request = self._download_webpage( - self._LOGIN_URL, None, - note='Logging in', - data=urlencode_postdata(login_form), - headers={ - 'Referer': self._LOGIN_URL, - }) - - if not any(re.search(p, login_request) for p in ( - r'href=["\']https?://(?:www\.)?roosterteeth\.com/logout"', - r'>Sign Out<')): - error = self._html_search_regex( - r'(?s)<div[^>]+class=(["\']).*?\balert-danger\b.*?\1[^>]*>(?:\s*<button[^>]*>.*?</button>)?(?P<error>.+?)</div>', - login_request, 'alert', default=None, group='error') - if error: - raise ExtractorError('Unable to login: %s' % error, expected=True) - raise ExtractorError('Unable to log in') + try: + self._download_json( + 'https://auth.roosterteeth.com/oauth/token', + None, 'Logging in', data=urlencode_postdata({ + 'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5', + 'grant_type': 'password', + 'username': username, + 'password': password, + })) + except ExtractorError as e: + msg = 'Unable to login' + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + resp = self._parse_json(e.cause.read().decode(), None, fatal=False) + if resp: + error = resp.get('extra_info') or resp.get('error_description') or resp.get('error') + if error: + msg += ': ' + error + self.report_warning(msg) def _real_initialize(self): + if self._get_cookies(self._EPISODE_BASE_URL).get('rt_access_token'): + return self._login() def _real_extract(self, url): display_id = self._match_id(url) - api_episode_url = 'https://svod-be.roosterteeth.com/api/v1/episodes/%s' % display_id + api_episode_url = self._EPISODE_BASE_URL + display_id try: m3u8_url = self._download_json( diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index bd9ee1647..2cc665122 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_parse_qs, - compat_str, compat_urlparse, ) from ..utils import ( @@ -39,13 +38,13 @@ class SafariBaseIE(InfoExtractor): 'Downloading login page') def is_logged(urlh): - return 'learning.oreilly.com/home/' in compat_str(urlh.geturl()) + return 'learning.oreilly.com/home/' in urlh.geturl() if is_logged(urlh): self.LOGGED_IN = True return - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() parsed_url = compat_urlparse.urlparse(redirect_url) qs = compat_parse_qs(parsed_url.query) next_uri = compat_urlparse.urljoin( @@ -165,7 +164,8 @@ class SafariIE(SafariBaseIE): kaltura_session = self._download_json( '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id), video_id, 'Downloading kaltura session JSON', - 'Unable to download kaltura session JSON', fatal=False) + 'Unable to download kaltura session JSON', fatal=False, + headers={'Accept': 'application/json'}) if kaltura_session: session = kaltura_session.get('session') if session: diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index 8b3275735..b40b4c4af 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -7,6 +7,7 @@ import re from .aws import AWSIE from .anvato import AnvatoIE +from .common import InfoExtractor from ..utils import ( smuggle_url, urlencode_postdata, @@ -102,3 +103,50 @@ class ScrippsNetworksWatchIE(AWSIE): 'anvato:anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a:%s' % mcp_id, {'geo_countries': ['US']}), AnvatoIE.ie_key(), video_id=mcp_id) + + +class ScrippsNetworksIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?(?P<site>cookingchanneltv|discovery|(?:diy|food)network|hgtv|travelchannel)\.com/videos/[0-9a-z-]+-(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://www.cookingchanneltv.com/videos/the-best-of-the-best-0260338', + 'info_dict': { + 'id': '0260338', + 'ext': 'mp4', + 'title': 'The Best of the Best', + 'description': 'Catch a new episode of MasterChef Canada Tuedsay at 9/8c.', + 'timestamp': 1475678834, + 'upload_date': '20161005', + 'uploader': 'SCNI-SCND', + }, + 'add_ie': ['ThePlatform'], + }, { + 'url': 'https://www.diynetwork.com/videos/diy-barnwood-tablet-stand-0265790', + 'only_matching': True, + }, { + 'url': 'https://www.foodnetwork.com/videos/chocolate-strawberry-cake-roll-7524591', + 'only_matching': True, + }, { + 'url': 'https://www.hgtv.com/videos/cookie-decorating-101-0301929', + 'only_matching': True, + }, { + 'url': 'https://www.travelchannel.com/videos/two-climates-one-bag-5302184', + 'only_matching': True, + }, { + 'url': 'https://www.discovery.com/videos/guardians-of-the-glades-cooking-with-tom-cobb-5578368', + 'only_matching': True, + }] + _ACCOUNT_MAP = { + 'cookingchanneltv': 2433005105, + 'discovery': 2706091867, + 'diynetwork': 2433004575, + 'foodnetwork': 2433005105, + 'hgtv': 2433004575, + 'travelchannel': 2433005739, + } + _TP_TEMPL = 'https://link.theplatform.com/s/ip77QC/media/guid/%d/%s?mbr=true' + + def _real_extract(self, url): + site, guid = re.match(self._VALID_URL, url).groups() + return self.url_result(smuggle_url( + self._TP_TEMPL % (self._ACCOUNT_MAP[site], guid), + {'force_smil_url': True}), 'ThePlatform', guid) diff --git a/youtube_dl/extractor/scte.py b/youtube_dl/extractor/scte.py new file mode 100644 index 000000000..ca1de63b6 --- /dev/null +++ b/youtube_dl/extractor/scte.py @@ -0,0 +1,144 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + decode_packed_codes, + ExtractorError, + urlencode_postdata, +) + + +class SCTEBaseIE(InfoExtractor): + _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx' + _NETRC_MACHINE = 'scte' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + login_popup = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login popup') + + def is_logged(webpage): + return any(re.search(p, webpage) for p in ( + r'class=["\']welcome\b', r'>Sign Out<')) + + # already logged in + if is_logged(login_popup): + return + + login_form = self._hidden_inputs(login_popup) + + login_form.update({ + 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username, + 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password, + 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on', + }) + + response = self._download_webpage( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form)) + + if '|pageRedirect|' not in response and not is_logged(response): + error = self._html_search_regex( + r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)</', + response, 'error message', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + +class SCTEIE(SCTEBaseIE): + _VALID_URL = r'https?://learning\.scte\.org/mod/scorm/view\.php?.*?\bid=(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484', + 'info_dict': { + 'title': 'Introduction to DOCSIS Engineering Professional', + 'id': '31484', + }, + 'playlist_count': 5, + 'skip': 'Requires account credentials', + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex(r'<h1>(.+?)</h1>', webpage, 'title') + + context_id = self._search_regex(r'context-(\d+)', webpage, video_id) + content_base = 'https://learning.scte.org/pluginfile.php/%s/mod_scorm/content/8/' % context_id + context = decode_packed_codes(self._download_webpage( + '%smobile/data.js' % content_base, video_id)) + + data = self._parse_xml( + self._search_regex( + r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"), + video_id) + + entries = [] + for asset in data.findall('.//asset'): + asset_url = asset.get('url') + if not asset_url or not asset_url.endswith('.mp4'): + continue + asset_id = self._search_regex( + r'video_([^_]+)_', asset_url, 'asset id', default=None) + if not asset_id: + continue + entries.append({ + 'id': asset_id, + 'title': title, + 'url': content_base + asset_url, + }) + + return self.playlist_result(entries, video_id, title) + + +class SCTECourseIE(SCTEBaseIE): + _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491', + 'only_matching': True, + }, { + 'url': 'https://learning.scte.org/course/view.php?id=3639', + 'only_matching': True, + }, { + 'url': 'https://learning.scte.org/course/view.php?id=3073', + 'only_matching': True, + }] + + def _real_extract(self, url): + course_id = self._match_id(url) + + webpage = self._download_webpage(url, course_id) + + title = self._search_regex( + r'<h1>(.+?)</h1>', webpage, 'title', default=None) + + entries = [] + for mobj in re.finditer( + r'''(?x) + <a[^>]+ + href=(["\']) + (?P<url> + https?://learning\.scte\.org/mod/ + (?P<kind>scorm|subcourse)/view\.php?(?:(?!\1).)*? + \bid=\d+ + ) + ''', + webpage): + item_url = mobj.group('url') + if item_url == url: + continue + ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm' + else SCTECourseIE.ie_key()) + entries.append(self.url_result(item_url, ie=ie)) + + return self.playlist_result(entries, course_id, title) diff --git a/youtube_dl/extractor/seeker.py b/youtube_dl/extractor/seeker.py index 3b9c65e7e..7872dc80d 100644 --- a/youtube_dl/extractor/seeker.py +++ b/youtube_dl/extractor/seeker.py @@ -4,34 +4,37 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + get_element_by_class, + strip_or_none, +) class SeekerIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P<display_id>.*)-(?P<article_id>\d+)\.html' _TESTS = [{ - # player.loadRevision3Item 'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html', - 'md5': '30c1dc4030cc715cf05b423d0947ac18', + 'md5': '897d44bbe0d8986a2ead96de565a92db', 'info_dict': { - 'id': '76243', - 'ext': 'webm', + 'id': 'Elrn3gnY', + 'ext': 'mp4', 'title': 'Should Trump Be Required To Release His Tax Returns?', - 'description': 'Donald Trump has been secretive about his "big," "beautiful" tax returns. So what can we learn if he decides to release them?', - 'uploader': 'Seeker Daily', - 'uploader_id': 'seekerdaily', + 'description': 'md5:41efa8cfa8d627841045eec7b018eb45', + 'timestamp': 1490090165, + 'upload_date': '20170321', } }, { 'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html', 'playlist': [ { - 'md5': '83bcd157cab89ad7318dd7b8c9cf1306', + 'md5': '0497b9f20495174be73ae136949707d2', 'info_dict': { - 'id': '67558', + 'id': 'FihYQ8AE', 'ext': 'mp4', 'title': 'The Pros & Cons Of Zoos', - 'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?', - 'uploader': 'DNews', - 'uploader_id': 'dnews', + 'description': 'md5:d88f99a8ea8e7d25e6ff77f271b1271c', + 'timestamp': 1490039133, + 'upload_date': '20170320', }, } ], @@ -45,13 +48,11 @@ class SeekerIE(InfoExtractor): def _real_extract(self, url): display_id, article_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) - mobj = re.search(r"player\.loadRevision3Item\('([^']+)'\s*,\s*(\d+)\);", webpage) - if mobj: - playlist_type, playlist_id = mobj.groups() - return self.url_result( - 'revision3:%s:%s' % (playlist_type, playlist_id), 'Revision3Embed', playlist_id) - else: - entries = [self.url_result('revision3:video_id:%s' % video_id, 'Revision3Embed', video_id) for video_id in re.findall( - r'<iframe[^>]+src=[\'"](?:https?:)?//api\.seekernetwork\.com/player/embed\?videoId=(\d+)', webpage)] - return self.playlist_result( - entries, article_id, self._og_search_title(webpage), self._og_search_description(webpage)) + entries = [] + for jwp_id in re.findall(r'data-video-id="([a-zA-Z0-9]{8})"', webpage): + entries.append(self.url_result( + 'jwplatform:' + jwp_id, 'JWPlatform', jwp_id)) + return self.playlist_result( + entries, article_id, + self._og_search_title(webpage), + strip_or_none(get_element_by_class('subtitle__text', webpage)) or self._og_search_description(webpage)) diff --git a/youtube_dl/extractor/servingsys.py b/youtube_dl/extractor/servingsys.py deleted file mode 100644 index c013d678f..000000000 --- a/youtube_dl/extractor/servingsys.py +++ /dev/null @@ -1,72 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, -) - - -class ServingSysIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P<id>[0-9]+)' - - _TEST = { - 'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?', - 'info_dict': { - 'id': '5349193', - 'title': 'AdAPPter_Hyundai_demo', - }, - 'playlist': [{ - 'md5': 'baed851342df6846eb8677a60a011a0f', - 'info_dict': { - 'id': '29955898', - 'ext': 'flv', - 'title': 'AdAPPter_Hyundai_demo (1)', - 'duration': 74, - 'tbr': 1378, - 'width': 640, - 'height': 400, - }, - }, { - 'md5': '979b4da2655c4bc2d81aeb915a8c5014', - 'info_dict': { - 'id': '29907998', - 'ext': 'flv', - 'title': 'AdAPPter_Hyundai_demo (2)', - 'duration': 34, - 'width': 854, - 'height': 480, - 'tbr': 516, - }, - }], - 'params': { - 'playlistend': 2, - }, - '_skip': 'Blocked in the US [sic]', - } - - def _real_extract(self, url): - pl_id = self._match_id(url) - vast_doc = self._download_xml(url, pl_id) - - title = vast_doc.find('.//AdTitle').text - media = vast_doc.find('.//MediaFile').text - info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL') - - doc = self._download_xml(info_url, pl_id, 'Downloading video info') - entries = [{ - '_type': 'video', - 'id': a.attrib['id'], - 'title': '%s (%s)' % (title, a.attrib['assetID']), - 'url': a.attrib['URL'], - 'duration': int_or_none(a.attrib.get('length')), - 'tbr': int_or_none(a.attrib.get('bitrate')), - 'height': int_or_none(a.attrib.get('height')), - 'width': int_or_none(a.attrib.get('width')), - } for a in doc.findall('.//AdditionalAssets/asset')] - - return { - '_type': 'playlist', - 'id': pl_id, - 'title': title, - 'entries': entries, - } diff --git a/youtube_dl/extractor/servus.py b/youtube_dl/extractor/servus.py index e579d42cf..9401bf2cf 100644 --- a/youtube_dl/extractor/servus.py +++ b/youtube_dl/extractor/servus.py @@ -7,9 +7,18 @@ from .common import InfoExtractor class ServusIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?: + servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)| + servustv\.com/videos + ) + /(?P<id>[aA]{2}-\w+|\d+-\d+) + ''' _TESTS = [{ - 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', + # new URL schema + 'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/', 'md5': '3e1dd16775aa8d5cbef23628cfffc1f4', 'info_dict': { 'id': 'AA-1T6VBU5PW1W12', @@ -19,6 +28,10 @@ class ServusIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg', } }, { + # old URL schema + 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', + 'only_matching': True, + }, { 'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/', 'only_matching': True, }, { diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index ff575f592..02295d1a4 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -1,13 +1,18 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_b64decode +from ..compat import ( + compat_b64decode, + compat_urllib_parse_unquote_plus, +) from ..utils import ( determine_ext, ExtractorError, int_or_none, + js_to_json, KNOWN_EXTENSIONS, parse_filesize, + rot47, url_or_none, urlencode_postdata, ) @@ -112,16 +117,22 @@ class VivoIE(SharedBaseIE): webpage, 'filesize', fatal=False)) def _extract_video_url(self, webpage, video_id, url): - def decode_url(encoded_url): + def decode_url_old(encoded_url): return compat_b64decode(encoded_url).decode('utf-8') - stream_url = url_or_none(decode_url(self._search_regex( + stream_url = self._search_regex( r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, - 'stream url', default=None, group='url'))) + 'stream url', default=None, group='url') + if stream_url: + stream_url = url_or_none(decode_url_old(stream_url)) if stream_url: return stream_url - return self._parse_json( + + def decode_url(encoded_url): + return rot47(compat_urllib_parse_unquote_plus(encoded_url)) + + return decode_url(self._parse_json( self._search_regex( - r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', - webpage, 'stream', group='url'), - video_id, transform_source=decode_url)[0] + r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage, + 'stream'), + video_id, transform_source=js_to_json)['source']) diff --git a/youtube_dl/extractor/slideslive.py b/youtube_dl/extractor/slideslive.py index ed84322c5..d9ea76831 100644 --- a/youtube_dl/extractor/slideslive.py +++ b/youtube_dl/extractor/slideslive.py @@ -2,7 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import smuggle_url class SlidesLiveIE(InfoExtractor): @@ -14,9 +14,9 @@ class SlidesLiveIE(InfoExtractor): 'info_dict': { 'id': 'LMtgR8ba0b0', 'ext': 'mp4', - 'title': '38902413: external video', - 'description': '3890241320170925-9-1yd6ech.mp4', - 'uploader': 'SlidesLive Administrator', + 'title': 'GCC IA16 backend', + 'description': 'Watch full version of this video at https://slideslive.com/38902413.', + 'uploader': 'SlidesLive Videos - A', 'uploader_id': 'UC62SdArr41t_-_fX40QCLRw', 'upload_date': '20170925', } @@ -24,16 +24,38 @@ class SlidesLiveIE(InfoExtractor): # video_service_name = youtube 'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend', 'only_matching': True, + }, { + # video_service_name = url + 'url': 'https://slideslive.com/38922070/learning-transferable-skills-1', + 'only_matching': True, + }, { + # video_service_name = vimeo + 'url': 'https://slideslive.com/38921896/retrospectives-a-venue-for-selfreflection-in-ml-research-3', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) video_data = self._download_json( - url, video_id, headers={'Accept': 'application/json'}) + 'https://ben.slideslive.com/player/' + video_id, video_id) service_name = video_data['video_service_name'].lower() - if service_name == 'youtube': - yt_video_id = video_data['video_service_id'] - return self.url_result(yt_video_id, 'Youtube', video_id=yt_video_id) + assert service_name in ('url', 'vimeo', 'youtube') + service_id = video_data['video_service_id'] + info = { + 'id': video_id, + 'thumbnail': video_data.get('thumbnail'), + 'url': service_id, + } + if service_name == 'url': + info['title'] = video_data['title'] else: - raise ExtractorError( - 'Unsupported service name: {0}'.format(service_name), expected=True) + info.update({ + '_type': 'url_transparent', + 'ie_key': service_name.capitalize(), + 'title': video_data.get('title'), + }) + if service_name == 'vimeo': + info['url'] = smuggle_url( + 'https://player.vimeo.com/video/' + service_id, + {'http_headers': {'Referer': url}}) + return info diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 05538f3d6..a1372d389 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -9,16 +9,18 @@ from .common import ( SearchInfoExtractor ) from ..compat import ( + compat_HTTPError, + compat_kwargs, compat_str, compat_urlparse, - compat_urllib_parse_urlencode, ) from ..utils import ( + error_to_compat_str, ExtractorError, float_or_none, + HEADRequest, int_or_none, KNOWN_EXTENSIONS, - merge_dicts, mimetype2ext, str_or_none, try_get, @@ -28,6 +30,30 @@ from ..utils import ( ) +class SoundcloudEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?\burl=(?P<id>.+)' + _TEST = { + # from https://www.soundi.fi/uutiset/ennakkokuuntelussa-timo-kaukolammen-station-to-station-to-station-julkaisua-juhlitaan-tanaan-g-livelabissa/ + 'url': 'https://w.soundcloud.com/player/?visual=true&url=https%3A%2F%2Fapi.soundcloud.com%2Fplaylists%2F922213810&show_artwork=true&maxwidth=640&maxheight=960&dnt=1&secret_token=s-ziYey', + 'only_matching': True, + } + + @staticmethod + def _extract_urls(webpage): + return [m.group('url') for m in re.finditer( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', + webpage)] + + def _real_extract(self, url): + query = compat_urlparse.parse_qs( + compat_urlparse.urlparse(url).query) + api_url = query['url'][0] + secret_token = query.get('secret_token') + if secret_token: + api_url = update_url_query(api_url, {'secret_token': secret_token[0]}) + return self.url_result(api_url) + + class SoundcloudIE(InfoExtractor): """Information extractor for soundcloud.com To access the media, the uid of the song and a stream token @@ -44,9 +70,8 @@ class SoundcloudIE(InfoExtractor): (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) - |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) + |(?:api(?:-v2)?\.soundcloud\.com/tracks/(?P<track_id>\d+) (?:/?\?secret_token=(?P<secret_token>[^&]+))?) - |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' IE_NAME = 'soundcloud' @@ -60,6 +85,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', 'uploader': 'E.T. ExTerrestrial Music', + 'uploader_id': '1571244', 'timestamp': 1349920598, 'upload_date': '20121011', 'duration': 143.216, @@ -70,7 +96,7 @@ class SoundcloudIE(InfoExtractor): 'repost_count': int, } }, - # not streamable song + # not streamable song, preview { 'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', 'info_dict': { @@ -79,6 +105,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Goldrushed', 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', 'uploader': 'The Royal Concept', + 'uploader_id': '9615865', 'timestamp': 1337635207, 'upload_date': '20120521', 'duration': 30, @@ -103,6 +130,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Youtube - Dl Test Video \'\' Ä↭', 'description': 'test chars: \"\'/\\ä↭', 'uploader': 'jaimeMF', + 'uploader_id': '69767071', 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9.927, @@ -123,6 +151,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Youtube - Dl Test Video \'\' Ä↭', 'description': 'test chars: \"\'/\\ä↭', 'uploader': 'jaimeMF', + 'uploader_id': '69767071', 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9.927, @@ -143,6 +172,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Bus Brakes', 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', + 'uploader_id': '73680509', 'timestamp': 1389232924, 'upload_date': '20140109', 'duration': 17.346, @@ -163,6 +193,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', 'uploader': 'Ori Uplift Music', + 'uploader_id': '12563093', 'timestamp': 1504206263, 'upload_date': '20170831', 'duration': 7449.096, @@ -183,6 +214,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Sideways (Prod. Mad Real)', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'uploader': 'garyvee', + 'uploader_id': '2366352', 'timestamp': 1488152409, 'upload_date': '20170226', 'duration': 207.012, @@ -206,7 +238,8 @@ class SoundcloudIE(InfoExtractor): 'ext': 'mp3', 'title': 'Mezzo Valzer', 'description': 'md5:4138d582f81866a530317bae316e8b61', - 'uploader': 'Giovanni Sarani', + 'uploader': 'Micronie', + 'uploader_id': '3352531', 'timestamp': 1551394171, 'upload_date': '20190228', 'duration': 180.157, @@ -221,114 +254,124 @@ class SoundcloudIE(InfoExtractor): } ] - _CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI' + _API_BASE = 'https://api.soundcloud.com/' + _API_V2_BASE = 'https://api-v2.soundcloud.com/' + _BASE_URL = 'https://soundcloud.com/' + _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' + + _ARTWORK_MAP = { + 'mini': 16, + 'tiny': 20, + 'small': 32, + 'badge': 47, + 't67x67': 67, + 'large': 100, + 't300x300': 300, + 'crop': 400, + 't500x500': 500, + 'original': 0, + } - @staticmethod - def _extract_urls(webpage): - return [m.group('url') for m in re.finditer( - r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', - webpage)] + def _store_client_id(self, client_id): + self._downloader.cache.store('soundcloud', 'client_id', client_id) + + def _update_client_id(self): + webpage = self._download_webpage('https://soundcloud.com/', None) + for src in reversed(re.findall(r'<script[^>]+src="([^"]+)"', webpage)): + script = self._download_webpage(src, None, fatal=False) + if script: + client_id = self._search_regex( + r'client_id\s*:\s*"([0-9a-zA-Z]{32})"', + script, 'client id', default=None) + if client_id: + self._CLIENT_ID = client_id + self._store_client_id(client_id) + return + raise ExtractorError('Unable to extract client id') + + def _download_json(self, *args, **kwargs): + non_fatal = kwargs.get('fatal') is False + if non_fatal: + del kwargs['fatal'] + query = kwargs.get('query', {}).copy() + for _ in range(2): + query['client_id'] = self._CLIENT_ID + kwargs['query'] = query + try: + return super(SoundcloudIE, self)._download_json(*args, **compat_kwargs(kwargs)) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + self._store_client_id(None) + self._update_client_id() + continue + elif non_fatal: + self._downloader.report_warning(error_to_compat_str(e)) + return False + raise + + def _real_initialize(self): + self._CLIENT_ID = self._downloader.cache.load('soundcloud', 'client_id') or 'YUKXoArFcqrlQn9tfNHvvyfnDISj04zk' @classmethod def _resolv_url(cls, url): - return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID + return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url - def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None): + def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2): track_id = compat_str(info['id']) title = info['title'] - name = full_title or track_id - if quiet: - self.report_extraction(name) - thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') - if isinstance(thumbnail, compat_str): - thumbnail = thumbnail.replace('-large', '-t500x500') - username = try_get(info, lambda x: x['user']['username'], compat_str) - - def extract_count(key): - return int_or_none(info.get('%s_count' % key)) - - like_count = extract_count('favoritings') - if like_count is None: - like_count = extract_count('likes') - - result = { - 'id': track_id, - 'uploader': username, - 'timestamp': unified_timestamp(info.get('created_at')), - 'title': title, - 'description': info.get('description'), - 'thumbnail': thumbnail, - 'duration': float_or_none(info.get('duration'), 1000), - 'webpage_url': info.get('permalink_url'), - 'license': info.get('license'), - 'view_count': extract_count('playback'), - 'like_count': like_count, - 'comment_count': extract_count('comment'), - 'repost_count': extract_count('reposts'), - 'genre': info.get('genre'), - } + track_base_url = self._API_BASE + 'tracks/%s' % track_id format_urls = set() formats = [] query = {'client_id': self._CLIENT_ID} - if secret_token is not None: + if secret_token: query['secret_token'] = secret_token - if info.get('downloadable', False): - # We can build a direct link to the song + + if info.get('downloadable') and info.get('has_downloads_left'): format_url = update_url_query( - 'https://api.soundcloud.com/tracks/%s/download' % track_id, query) + info.get('download_url') or track_base_url + '/download', query) format_urls.add(format_url) + if version == 2: + v1_info = self._download_json( + track_base_url, track_id, query=query, fatal=False) or {} + else: + v1_info = info formats.append({ 'format_id': 'download', - 'ext': info.get('original_format', 'mp3'), + 'ext': v1_info.get('original_format') or 'mp3', + 'filesize': int_or_none(v1_info.get('original_content_size')), 'url': format_url, - 'vcodec': 'none', 'preference': 10, }) - # Old API, does not work for some tracks (e.g. - # https://soundcloud.com/giovannisarani/mezzo-valzer) - format_dict = self._download_json( - 'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id, - track_id, 'Downloading track url', query=query, fatal=False) + def invalid_url(url): + return not url or url in format_urls - if format_dict: - for key, stream_url in format_dict.items(): - if stream_url in format_urls: - continue - format_urls.add(stream_url) - ext, abr = 'mp3', None - mobj = re.search(r'_([^_]+)_(\d+)_url', key) - if mobj: - ext, abr = mobj.groups() - abr = int(abr) - if key.startswith('http'): - stream_formats = [{ - 'format_id': key, - 'ext': ext, - 'url': stream_url, - }] - elif key.startswith('rtmp'): - # The url doesn't have an rtmp app, we have to extract the playpath - url, path = stream_url.split('mp3:', 1) - stream_formats = [{ - 'format_id': key, - 'url': url, - 'play_path': 'mp3:' + path, - 'ext': 'flv', - }] - elif key.startswith('hls'): - stream_formats = self._extract_m3u8_formats( - stream_url, track_id, ext, entry_protocol='m3u8_native', - m3u8_id=key, fatal=False) - else: - continue - - if abr: - for f in stream_formats: - f['abr'] = abr - - formats.extend(stream_formats) + def add_format(f, protocol, is_preview=False): + mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url) + if mobj: + for k, v in mobj.groupdict().items(): + if not f.get(k): + f[k] = v + format_id_list = [] + if protocol: + format_id_list.append(protocol) + for k in ('ext', 'abr'): + v = f.get(k) + if v: + format_id_list.append(v) + preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url']) + if preview: + format_id_list.append('preview') + abr = f.get('abr') + if abr: + f['abr'] = int(abr) + f.update({ + 'format_id': '_'.join(format_id_list), + 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', + 'preference': -10 if preview else None, + }) + formats.append(f) # New API transcodings = try_get( @@ -340,126 +383,174 @@ class SoundcloudIE(InfoExtractor): if not format_url: continue stream = self._download_json( - update_url_query(format_url, query), track_id, fatal=False) + format_url, track_id, query=query, fatal=False) if not isinstance(stream, dict): continue stream_url = url_or_none(stream.get('url')) - if not stream_url: - continue - if stream_url in format_urls: + if invalid_url(stream_url): continue format_urls.add(stream_url) - protocol = try_get(t, lambda x: x['format']['protocol'], compat_str) + stream_format = t.get('format') or {} + protocol = stream_format.get('protocol') if protocol != 'hls' and '/hls' in format_url: protocol = 'hls' ext = None preset = str_or_none(t.get('preset')) if preset: ext = preset.split('_')[0] - if ext not in KNOWN_EXTENSIONS: - mimetype = try_get( - t, lambda x: x['format']['mime_type'], compat_str) - ext = mimetype2ext(mimetype) or 'mp3' - format_id_list = [] - if protocol: - format_id_list.append(protocol) - format_id_list.append(ext) - format_id = '_'.join(format_id_list) - formats.append({ + if ext not in KNOWN_EXTENSIONS: + ext = mimetype2ext(stream_format.get('mime_type')) + add_format({ 'url': stream_url, - 'format_id': format_id, 'ext': ext, - 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', - }) + }, 'http' if protocol == 'progressive' else protocol, + t.get('snipped') or '/preview/' in format_url) + + if not formats: + # Old API, does not work for some tracks (e.g. + # https://soundcloud.com/giovannisarani/mezzo-valzer) + # and might serve preview URLs (e.g. + # http://www.soundcloud.com/snbrn/ele) + format_dict = self._download_json( + track_base_url + '/streams', track_id, + 'Downloading track url', query=query, fatal=False) or {} + + for key, stream_url in format_dict.items(): + if invalid_url(stream_url): + continue + format_urls.add(stream_url) + mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key) + if mobj: + protocol, ext, abr = mobj.groups() + add_format({ + 'abr': abr, + 'ext': ext, + 'url': stream_url, + }, protocol) if not formats: # We fallback to the stream_url in the original info, this # cannot be always used, sometimes it can give an HTTP 404 error - formats.append({ - 'format_id': 'fallback', - 'url': update_url_query(info['stream_url'], query), - 'ext': 'mp3', - }) - self._check_formats(formats, track_id) + urlh = self._request_webpage( + HEADRequest(info.get('stream_url') or track_base_url + '/stream'), + track_id, query=query, fatal=False) + if urlh: + stream_url = urlh.geturl() + if not invalid_url(stream_url): + add_format({'url': stream_url}, 'http') for f in formats: f['vcodec'] = 'none' self._sort_formats(formats) - result['formats'] = formats - return result + user = info.get('user') or {} + + thumbnails = [] + artwork_url = info.get('artwork_url') + thumbnail = artwork_url or user.get('avatar_url') + if isinstance(thumbnail, compat_str): + if re.search(self._IMAGE_REPL_RE, thumbnail): + for image_id, size in self._ARTWORK_MAP.items(): + i = { + 'id': image_id, + 'url': re.sub(self._IMAGE_REPL_RE, '-%s.jpg' % image_id, thumbnail), + } + if image_id == 'tiny' and not artwork_url: + size = 18 + elif image_id == 'original': + i['preference'] = 10 + if size: + i.update({ + 'width': size, + 'height': size, + }) + thumbnails.append(i) + else: + thumbnails = [{'url': thumbnail}] + + def extract_count(key): + return int_or_none(info.get('%s_count' % key)) + + return { + 'id': track_id, + 'uploader': user.get('username'), + 'uploader_id': str_or_none(user.get('id')) or user.get('permalink'), + 'uploader_url': user.get('permalink_url'), + 'timestamp': unified_timestamp(info.get('created_at')), + 'title': title, + 'description': info.get('description'), + 'thumbnails': thumbnails, + 'duration': float_or_none(info.get('duration'), 1000), + 'webpage_url': info.get('permalink_url'), + 'license': info.get('license'), + 'view_count': extract_count('playback'), + 'like_count': extract_count('favoritings') or extract_count('likes'), + 'comment_count': extract_count('comment'), + 'repost_count': extract_count('reposts'), + 'genre': info.get('genre'), + 'formats': formats + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) + mobj = re.match(self._VALID_URL, url) track_id = mobj.group('track_id') - new_info = {} - if track_id is not None: - info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID + query = {} + if track_id: + info_json_url = self._API_V2_BASE + 'tracks/' + track_id full_title = track_id token = mobj.group('secret_token') if token: - info_json_url += '&secret_token=' + token - elif mobj.group('player'): - query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - real_url = query['url'][0] - # If the token is in the query of the original url we have to - # manually add it - if 'secret_token' in query: - real_url += '?secret_token=' + query['secret_token'][0] - return self.url_result(real_url) + query['secret_token'] = token else: - # extract uploader (which is in the url) - uploader = mobj.group('uploader') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group('title') + full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title') token = mobj.group('token') - full_title = resolve_title = '%s/%s' % (uploader, slug_title) if token: resolve_title += '/%s' % token + info_json_url = self._resolv_url(self._BASE_URL + resolve_title) - webpage = self._download_webpage(url, full_title, fatal=False) - if webpage: - entries = self._parse_json( - self._search_regex( - r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage, - 'data', default='[]'), full_title, fatal=False) - if entries: - for e in entries: - if not isinstance(e, dict): - continue - if e.get('id') != 67: - continue - data = try_get(e, lambda x: x['data'][0], dict) - if data: - new_info = data - break - info_json_url = self._resolv_url( - 'https://soundcloud.com/%s' % resolve_title) - - # Contains some additional info missing from new_info + version = 2 info = self._download_json( - info_json_url, full_title, 'Downloading info JSON') + info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False) + if not info: + info = self._download_json( + info_json_url.replace(self._API_V2_BASE, self._API_BASE), + full_title, 'Downloading info JSON', query=query) + version = 1 - return self._extract_info_dict( - merge_dicts(info, new_info), full_title, secret_token=token) + return self._extract_info_dict(info, full_title, token, version) class SoundcloudPlaylistBaseIE(SoundcloudIE): - @staticmethod - def _extract_id(e): - return compat_str(e['id']) if e.get('id') else None - - def _extract_track_entries(self, tracks): - return [ - self.url_result( - track['permalink_url'], SoundcloudIE.ie_key(), - video_id=self._extract_id(track)) - for track in tracks if track.get('permalink_url')] + def _extract_set(self, playlist, token=None): + playlist_id = compat_str(playlist['id']) + tracks = playlist.get('tracks') or [] + if not all([t.get('permalink_url') for t in tracks]) and token: + tracks = self._download_json( + self._API_V2_BASE + 'tracks', playlist_id, + 'Downloading tracks', query={ + 'ids': ','.join([compat_str(t['id']) for t in tracks]), + 'playlistId': playlist_id, + 'playlistSecretToken': token, + }) + entries = [] + for track in tracks: + track_id = str_or_none(track.get('id')) + url = track.get('permalink_url') + if not url: + if not track_id: + continue + url = self._API_V2_BASE + 'tracks/' + track_id + if token: + url += '?secret_token=' + token + entries.append(self.url_result( + url, SoundcloudIE.ie_key(), track_id)) + return self.playlist_result( + entries, playlist_id, + playlist.get('title'), + playlist.get('description')) class SoundcloudSetIE(SoundcloudPlaylistBaseIE): @@ -470,6 +561,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): 'info_dict': { 'id': '2284613', 'title': 'The Royal Concept EP', + 'description': 'md5:71d07087c7a449e8941a70a29e34671e', }, 'playlist_mincount': 5, }, { @@ -480,54 +572,38 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - # extract uploader (which is in the url) - uploader = mobj.group('uploader') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group('slug_title') - full_title = '%s/sets/%s' % (uploader, slug_title) - url = 'https://soundcloud.com/%s/sets/%s' % (uploader, slug_title) - + full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title') token = mobj.group('token') if token: full_title += '/' + token - url += '/' + token - resolv_url = self._resolv_url(url) - info = self._download_json(resolv_url, full_title) + info = self._download_json(self._resolv_url( + self._BASE_URL + full_title), full_title) if 'errors' in info: msgs = (compat_str(err['error_message']) for err in info['errors']) raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) - entries = self._extract_track_entries(info['tracks']) - - return { - '_type': 'playlist', - 'entries': entries, - 'id': '%s' % info['id'], - 'title': info['title'], - } - + return self._extract_set(info, token) -class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): - _API_V2_BASE = 'https://api-v2.soundcloud.com' +class SoundcloudPagedPlaylistBaseIE(SoundcloudIE): def _extract_playlist(self, base_url, playlist_id, playlist_title): COMMON_QUERY = { - 'limit': 50, - 'client_id': self._CLIENT_ID, + 'limit': 2000000000, 'linked_partitioning': '1', } query = COMMON_QUERY.copy() query['offset'] = 0 - next_href = base_url + '?' + compat_urllib_parse_urlencode(query) + next_href = base_url entries = [] for i in itertools.count(): response = self._download_json( - next_href, playlist_id, 'Downloading track page %s' % (i + 1)) + next_href, playlist_id, + 'Downloading track page %s' % (i + 1), query=query) collection = response['collection'] @@ -546,9 +622,8 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): continue return self.url_result( permalink_url, - ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, - video_id=self._extract_id(cand), - video_title=cand.get('title')) + SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + str_or_none(cand.get('id')), cand.get('title')) for e in collection: entry = resolve_entry((e, e.get('track'), e.get('playlist'))) @@ -559,11 +634,10 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): if not next_href: break - parsed_next_href = compat_urlparse.urlparse(response['next_href']) - qs = compat_urlparse.parse_qs(parsed_next_href.query) - qs.update(COMMON_QUERY) - next_href = compat_urlparse.urlunparse( - parsed_next_href._replace(query=compat_urllib_parse_urlencode(qs, True))) + next_href = response['next_href'] + parsed_next_href = compat_urlparse.urlparse(next_href) + query = compat_urlparse.parse_qs(parsed_next_href.query) + query.update(COMMON_QUERY) return { '_type': 'playlist', @@ -609,7 +683,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'url': 'https://soundcloud.com/jcv246/sets', 'info_dict': { 'id': '12982173', - 'title': 'Jordi / cv (Playlists)', + 'title': 'Jordi / cv (Sets)', }, 'playlist_mincount': 2, }, { @@ -636,39 +710,29 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): }] _BASE_URL_MAP = { - 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - } - - _TITLE_MAP = { - 'all': 'All', - 'tracks': 'Tracks', - 'albums': 'Albums', - 'sets': 'Playlists', - 'reposts': 'Reposts', - 'likes': 'Likes', - 'spotlight': 'Spotlight', + 'all': 'stream/users/%s', + 'tracks': 'users/%s/tracks', + 'albums': 'users/%s/albums', + 'sets': 'users/%s/playlists', + 'reposts': 'stream/users/%s/reposts', + 'likes': 'users/%s/likes', + 'spotlight': 'users/%s/spotlight', } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) uploader = mobj.group('user') - url = 'https://soundcloud.com/%s/' % uploader - resolv_url = self._resolv_url(url) user = self._download_json( - resolv_url, uploader, 'Downloading user info') + self._resolv_url(self._BASE_URL + uploader), + uploader, 'Downloading user info') resource = mobj.group('rsrc') or 'all' return self._extract_playlist( - self._BASE_URL_MAP[resource] % user['id'], compat_str(user['id']), - '%s (%s)' % (user['username'], self._TITLE_MAP[resource])) + self._API_V2_BASE + self._BASE_URL_MAP[resource] % user['id'], + str_or_none(user.get('id')), + '%s (%s)' % (user['username'], resource.capitalize())) class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): @@ -678,7 +742,7 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): 'url': 'https://soundcloud.com/stations/track/officialsundial/your-text', 'info_dict': { 'id': '286017854', - 'title': 'Track station: your-text', + 'title': 'Track station: your text', }, 'playlist_mincount': 47, }] @@ -686,19 +750,17 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): def _real_extract(self, url): track_name = self._match_id(url) - webpage = self._download_webpage(url, track_name) - + track = self._download_json(self._resolv_url(url), track_name) track_id = self._search_regex( - r'soundcloud:track-stations:(\d+)', webpage, 'track id') + r'soundcloud:track-stations:(\d+)', track['id'], 'track id') return self._extract_playlist( - '%s/stations/soundcloud:track-stations:%s/tracks' - % (self._API_V2_BASE, track_id), - track_id, 'Track station: %s' % track_name) + self._API_V2_BASE + 'stations/%s/tracks' % track['id'], + track_id, 'Track station: %s' % track['title']) class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): - _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' + _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' IE_NAME = 'soundcloud:playlist' _TESTS = [{ 'url': 'https://api.soundcloud.com/playlists/4110309', @@ -713,29 +775,17 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) playlist_id = mobj.group('id') - base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id) - data_dict = { - 'client_id': self._CLIENT_ID, - } + query = {} token = mobj.group('token') - if token: - data_dict['secret_token'] = token + query['secret_token'] = token - data = compat_urllib_parse_urlencode(data_dict) data = self._download_json( - base_url + data, playlist_id, 'Downloading playlist') + self._API_V2_BASE + 'playlists/' + playlist_id, + playlist_id, 'Downloading playlist', query=query) - entries = self._extract_track_entries(data['tracks']) - - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': data.get('title'), - 'description': data.get('description'), - 'entries': entries, - } + return self._extract_set(data, token) class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): @@ -753,18 +803,17 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): _SEARCH_KEY = 'scsearch' _MAX_RESULTS_PER_PAGE = 200 _DEFAULT_RESULTS_PER_PAGE = 50 - _API_V2_BASE = 'https://api-v2.soundcloud.com' def _get_collection(self, endpoint, collection_id, **query): limit = min( query.get('limit', self._DEFAULT_RESULTS_PER_PAGE), self._MAX_RESULTS_PER_PAGE) - query['limit'] = limit - query['client_id'] = self._CLIENT_ID - query['linked_partitioning'] = '1' - query['offset'] = 0 - data = compat_urllib_parse_urlencode(query) - next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data) + query.update({ + 'limit': limit, + 'linked_partitioning': 1, + 'offset': 0, + }) + next_url = update_url_query(self._API_V2_BASE + endpoint, query) collected_results = 0 @@ -791,5 +840,5 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): break def _get_n_results(self, query, n): - tracks = self._get_collection('/search/tracks', query, limit=n, q=query) + tracks = self._get_collection('search/tracks', query, limit=n, q=query) return self.playlist_result(tracks, playlist_title=query) diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index e040ada29..61ca902ce 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + determine_ext, ExtractorError, merge_dicts, orderedSet, @@ -64,7 +65,7 @@ class SpankBangIE(InfoExtractor): url.replace('/%s/embed' % video_id, '/%s/video' % video_id), video_id, headers={'Cookie': 'country=US'}) - if re.search(r'<[^>]+\bid=["\']video_removed', webpage): + if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage): raise ExtractorError( 'Video %s is not available' % video_id, expected=True) @@ -75,11 +76,20 @@ class SpankBangIE(InfoExtractor): if not f_url: return f = parse_resolution(format_id) - f.update({ - 'url': f_url, - 'format_id': format_id, - }) - formats.append(f) + ext = determine_ext(f_url) + if format_id.startswith('m3u8') or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + f_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif format_id.startswith('mpd') or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + f_url, video_id, mpd_id='dash', fatal=False)) + elif ext == 'mp4' or f.get('width') or f.get('height'): + f.update({ + 'url': f_url, + 'format_id': format_id, + }) + formats.append(f) STREAM_URL_PREFIX = 'stream_url_' @@ -93,28 +103,22 @@ class SpankBangIE(InfoExtractor): r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'stream key', group='value') - sb_csrf_session = self._get_cookies( - 'https://spankbang.com')['sb_csrf_session'].value - stream = self._download_json( 'https://spankbang.com/api/videos/stream', video_id, 'Downloading stream JSON', data=urlencode_postdata({ 'id': stream_key, 'data': 0, - 'sb_csrf_session': sb_csrf_session, }), headers={ 'Referer': url, - 'X-CSRFToken': sb_csrf_session, + 'X-Requested-With': 'XMLHttpRequest', }) for format_id, format_url in stream.items(): - if format_id.startswith(STREAM_URL_PREFIX): - if format_url and isinstance(format_url, list): - format_url = format_url[0] - extract_format( - format_id[len(STREAM_URL_PREFIX):], format_url) + if format_url and isinstance(format_url, list): + format_url = format_url[0] + extract_format(format_id, format_url) - self._sort_formats(formats) + self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id')) info = self._search_json_ld(webpage, video_id, default={}) diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py index a3c35a899..378fc7568 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -13,36 +13,18 @@ from ..utils import ( class SportDeutschlandIE(InfoExtractor): _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])' _TESTS = [{ - 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0', 'info_dict': { - 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'id': 're-live-deutsche-meisterschaften-2020-halbfinals', 'ext': 'mp4', - 'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', - 'categories': ['Badminton'], + 'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals', + 'categories': ['Badminton-Deutschland'], 'view_count': int, - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': r're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV', + 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', 'timestamp': int, - 'upload_date': 're:^201408[23][0-9]$', + 'upload_date': '20200201', + 'description': 're:.*', # meaningless description for THIS video }, - 'params': { - 'skip_download': 'Live stream', - }, - }, { - 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', - 'info_dict': { - 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', - 'ext': 'mp4', - 'upload_date': '20140825', - 'description': 'md5:60a20536b57cee7d9a4ec005e8687504', - 'timestamp': 1408976060, - 'duration': 2732, - 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee', - 'thumbnail': r're:^https?://.*\.jpg$', - 'view_count': int, - 'categories': ['Li-Ning Badminton WM 2014'], - - } }] def _real_extract(self, url): @@ -50,7 +32,7 @@ class SportDeutschlandIE(InfoExtractor): video_id = mobj.group('id') sport_id = mobj.group('sport') - api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( + api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( sport_id, video_id) req = sanitized_Request(api_url, headers={ 'Accept': 'application/vnd.vidibus.v2.html+json', diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py index 28baf901c..359dadaa3 100644 --- a/youtube_dl/extractor/srmediathek.py +++ b/youtube_dl/extractor/srmediathek.py @@ -1,14 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -from .ard import ARDMediathekIE +from .ard import ARDMediathekBaseIE from ..utils import ( ExtractorError, get_element_by_attribute, ) -class SRMediathekIE(ARDMediathekIE): +class SRMediathekIE(ARDMediathekBaseIE): IE_NAME = 'sr:mediathek' IE_DESC = 'Saarländischer Rundfunk' _VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)' diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py deleted file mode 100644 index f1e17dd88..000000000 --- a/youtube_dl/extractor/streamango.py +++ /dev/null @@ -1,128 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_chr -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - js_to_json, -) - - -class StreamangoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P<id>[^/?#&]+)' - _TESTS = [{ - 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4', - 'md5': 'e992787515a182f55e38fc97588d802a', - 'info_dict': { - 'id': 'clapasobsptpkdfe', - 'ext': 'mp4', - 'title': '20170315_150006.mp4', - } - }, { - # no og:title - 'url': 'https://streamango.com/embed/foqebrpftarclpob/asdf_asd_2_mp4', - 'info_dict': { - 'id': 'foqebrpftarclpob', - 'ext': 'mp4', - 'title': 'foqebrpftarclpob', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'gone', - }, { - 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4', - 'only_matching': True, - }, { - 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4', - 'only_matching': True, - }, { - 'url': 'https://streamcherry.com/f/clapasobsptpkdfe/', - 'only_matching': True, - }] - - def _real_extract(self, url): - def decrypt_src(encoded, val): - ALPHABET = '=/+9876543210zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA' - encoded = re.sub(r'[^A-Za-z0-9+/=]', '', encoded) - decoded = '' - sm = [None] * 4 - i = 0 - str_len = len(encoded) - while i < str_len: - for j in range(4): - sm[j % 4] = ALPHABET.index(encoded[i]) - i += 1 - char_code = ((sm[0] << 0x2) | (sm[1] >> 0x4)) ^ val - decoded += compat_chr(char_code) - if sm[2] != 0x40: - char_code = ((sm[1] & 0xf) << 0x4) | (sm[2] >> 0x2) - decoded += compat_chr(char_code) - if sm[3] != 0x40: - char_code = ((sm[2] & 0x3) << 0x6) | sm[3] - decoded += compat_chr(char_code) - return decoded - - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - title = self._og_search_title(webpage, default=video_id) - - formats = [] - for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage): - mobj = re.search(r'(src\s*:\s*[^(]+\(([^)]*)\)[\s,]*)', format_) - if mobj is None: - continue - - format_ = format_.replace(mobj.group(0), '') - - video = self._parse_json( - format_, video_id, transform_source=js_to_json, - fatal=False) or {} - - mobj = re.search( - r'([\'"])(?P<src>(?:(?!\1).)+)\1\s*,\s*(?P<val>\d+)', - mobj.group(1)) - if mobj is None: - continue - - src = decrypt_src(mobj.group('src'), int_or_none(mobj.group('val'))) - if not src: - continue - - ext = determine_ext(src, default_ext=None) - if video.get('type') == 'application/dash+xml' or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - src, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'url': src, - 'ext': ext or 'mp4', - 'width': int_or_none(video.get('width')), - 'height': int_or_none(video.get('height')), - 'tbr': int_or_none(video.get('bitrate')), - }) - - if not formats: - error = self._search_regex( - r'<p[^>]+\bclass=["\']lead[^>]+>(.+?)</p>', webpage, - 'error', default=None) - if not error and '>Sorry' in webpage: - error = 'Video %s is not available' % video_id - if error: - raise ExtractorError(error, expected=True) - - self._sort_formats(formats) - - return { - 'id': video_id, - 'url': url, - 'title': title, - 'formats': formats, - } diff --git a/youtube_dl/extractor/stretchinternet.py b/youtube_dl/extractor/stretchinternet.py index ae2ac1b42..4dbead2ba 100644 --- a/youtube_dl/extractor/stretchinternet.py +++ b/youtube_dl/extractor/stretchinternet.py @@ -5,44 +5,28 @@ from ..utils import int_or_none class StretchInternetIE(InfoExtractor): - _VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/portal\.htm\?.*?\beventId=(?P<id>\d+)' + _VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/(?:portal|full)\.htm\?.*?\beventId=(?P<id>\d+)' _TEST = { - 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video', + 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=573272&streamType=video', 'info_dict': { - 'id': '313900', + 'id': '573272', 'ext': 'mp4', - 'title': 'Augustana (S.D.) Baseball vs University of Mary', - 'description': 'md5:7578478614aae3bdd4a90f578f787438', - 'timestamp': 1490468400, - 'upload_date': '20170325', + 'title': 'University of Mary Wrestling vs. Upper Iowa', + 'timestamp': 1575668361, + 'upload_date': '20191206', } } def _real_extract(self, url): video_id = self._match_id(url) - stream = self._download_json( - 'https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s' - % video_id, video_id) - - video_url = 'https://%s' % stream['source'] - event = self._download_json( - 'https://neo-client.stretchinternet.com/portal-ws/getEvent.json', - video_id, query={ - 'clientID': 99997, - 'eventID': video_id, - 'token': 'asdf', - })['event'] - - title = event.get('title') or event['mobileTitle'] - description = event.get('customText') - timestamp = int_or_none(event.get('longtime')) + 'https://api.stretchinternet.com/trinity/event/tcg/' + video_id, + video_id)[0] return { 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'url': video_url, + 'title': event['title'], + 'timestamp': int_or_none(event.get('dateCreated'), 1000), + 'url': 'https://' + event['media'][0]['url'], } diff --git a/youtube_dl/extractor/stv.py b/youtube_dl/extractor/stv.py index ccb074cd4..bae8b71f4 100644 --- a/youtube_dl/extractor/stv.py +++ b/youtube_dl/extractor/stv.py @@ -4,15 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_parse_qs, - compat_urllib_parse_urlparse -) from ..utils import ( - extract_attributes, + compat_str, float_or_none, int_or_none, - str_or_none, ) @@ -20,20 +15,20 @@ class STVPlayerIE(InfoExtractor): IE_NAME = 'stv:player' _VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})' _TEST = { - 'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/', - 'md5': '2ad867d4afd641fa14187596e0fbc91b', + 'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/', + 'md5': '5adf9439c31d554f8be0707c7abe7e0a', 'info_dict': { - 'id': '6016487034001', + 'id': '5333973339001', 'ext': 'mp4', - 'upload_date': '20190321', - 'title': 'Interview with the cast ahead of new Victoria', - 'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.', - 'timestamp': 1553179628, + 'upload_date': '20170301', + 'title': '60 seconds on set with Laura Norton', + 'description': "How many questions can Laura - a.k.a Kerry Wyatt - answer in 60 seconds? Let\'s find out!", + 'timestamp': 1488388054, 'uploader_id': '1486976045', }, 'skip': 'this resource is unavailable outside of the UK', } - _PUBLISHER_ID = '1486976045' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1486976045/default_default/index.html?videoId=%s' _PTYPE_MAP = { 'episode': 'episodes', 'video': 'shortform', @@ -41,54 +36,32 @@ class STVPlayerIE(InfoExtractor): def _real_extract(self, url): ptype, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) + resp = self._download_json( + 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], video_id), + video_id) - qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex( - r'itemprop="embedURL"[^>]+href="([^"]+)', - webpage, 'embed URL', default=None)).query) - publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID + result = resp['results'] + video = result['video'] + video_id = compat_str(video['id']) - player_attr = extract_attributes(self._search_regex( - r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {} + subtitles = {} + _subtitles = result.get('_subtitles') or {} + for ext, sub_url in _subtitles.items(): + subtitles.setdefault('en', []).append({ + 'ext': 'vtt' if ext == 'webvtt' else ext, + 'url': sub_url, + }) - info = {} - duration = ref_id = series = video_id = None - api_ref_id = player_attr.get('data-player-api-refid') - if api_ref_id: - resp = self._download_json( - 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id), - api_ref_id, fatal=False) - if resp: - result = resp.get('results') or {} - video = result.get('video') or {} - video_id = str_or_none(video.get('id')) - ref_id = video.get('guid') - duration = video.get('length') - programme = result.get('programme') or {} - series = programme.get('name') or programme.get('shortName') - subtitles = {} - _subtitles = result.get('_subtitles') or {} - for ext, sub_url in _subtitles.items(): - subtitles.setdefault('en', []).append({ - 'ext': 'vtt' if ext == 'webvtt' else ext, - 'url': sub_url, - }) - info.update({ - 'description': result.get('summary'), - 'subtitles': subtitles, - 'view_count': int_or_none(result.get('views')), - }) - if not video_id: - video_id = qs.get('videoId', [None])[0] or self._search_regex( - r'<link\s+itemprop="url"\s+href="(\d+)"', - webpage, 'video id', default=None) or 'ref:' + (ref_id or player_attr['data-refid']) + programme = result.get('programme') or {} - info.update({ + return { '_type': 'url_transparent', - 'duration': float_or_none(duration or player_attr.get('data-duration'), 1000), 'id': video_id, + 'url': self.BRIGHTCOVE_URL_TEMPLATE % video_id, + 'description': result.get('summary'), + 'duration': float_or_none(video.get('length'), 1000), + 'subtitles': subtitles, + 'view_count': int_or_none(result.get('views')), + 'series': programme.get('name') or programme.get('shortName'), 'ie_key': 'BrightcoveNew', - 'series': series or player_attr.get('data-programme-name'), - 'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id), - }) - return info + } diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index 0901c3163..e12389cad 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -4,19 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_parse_qs, - compat_urllib_parse_urlparse, -) +from ..compat import compat_str from ..utils import ( determine_ext, dict_get, int_or_none, - orderedSet, + str_or_none, strip_or_none, try_get, - urljoin, - compat_str, ) @@ -237,23 +232,23 @@ class SVTPlayIE(SVTPlayBaseIE): class SVTSeriesIE(SVTPlayBaseIE): - _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)' + _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?' _TESTS = [{ 'url': 'https://www.svtplay.se/rederiet', 'info_dict': { - 'id': 'rederiet', + 'id': '14445680', 'title': 'Rederiet', - 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e', + 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039', }, 'playlist_mincount': 318, }, { - 'url': 'https://www.svtplay.se/rederiet?tab=sasong2', + 'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680', 'info_dict': { - 'id': 'rederiet-sasong2', + 'id': 'season-2-14445680', 'title': 'Rederiet - Säsong 2', - 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e', + 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039', }, - 'playlist_count': 12, + 'playlist_mincount': 12, }] @classmethod @@ -261,83 +256,87 @@ class SVTSeriesIE(SVTPlayBaseIE): return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url) def _real_extract(self, url): - series_id = self._match_id(url) - - qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) - season_slug = qs.get('tab', [None])[0] - - if season_slug: - series_id += '-%s' % season_slug - - webpage = self._download_webpage( - url, series_id, 'Downloading series page') - - root = self._parse_json( - self._search_regex( - self._SVTPLAY_RE, webpage, 'content', group='json'), - series_id) + series_slug, season_id = re.match(self._VALID_URL, url).groups() + + series = self._download_json( + 'https://api.svt.se/contento/graphql', series_slug, + 'Downloading series page', query={ + 'query': '''{ + listablesBySlug(slugs: ["%s"]) { + associatedContent(include: [productionPeriod, season]) { + items { + item { + ... on Episode { + videoSvtId + } + } + } + id + name + } + id + longDescription + name + shortDescription + } +}''' % series_slug, + })['data']['listablesBySlug'][0] season_name = None entries = [] - for season in root['relatedVideoContent']['relatedVideosAccordion']: + for season in series['associatedContent']: if not isinstance(season, dict): continue - if season_slug: - if season.get('slug') != season_slug: + if season_id: + if season.get('id') != season_id: continue season_name = season.get('name') - videos = season.get('videos') - if not isinstance(videos, list): + items = season.get('items') + if not isinstance(items, list): continue - for video in videos: - content_url = video.get('contentUrl') - if not content_url or not isinstance(content_url, compat_str): + for item in items: + video = item.get('item') or {} + content_id = video.get('videoSvtId') + if not content_id or not isinstance(content_id, compat_str): continue - entries.append( - self.url_result( - urljoin(url, content_url), - ie=SVTPlayIE.ie_key(), - video_title=video.get('title') - )) - - metadata = root.get('metaData') - if not isinstance(metadata, dict): - metadata = {} + entries.append(self.url_result( + 'svt:' + content_id, SVTPlayIE.ie_key(), content_id)) - title = metadata.get('title') - season_name = season_name or season_slug + title = series.get('name') + season_name = season_name or season_id if title and season_name: title = '%s - %s' % (title, season_name) - elif season_slug: - title = season_slug + elif season_id: + title = season_id return self.playlist_result( - entries, series_id, title, metadata.get('description')) + entries, season_id or series.get('id'), title, + dict_get(series, ('longDescription', 'shortDescription'))) class SVTPageIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)' + _VALID_URL = r'https?://(?:www\.)?svt\.se/(?P<path>(?:[^/]+/)*(?P<id>[^/?&#]+))' _TESTS = [{ - 'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', + 'url': 'https://www.svt.se/sport/ishockey/bakom-masken-lehners-kamp-mot-mental-ohalsa', 'info_dict': { - 'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', - 'title': 'GUIDE: Sommarträning du kan göra var och när du vill', + 'id': '25298267', + 'title': 'Bakom masken – Lehners kamp mot mental ohälsa', }, - 'playlist_count': 7, + 'playlist_count': 4, }, { - 'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', + 'url': 'https://www.svt.se/nyheter/utrikes/svenska-andrea-ar-en-mil-fran-branderna-i-kalifornien', 'info_dict': { - 'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', - 'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”', + 'id': '24243746', + 'title': 'Svenska Andrea redo att fly sitt hem i Kalifornien', }, - 'playlist_count': 1, + 'playlist_count': 2, }, { # only programTitle 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', 'info_dict': { - 'id': '2900353', + 'id': '8439V2K', 'ext': 'mp4', 'title': 'Stjärnorna skojar till det - under SVT-intervjun', 'duration': 27, @@ -356,16 +355,26 @@ class SVTPageIE(InfoExtractor): return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url) def _real_extract(self, url): - playlist_id = self._match_id(url) + path, display_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, playlist_id) + article = self._download_json( + 'https://api.svt.se/nss-api/page/' + path, display_id, + query={'q': 'articles'})['articles']['content'][0] - entries = [ - self.url_result( - 'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id) - for video_id in orderedSet(re.findall( - r'data-video-id=["\'](\d+)', webpage))] + entries = [] - title = strip_or_none(self._og_search_title(webpage, default=None)) + def _process_content(content): + if content.get('_type') in ('VIDEOCLIP', 'VIDEOEPISODE'): + video_id = compat_str(content['image']['svtId']) + entries.append(self.url_result( + 'svt:' + video_id, SVTPlayIE.ie_key(), video_id)) - return self.playlist_result(entries, playlist_id, title) + for media in article.get('media', []): + _process_content(media) + + for obj in article.get('structuredBody', []): + _process_content(obj.get('content') or {}) + + return self.playlist_result( + entries, str_or_none(article.get('id')), + strip_or_none(article.get('title'))) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 7d2e34b3b..4316a6962 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -4,7 +4,6 @@ import re from .common import InfoExtractor from .wistia import WistiaIE -from ..compat import compat_str from ..utils import ( clean_html, ExtractorError, @@ -58,7 +57,7 @@ class TeachableBaseIE(InfoExtractor): self._logged_in = True return - login_url = compat_str(urlh.geturl()) + login_url = urlh.geturl() login_form = self._hidden_inputs(login_page) @@ -160,22 +159,28 @@ class TeachableIE(TeachableBaseIE): webpage = self._download_webpage(url, video_id) - wistia_url = WistiaIE._extract_url(webpage) - if not wistia_url: + wistia_urls = WistiaIE._extract_urls(webpage) + if not wistia_urls: if any(re.search(p, webpage) for p in ( r'class=["\']lecture-contents-locked', r'>\s*Lecture contents locked', - r'id=["\']lecture-locked')): + r'id=["\']lecture-locked', + # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313 + r'class=["\'](?:inner-)?lesson-locked', + r'>LESSON LOCKED<')): self.raise_login_required('Lecture contents locked') + raise ExtractorError('Unable to find video URL') title = self._og_search_title(webpage, default=None) - return { + entries = [{ '_type': 'url_transparent', 'url': wistia_url, 'ie_key': WistiaIE.ie_key(), 'title': title, - } + } for wistia_url in wistia_urls] + + return self.playlist_result(entries, video_id, title) class TeachableCourseIE(TeachableBaseIE): diff --git a/youtube_dl/extractor/teachingchannel.py b/youtube_dl/extractor/teachingchannel.py index e89759714..624cdb3ad 100644 --- a/youtube_dl/extractor/teachingchannel.py +++ b/youtube_dl/extractor/teachingchannel.py @@ -1,35 +1,33 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .ooyala import OoyalaIE class TeachingChannelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos/(?P<title>.+)' + _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos?/(?P<id>[^/?&#]+)' _TEST = { 'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution', - 'md5': '3d6361864d7cac20b57c8784da17166f', 'info_dict': { - 'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM', + 'id': '3swwlzkT', 'ext': 'mp4', 'title': 'A History of Teaming', 'description': 'md5:2a9033db8da81f2edffa4c99888140b3', - 'duration': 422.255, + 'duration': 422, + 'upload_date': '20170316', + 'timestamp': 1489691297, }, 'params': { 'skip_download': True, }, - 'add_ie': ['Ooyala'], + 'add_ie': ['JWPlatform'], } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - title = mobj.group('title') - webpage = self._download_webpage(url, title) - ooyala_code = self._search_regex( - r'data-embed-code=\'(.+?)\'', webpage, 'ooyala code') + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + mid = self._search_regex( + r'(?:data-mid=["\']|id=["\']jw-video-player-)([a-zA-Z0-9]{8})', + webpage, 'media id') - return OoyalaIE._build_url_result(ooyala_code) + return self.url_result('jwplatform:' + mid, 'JWPlatform', mid) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 7640cf00a..5793b711f 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -84,6 +84,19 @@ class TeamcocoIE(TurnerBaseIE): 'only_matching': True, } ] + _RECORD_TEMPL = '''id + title + teaser + publishOn + thumb { + preview + } + tags { + name + } + duration + turnerMediaId + turnerMediaAuthToken''' def _graphql_call(self, query_template, object_type, object_id): find_object = 'find' + object_type @@ -98,36 +111,36 @@ class TeamcocoIE(TurnerBaseIE): display_id = self._match_id(url) response = self._graphql_call('''{ - %s(slug: "%s") { + %%s(slug: "%%s") { ... on RecordSlug { record { + %s + } + } + ... on PageSlug { + child { id - title - teaser - publishOn - thumb { - preview - } - file { - url - } - tags { - name - } - duration - turnerMediaId - turnerMediaAuthToken } } ... on NotFoundSlug { status } } -}''', 'Slug', display_id) +}''' % self._RECORD_TEMPL, 'Slug', display_id) if response.get('status'): raise ExtractorError('This video is no longer available.', expected=True) - record = response['record'] + child = response.get('child') + if child: + record = self._graphql_call('''{ + %%s(id: "%%s") { + ... on Video { + %s + } + } +}''' % self._RECORD_TEMPL, 'Record', child['id']) + else: + record = response['record'] video_id = record['id'] info = { @@ -150,25 +163,21 @@ class TeamcocoIE(TurnerBaseIE): 'accessTokenType': 'jws', })) else: - d = self._download_json( + video_sources = self._download_json( 'https://teamcoco.com/_truman/d/' + video_id, - video_id, fatal=False) or {} - video_sources = d.get('meta') or {} - if not video_sources: - video_sources = self._graphql_call('''{ - %s(id: "%s") { - src - } -}''', 'RecordVideoSource', video_id) or {} + video_id)['meta']['src'] + if isinstance(video_sources, dict): + video_sources = video_sources.values() formats = [] get_quality = qualities(['low', 'sd', 'hd', 'uhd']) - for format_id, src in video_sources.get('src', {}).items(): + for src in video_sources: if not isinstance(src, dict): continue src_url = src.get('src') if not src_url: continue + format_id = src.get('label') ext = determine_ext(src_url, mimetype2ext(src.get('type'))) if format_id == 'hls' or ext == 'm3u8': # compat_urllib_parse.urljoin does not work here @@ -190,9 +199,6 @@ class TeamcocoIE(TurnerBaseIE): 'format_id': format_id, 'quality': get_quality(format_id), }) - if not formats: - formats = self._extract_m3u8_formats( - record['file']['url'], video_id, 'mp4', fatal=False) self._sort_formats(formats) info['formats'] = formats diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index d37e1b055..9ba3da341 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -11,6 +11,7 @@ from ..utils import ( determine_ext, int_or_none, str_or_none, + try_get, urljoin, ) @@ -24,7 +25,7 @@ class TelecincoIE(InfoExtractor): 'info_dict': { 'id': '1876350223', 'title': 'Bacalao con kokotxas al pil-pil', - 'description': 'md5:1382dacd32dd4592d478cbdca458e5bb', + 'description': 'md5:716caf5601e25c3c5ab6605b1ae71529', }, 'playlist': [{ 'md5': 'adb28c37238b675dad0f042292f209a7', @@ -56,6 +57,26 @@ class TelecincoIE(InfoExtractor): 'duration': 50, }, }, { + # video in opening's content + 'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html', + 'info_dict': { + 'id': '2907195140', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'description': 'md5:73f340a7320143d37ab895375b2bf13a', + }, + 'playlist': [{ + 'md5': 'adb28c37238b675dad0f042292f209a7', + 'info_dict': { + 'id': 'TpI2EttSDAReWpJ1o0NVh2', + 'ext': 'mp4', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'duration': 1015, + }, + }], + 'params': { + 'skip_download': True, + }, + }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', 'only_matching': True, }, { @@ -135,17 +156,28 @@ class TelecincoIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) article = self._parse_json(self._search_regex( - r'window\.\$REACTBASE_STATE\.article\s*=\s*({.+})', + r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})', webpage, 'article'), display_id)['article'] title = article.get('title') - description = clean_html(article.get('leadParagraph')) + description = clean_html(article.get('leadParagraph')) or '' if article.get('editorialType') != 'VID': entries = [] - for p in article.get('body', []): + body = [article.get('opening')] + body.extend(try_get(article, lambda x: x['body'], list) or []) + for p in body: + if not isinstance(p, dict): + continue content = p.get('content') - if p.get('type') != 'video' or not content: + if not content: + continue + type_ = p.get('type') + if type_ == 'paragraph': + content_str = str_or_none(content) + if content_str: + description += content_str continue - entries.append(self._parse_content(content, url)) + if type_ == 'video' and isinstance(content, dict): + entries.append(self._parse_content(content, url)) return self.playlist_result( entries, str_or_none(article.get('id')), title, description) content = article['opening']['content'] diff --git a/youtube_dl/extractor/telegraaf.py b/youtube_dl/extractor/telegraaf.py index 0f576c1ab..2dc020537 100644 --- a/youtube_dl/extractor/telegraaf.py +++ b/youtube_dl/extractor/telegraaf.py @@ -4,21 +4,25 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( determine_ext, - remove_end, + int_or_none, + parse_iso8601, + try_get, ) class TelegraafIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P<id>\d+)/[^/]+\.html' + _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/video/(?P<id>\d+)' _TEST = { - 'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html', + 'url': 'https://www.telegraaf.nl/video/734366489/historisch-scheepswrak-slaat-na-100-jaar-los', 'info_dict': { - 'id': '24353229', + 'id': 'gaMItuoSeUg2', 'ext': 'mp4', - 'title': 'Tikibad ontruimd wegens brand', - 'description': 'md5:05ca046ff47b931f9b04855015e163a4', - 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 33, + 'title': 'Historisch scheepswrak slaat na 100 jaar los', + 'description': 'md5:6f53b7c4f55596722ac24d6c0ec00cfb', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 55, + 'timestamp': 1572805527, + 'upload_date': '20191103', }, 'params': { # m3u8 download @@ -27,23 +31,30 @@ class TelegraafIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + article_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + video_id = self._download_json( + 'https://www.telegraaf.nl/graphql', article_id, query={ + 'query': '''{ + article(uid: %s) { + videos { + videoId + } + } +}''' % article_id, + })['data']['article']['videos'][0]['videoId'] - player_url = self._html_search_regex( - r'<iframe[^>]+src="([^"]+")', webpage, 'player URL') - player_page = self._download_webpage( - player_url, video_id, note='Download player webpage') - playlist_url = self._search_regex( - r'playlist\s*:\s*"([^"]+)"', player_page, 'playlist URL') - playlist_data = self._download_json(playlist_url, video_id) + item = self._download_json( + 'https://content.tmgvideo.nl/playlist/item=%s/playlist.json' % video_id, + video_id)['items'][0] + title = item['title'] - item = playlist_data['items'][0] formats = [] - locations = item['locations'] + locations = item.get('locations') or {} for location in locations.get('adaptive', []): - manifest_url = location['src'] + manifest_url = location.get('src') + if not manifest_url: + continue ext = determine_ext(manifest_url) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( @@ -54,25 +65,25 @@ class TelegraafIE(InfoExtractor): else: self.report_warning('Unknown adaptive format %s' % ext) for location in locations.get('progressive', []): + src = try_get(location, lambda x: x['sources'][0]['src']) + if not src: + continue + label = location.get('label') formats.append({ - 'url': location['sources'][0]['src'], - 'width': location.get('width'), - 'height': location.get('height'), - 'format_id': 'http-%s' % location['label'], + 'url': src, + 'width': int_or_none(location.get('width')), + 'height': int_or_none(location.get('height')), + 'format_id': 'http' + ('-%s' % label if label else ''), }) self._sort_formats(formats) - title = remove_end(self._og_search_title(webpage), ' - VIDEO') - description = self._og_search_description(webpage) - duration = item.get('duration') - thumbnail = item.get('poster') - return { 'id': video_id, 'title': title, - 'description': description, + 'description': item.get('description'), 'formats': formats, - 'duration': duration, - 'thumbnail': thumbnail, + 'duration': int_or_none(item.get('duration')), + 'thumbnail': item.get('poster'), + 'timestamp': parse_iso8601(item.get('datecreated'), ' '), } diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py new file mode 100644 index 000000000..dff44a4e2 --- /dev/null +++ b/youtube_dl/extractor/tenplay.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_age_limit, + parse_iso8601, + smuggle_url, +) + + +class TenPlayIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/[^/]+/episodes/[^/]+/[^/]+/(?P<id>tpv\d{6}[a-z]{5})' + _TEST = { + 'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga', + 'info_dict': { + 'id': '6060533435001', + 'ext': 'mp4', + 'title': 'MasterChef - S1 Ep. 1', + 'description': 'md5:4fe7b78e28af8f2d900cd20d900ef95c', + 'age_limit': 10, + 'timestamp': 1240828200, + 'upload_date': '20090427', + 'uploader_id': '2199827728001', + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + } + } + BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s' + + def _real_extract(self, url): + content_id = self._match_id(url) + data = self._download_json( + 'https://10play.com.au/api/video/' + content_id, content_id) + video = data.get('video') or {} + metadata = data.get('metaData') or {} + brightcove_id = video.get('videoId') or metadata['showContentVideoId'] + brightcove_url = smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['AU']}) + + return { + '_type': 'url_transparent', + 'url': brightcove_url, + 'id': content_id, + 'title': video.get('title') or metadata.get('pageContentName') or metadata.get('showContentName'), + 'description': video.get('description'), + 'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')), + 'series': metadata.get('showName'), + 'season': metadata.get('showContentSeason'), + 'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')), + 'ie_key': 'BrightcoveNew', + } diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py index 22d003776..15d4a6932 100644 --- a/youtube_dl/extractor/thesun.py +++ b/youtube_dl/extractor/thesun.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .ooyala import OoyalaIE +from ..utils import extract_attributes class TheSunIE(InfoExtractor): @@ -16,6 +16,7 @@ class TheSunIE(InfoExtractor): }, 'playlist_count': 2, } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' def _real_extract(self, url): article_id = self._match_id(url) @@ -23,10 +24,15 @@ class TheSunIE(InfoExtractor): webpage = self._download_webpage(url, article_id) entries = [] - for ooyala_id in re.findall( - r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)', + for video in re.findall( + r'<video[^>]+data-video-id-pending=[^>]+>', webpage): - entries.append(OoyalaIE._build_url_result(ooyala_id)) + attrs = extract_attributes(video) + video_id = attrs['data-video-id-pending'] + account_id = attrs.get('data-account', '5067014667001') + entries.append(self.url_result( + self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), + 'BrightcoveNew', video_id)) return self.playlist_result( entries, article_id, self._og_search_title(webpage, fatal=False)) diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 6ab147ad7..387f955ee 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -2,43 +2,42 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str -from ..utils import try_get class ThisOldHouseIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)' _TESTS = [{ 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', - 'md5': '568acf9ca25a639f0c4ff905826b662f', 'info_dict': { - 'id': '2REGtUDQ', + 'id': '5dcdddf673c3f956ef5db202', 'ext': 'mp4', 'title': 'How to Build a Storage Bench', 'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.', 'timestamp': 1442548800, 'upload_date': '20150918', - } + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', 'only_matching': True, }, { 'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric', 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench', + 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost', + 'only_matching': True, }] + _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - (r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', - r'id=(["\'])inline-video-player-(?P<id>(?:(?!\1).)+)\1'), - webpage, 'video id', default=None, group='id') - if not video_id: - drupal_settings = self._parse_json(self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings'), display_id) - video_id = try_get( - drupal_settings, lambda x: x['jwplatform']['video_id'], - compat_str) or list(drupal_settings['comScore'])[0] - return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id) + r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})', + webpage, 'video id') + return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id) diff --git a/youtube_dl/extractor/toggle.py b/youtube_dl/extractor/toggle.py index 5e5efda0f..ca2e36efe 100644 --- a/youtube_dl/extractor/toggle.py +++ b/youtube_dl/extractor/toggle.py @@ -17,9 +17,9 @@ from ..utils import ( class ToggleIE(InfoExtractor): IE_NAME = 'toggle' - _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)' _TESTS = [{ - 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', + 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', 'info_dict': { 'id': '343115', 'ext': 'mp4', @@ -33,7 +33,7 @@ class ToggleIE(InfoExtractor): } }, { 'note': 'DRM-protected video', - 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', + 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413', 'info_dict': { 'id': '341413', 'ext': 'wvm', @@ -48,7 +48,7 @@ class ToggleIE(InfoExtractor): }, { # this also tests correct video id extraction 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', - 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', + 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', 'info_dict': { 'id': '332861', 'ext': 'mp4', @@ -65,19 +65,22 @@ class ToggleIE(InfoExtractor): 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', + 'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', + 'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/movies/seven-days/321936', + 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', 'only_matching': True, }, { - 'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'url': 'http://www.mewatch.sg/en/movies/seven-days/321936', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585', + 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'only_matching': True, + }, { + 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585', 'only_matching': True, }] diff --git a/youtube_dl/extractor/trunews.py b/youtube_dl/extractor/trunews.py index b0c7caabf..cca5b5ceb 100644 --- a/youtube_dl/extractor/trunews.py +++ b/youtube_dl/extractor/trunews.py @@ -1,21 +1,12 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - dict_get, - float_or_none, - int_or_none, - unified_timestamp, - update_url_query, - url_or_none, -) class TruNewsIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)' _TEST = { 'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', - 'md5': 'a19c024c3906ff954fac9b96ce66bb08', 'info_dict': { 'id': '5c5a21e65d3c196e1c0020cc', 'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', @@ -28,48 +19,16 @@ class TruNewsIE(InfoExtractor): }, 'add_ie': ['Zype'], } + _ZYPE_TEMPL = 'https://player.zype.com/embed/%s.js?api_key=X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt' def _real_extract(self, url): display_id = self._match_id(url) - video = self._download_json( + zype_id = self._download_json( 'https://api.zype.com/videos', display_id, query={ 'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H', 'per_page': 1, 'active': 'true', 'friendly_title': display_id, - })['response'][0] - - zype_id = video['_id'] - - thumbnails = [] - thumbnails_list = video.get('thumbnails') - if isinstance(thumbnails_list, list): - for thumbnail in thumbnails_list: - if not isinstance(thumbnail, dict): - continue - thumbnail_url = url_or_none(thumbnail.get('url')) - if not thumbnail_url: - continue - thumbnails.append({ - 'url': thumbnail_url, - 'width': int_or_none(thumbnail.get('width')), - 'height': int_or_none(thumbnail.get('height')), - }) - - return { - '_type': 'url_transparent', - 'url': update_url_query( - 'https://player.zype.com/embed/%s.js' % zype_id, - {'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}), - 'ie_key': 'Zype', - 'id': zype_id, - 'display_id': display_id, - 'title': video.get('title'), - 'description': dict_get(video, ('description', 'ott_description', 'short_description')), - 'duration': int_or_none(video.get('duration')), - 'timestamp': unified_timestamp(video.get('published_at')), - 'average_rating': float_or_none(video.get('rating')), - 'view_count': int_or_none(video.get('request_count')), - 'thumbnails': thumbnails, - } + })['response'][0]['_id'] + return self.url_result(self._ZYPE_TEMPL % zype_id, 'Zype', zype_id) diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index edbb0aa69..ae584ad69 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, @@ -151,7 +150,7 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage, urlh = self._download_webpage_handle(url, video_id) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() if 'tumblr.com/safe-mode' in redirect_url or redirect_url.startswith('/safe-mode'): raise ExtractorError( 'This Tumblr may contain sensitive media. ' diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py deleted file mode 100644 index 362318b24..000000000 --- a/youtube_dl/extractor/tutv.py +++ /dev/null @@ -1,36 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import ( - compat_b64decode, - compat_parse_qs, -) - - -class TutvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)' - _TEST = { - 'url': 'http://tu.tv/videos/robots-futbolistas', - 'md5': '0cd9e28ad270488911b0d2a72323395d', - 'info_dict': { - 'id': '2973058', - 'ext': 'mp4', - 'title': 'Robots futbolistas', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') - - data_content = self._download_webpage( - 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') - video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') - - return { - 'id': internal_id, - 'url': video_url, - 'title': self._og_search_title(webpage), - } diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py index d5071e8a5..4a19b9be6 100644 --- a/youtube_dl/extractor/tv2.py +++ b/youtube_dl/extractor/tv2.py @@ -4,13 +4,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, + ExtractorError, int_or_none, float_or_none, js_to_json, parse_iso8601, remove_end, + strip_or_none, + try_get, ) @@ -20,7 +24,7 @@ class TV2IE(InfoExtractor): 'url': 'http://www.tv2.no/v/916509/', 'info_dict': { 'id': '916509', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Se Frode Gryttens hyllest av Steven Gerrard', 'description': 'TV 2 Sportens huspoet tar avskjed med Liverpools kaptein Steven Gerrard.', 'timestamp': 1431715610, @@ -29,22 +33,40 @@ class TV2IE(InfoExtractor): 'view_count': int, 'categories': list, }, - 'params': { - # m3u8 download - 'skip_download': True, - }, } + _API_DOMAIN = 'sumo.tv2.no' + _PROTOCOLS = ('HDS', 'HLS', 'DASH') + _GEO_COUNTRIES = ['NO'] def _real_extract(self, url): video_id = self._match_id(url) + api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id) formats = [] format_urls = [] - for protocol in ('HDS', 'HLS'): - data = self._download_json( - 'http://sumo.tv2.no/api/web/asset/%s/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % (video_id, protocol), - video_id, 'Downloading play JSON')['playback'] - for item in data['items']['item']: + for protocol in self._PROTOCOLS: + try: + data = self._download_json( + api_base + '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol, + video_id, 'Downloading play JSON')['playback'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + error = self._parse_json(e.cause.read().decode(), video_id)['error'] + error_code = error.get('code') + if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION': + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) + elif error_code == 'SESSION_NOT_AUTHENTICATED': + self.raise_login_required() + raise ExtractorError(error['description']) + raise + items = try_get(data, lambda x: x['items']['item']) + if not items: + continue + if not isinstance(items, list): + items = [items] + for item in items: + if not isinstance(item, dict): + continue video_url = item.get('url') if not video_url or video_url in format_urls: continue @@ -57,9 +79,13 @@ class TV2IE(InfoExtractor): formats.extend(self._extract_f4m_formats( video_url, video_id, f4m_id=format_id, fatal=False)) elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id=format_id, fatal=False)) + if not data.get('drmProtected'): + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id=format_id, fatal=False)) + elif ext == 'mpd': + formats.extend(self._extract_mpd_formats( + video_url, video_id, format_id, fatal=False)) elif ext == 'ism' or video_url.endswith('.ism/Manifest'): pass else: @@ -69,34 +95,30 @@ class TV2IE(InfoExtractor): 'tbr': int_or_none(item.get('bitrate')), 'filesize': int_or_none(item.get('fileSize')), }) + if not formats and data.get('drmProtected'): + raise ExtractorError('This video is DRM protected.', expected=True) self._sort_formats(formats) asset = self._download_json( - 'http://sumo.tv2.no/api/web/asset/%s.json' % video_id, - video_id, 'Downloading metadata JSON')['asset'] - + api_base + '.json', video_id, + 'Downloading metadata JSON')['asset'] title = asset['title'] - description = asset.get('description') - timestamp = parse_iso8601(asset.get('createTime')) - duration = float_or_none(asset.get('accurateDuration') or asset.get('duration')) - view_count = int_or_none(asset.get('views')) - categories = asset.get('keywords', '').split(',') thumbnails = [{ 'id': thumbnail.get('@type'), 'url': thumbnail.get('url'), - } for _, thumbnail in asset.get('imageVersions', {}).items()] + } for _, thumbnail in (asset.get('imageVersions') or {}).items()] return { 'id': video_id, 'url': video_url, 'title': title, - 'description': description, + 'description': strip_or_none(asset.get('description')), 'thumbnails': thumbnails, - 'timestamp': timestamp, - 'duration': duration, - 'view_count': view_count, - 'categories': categories, + 'timestamp': parse_iso8601(asset.get('createTime')), + 'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')), + 'view_count': int_or_none(asset.get('views')), + 'categories': asset.get('keywords', '').split(','), 'formats': formats, } @@ -108,7 +130,7 @@ class TV2ArticleIE(InfoExtractor): 'info_dict': { 'id': '6930542', 'title': 'Russen hetses etter pingvintyveri - innrømmer å ha åpnet luken på buret', - 'description': 'md5:339573779d3eea3542ffe12006190954', + 'description': 'De fire siktede nekter fortsatt for å ha stjålet pingvinbabyene, men innrømmer å ha åpnet luken til de små kyllingene.', }, 'playlist_count': 2, }, { @@ -126,7 +148,7 @@ class TV2ArticleIE(InfoExtractor): if not assets: # New embed pattern - for v in re.findall(r'TV2ContentboxVideo\(({.+?})\)', webpage): + for v in re.findall(r'(?s)TV2ContentboxVideo\(({.+?})\)', webpage): video = self._parse_json( v, playlist_id, transform_source=js_to_json, fatal=False) if not video: @@ -143,3 +165,28 @@ class TV2ArticleIE(InfoExtractor): description = remove_end(self._og_search_description(webpage), ' - TV2.no') return self.playlist_result(entries, playlist_id, title, description) + + +class KatsomoIE(TV2IE): + _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv)\.fi/(?:#!/)?(?:[^/]+/[0-9a-z-]+-\d+/[0-9a-z-]+-|[^/]+/\d+/[^/]+/)(?P<id>\d+)' + _TEST = { + 'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321', + 'info_dict': { + 'id': '1181321', + 'ext': 'mp4', + 'title': 'MTV Uutiset Live', + 'description': 'Päätöksen teki Pelicansin hallitus.', + 'timestamp': 1575116484, + 'upload_date': '20191130', + 'duration': 37.12, + 'view_count': int, + 'categories': list, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + _API_DOMAIN = 'api.katsomo.fi' + _PROTOCOLS = ('HLS', 'MPD') + _GEO_COUNTRIES = ['FI'] diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py new file mode 100644 index 000000000..8bda9348d --- /dev/null +++ b/youtube_dl/extractor/tv2dk.py @@ -0,0 +1,154 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + extract_attributes, + js_to_json, + url_or_none, +) + + +class TV2DKIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?: + tvsyd| + tv2ostjylland| + tvmidtvest| + tv2fyn| + tv2east| + tv2lorry| + tv2nord + )\.dk/ + (:[^/]+/)* + (?P<id>[^/?\#&]+) + ''' + _TESTS = [{ + 'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player', + 'info_dict': { + 'id': '0_52jmwa0p', + 'ext': 'mp4', + 'title': '19:30 - 28. okt. 2019', + 'timestamp': 1572290248, + 'upload_date': '20191028', + 'uploader_id': 'tvsyd', + 'duration': 1347, + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Kaltura'], + }, { + 'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi', + 'only_matching': True, + }, { + 'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player', + 'only_matching': True, + }, { + 'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019', + 'only_matching': True, + }, { + 'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof', + 'only_matching': True, + }, { + 'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy', + 'only_matching': True, + }, { + 'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player', + 'only_matching': True, + }, { + 'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + entries = [] + for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage): + video = extract_attributes(video_el) + kaltura_id = video.get('data-entryid') + if not kaltura_id: + continue + partner_id = video.get('data-partnerid') + if not partner_id: + continue + entries.append(self.url_result( + 'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura', + video_id=kaltura_id)) + return self.playlist_result(entries) + + +class TV2DKBornholmPlayIE(InfoExtractor): + _VALID_URL = r'https?://play\.tv2bornholm\.dk/\?.*?\bid=(?P<id>\d+)' + _TEST = { + 'url': 'http://play.tv2bornholm.dk/?area=specifikTV&id=781021', + 'info_dict': { + 'id': '781021', + 'ext': 'mp4', + 'title': '12Nyheder-27.11.19', + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, + data=json.dumps({ + 'playlist_id': video_id, + 'serienavn': '', + }).encode(), headers={ + 'X-Requested-With': 'XMLHttpRequest', + 'Content-Type': 'application/json; charset=UTF-8', + })['d'] + + # TODO: generalize flowplayer + title = self._search_regex( + r'title\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', video, 'title', + group='value') + sources = self._parse_json(self._search_regex( + r'(?s)sources:\s*(\[.+?\]),', video, 'sources'), + video_id, js_to_json) + + formats = [] + srcs = set() + for source in sources: + src = url_or_none(source.get('src')) + if not src: + continue + if src in srcs: + continue + srcs.add(src) + ext = determine_ext(src) + src_type = source.get('type') + if src_type == 'application/x-mpegurl' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + src, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif src_type == 'application/dash+xml' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + src, video_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'url': src, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tv5mondeplus.py b/youtube_dl/extractor/tv5mondeplus.py index 88b6baa31..b7fe082b9 100644 --- a/youtube_dl/extractor/tv5mondeplus.py +++ b/youtube_dl/extractor/tv5mondeplus.py @@ -3,31 +3,51 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - clean_html, determine_ext, extract_attributes, - get_element_by_class, int_or_none, parse_duration, - parse_iso8601, ) class TV5MondePlusIE(InfoExtractor): IE_DESC = 'TV5MONDE+' - _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)' - _TEST = { - 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', - 'md5': '12130fc199f020673138a83466542ec6', + _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)' + _TESTS = [{ + # movie + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit', + 'md5': '8cbde5ea7b296cf635073e27895e227f', 'info_dict': { - 'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', + 'id': '822a4756-0712-7329-1859-a13ac7fd1407', + 'display_id': 'rendez-vous-a-atlit', 'ext': 'mp4', - 'title': 'Tdah, mon amour - Enfants', - 'description': 'md5:230e3aca23115afcf8006d1bece6df74', - 'upload_date': '20170401', - 'timestamp': 1491022860, - } - } + 'title': 'Rendez-vous à Atlit', + 'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb', + 'upload_date': '20200130', + }, + }, { + # series episode + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree', + 'info_dict': { + 'id': '0df7007c-4900-3936-c601-87a13a93a068', + 'display_id': 'c-est-la-vie-ennemie-juree', + 'ext': 'mp4', + 'title': "C'est la vie - Ennemie jurée", + 'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e', + 'upload_date': '20200130', + 'series': "C'est la vie", + 'episode': 'Ennemie jurée', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver', + 'only_matching': True, + }, { + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30', + 'only_matching': True, + }] _GEO_BYPASS = False def _real_extract(self, url): @@ -37,11 +57,7 @@ class TV5MondePlusIE(InfoExtractor): if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage: self.raise_geo_restricted(countries=['FR']) - series = get_element_by_class('video-detail__title', webpage) - title = episode = get_element_by_class( - 'video-detail__subtitle', webpage) or series - if series and series != title: - title = '%s - %s' % (series, title) + title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title') vpl_data = extract_attributes(self._search_regex( r'(<[^>]+class="video_player_loader"[^>]+>)', webpage, 'video player loader')) @@ -65,15 +81,37 @@ class TV5MondePlusIE(InfoExtractor): }) self._sort_formats(formats) + description = self._html_search_regex( + r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage, + 'description', fatal=False) + + series = self._html_search_regex( + r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage, + 'series', default=None) + + if series and series != title: + title = '%s - %s' % (series, title) + + upload_date = self._search_regex( + r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})', + webpage, 'upload date', default=None) + if upload_date: + upload_date = upload_date.replace('_', '') + + video_id = self._search_regex( + (r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', + r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id', + default=display_id) + return { - 'id': display_id, + 'id': video_id, 'display_id': display_id, 'title': title, - 'description': clean_html(get_element_by_class('video-detail__description', webpage)), + 'description': description, 'thumbnail': vpl_data.get('data-image'), 'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)), - 'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)), + 'upload_date': upload_date, 'formats': formats, - 'episode': episode, 'series': series, + 'episode': episode, } diff --git a/youtube_dl/extractor/tva.py b/youtube_dl/extractor/tva.py index 0b863df2f..443f46e8a 100644 --- a/youtube_dl/extractor/tva.py +++ b/youtube_dl/extractor/tva.py @@ -9,8 +9,8 @@ from ..utils import ( class TVAIE(InfoExtractor): - _VALID_URL = r'https?://videos\.tva\.ca/details/_(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)' + _TESTS = [{ 'url': 'https://videos.tva.ca/details/_5596811470001', 'info_dict': { 'id': '5596811470001', @@ -24,7 +24,10 @@ class TVAIE(InfoExtractor): # m3u8 download 'skip_download': True, } - } + }, { + 'url': 'https://video.tva.ca/details/_5596811470001', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s' def _real_extract(self, url): diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 1d66eeaff..74d14049b 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -17,8 +17,8 @@ class TwentyFourVideoIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?P<host> - (?:(?:www|porno)\.)?24video\. - (?:net|me|xxx|sexy?|tube|adult|site) + (?:(?:www|porno?)\.)?24video\. + (?:net|me|xxx|sexy?|tube|adult|site|vip) )/ (?: video/(?:(?:view|xml)/)?| @@ -59,6 +59,12 @@ class TwentyFourVideoIE(InfoExtractor): }, { 'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle', 'only_matching': True, + }, { + 'url': 'https://www.24video.vip/video/view/1044982', + 'only_matching': True, + }, { + 'url': 'https://porn.24video.net/video/2640421-vsya-takay', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 0500e33a6..0db2dca41 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -17,12 +17,10 @@ from ..compat import ( from ..utils import ( clean_html, ExtractorError, - float_or_none, int_or_none, orderedSet, parse_duration, parse_iso8601, - qualities, try_get, unified_timestamp, update_url_query, @@ -248,7 +246,7 @@ class TwitchVodIE(TwitchItemBaseIE): https?:// (?: (?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v(?:ideo)?|videos)/| - player\.twitch\.tv/\?.*?\bvideo=v + player\.twitch\.tv/\?.*?\bvideo=v? ) (?P<id>\d+) ''' @@ -306,6 +304,9 @@ class TwitchVodIE(TwitchItemBaseIE): }, { 'url': 'https://www.twitch.tv/northernlion/video/291940395', 'only_matching': True, + }, { + 'url': 'https://player.twitch.tv/?video=480452374', + 'only_matching': True, }] def _real_extract(self, url): @@ -324,6 +325,7 @@ class TwitchVodIE(TwitchItemBaseIE): 'allow_audio_only': 'true', 'allow_spectre': 'true', 'player': 'twitchweb', + 'playlist_include_framerate': 'true', 'nauth': access_token['token'], 'nauthsig': access_token['sig'], })), @@ -341,9 +343,8 @@ class TwitchVodIE(TwitchItemBaseIE): info['subtitles'] = { 'rechat': [{ 'url': update_url_query( - 'https://rechat.twitch.tv/rechat-messages', { - 'video_id': 'v%s' % item_id, - 'start': info['timestamp'], + 'https://api.twitch.tv/v5/videos/%s/comments' % item_id, { + 'client_id': self._CLIENT_ID, }), 'ext': 'json', }], @@ -574,8 +575,8 @@ class TwitchStreamIE(TwitchBaseIE): channel_id = self._match_id(url) stream = self._call_api( - 'kraken/streams/%s?stream_type=all' % channel_id, channel_id, - 'Downloading stream JSON').get('stream') + 'kraken/streams/%s?stream_type=all' % channel_id.lower(), + channel_id, 'Downloading stream JSON').get('stream') if not stream: raise ExtractorError('%s is offline' % channel_id, expected=True) @@ -596,6 +597,7 @@ class TwitchStreamIE(TwitchBaseIE): 'allow_spectre': 'true', 'p': random.randint(1000000, 10000000), 'player': 'twitchweb', + 'playlist_include_framerate': 'true', 'segment_preference': '4', 'sig': access_token['sig'].encode('utf-8'), 'token': access_token['token'].encode('utf-8'), @@ -641,7 +643,7 @@ class TwitchStreamIE(TwitchBaseIE): class TwitchClipsIE(TwitchBaseIE): IE_NAME = 'twitch:clips' - _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:[^/]+/)*|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat', @@ -664,68 +666,89 @@ class TwitchClipsIE(TwitchBaseIE): }, { 'url': 'https://www.twitch.tv/sergeynixon/clip/StormyThankfulSproutFutureMan', 'only_matching': True, + }, { + 'url': 'https://clips.twitch.tv/embed?clip=InquisitiveBreakableYogurtJebaited', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - status = self._download_json( - 'https://clips.twitch.tv/api/v2/clips/%s/status' % video_id, - video_id) + clip = self._download_json( + 'https://gql.twitch.tv/gql', video_id, data=json.dumps({ + 'query': '''{ + clip(slug: "%s") { + broadcaster { + displayName + } + createdAt + curator { + displayName + id + } + durationSeconds + id + tiny: thumbnailURL(width: 86, height: 45) + small: thumbnailURL(width: 260, height: 147) + medium: thumbnailURL(width: 480, height: 272) + title + videoQualities { + frameRate + quality + sourceURL + } + viewCount + } +}''' % video_id, + }).encode(), headers={ + 'Client-ID': self._CLIENT_ID, + })['data']['clip'] + + if not clip: + raise ExtractorError( + 'This clip is no longer available', expected=True) formats = [] - - for option in status['quality_options']: + for option in clip.get('videoQualities', []): if not isinstance(option, dict): continue - source = url_or_none(option.get('source')) + source = url_or_none(option.get('sourceURL')) if not source: continue formats.append({ 'url': source, 'format_id': option.get('quality'), 'height': int_or_none(option.get('quality')), - 'fps': int_or_none(option.get('frame_rate')), + 'fps': int_or_none(option.get('frameRate')), }) - self._sort_formats(formats) - info = { + thumbnails = [] + for thumbnail_id in ('tiny', 'small', 'medium'): + thumbnail_url = clip.get(thumbnail_id) + if not thumbnail_url: + continue + thumb = { + 'id': thumbnail_id, + 'url': thumbnail_url, + } + mobj = re.search(r'-(\d+)x(\d+)\.', thumbnail_url) + if mobj: + thumb.update({ + 'height': int(mobj.group(2)), + 'width': int(mobj.group(1)), + }) + thumbnails.append(thumb) + + return { + 'id': clip.get('id') or video_id, + 'title': clip.get('title') or video_id, 'formats': formats, + 'duration': int_or_none(clip.get('durationSeconds')), + 'views': int_or_none(clip.get('viewCount')), + 'timestamp': unified_timestamp(clip.get('createdAt')), + 'thumbnails': thumbnails, + 'creator': try_get(clip, lambda x: x['broadcaster']['displayName'], compat_str), + 'uploader': try_get(clip, lambda x: x['curator']['displayName'], compat_str), + 'uploader_id': try_get(clip, lambda x: x['curator']['id'], compat_str), } - - clip = self._call_api( - 'kraken/clips/%s' % video_id, video_id, fatal=False, headers={ - 'Accept': 'application/vnd.twitchtv.v5+json', - }) - - if clip: - quality_key = qualities(('tiny', 'small', 'medium')) - thumbnails = [] - thumbnails_dict = clip.get('thumbnails') - if isinstance(thumbnails_dict, dict): - for thumbnail_id, thumbnail_url in thumbnails_dict.items(): - thumbnails.append({ - 'id': thumbnail_id, - 'url': thumbnail_url, - 'preference': quality_key(thumbnail_id), - }) - - info.update({ - 'id': clip.get('tracking_id') or video_id, - 'title': clip.get('title') or video_id, - 'duration': float_or_none(clip.get('duration')), - 'views': int_or_none(clip.get('views')), - 'timestamp': unified_timestamp(clip.get('created_at')), - 'thumbnails': thumbnails, - 'creator': try_get(clip, lambda x: x['broadcaster']['display_name'], compat_str), - 'uploader': try_get(clip, lambda x: x['curator']['display_name'], compat_str), - 'uploader_id': try_get(clip, lambda x: x['curator']['id'], compat_str), - }) - else: - info.update({ - 'title': video_id, - 'id': video_id, - }) - - return info diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index cebb6238c..01468981c 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -4,32 +4,67 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_HTTPError, + compat_parse_qs, + compat_urllib_parse_unquote, + compat_urllib_parse_urlparse, +) from ..utils import ( - determine_ext, dict_get, ExtractorError, float_or_none, int_or_none, - remove_end, try_get, + strip_or_none, + unified_timestamp, + update_url_query, xpath_text, ) -from .periscope import PeriscopeIE +from .periscope import ( + PeriscopeBaseIE, + PeriscopeIE, +) class TwitterBaseIE(InfoExtractor): + _API_BASE = 'https://api.twitter.com/1.1/' + _BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?twitter\.com/' + _GUEST_TOKEN = None + + def _extract_variant_formats(self, variant, video_id): + variant_url = variant.get('url') + if not variant_url: + return [] + elif '.m3u8' in variant_url: + return self._extract_m3u8_formats( + variant_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + else: + tbr = int_or_none(dict_get(variant, ('bitrate', 'bit_rate')), 1000) or None + f = { + 'url': variant_url, + 'format_id': 'http' + ('-%d' % tbr if tbr else ''), + 'tbr': tbr, + } + self._search_dimensions_in_video_url(f, variant_url) + return [f] + def _extract_formats_from_vmap_url(self, vmap_url, video_id): vmap_data = self._download_xml(vmap_url, video_id) - video_url = xpath_text(vmap_data, './/MediaFile').strip() - if determine_ext(video_url) == 'm3u8': - return self._extract_m3u8_formats( - video_url, video_id, ext='mp4', m3u8_id='hls', - entry_protocol='m3u8_native') - return [{ - 'url': video_url, - }] + formats = [] + urls = [] + for video_variant in vmap_data.findall('.//{http://twitter.com/schema/videoVMapV2.xsd}videoVariant'): + video_variant.attrib['url'] = compat_urllib_parse_unquote( + video_variant.attrib['url']) + urls.append(video_variant.attrib['url']) + formats.extend(self._extract_variant_formats( + video_variant.attrib, video_id)) + video_url = strip_or_none(xpath_text(vmap_data, './/MediaFile')) + if video_url not in urls: + formats.extend(self._extract_variant_formats({'url': video_url}, video_id)) + return formats @staticmethod def _search_dimensions_in_video_url(a_format, video_url): @@ -40,10 +75,30 @@ class TwitterBaseIE(InfoExtractor): 'height': int(m.group('height')), }) - -class TwitterCardIE(TwitterBaseIE): + def _call_api(self, path, video_id, query={}): + headers = { + 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw', + } + if not self._GUEST_TOKEN: + self._GUEST_TOKEN = self._download_json( + self._API_BASE + 'guest/activate.json', video_id, + 'Downloading guest token', data=b'', + headers=headers)['guest_token'] + headers['x-guest-token'] = self._GUEST_TOKEN + try: + return self._download_json( + self._API_BASE + path, video_id, headers=headers, query=query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + raise ExtractorError(self._parse_json( + e.cause.read().decode(), + video_id)['errors'][0]['message'], expected=True) + raise + + +class TwitterCardIE(InfoExtractor): IE_NAME = 'twitter:card' - _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?P<path>cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' + _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', @@ -51,19 +106,28 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '560070183650213889', 'ext': 'mp4', - 'title': 'Twitter web player', - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': "Twitter - You can now shoot, edit and share video on Twitter. Capture life's most moving moments from your perspective.", + 'description': 'md5:18d3e24bb4f6e5007487dd546e53bd96', + 'uploader': 'Twitter', + 'uploader_id': 'Twitter', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 30.033, + 'timestamp': 1422366112, + 'upload_date': '20150127', }, }, { 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768', - 'md5': '7ee2a553b63d1bccba97fbed97d9e1c8', + 'md5': '7137eca597f72b9abbe61e5ae0161399', 'info_dict': { 'id': '623160978427936768', 'ext': 'mp4', - 'title': 'Twitter web player', - 'thumbnail': r're:^https?://.*$', + 'title': "NASA - Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video.", + 'description': "Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video. https://t.co/BJYgOjSeGA", + 'uploader': 'NASA', + 'uploader_id': 'NASA', + 'timestamp': 1437408129, + 'upload_date': '20150720', }, }, { @@ -75,7 +139,7 @@ class TwitterCardIE(TwitterBaseIE): 'title': 'Ubuntu 11.10 Overview', 'description': 'md5:a831e97fa384863d6e26ce48d1c43376', 'upload_date': '20111013', - 'uploader': 'OMG! Ubuntu!', + 'uploader': 'OMG! UBUNTU!', 'uploader_id': 'omgubuntu', }, 'add_ie': ['Youtube'], @@ -99,190 +163,30 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '705235433198714880', 'ext': 'mp4', - 'title': 'Twitter web player', - 'thumbnail': r're:^https?://.*', + 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.", + 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns", + 'uploader': 'Brent Yarina', + 'uploader_id': 'BTNBrentYarina', + 'timestamp': 1456976204, + 'upload_date': '20160303', }, + 'skip': 'This content is no longer available.', }, { 'url': 'https://twitter.com/i/videos/752274308186120192', 'only_matching': True, }, ] - _API_BASE = 'https://api.twitter.com/1.1' - - def _parse_media_info(self, media_info, video_id): - formats = [] - for media_variant in media_info.get('variants', []): - media_url = media_variant['url'] - if media_url.endswith('.m3u8'): - formats.extend(self._extract_m3u8_formats(media_url, video_id, ext='mp4', m3u8_id='hls')) - elif media_url.endswith('.mpd'): - formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash')) - else: - tbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000) - a_format = { - 'url': media_url, - 'format_id': 'http-%d' % tbr if tbr else 'http', - 'tbr': tbr, - } - # Reported bitRate may be zero - if not a_format['tbr']: - del a_format['tbr'] - - self._search_dimensions_in_video_url(a_format, media_url) - - formats.append(a_format) - return formats - - def _extract_mobile_formats(self, username, video_id): - webpage = self._download_webpage( - 'https://mobile.twitter.com/%s/status/%s' % (username, video_id), - video_id, 'Downloading mobile webpage', - headers={ - # A recent mobile UA is necessary for `gt` cookie - 'User-Agent': 'Mozilla/5.0 (Android 6.0.1; Mobile; rv:54.0) Gecko/54.0 Firefox/54.0', - }) - main_script_url = self._html_search_regex( - r'<script[^>]+src="([^"]+main\.[^"]+)"', webpage, 'main script URL') - main_script = self._download_webpage( - main_script_url, video_id, 'Downloading main script') - bearer_token = self._search_regex( - r'BEARER_TOKEN\s*:\s*"([^"]+)"', - main_script, 'bearer token') - # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id - api_data = self._download_json( - '%s/statuses/show/%s.json' % (self._API_BASE, video_id), - video_id, 'Downloading API data', - headers={ - 'Authorization': 'Bearer ' + bearer_token, - }) - media_info = try_get(api_data, lambda o: o['extended_entities']['media'][0]['video_info']) or {} - return self._parse_media_info(media_info, video_id) - def _real_extract(self, url): - path, video_id = re.search(self._VALID_URL, url).groups() - - config = None - formats = [] - duration = None - - urls = [url] - if path.startswith('cards/'): - urls.append('https://twitter.com/i/videos/' + video_id) - - for u in urls: - webpage = self._download_webpage( - u, video_id, headers={'Referer': 'https://twitter.com/'}) - - iframe_url = self._html_search_regex( - r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', - webpage, 'video iframe', default=None) - if iframe_url: - return self.url_result(iframe_url) - - config = self._parse_json(self._html_search_regex( - r'data-(?:player-)?config="([^"]+)"', webpage, - 'data player config', default='{}'), - video_id) - - if config.get('source_type') == 'vine': - return self.url_result(config['player_url'], 'Vine') - - periscope_url = PeriscopeIE._extract_url(webpage) - if periscope_url: - return self.url_result(periscope_url, PeriscopeIE.ie_key()) - - video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source') - - if video_url: - if determine_ext(video_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) - else: - f = { - 'url': video_url, - } - - self._search_dimensions_in_video_url(f, video_url) - - formats.append(f) - - vmap_url = config.get('vmapUrl') or config.get('vmap_url') - if vmap_url: - formats.extend( - self._extract_formats_from_vmap_url(vmap_url, video_id)) - - media_info = None - - for entity in config.get('status', {}).get('entities', []): - if 'mediaInfo' in entity: - media_info = entity['mediaInfo'] - - if media_info: - formats.extend(self._parse_media_info(media_info, video_id)) - duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) - - username = config.get('user', {}).get('screen_name') - if username: - formats.extend(self._extract_mobile_formats(username, video_id)) - - if formats: - title = self._search_regex(r'<title>([^<]+)</title>', webpage, 'title') - thumbnail = config.get('posterImageUrl') or config.get('image_src') - duration = float_or_none(config.get('duration'), scale=1000) or duration - break - - if not formats: - headers = { - 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw', - 'Referer': url, - } - ct0 = self._get_cookies(url).get('ct0') - if ct0: - headers['csrf_token'] = ct0.value - guest_token = self._download_json( - '%s/guest/activate.json' % self._API_BASE, video_id, - 'Downloading guest token', data=b'', - headers=headers)['guest_token'] - headers['x-guest-token'] = guest_token - self._set_cookie('api.twitter.com', 'gt', guest_token) - config = self._download_json( - '%s/videos/tweet/config/%s.json' % (self._API_BASE, video_id), - video_id, headers=headers) - track = config['track'] - vmap_url = track.get('vmapUrl') - if vmap_url: - formats = self._extract_formats_from_vmap_url(vmap_url, video_id) - else: - playback_url = track['playbackUrl'] - if determine_ext(playback_url) == 'm3u8': - formats = self._extract_m3u8_formats( - playback_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls') - else: - formats = [{ - 'url': playback_url, - }] - title = 'Twitter web player' - thumbnail = config.get('posterImage') - duration = float_or_none(track.get('durationMs'), scale=1000) - - self._remove_duplicate_formats(formats) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - } + status_id = self._match_id(url) + return self.url_result( + 'https://twitter.com/statuses/' + status_id, + TwitterIE.ie_key(), status_id) -class TwitterIE(InfoExtractor): +class TwitterIE(TwitterBaseIE): IE_NAME = 'twitter' - _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?:i/web|(?P<user_id>[^/]+))/status/(?P<id>\d+)' - _TEMPLATE_URL = 'https://twitter.com/%s/status/%s' - _TEMPLATE_STATUSES_URL = 'https://twitter.com/statuses/%s' + _VALID_URL = TwitterBaseIE._BASE_REGEX + r'(?:(?:i/web|[^/]+)/status|statuses)/(?P<id>\d+)' _TESTS = [{ 'url': 'https://twitter.com/freethenipple/status/643211948184596480', @@ -291,10 +195,13 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"', + 'description': 'FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ', 'uploader': 'FREE THE NIPPLE', 'uploader_id': 'freethenipple', 'duration': 12.922, + 'timestamp': 1442188653, + 'upload_date': '20150913', + 'age_limit': 18, }, }, { 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', @@ -316,19 +223,23 @@ class TwitterIE(InfoExtractor): 'id': '665052190608723968', 'ext': 'mp4', 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.', - 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."', + 'description': 'A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens. https://t.co/OkSqT2fjWJ', 'uploader_id': 'starwars', 'uploader': 'Star Wars', + 'timestamp': 1447395772, + 'upload_date': '20151113', }, }, { 'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880', 'info_dict': { 'id': '705235433198714880', 'ext': 'mp4', - 'title': 'Brent Yarina - Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight.', - 'description': 'Brent Yarina on Twitter: "Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight."', + 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.", + 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns", 'uploader_id': 'BTNBrentYarina', 'uploader': 'Brent Yarina', + 'timestamp': 1456976204, + 'upload_date': '20160303', }, 'params': { # The same video as https://twitter.com/i/videos/tweet/705235433198714880 @@ -340,12 +251,14 @@ class TwitterIE(InfoExtractor): 'info_dict': { 'id': '700207533655363584', 'ext': 'mp4', - 'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel', - 'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', + 'title': 'simon vetugo - BEAT PROD: @suhmeduh #Damndaniel', + 'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ', 'thumbnail': r're:^https?://.*\.jpg', - 'uploader': 'JG', - 'uploader_id': 'jaydingeer', + 'uploader': 'simon vetugo', + 'uploader_id': 'simonvertugo', 'duration': 30.0, + 'timestamp': 1455777459, + 'upload_date': '20160218', }, }, { 'url': 'https://twitter.com/Filmdrunk/status/713801302971588609', @@ -353,10 +266,9 @@ class TwitterIE(InfoExtractor): 'info_dict': { 'id': 'MIOxnrUteUd', 'ext': 'mp4', - 'title': 'Vince Mancini - Vine of the day', - 'description': 'Vince Mancini on Twitter: "Vine of the day https://t.co/xmTvRdqxWf"', - 'uploader': 'Vince Mancini', - 'uploader_id': 'Filmdrunk', + 'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン', + 'uploader': 'TAKUMA', + 'uploader_id': '1004126642786242560', 'timestamp': 1402826626, 'upload_date': '20140615', }, @@ -367,21 +279,22 @@ class TwitterIE(InfoExtractor): 'id': '719944021058060289', 'ext': 'mp4', 'title': 'Captain America - @King0fNerd Are you sure you made the right choice? Find out in theaters.', - 'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"', - 'uploader_id': 'captainamerica', + 'description': '@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI', + 'uploader_id': 'CaptainAmerica', 'uploader': 'Captain America', 'duration': 3.17, + 'timestamp': 1460483005, + 'upload_date': '20160412', }, }, { 'url': 'https://twitter.com/OPP_HSD/status/779210622571536384', 'info_dict': { 'id': '1zqKVVlkqLaKB', 'ext': 'mp4', - 'title': 'Sgt Kerry Schmidt - LIVE on #Periscope: Road rage, mischief, assault, rollover and fire in one occurrence', - 'description': 'Sgt Kerry Schmidt on Twitter: "LIVE on #Periscope: Road rage, mischief, assault, rollover and fire in one occurrence https://t.co/EKrVgIXF3s"', + 'title': 'Sgt Kerry Schmidt - Ontario Provincial Police - Road rage, mischief, assault, rollover and fire in one occurrence', 'upload_date': '20160923', - 'uploader_id': 'OPP_HSD', - 'uploader': 'Sgt Kerry Schmidt', + 'uploader_id': '1PmKqpJdOJQoY', + 'uploader': 'Sgt Kerry Schmidt - Ontario Provincial Police', 'timestamp': 1474613214, }, 'add_ie': ['Periscope'], @@ -392,10 +305,12 @@ class TwitterIE(InfoExtractor): 'id': '852138619213144067', 'ext': 'mp4', 'title': 'عالم الأخبار - كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة', - 'description': 'عالم الأخبار on Twitter: "كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN"', + 'description': 'كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN', 'uploader': 'عالم الأخبار', 'uploader_id': 'news_al3alm', 'duration': 277.4, + 'timestamp': 1492000653, + 'upload_date': '20170412', }, }, { 'url': 'https://twitter.com/i/web/status/910031516746514432', @@ -404,10 +319,12 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 'Préfet de Guadeloupe - [Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre.', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'Préfet de Guadeloupe on Twitter: "[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo"', + 'description': '[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo', 'uploader': 'Préfet de Guadeloupe', 'uploader_id': 'Prefet971', 'duration': 47.48, + 'timestamp': 1505803395, + 'upload_date': '20170919', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -420,10 +337,12 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 're:.*?Shep is on a roll today.*?', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'md5:63b036c228772523ae1924d5f8e5ed6b', + 'description': 'md5:37b9f2ff31720cef23b2bd42ee8a0f09', 'uploader': 'Lis Power', 'uploader_id': 'LisPower1', 'duration': 111.278, + 'timestamp': 1527623489, + 'upload_date': '20180529', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -435,88 +354,168 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 'Twitter - A new is coming. Some of you got an opt-in to try it now. Check out the emoji button, quick keyboard shortcuts, upgraded trends, advanced search, and more. Let us know your thoughts!', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'md5:66d493500c013e3e2d434195746a7f78', + 'description': 'md5:6dfd341a3310fb97d80d2bf7145df976', 'uploader': 'Twitter', 'uploader_id': 'Twitter', 'duration': 61.567, + 'timestamp': 1548184644, + 'upload_date': '20190122', + }, + }, { + # not available in Periscope + 'url': 'https://twitter.com/ViviEducation/status/1136534865145286656', + 'info_dict': { + 'id': '1vOGwqejwoWxB', + 'ext': 'mp4', + 'title': 'Vivi - Vivi founder @lior_rauchy announcing our new student feedback tool live at @EduTECH_AU #EduTECH2019', + 'uploader': 'Vivi', + 'uploader_id': '1eVjYOLGkGrQL', }, + 'add_ie': ['TwitterBroadcast'], + }, { + # Twitch Clip Embed + 'url': 'https://twitter.com/GunB1g/status/1163218564784017422', + 'only_matching': True, + }, { + # promo_video_website card + 'url': 'https://twitter.com/GunB1g/status/1163218564784017422', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - twid = mobj.group('id') - - webpage, urlh = self._download_webpage_handle( - self._TEMPLATE_STATUSES_URL % twid, twid) - - if 'twitter.com/account/suspended' in urlh.geturl(): - raise ExtractorError('Account suspended by Twitter.', expected=True) - - user_id = None - - redirect_mobj = re.match(self._VALID_URL, urlh.geturl()) - if redirect_mobj: - user_id = redirect_mobj.group('user_id') - - if not user_id: - user_id = mobj.group('user_id') - - username = remove_end(self._og_search_title(webpage), ' on Twitter') - - title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”') + twid = self._match_id(url) + status = self._call_api( + 'statuses/show/%s.json' % twid, twid, { + 'cards_platform': 'Web-12', + 'include_cards': 1, + 'include_reply_count': 1, + 'include_user_entities': 0, + 'tweet_mode': 'extended', + }) + title = description = status['full_text'].replace('\n', ' ') # strip 'https -_t.co_BJYgOjSeGA' junk from filenames title = re.sub(r'\s+(https?://[^ ]+)', '', title) + user = status.get('user') or {} + uploader = user.get('name') + if uploader: + title = '%s - %s' % (uploader, title) + uploader_id = user.get('screen_name') + + tags = [] + for hashtag in (try_get(status, lambda x: x['entities']['hashtags'], list) or []): + hashtag_text = hashtag.get('text') + if not hashtag_text: + continue + tags.append(hashtag_text) info = { - 'uploader_id': user_id, - 'uploader': username, - 'webpage_url': url, - 'description': '%s on Twitter: "%s"' % (username, description), - 'title': username + ' - ' + title, + 'id': twid, + 'title': title, + 'description': description, + 'uploader': uploader, + 'timestamp': unified_timestamp(status.get('created_at')), + 'uploader_id': uploader_id, + 'uploader_url': 'https://twitter.com/' + uploader_id if uploader_id else None, + 'like_count': int_or_none(status.get('favorite_count')), + 'repost_count': int_or_none(status.get('retweet_count')), + 'comment_count': int_or_none(status.get('reply_count')), + 'age_limit': 18 if status.get('possibly_sensitive') else 0, + 'tags': tags, } - mobj = re.search(r'''(?x) - <video[^>]+class="animated-gif"(?P<more_info>[^>]+)>\s* - <source[^>]+video-src="(?P<url>[^"]+)" - ''', webpage) - - if mobj: - more_info = mobj.group('more_info') - height = int_or_none(self._search_regex( - r'data-height="(\d+)"', more_info, 'height', fatal=False)) - width = int_or_none(self._search_regex( - r'data-width="(\d+)"', more_info, 'width', fatal=False)) - thumbnail = self._search_regex( - r'poster="([^"]+)"', more_info, 'poster', fatal=False) - info.update({ - 'id': twid, - 'url': mobj.group('url'), - 'height': height, - 'width': width, - 'thumbnail': thumbnail, - }) - return info - - twitter_card_url = None - if 'class="PlayableMedia' in webpage: - twitter_card_url = '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid) - else: - twitter_card_iframe_url = self._search_regex( - r'data-full-card-iframe-url=([\'"])(?P<url>(?:(?!\1).)+)\1', - webpage, 'Twitter card iframe URL', default=None, group='url') - if twitter_card_iframe_url: - twitter_card_url = compat_urlparse.urljoin(url, twitter_card_iframe_url) + media = try_get(status, lambda x: x['extended_entities']['media'][0]) + if media and media.get('type') != 'photo': + video_info = media.get('video_info') or {} + + formats = [] + for variant in video_info.get('variants', []): + formats.extend(self._extract_variant_formats(variant, twid)) + self._sort_formats(formats) + + thumbnails = [] + media_url = media.get('media_url_https') or media.get('media_url') + if media_url: + def add_thumbnail(name, size): + thumbnails.append({ + 'id': name, + 'url': update_url_query(media_url, {'name': name}), + 'width': int_or_none(size.get('w') or size.get('width')), + 'height': int_or_none(size.get('h') or size.get('height')), + }) + for name, size in media.get('sizes', {}).items(): + add_thumbnail(name, size) + add_thumbnail('orig', media.get('original_info') or {}) - if twitter_card_url: info.update({ - '_type': 'url_transparent', - 'ie_key': 'TwitterCard', - 'url': twitter_card_url, + 'formats': formats, + 'thumbnails': thumbnails, + 'duration': float_or_none(video_info.get('duration_millis'), 1000), }) - return info - - raise ExtractorError('There\'s no video in this tweet.') + else: + card = status.get('card') + if card: + binding_values = card['binding_values'] + + def get_binding_value(k): + o = binding_values.get(k) or {} + return try_get(o, lambda x: x[x['type'].lower() + '_value']) + + card_name = card['name'].split(':')[-1] + if card_name in ('amplify', 'promo_video_website'): + is_amplify = card_name == 'amplify' + vmap_url = get_binding_value('amplify_url_vmap') if is_amplify else get_binding_value('player_stream_url') + content_id = get_binding_value('%s_content_id' % (card_name if is_amplify else 'player')) + formats = self._extract_formats_from_vmap_url(vmap_url, content_id or twid) + self._sort_formats(formats) + + thumbnails = [] + for suffix in ('_small', '', '_large', '_x_large', '_original'): + image = get_binding_value('player_image' + suffix) or {} + image_url = image.get('url') + if not image_url or '/player-placeholder' in image_url: + continue + thumbnails.append({ + 'id': suffix[1:] if suffix else 'medium', + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + info.update({ + 'formats': formats, + 'thumbnails': thumbnails, + 'duration': int_or_none(get_binding_value( + 'content_duration_seconds')), + }) + elif card_name == 'player': + info.update({ + '_type': 'url', + 'url': get_binding_value('player_url'), + }) + elif card_name == 'periscope_broadcast': + info.update({ + '_type': 'url', + 'url': get_binding_value('url') or get_binding_value('player_url'), + 'ie_key': PeriscopeIE.ie_key(), + }) + elif card_name == 'broadcast': + info.update({ + '_type': 'url', + 'url': get_binding_value('broadcast_url'), + 'ie_key': TwitterBroadcastIE.ie_key(), + }) + else: + raise ExtractorError('Unsupported Twitter Card.') + else: + expanded_url = try_get(status, lambda x: x['entities']['urls'][0]['expanded_url']) + if not expanded_url: + raise ExtractorError("There's no video in this tweet.") + info.update({ + '_type': 'url', + 'url': expanded_url, + }) + return info class TwitterAmplifyIE(TwitterBaseIE): @@ -573,3 +572,27 @@ class TwitterAmplifyIE(TwitterBaseIE): 'formats': formats, 'thumbnails': thumbnails, } + + +class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE): + IE_NAME = 'twitter:broadcast' + _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/broadcasts/(?P<id>[0-9a-zA-Z]{13})' + + def _real_extract(self, url): + broadcast_id = self._match_id(url) + broadcast = self._call_api( + 'broadcasts/show.json', broadcast_id, + {'ids': broadcast_id})['broadcasts'][broadcast_id] + info = self._parse_broadcast_data(broadcast, broadcast_id) + media_key = broadcast['media_key'] + source = self._call_api( + 'live_video_stream/status/' + media_key, media_key)['source'] + m3u8_url = source.get('noRedirectPlaybackUrl') or source['location'] + if '/live_video_stream/geoblocked/' in m3u8_url: + self.raise_geo_restricted() + m3u8_id = compat_parse_qs(compat_urllib_parse_urlparse( + m3u8_url).query).get('type', [None])[0] + state, width, height = self._extract_common_format_info(broadcast) + info['formats'] = self._extract_pscp_m3u8_formats( + m3u8_url, broadcast_id, m3u8_id, state, width, height) + return info diff --git a/youtube_dl/extractor/ufctv.py b/youtube_dl/extractor/ufctv.py index f3eaee6b3..3d74ba071 100644 --- a/youtube_dl/extractor/ufctv.py +++ b/youtube_dl/extractor/ufctv.py @@ -1,73 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - parse_duration, - parse_iso8601, - urlencode_postdata, -) +from .imggaming import ImgGamingBaseIE -class UFCTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ufc\.tv/video/(?P<id>[^/]+)' +class UFCTVIE(ImgGamingBaseIE): + _VALID_URL = ImgGamingBaseIE._VALID_URL_TEMPL % r'(?:(?:app|www)\.)?(?:ufc\.tv|(?:ufc)?fightpass\.com)|ufcfightpass\.img(?:dge|gaming)\.com' _NETRC_MACHINE = 'ufctv' - _TEST = { - 'url': 'https://www.ufc.tv/video/ufc-219-countdown-full-episode', - 'info_dict': { - 'id': '34167', - 'ext': 'mp4', - 'title': 'UFC 219 Countdown: Full Episode', - 'description': 'md5:26d4e8bf4665ae5878842d7050c3c646', - 'timestamp': 1513962360, - 'upload_date': '20171222', - }, - 'params': { - # m3u8 download - 'skip_download': True, - } - } + _REALM = 'ufc' - def _real_initialize(self): - username, password = self._get_login_info() - if username is None: - return - code = self._download_json( - 'https://www.ufc.tv/secure/authenticate', - None, 'Logging in', data=urlencode_postdata({ - 'username': username, - 'password': password, - 'format': 'json', - })).get('code') - if code and code != 'loginsuccess': - raise ExtractorError(code, expected=True) - - def _real_extract(self, url): - display_id = self._match_id(url) - video_data = self._download_json(url, display_id, query={ - 'format': 'json', - }) - video_id = str(video_data['id']) - title = video_data['name'] - m3u8_url = self._download_json( - 'https://www.ufc.tv/service/publishpoint', video_id, query={ - 'type': 'video', - 'format': 'json', - 'id': video_id, - }, headers={ - 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0_1 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A402 Safari/604.1', - })['path'] - m3u8_url = m3u8_url.replace('_iphone.', '.') - formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'description': video_data.get('description'), - 'duration': parse_duration(video_data.get('runtime')), - 'timestamp': parse_iso8601(video_data.get('releaseDate')), - 'formats': formats, - } +class UFCArabiaIE(ImgGamingBaseIE): + _VALID_URL = ImgGamingBaseIE._VALID_URL_TEMPL % r'(?:(?:app|www)\.)?ufcarabia\.(?:ae|com)' + _NETRC_MACHINE = 'ufcarabia' + _REALM = 'admufc' diff --git a/youtube_dl/extractor/vessel.py b/youtube_dl/extractor/vessel.py deleted file mode 100644 index 31eee0ba7..000000000 --- a/youtube_dl/extractor/vessel.py +++ /dev/null @@ -1,157 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import json -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - parse_iso8601, - sanitized_Request, -) - - -class VesselIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)' - _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s' - _LOGIN_URL = 'https://www.vessel.com/api/account/login' - _NETRC_MACHINE = 'vessel' - _TESTS = [{ - 'url': 'https://www.vessel.com/videos/HDN7G5UMs', - 'md5': '455cdf8beb71c6dd797fd2f3818d05c4', - 'info_dict': { - 'id': 'HDN7G5UMs', - 'ext': 'mp4', - 'title': 'Nvidia GeForce GTX Titan X - The Best Video Card on the Market?', - 'thumbnail': r're:^https?://.*\.jpg$', - 'upload_date': '20150317', - 'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?', - 'timestamp': int, - }, - }, { - 'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346', - 'only_matching': True, - }, { - 'url': 'https://www.vessel.com/videos/F01_dsLj1', - 'only_matching': True, - }, { - 'url': 'https://www.vessel.com/videos/RRX-sir-J', - 'only_matching': True, - }] - - @staticmethod - def _extract_urls(webpage): - return [url for _, url in re.findall( - r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z-_]+.*?)\1', - webpage)] - - @staticmethod - def make_json_request(url, data): - payload = json.dumps(data).encode('utf-8') - req = sanitized_Request(url, payload) - req.add_header('Content-Type', 'application/json; charset=utf-8') - return req - - @staticmethod - def find_assets(data, asset_type, asset_id=None): - for asset in data.get('assets', []): - if not asset.get('type') == asset_type: - continue - elif asset_id is not None and not asset.get('id') == asset_id: - continue - else: - yield asset - - def _check_access_rights(self, data): - access_info = data.get('__view', {}) - if not access_info.get('allow_access', True): - err_code = access_info.get('error_code') or '' - if err_code == 'ITEM_PAID_ONLY': - raise ExtractorError( - 'This video requires subscription.', expected=True) - else: - raise ExtractorError( - 'Access to this content is restricted. (%s said: %s)' % (self.IE_NAME, err_code), expected=True) - - def _login(self): - username, password = self._get_login_info() - if username is None: - return - self.report_login() - data = { - 'client_id': 'web', - 'type': 'password', - 'user_key': username, - 'password': password, - } - login_request = VesselIE.make_json_request(self._LOGIN_URL, data) - self._download_webpage(login_request, None, False, 'Wrong login info') - - def _real_initialize(self): - self._login() - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - data = self._parse_json(self._search_regex( - r'App\.bootstrapData\((.*?)\);', webpage, 'data'), video_id) - asset_id = data['model']['data']['id'] - - req = VesselIE.make_json_request( - self._API_URL_TEMPLATE % asset_id, {'client': 'web'}) - data = self._download_json(req, video_id) - video_asset_id = data.get('main_video_asset') - - self._check_access_rights(data) - - try: - video_asset = next( - VesselIE.find_assets(data, 'video', asset_id=video_asset_id)) - except StopIteration: - raise ExtractorError('No video assets found') - - formats = [] - for f in video_asset.get('sources', []): - location = f.get('location') - if not location: - continue - name = f.get('name') - if name == 'hls-index': - formats.extend(self._extract_m3u8_formats( - location, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id='m3u8', fatal=False)) - elif name == 'dash-index': - formats.extend(self._extract_mpd_formats( - location, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': name, - 'tbr': f.get('bitrate'), - 'height': f.get('height'), - 'width': f.get('width'), - 'url': location, - }) - self._sort_formats(formats) - - thumbnails = [] - for im_asset in VesselIE.find_assets(data, 'image'): - thumbnails.append({ - 'url': im_asset['location'], - 'width': im_asset.get('width', 0), - 'height': im_asset.get('height', 0), - }) - - return { - 'id': video_id, - 'title': data['title'], - 'formats': formats, - 'thumbnails': thumbnails, - 'description': data.get('short_description'), - 'duration': data.get('duration'), - 'comment_count': data.get('comment_count'), - 'like_count': data.get('like_count'), - 'view_count': data.get('view_count'), - 'timestamp': parse_iso8601(data.get('released_at')), - } diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 8fdfd743d..e37499512 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,35 +1,50 @@ # coding: utf-8 from __future__ import unicode_literals -import re -import time +import functools import hashlib import json import random +import re +import time from .adobepass import AdobePassIE -from .youtube import YoutubeIE from .common import InfoExtractor +from .youtube import YoutubeIE from ..compat import ( compat_HTTPError, compat_str, ) from ..utils import ( + clean_html, ExtractorError, int_or_none, + OnDemandPagedList, parse_age_limit, str_or_none, try_get, ) -class ViceIE(AdobePassIE): +class ViceBaseIE(InfoExtractor): + def _call_api(self, resource, resource_key, resource_id, locale, fields, args=''): + return self._download_json( + 'https://video.vice.com/api/v1/graphql', resource_id, query={ + 'query': '''{ + %s(locale: "%s", %s: "%s"%s) { + %s + } +}''' % (resource, locale, resource_key, resource_id, args, fields), + })['data'][resource] + + +class ViceIE(ViceBaseIE, AdobePassIE): IE_NAME = 'vice' - _VALID_URL = r'https?://(?:(?:video|vms)\.vice|(?:www\.)?viceland)\.com/(?P<locale>[^/]+)/(?:video/[^/]+|embed)/(?P<id>[\da-f]+)' + _VALID_URL = r'https?://(?:(?:video|vms)\.vice|(?:www\.)?vice(?:land|tv))\.com/(?P<locale>[^/]+)/(?:video/[^/]+|embed)/(?P<id>[\da-f]{24})' _TESTS = [{ 'url': 'https://video.vice.com/en_us/video/pet-cremator/58c69e38a55424f1227dc3f7', 'info_dict': { - 'id': '5e647f0125e145c9aef2069412c0cbde', + 'id': '58c69e38a55424f1227dc3f7', 'ext': 'mp4', 'title': '10 Questions You Always Wanted To Ask: Pet Cremator', 'description': 'md5:fe856caacf61fe0e74fab15ce2b07ca5', @@ -43,17 +58,16 @@ class ViceIE(AdobePassIE): # m3u8 download 'skip_download': True, }, - 'add_ie': ['UplynkPreplay'], }, { # geo restricted to US 'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56', 'info_dict': { - 'id': '930c0ad1f47141cc955087eecaddb0e2', + 'id': '5816510690b70e6c5fd39a56', 'ext': 'mp4', - 'uploader': 'waypoint', + 'uploader': 'vice', 'title': 'The Signal From Tölva', 'description': 'md5:3927e3c79f9e8094606a2b3c5b5e55d5', - 'uploader_id': '57f7d621e05ca860fa9ccaf9', + 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1477941983, 'upload_date': '20161031', }, @@ -61,15 +75,14 @@ class ViceIE(AdobePassIE): # m3u8 download 'skip_download': True, }, - 'add_ie': ['UplynkPreplay'], }, { 'url': 'https://video.vice.com/alps/video/ulfs-wien-beruchtigste-grafitti-crew-part-1/581b12b60a0e1f4c0fb6ea2f', 'info_dict': { 'id': '581b12b60a0e1f4c0fb6ea2f', 'ext': 'mp4', 'title': 'ULFs - Wien berüchtigste Grafitti Crew - Part 1', - 'description': '<p>Zwischen Hinterzimmer-Tattoos und U-Bahnschächten erzählen uns die Ulfs, wie es ist, "süchtig nach Sachbeschädigung" zu sein.</p>', - 'uploader': 'VICE', + 'description': 'Zwischen Hinterzimmer-Tattoos und U-Bahnschächten erzählen uns die Ulfs, wie es ist, "süchtig nach Sachbeschädigung" zu sein.', + 'uploader': 'vice', 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1485368119, 'upload_date': '20170125', @@ -78,9 +91,7 @@ class ViceIE(AdobePassIE): 'params': { # AES-encrypted m3u8 'skip_download': True, - 'proxy': '127.0.0.1:8118', }, - 'add_ie': ['UplynkPreplay'], }, { 'url': 'https://video.vice.com/en_us/video/pizza-show-trailer/56d8c9a54d286ed92f7f30e4', 'only_matching': True, @@ -98,7 +109,7 @@ class ViceIE(AdobePassIE): @staticmethod def _extract_urls(webpage): return re.findall( - r'<iframe\b[^>]+\bsrc=["\']((?:https?:)?//video\.vice\.com/[^/]+/embed/[\da-f]+)', + r'<iframe\b[^>]+\bsrc=["\']((?:https?:)?//video\.vice\.com/[^/]+/embed/[\da-f]{24})', webpage) @staticmethod @@ -109,31 +120,16 @@ class ViceIE(AdobePassIE): def _real_extract(self, url): locale, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage( - 'https://video.vice.com/%s/embed/%s' % (locale, video_id), - video_id) - - video = self._parse_json( - self._search_regex( - r'PREFETCH_DATA\s*=\s*({.+?})\s*;\s*\n', webpage, - 'app state'), video_id)['video'] - video_id = video.get('vms_id') or video.get('id') or video_id - title = video['title'] - is_locked = video.get('locked') + video = self._call_api('videos', 'id', video_id, locale, '''body + locked + rating + thumbnail_url + title''')[0] + title = video['title'].strip() rating = video.get('rating') - thumbnail = video.get('thumbnail_url') - duration = int_or_none(video.get('duration')) - series = try_get( - video, lambda x: x['episode']['season']['show']['title'], - compat_str) - episode_number = try_get( - video, lambda x: x['episode']['episode_number']) - season_number = try_get( - video, lambda x: x['episode']['season']['season_number']) - uploader = None query = {} - if is_locked: + if video.get('locked'): resource = self._get_mvpd_resource( 'VICELAND', title, video_id, rating) query['tvetoken'] = self._extract_mvpd_auth( @@ -148,12 +144,9 @@ class ViceIE(AdobePassIE): query.update({ 'exp': exp, 'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(), - '_ad_blocked': None, - '_ad_unit': '', - '_debug': '', + 'skipadstitching': 1, 'platform': 'desktop', 'rn': random.randint(10000, 100000), - 'fbprebidtoken': '', }) try: @@ -169,85 +162,94 @@ class ViceIE(AdobePassIE): raise video_data = preplay['video'] - base = video_data['base'] - uplynk_preplay_url = preplay['preplayURL'] - episode = video_data.get('episode', {}) - channel = video_data.get('channel', {}) + formats = self._extract_m3u8_formats( + preplay['playURL'], video_id, 'mp4', 'm3u8_native') + self._sort_formats(formats) + episode = video_data.get('episode') or {} + channel = video_data.get('channel') or {} + season = video_data.get('season') or {} subtitles = {} - cc_url = preplay.get('ccURL') - if cc_url: - subtitles['en'] = [{ + for subtitle in preplay.get('subtitleURLs', []): + cc_url = subtitle.get('url') + if not cc_url: + continue + language_code = try_get(subtitle, lambda x: x['languages'][0]['language_code'], compat_str) or 'en' + subtitles.setdefault(language_code, []).append({ 'url': cc_url, - }] + }) return { - '_type': 'url_transparent', - 'url': uplynk_preplay_url, + 'formats': formats, 'id': video_id, 'title': title, - 'description': base.get('body') or base.get('display_body'), - 'thumbnail': thumbnail, - 'duration': int_or_none(video_data.get('video_duration')) or duration, + 'description': clean_html(video.get('body')), + 'thumbnail': video.get('thumbnail_url'), + 'duration': int_or_none(video_data.get('video_duration')), 'timestamp': int_or_none(video_data.get('created_at'), 1000), - 'age_limit': parse_age_limit(video_data.get('video_rating')), - 'series': video_data.get('show_title') or series, - 'episode_number': int_or_none(episode.get('episode_number') or episode_number), + 'age_limit': parse_age_limit(video_data.get('video_rating') or rating), + 'series': try_get(video_data, lambda x: x['show']['base']['display_title'], compat_str), + 'episode_number': int_or_none(episode.get('episode_number')), 'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')), - 'season_number': int_or_none(season_number), - 'season_id': str_or_none(episode.get('season_id')), - 'uploader': channel.get('base', {}).get('title') or channel.get('name') or uploader, + 'season_number': int_or_none(season.get('season_number')), + 'season_id': str_or_none(season.get('id') or video_data.get('season_id')), + 'uploader': channel.get('name'), 'uploader_id': str_or_none(channel.get('id')), 'subtitles': subtitles, - 'ie_key': 'UplynkPreplay', } -class ViceShowIE(InfoExtractor): +class ViceShowIE(ViceBaseIE): IE_NAME = 'vice:show' - _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)' - - _TEST = { - 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2', + _VALID_URL = r'https?://(?:video\.vice|(?:www\.)?vice(?:land|tv))\.com/(?P<locale>[^/]+)/show/(?P<id>[^/?#&]+)' + _PAGE_SIZE = 25 + _TESTS = [{ + 'url': 'https://video.vice.com/en_us/show/fck-thats-delicious', 'info_dict': { - 'id': 'fuck-thats-delicious-2', - 'title': "Fuck, That's Delicious", - 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.', + 'id': '57a2040c8cb727dec794c901', + 'title': 'F*ck, That’s Delicious', + 'description': 'The life and eating habits of rap’s greatest bon vivant, Action Bronson.', }, - 'playlist_count': 17, - } + 'playlist_mincount': 64, + }, { + 'url': 'https://www.vicetv.com/en_us/show/fck-thats-delicious', + 'only_matching': True, + }] - def _real_extract(self, url): - show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) + def _fetch_page(self, locale, show_id, page): + videos = self._call_api('videos', 'show_id', show_id, locale, '''body + id + url''', ', page: %d, per_page: %d' % (page + 1, self._PAGE_SIZE)) + for video in videos: + yield self.url_result( + video['url'], ViceIE.ie_key(), video.get('id')) - entries = [ - self.url_result(video_url, ViceIE.ie_key()) - for video_url, _ in re.findall( - r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"' - % ViceIE._VALID_URL, webpage)] + def _real_extract(self, url): + locale, display_id = re.match(self._VALID_URL, url).groups() + show = self._call_api('shows', 'slug', display_id, locale, '''dek + id + title''')[0] + show_id = show['id'] - title = self._search_regex( - r'<title>(.+?)</title>', webpage, 'title', default=None) - if title: - title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip() - description = self._html_search_meta( - 'description', webpage, 'description') + entries = OnDemandPagedList( + functools.partial(self._fetch_page, locale, show_id), + self._PAGE_SIZE) - return self.playlist_result(entries, show_id, title, description) + return self.playlist_result( + entries, show_id, show.get('title'), show.get('dek')) -class ViceArticleIE(InfoExtractor): +class ViceArticleIE(ViceBaseIE): IE_NAME = 'vice:article' - _VALID_URL = r'https://www\.vice\.com/[^/]+/article/(?P<id>[^?#]+)' + _VALID_URL = r'https://(?:www\.)?vice\.com/(?P<locale>[^/]+)/article/(?:[0-9a-z]{6}/)?(?P<id>[^?#]+)' _TESTS = [{ 'url': 'https://www.vice.com/en_us/article/on-set-with-the-woman-making-mormon-porn-in-utah', 'info_dict': { - 'id': '41eae2a47b174a1398357cec55f1f6fc', + 'id': '58dc0a3dee202d2a0ccfcbd8', 'ext': 'mp4', - 'title': 'Mormon War on Porn ', - 'description': 'md5:6394a8398506581d0346b9ab89093fef', + 'title': 'Mormon War on Porn', + 'description': 'md5:1c5d91fe25fa8aa304f9def118b92dbf', 'uploader': 'vice', 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1491883129, @@ -258,10 +260,10 @@ class ViceArticleIE(InfoExtractor): # AES-encrypted m3u8 'skip_download': True, }, - 'add_ie': ['UplynkPreplay'], + 'add_ie': [ViceIE.ie_key()], }, { 'url': 'https://www.vice.com/en_us/article/how-to-hack-a-car', - 'md5': '7fe8ebc4fa3323efafc127b82bd821d9', + 'md5': '13010ee0bc694ea87ec40724397c2349', 'info_dict': { 'id': '3jstaBeXgAs', 'ext': 'mp4', @@ -271,15 +273,15 @@ class ViceArticleIE(InfoExtractor): 'uploader_id': 'MotherboardTV', 'upload_date': '20140529', }, - 'add_ie': ['Youtube'], + 'add_ie': [YoutubeIE.ie_key()], }, { 'url': 'https://www.vice.com/en_us/article/znm9dx/karley-sciortino-slutever-reloaded', 'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2', 'info_dict': { - 'id': 'e2ed435eb67e43efb66e6ef9a6930a88', + 'id': '57f41d3556a0a80f54726060', 'ext': 'mp4', 'title': "Making The World's First Male Sex Doll", - 'description': 'md5:916078ef0e032d76343116208b6cc2c4', + 'description': 'md5:19b00b215b99961cf869c40fbe9df755', 'uploader': 'vice', 'uploader_id': '57a204088cb727dec794c67b', 'timestamp': 1476919911, @@ -288,6 +290,7 @@ class ViceArticleIE(InfoExtractor): }, 'params': { 'skip_download': True, + 'format': 'bestvideo', }, 'add_ie': [ViceIE.ie_key()], }, { @@ -299,14 +302,11 @@ class ViceArticleIE(InfoExtractor): }] def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) + locale, display_id = re.match(self._VALID_URL, url).groups() - prefetch_data = self._parse_json(self._search_regex( - r'__APP_STATE\s*=\s*({.+?})(?:\s*\|\|\s*{}\s*)?;\s*\n', - webpage, 'app state'), display_id)['pageData'] - body = prefetch_data['body'] + article = self._call_api('articles', 'slug', display_id, locale, '''body + embed_code''')[0] + body = article['body'] def _url_res(video_url, ie_key): return { @@ -316,7 +316,7 @@ class ViceArticleIE(InfoExtractor): 'ie_key': ie_key, } - vice_url = ViceIE._extract_url(webpage) + vice_url = ViceIE._extract_url(body) if vice_url: return _url_res(vice_url, ViceIE.ie_key()) @@ -332,6 +332,6 @@ class ViceArticleIE(InfoExtractor): video_url = self._html_search_regex( r'data-video-url="([^"]+)"', - prefetch_data['embed_code'], 'video URL') + article['embed_code'], 'video URL') return _url_res(video_url, ViceIE.ie_key()) diff --git a/youtube_dl/extractor/videodetective.py b/youtube_dl/extractor/videodetective.py index a19411a05..fe70db713 100644 --- a/youtube_dl/extractor/videodetective.py +++ b/youtube_dl/extractor/videodetective.py @@ -1,7 +1,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urlparse from .internetvideoarchive import InternetVideoArchiveIE @@ -13,7 +12,7 @@ class VideoDetectiveIE(InfoExtractor): 'info_dict': { 'id': '194487', 'ext': 'mp4', - 'title': 'KICK-ASS 2', + 'title': 'Kick-Ass 2', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', }, 'params': { @@ -24,7 +23,7 @@ class VideoDetectiveIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - og_video = self._og_search_video_url(webpage) - query = compat_urlparse.urlparse(og_video).query - return self.url_result(InternetVideoArchiveIE._build_json_url(query), ie=InternetVideoArchiveIE.ie_key()) + query = 'customerid=69249&publishedid=' + video_id + return self.url_result( + InternetVideoArchiveIE._build_json_url(query), + ie=InternetVideoArchiveIE.ie_key()) diff --git a/youtube_dl/extractor/videopremium.py b/youtube_dl/extractor/videopremium.py deleted file mode 100644 index cf690d7b0..000000000 --- a/youtube_dl/extractor/videopremium.py +++ /dev/null @@ -1,46 +0,0 @@ -from __future__ import unicode_literals - -import re -import random - -from .common import InfoExtractor - - -class VideoPremiumIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?videopremium\.(?:tv|me)/(?P<id>\w+)(?:/.*)?' - _TEST = { - 'url': 'http://videopremium.tv/4w7oadjsf156', - 'info_dict': { - 'id': '4w7oadjsf156', - 'ext': 'f4v', - 'title': 'youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4' - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Test file has been deleted.', - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage_url = 'http://videopremium.tv/' + video_id - webpage = self._download_webpage(webpage_url, video_id) - - if re.match(r'^<html><head><script[^>]*>window\.location\s*=', webpage): - # Download again, we need a cookie - webpage = self._download_webpage( - webpage_url, video_id, - note='Downloading webpage again (with cookie)') - - video_title = self._html_search_regex( - r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, 'video title') - - return { - 'id': video_id, - 'url': 'rtmp://e%d.md.iplay.md/play' % random.randint(1, 16), - 'play_path': 'mp4:%s.f4v' % video_id, - 'page_url': 'http://videopremium.tv/' + video_id, - 'player_url': 'http://videopremium.tv/uplayer/uppod.swf', - 'ext': 'f4v', - 'title': video_title, - } diff --git a/youtube_dl/extractor/viewlift.py b/youtube_dl/extractor/viewlift.py index 851ad936c..d6b92b1c8 100644 --- a/youtube_dl/extractor/viewlift.py +++ b/youtube_dl/extractor/viewlift.py @@ -1,28 +1,62 @@ from __future__ import unicode_literals -import base64 +import json import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, - clean_html, - determine_ext, int_or_none, - js_to_json, parse_age_limit, - parse_duration, - try_get, ) class ViewLiftBaseIE(InfoExtractor): - _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv' + _API_BASE = 'https://prod-api.viewlift.com/' + _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv' + _SITE_MAP = { + 'ftfnext': 'lax', + 'funnyforfree': 'snagfilms', + 'hoichoi': 'hoichoitv', + 'kiddovid': 'snagfilms', + 'laxsportsnetwork': 'lax', + 'legapallacanestro': 'lnp', + 'marquee': 'marquee-tv', + 'monumentalsportsnetwork': 'monumental-network', + 'moviespree': 'bingeflix', + 'pflmma': 'pfl', + 'snagxtreme': 'snagfilms', + 'theidentitytb': 'tampabay', + 'vayafilm': 'snagfilms', + } + _TOKENS = {} + + def _call_api(self, site, path, video_id, query): + token = self._TOKENS.get(site) + if not token: + token_query = {'site': site} + email, password = self._get_login_info(netrc_machine=site) + if email: + resp = self._download_json( + self._API_BASE + 'identity/signin', video_id, + 'Logging in', query=token_query, data=json.dumps({ + 'email': email, + 'password': password, + }).encode()) + else: + resp = self._download_json( + self._API_BASE + 'identity/anonymous-token', video_id, + 'Downloading authorization token', query=token_query) + self._TOKENS[site] = token = resp['authorizationToken'] + return self._download_json( + self._API_BASE + path, video_id, + headers={'Authorization': token}, query=query) class ViewLiftEmbedIE(ViewLiftBaseIE): - _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX + IE_NAME = 'viewlift:embed' + _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P<domain>%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX _TESTS = [{ 'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500', 'md5': '2924e9215c6eff7a55ed35b72276bd93', @@ -30,6 +64,9 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): 'id': '74849a00-85a9-11e1-9660-123139220831', 'ext': 'mp4', 'title': '#whilewewatch', + 'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8', + 'timestamp': 1334350096, + 'upload_date': '20120413', } }, { # invalid labels, 360p is better that 480p @@ -39,7 +76,8 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): 'id': '17ca0950-a74a-11e0-a92a-0026bb61d036', 'ext': 'mp4', 'title': 'Life in Limbo', - } + }, + 'skip': 'The video does not exist', }, { 'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017', 'only_matching': True, @@ -54,67 +92,68 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): return mobj.group('url') def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - if '>This film is not playable in your area.<' in webpage: - raise ExtractorError( - 'Film %s is not playable in your area.' % video_id, expected=True) + domain, film_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[-2] + if site in self._SITE_MAP: + site = self._SITE_MAP[site] + try: + content_data = self._call_api( + site, 'entitlement/video/status', film_id, { + 'id': film_id + })['video'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + error_message = self._parse_json(e.cause.read().decode(), film_id).get('errorMessage') + if error_message == 'User does not have a valid subscription or has not purchased this content.': + self.raise_login_required() + raise ExtractorError(error_message, expected=True) + raise + gist = content_data['gist'] + title = gist['title'] + video_assets = content_data['streamingInfo']['videoAssets'] formats = [] - has_bitrate = False - sources = self._parse_json(self._search_regex( - r'(?s)sources:\s*(\[.+?\]),', webpage, - 'sources', default='[]'), video_id, js_to_json) - for source in sources: - file_ = source.get('file') - if not file_: + mpeg_video_assets = video_assets.get('mpeg') or [] + for video_asset in mpeg_video_assets: + video_asset_url = video_asset.get('url') + if not video_asset: continue - type_ = source.get('type') - ext = determine_ext(file_) - format_id = source.get('label') or ext - if all(v in ('m3u8', 'hls') for v in (type_, ext)): - formats.extend(self._extract_m3u8_formats( - file_, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - else: - bitrate = int_or_none(self._search_regex( - [r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext], - file_, 'bitrate', default=None)) - if not has_bitrate and bitrate: - has_bitrate = True - height = int_or_none(self._search_regex( - r'^(\d+)[pP]$', format_id, 'height', default=None)) - formats.append({ - 'url': file_, - 'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')), - 'tbr': bitrate, - 'height': height, - }) - if not formats: - hls_url = self._parse_json(self._search_regex( - r'filmInfo\.src\s*=\s*({.+?});', - webpage, 'src'), video_id, js_to_json)['src'] - formats = self._extract_m3u8_formats( - hls_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False) - field_preference = None if has_bitrate else ('height', 'tbr', 'format_id') - self._sort_formats(formats, field_preference) - - title = self._search_regex( - [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'], - webpage, 'title') - - return { - 'id': video_id, + bitrate = int_or_none(video_asset.get('bitrate')) + height = int_or_none(self._search_regex( + r'^_?(\d+)[pP]$', video_asset.get('renditionValue'), + 'height', default=None)) + formats.append({ + 'url': video_asset_url, + 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''), + 'tbr': bitrate, + 'height': height, + 'vcodec': video_asset.get('codec'), + }) + + hls_url = video_assets.get('hls') + if hls_url: + formats.extend(self._extract_m3u8_formats( + hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + self._sort_formats(formats, ('height', 'tbr', 'format_id')) + + info = { + 'id': film_id, 'title': title, + 'description': gist.get('description'), + 'thumbnail': gist.get('videoImageUrl'), + 'duration': int_or_none(gist.get('runtime')), + 'age_limit': parse_age_limit(content_data.get('parentalRating')), + 'timestamp': int_or_none(gist.get('publishDate'), 1000), 'formats': formats, } + for k in ('categories', 'tags'): + info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')] + return info class ViewLiftIE(ViewLiftBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX + IE_NAME = 'viewlift' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX _TESTS = [{ 'url': 'http://www.snagfilms.com/films/title/lost_for_life', 'md5': '19844f897b35af219773fd63bdec2942', @@ -151,10 +190,13 @@ class ViewLiftIE(ViewLiftBaseIE): 'id': '00000148-7b53-de26-a9fb-fbf306f70020', 'display_id': 'augie_alone/s_2_ep_12_love', 'ext': 'mp4', - 'title': 'Augie, Alone:S. 2 Ep. 12 - Love', - 'description': 'md5:db2a5c72d994f16a780c1eb353a8f403', + 'title': 'S. 2 Ep. 12 - Love', + 'description': 'Augie finds love.', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 107, + 'upload_date': '20141012', + 'timestamp': 1413129540, + 'age_limit': 17, }, 'params': { 'skip_download': True, @@ -177,6 +219,9 @@ class ViewLiftIE(ViewLiftBaseIE): # Was once Kaltura embed 'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15', 'only_matching': True, + }, { + 'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters', + 'only_matching': True, }] @classmethod @@ -184,119 +229,22 @@ class ViewLiftIE(ViewLiftBaseIE): return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url) def _real_extract(self, url): - domain, display_id = re.match(self._VALID_URL, url).groups() - - webpage = self._download_webpage(url, display_id) - - if ">Sorry, the Film you're looking for is not available.<" in webpage: - raise ExtractorError( - 'Film %s is not available.' % display_id, expected=True) - - initial_store_state = self._search_regex( - r"window\.initialStoreState\s*=.*?JSON\.parse\(unescape\(atob\('([^']+)'\)\)\)", - webpage, 'Initial Store State', default=None) - if initial_store_state: - modules = self._parse_json(compat_urllib_parse_unquote(base64.b64decode( - initial_store_state).decode()), display_id)['page']['data']['modules'] - content_data = next(m['contentData'][0] for m in modules if m.get('moduleType') == 'VideoDetailModule') - gist = content_data['gist'] - film_id = gist['id'] - title = gist['title'] - video_assets = try_get( - content_data, lambda x: x['streamingInfo']['videoAssets'], dict) - if not video_assets: - token = self._download_json( - 'https://prod-api.viewlift.com/identity/anonymous-token', - film_id, 'Downloading authorization token', - query={'site': 'snagfilms'})['authorizationToken'] - video_assets = self._download_json( - 'https://prod-api.viewlift.com/entitlement/video/status', - film_id, headers={ - 'Authorization': token, - 'Referer': url, - }, query={ - 'id': film_id - })['video']['streamingInfo']['videoAssets'] - - formats = [] - mpeg_video_assets = video_assets.get('mpeg') or [] - for video_asset in mpeg_video_assets: - video_asset_url = video_asset.get('url') - if not video_asset: - continue - bitrate = int_or_none(video_asset.get('bitrate')) - height = int_or_none(self._search_regex( - r'^_?(\d+)[pP]$', video_asset.get('renditionValue'), - 'height', default=None)) - formats.append({ - 'url': video_asset_url, - 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''), - 'tbr': bitrate, - 'height': height, - 'vcodec': video_asset.get('codec'), - }) - - hls_url = video_assets.get('hls') - if hls_url: - formats.extend(self._extract_m3u8_formats( - hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - self._sort_formats(formats, ('height', 'tbr', 'format_id')) - - info = { - 'id': film_id, - 'display_id': display_id, - 'title': title, - 'description': gist.get('description'), - 'thumbnail': gist.get('videoImageUrl'), - 'duration': int_or_none(gist.get('runtime')), - 'age_limit': parse_age_limit(content_data.get('parentalRating')), - 'timestamp': int_or_none(gist.get('publishDate'), 1000), - 'formats': formats, - } - for k in ('categories', 'tags'): - info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')] - return info - else: - film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id') - - snag = self._parse_json( - self._search_regex( - r'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag', default='[]'), - display_id) - - for item in snag: - if item.get('data', {}).get('film', {}).get('id') == film_id: - data = item['data']['film'] - title = data['title'] - description = clean_html(data.get('synopsis')) - thumbnail = data.get('image') - duration = int_or_none(data.get('duration') or data.get('runtime')) - categories = [ - category['title'] for category in data.get('categories', []) - if category.get('title')] - break - else: - title = self._html_search_regex( - (r'itemprop="title">([^<]+)<', - r'(?s)itemprop="title">(.+?)<div'), webpage, 'title') - description = self._html_search_regex( - r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>', - webpage, 'description', default=None) or self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - duration = parse_duration(self._search_regex( - r'<span itemprop="duration" class="film-duration strong">([^<]+)<', - webpage, 'duration', fatal=False)) - categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage) - - return { - '_type': 'url_transparent', - 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), - 'id': film_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'categories': categories, - 'ie_key': 'ViewLiftEmbed', - } + domain, path, display_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[-2] + if site in self._SITE_MAP: + site = self._SITE_MAP[site] + modules = self._call_api( + site, 'content/pages', display_id, { + 'includeContent': 'true', + 'moduleOffset': 1, + 'path': path, + 'site': site, + })['modules'] + film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule') + return { + '_type': 'url_transparent', + 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), + 'id': film_id, + 'display_id': display_id, + 'ie_key': 'ViewLiftEmbed', + } diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py deleted file mode 100644 index 6e318479c..000000000 --- a/youtube_dl/extractor/viewster.py +++ /dev/null @@ -1,217 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_urllib_parse_unquote, -) -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - parse_iso8601, - sanitized_Request, - HEADRequest, - url_basename, -) - - -class ViewsterIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)' - _TESTS = [{ - # movie, Type=Movie - 'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/', - 'md5': 'e642d1b27fcf3a4ffa79f194f5adde36', - 'info_dict': { - 'id': '1140-11855-000', - 'ext': 'mp4', - 'title': 'The listening Project', - 'description': 'md5:bac720244afd1a8ea279864e67baa071', - 'timestamp': 1214870400, - 'upload_date': '20080701', - 'duration': 4680, - }, - }, { - # series episode, Type=Episode - 'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/', - 'md5': '9243079a8531809efe1b089db102c069', - 'info_dict': { - 'id': '1284-19427-001', - 'ext': 'mp4', - 'title': 'The World and a Wall', - 'description': 'md5:24814cf74d3453fdf5bfef9716d073e3', - 'timestamp': 1428192000, - 'upload_date': '20150405', - 'duration': 1500, - }, - }, { - # serie, Type=Serie - 'url': 'http://www.viewster.com/serie/1303-19426-000/', - 'info_dict': { - 'id': '1303-19426-000', - 'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?', - 'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11', - }, - 'playlist_count': 13, - }, { - # unfinished serie, no Type - 'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/', - 'info_dict': { - 'id': '1284-19427-000', - 'title': 'Baby Steps—Season 2', - 'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1', - }, - 'playlist_mincount': 16, - }, { - # geo restricted series - 'url': 'https://www.viewster.com/serie/1280-18794-002/', - 'only_matching': True, - }, { - # geo restricted video - 'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/', - 'only_matching': True, - }] - - _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01' - - def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}): - request = sanitized_Request(url) - request.add_header('Accept', self._ACCEPT_HEADER) - request.add_header('Auth-token', self._AUTH_TOKEN) - return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query) - - def _real_extract(self, url): - video_id = self._match_id(url) - # Get 'api_token' cookie - self._request_webpage( - HEADRequest('http://www.viewster.com/'), - video_id, headers=self.geo_verification_headers()) - cookies = self._get_cookies('http://www.viewster.com/') - self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value) - - info = self._download_json( - 'https://public-api.viewster.com/search/%s' % video_id, - video_id, 'Downloading entry JSON') - - entry_id = info.get('Id') or info['id'] - - # unfinished serie has no Type - if info.get('Type') in ('Serie', None): - try: - episodes = self._download_json( - 'https://public-api.viewster.com/series/%s/episodes' % entry_id, - video_id, 'Downloading series JSON') - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: - self.raise_geo_restricted() - else: - raise - entries = [ - self.url_result( - 'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster') - for episode in episodes] - title = (info.get('Title') or info['Synopsis']['Title']).strip() - description = info.get('Synopsis', {}).get('Detailed') - return self.playlist_result(entries, video_id, title, description) - - formats = [] - for language_set in info.get('LanguageSets', []): - manifest_url = None - m3u8_formats = [] - audio = language_set.get('Audio') or '' - subtitle = language_set.get('Subtitle') or '' - base_format_id = audio - if subtitle: - base_format_id += '-%s' % subtitle - - def concat(suffix, sep='-'): - return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix - - medias = self._download_json( - 'https://public-api.viewster.com/movies/%s/videos' % entry_id, - video_id, fatal=False, query={ - 'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'], - 'language': audio, - 'subtitle': subtitle, - }) - if not medias: - continue - for media in medias: - video_url = media.get('Uri') - if not video_url: - continue - ext = determine_ext(video_url) - if ext == 'f4m': - manifest_url = video_url - video_url += '&' if '?' in video_url else '?' - video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1' - formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id=concat('hds'))) - elif ext == 'm3u8': - manifest_url = video_url - m3u8_formats = self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id=concat('hls'), - fatal=False) # m3u8 sometimes fail - if m3u8_formats: - formats.extend(m3u8_formats) - else: - qualities_basename = self._search_regex( - r'/([^/]+)\.csmil/', - manifest_url, 'qualities basename', default=None) - if not qualities_basename: - continue - QUALITIES_RE = r'((,\d+k)+,?)' - qualities = self._search_regex( - QUALITIES_RE, qualities_basename, - 'qualities', default=None) - if not qualities: - continue - qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(','))) - qualities.sort() - http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename) - http_url_basename = url_basename(video_url) - if m3u8_formats: - self._sort_formats(m3u8_formats) - m3u8_formats = list(filter( - lambda f: f.get('vcodec') != 'none', m3u8_formats)) - if len(qualities) == len(m3u8_formats): - for q, m3u8_format in zip(qualities, m3u8_formats): - f = m3u8_format.copy() - f.update({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'format_id': f['format_id'].replace('hls', 'http'), - 'protocol': 'http', - }) - formats.append(f) - else: - for q in qualities: - formats.append({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'ext': 'mp4', - 'format_id': 'http-%d' % q, - 'tbr': q, - }) - - if not formats and not info.get('VODSettings'): - self.raise_geo_restricted() - - self._sort_formats(formats) - - synopsis = info.get('Synopsis') or {} - # Prefer title outside synopsis since it's less messy - title = (info.get('Title') or synopsis['Title']).strip() - description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short') - duration = int_or_none(info.get('Duration')) - timestamp = parse_iso8601(info.get('ReleaseDate')) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index ddf375c6c..8cd611e1e 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -15,23 +15,25 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( + clean_html, determine_ext, + dict_get, ExtractorError, js_to_json, int_or_none, merge_dicts, - NO_DEFAULT, OnDemandPagedList, parse_filesize, - qualities, RegexNotFoundError, sanitized_Request, smuggle_url, std_headers, + str_or_none, try_get, unified_timestamp, unsmuggle_url, urlencode_postdata, + urljoin, unescapeHTML, ) @@ -190,7 +192,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): for tt in text_tracks: subtitles[tt['lang']] = [{ 'ext': 'vtt', - 'url': 'https://vimeo.com' + tt['url'], + 'url': urljoin('https://vimeo.com', tt['url']), }] thumbnails = [] @@ -211,6 +213,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): video_uploader_url = owner.get('url') return { + 'id': str_or_none(video_data.get('id')) or video_id, 'title': self._live_title(video_title) if is_live else video_title, 'uploader': owner.get('name'), 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, @@ -258,11 +261,11 @@ class VimeoIE(VimeoBaseInfoExtractor): (?: (?: www| - (?P<player>player) + player ) \. )? - vimeo(?P<pro>pro)?\.com/ + vimeo(?:pro)?\.com/ (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/) (?:.*?/)? (?: @@ -284,7 +287,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'id': '56015672', 'ext': 'mp4', 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479', + 'description': 'md5:2d3305bad981a06ff79f027f19865021', 'timestamp': 1355990239, 'upload_date': '20121220', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434', @@ -293,6 +296,9 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 10, 'license': 'by-sa', }, + 'params': { + 'format': 'best[protocol=https]', + }, }, { 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', @@ -305,8 +311,13 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_id': 'openstreetmapus', 'uploader': 'OpenStreetMap US', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', - 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', + 'description': 'md5:2c362968038d4499f4d79f88458590c1', 'duration': 1595, + 'upload_date': '20130610', + 'timestamp': 1370893156, + }, + 'params': { + 'format': 'best[protocol=https]', }, }, { @@ -323,6 +334,10 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 3610, 'description': None, }, + 'params': { + 'format': 'best[protocol=https]', + }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'http://vimeo.com/68375962', @@ -341,6 +356,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f', }, 'params': { + 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, }, @@ -441,10 +457,14 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader': '10Ft Films', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms', 'uploader_id': 'tenfootfilms', + 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384', + 'upload_date': '20130830', + 'timestamp': 1377853339, }, 'params': { 'skip_download': True, }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'http://player.vimeo.com/video/68375962', @@ -459,6 +479,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 10, }, 'params': { + 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, }, @@ -523,7 +544,7 @@ class VimeoIE(VimeoBaseInfoExtractor): def _verify_player_video_password(self, url, video_id, headers): password = self._downloader.params.get('videopassword') if password is None: - raise ExtractorError('This video is protected by a password, use the --video-password option') + raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) data = urlencode_postdata({ 'password': base64.b64encode(password.encode()), }) @@ -552,28 +573,26 @@ class VimeoIE(VimeoBaseInfoExtractor): r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None) # Extract ID from URL - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) orig_url = url - if mobj.group('pro'): + is_pro = 'vimeopro.com/' in url + is_player = '://player.vimeo.com/video/' in url + if is_pro: # some videos require portfolio_id to be present in player url # https://github.com/ytdl-org/youtube-dl/issues/20070 url = self._extract_url(url, self._download_webpage(url, video_id)) - elif mobj.group('player'): + if not url: + url = 'https://vimeo.com/' + video_id + elif is_player: url = 'https://player.vimeo.com/video/' + video_id elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): url = 'https://vimeo.com/' + video_id - # Retrieve video webpage to extract further information - request = sanitized_Request(url, headers=headers) try: - webpage, urlh = self._download_webpage_handle(request, video_id) - redirect_url = compat_str(urlh.geturl()) - # Some URLs redirect to ondemand can't be extracted with - # this extractor right away thus should be passed through - # ondemand extractor (e.g. https://vimeo.com/73445910) - if VimeoOndemandIE.suitable(redirect_url): - return self.url_result(redirect_url, VimeoOndemandIE.ie_key()) + # Retrieve video webpage to extract further information + webpage, urlh = self._download_webpage_handle( + url, video_id, headers=headers) + redirect_url = urlh.geturl() except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() @@ -600,6 +619,7 @@ class VimeoIE(VimeoBaseInfoExtractor): cc_license = None timestamp = None + video_description = None # Extract the config JSON try: @@ -611,17 +631,17 @@ class VimeoIE(VimeoBaseInfoExtractor): # Sometimes new react-based page is served instead of old one that require # different config URL extraction approach (see # https://github.com/ytdl-org/youtube-dl/pull/7209) - vimeo_clip_page_config = self._search_regex( - r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, - 'vimeo clip page config') - page_config = self._parse_json(vimeo_clip_page_config, video_id) + page_config = self._parse_json(self._search_regex( + r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});', + webpage, 'page config'), video_id) config_url = page_config['player']['config_url'] cc_license = page_config.get('cc_license') timestamp = try_get( page_config, lambda x: x['clip']['uploaded_on'], compat_str) - config_json = self._download_webpage(config_url, video_id) - config = json.loads(config_json) + video_description = clean_html(dict_get( + page_config, ('description', 'description_html_escaped'))) + config = self._download_json(config_url, video_id) except RegexNotFoundError: # For pro videos or player.vimeo.com urls # We try to find out to which variable is assigned the config dic @@ -675,14 +695,14 @@ class VimeoIE(VimeoBaseInfoExtractor): {'force_feature_id': True}), 'Vimeo') # Extract video description - - video_description = self._html_search_regex( - r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', - webpage, 'description', default=None) + if not video_description: + video_description = self._html_search_regex( + r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', + webpage, 'description', default=None) if not video_description: video_description = self._html_search_meta( 'description', webpage, default=None) - if not video_description and mobj.group('pro'): + if not video_description and is_pro: orig_webpage = self._download_webpage( orig_url, video_id, note='Downloading webpage for description', @@ -690,7 +710,7 @@ class VimeoIE(VimeoBaseInfoExtractor): if orig_webpage: video_description = self._html_search_meta( 'description', orig_webpage, default=None) - if not video_description and not mobj.group('player'): + if not video_description and not is_player: self._downloader.report_warning('Cannot find video description') # Extract upload date @@ -730,7 +750,6 @@ class VimeoIE(VimeoBaseInfoExtractor): channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None info_dict = { - 'id': video_id, 'formats': formats, 'timestamp': unified_timestamp(timestamp), 'description': video_description, @@ -748,9 +767,9 @@ class VimeoIE(VimeoBaseInfoExtractor): return info_dict -class VimeoOndemandIE(VimeoBaseInfoExtractor): +class VimeoOndemandIE(VimeoIE): IE_NAME = 'vimeo:ondemand' - _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)' _TESTS = [{ # ondemand video not available via https://vimeo.com/id 'url': 'https://vimeo.com/ondemand/20704', @@ -762,24 +781,32 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor): 'uploader': 'גם סרטים', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms', 'uploader_id': 'gumfilms', + 'description': 'md5:4c027c965e439de4baab621e48b60791', + 'upload_date': '20140906', + 'timestamp': 1410032453, }, 'params': { 'format': 'best[protocol=https]', }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { # requires Referer to be passed along with og:video:url 'url': 'https://vimeo.com/ondemand/36938/126682985', 'info_dict': { - 'id': '126682985', + 'id': '126584684', 'ext': 'mp4', 'title': 'Rävlock, rätt läte på rätt plats', 'uploader': 'Lindroth & Norin', - 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847', - 'uploader_id': 'user14430847', + 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin', + 'uploader_id': 'lindrothnorin', + 'description': 'md5:c3c46a90529612c8279fb6af803fc0df', + 'upload_date': '20150502', + 'timestamp': 1430586422, }, 'params': { 'skip_download': True, }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'https://vimeo.com/ondemand/nazmaalik', 'only_matching': True, @@ -791,16 +818,6 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor): 'only_matching': True, }] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - return self.url_result( - # Some videos require Referer to be passed along with og:video:url - # similarly to generic vimeo embeds (e.g. - # https://vimeo.com/ondemand/36938/126682985). - VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url), - VimeoIE.ie_key()) - class VimeoChannelIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:channel' @@ -816,6 +833,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): }, 'playlist_mincount': 25, }] + _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s' def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) @@ -824,33 +842,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): return self._TITLE or self._html_search_regex( self._TITLE_RE, webpage, 'list title', fatal=False) - def _login_list_password(self, page_url, list_id, webpage): - login_form = self._search_regex( - r'(?s)<form[^>]+?id="pw_form"(.*?)</form>', - webpage, 'login form', default=None) - if not login_form: - return webpage - - password = self._downloader.params.get('videopassword') - if password is None: - raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) - fields = self._hidden_inputs(login_form) - token, vuid = self._extract_xsrft_and_vuid(webpage) - fields['token'] = token - fields['password'] = password - post = urlencode_postdata(fields) - password_path = self._search_regex( - r'action="([^"]+)"', login_form, 'password URL') - password_url = compat_urlparse.urljoin(page_url, password_path) - password_request = sanitized_Request(password_url, post) - password_request.add_header('Content-type', 'application/x-www-form-urlencoded') - self._set_vimeo_cookie('vuid', vuid) - self._set_vimeo_cookie('xsrft', token) - - return self._download_webpage( - password_request, list_id, - 'Verifying the password', 'Wrong password') - def _title_and_entries(self, list_id, base_url): for pagenum in itertools.count(1): page_url = self._page_url(base_url, pagenum) @@ -859,7 +850,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): 'Downloading page %s' % pagenum) if pagenum == 1: - webpage = self._login_list_password(page_url, list_id, webpage) yield self._extract_list_title(webpage) # Try extracting href first since not all videos are available via @@ -887,14 +877,13 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): return self.playlist_result(title_and_entries, list_id, list_title) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) + channel_id = self._match_id(url) + return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id) class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' + _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' _TESTS = [{ 'url': 'https://vimeo.com/nkistudio/videos', @@ -904,14 +893,10 @@ class VimeoUserIE(VimeoChannelIE): }, 'playlist_mincount': 66, }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - return self._extract_videos(name, 'https://vimeo.com/%s' % name) + _BASE_URL_TEMPL = 'https://vimeo.com/%s' -class VimeoAlbumIE(VimeoChannelIE): +class VimeoAlbumIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:album' _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' @@ -939,7 +924,7 @@ class VimeoAlbumIE(VimeoChannelIE): def _fetch_page(self, album_id, authorizaion, hashed_pass, page): api_page = page + 1 query = { - 'fields': 'link', + 'fields': 'link,uri', 'page': api_page, 'per_page': self._PAGE_SIZE, } @@ -954,39 +939,60 @@ class VimeoAlbumIE(VimeoChannelIE): link = video.get('link') if not link: continue - yield self.url_result(link, VimeoIE.ie_key(), VimeoIE._match_id(link)) + uri = video.get('uri') + video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None + yield self.url_result(link, VimeoIE.ie_key(), video_id) def _real_extract(self, url): album_id = self._match_id(url) webpage = self._download_webpage(url, album_id) - webpage = self._login_list_password(url, album_id, webpage) - api_config = self._extract_vimeo_config(webpage, album_id)['api'] + viewer = self._parse_json(self._search_regex( + r'bootstrap_data\s*=\s*({.+?})</script>', + webpage, 'bootstrap data'), album_id)['viewer'] + jwt = viewer['jwt'] + album = self._download_json( + 'https://api.vimeo.com/albums/' + album_id, + album_id, headers={'Authorization': 'jwt ' + jwt}, + query={'fields': 'description,name,privacy'}) + hashed_pass = None + if try_get(album, lambda x: x['privacy']['view']) == 'password': + password = self._downloader.params.get('videopassword') + if not password: + raise ExtractorError( + 'This album is protected by a password, use the --video-password option', + expected=True) + self._set_vimeo_cookie('vuid', viewer['vuid']) + try: + hashed_pass = self._download_json( + 'https://vimeo.com/showcase/%s/auth' % album_id, + album_id, 'Verifying the password', data=urlencode_postdata({ + 'password': password, + 'token': viewer['xsrft'], + }), headers={ + 'X-Requested-With': 'XMLHttpRequest', + })['hashed_pass'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError('Wrong password', expected=True) + raise entries = OnDemandPagedList(functools.partial( - self._fetch_page, album_id, api_config['jwt'], - api_config.get('hashed_pass')), self._PAGE_SIZE) - return self.playlist_result(entries, album_id, self._html_search_regex( - r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False)) + self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE) + return self.playlist_result( + entries, album_id, album.get('name'), album.get('description')) -class VimeoGroupsIE(VimeoAlbumIE): +class VimeoGroupsIE(VimeoChannelIE): IE_NAME = 'vimeo:group' - _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)' + _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)' _TESTS = [{ - 'url': 'https://vimeo.com/groups/rolexawards', + 'url': 'https://vimeo.com/groups/kattykay', 'info_dict': { - 'id': 'rolexawards', - 'title': 'Rolex Awards for Enterprise', + 'id': 'kattykay', + 'title': 'Katty Kay', }, - 'playlist_mincount': 73, + 'playlist_mincount': 27, }] - - def _extract_list_title(self, webpage): - return self._og_search_title(webpage, fatal=False) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) + _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s' class VimeoReviewIE(VimeoBaseInfoExtractor): @@ -1002,7 +1008,9 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 'title': "DICK HARDWICK 'Comedian'", 'uploader': 'Richard Hardwick', 'uploader_id': 'user21297594', - } + 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks", + }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'note': 'video player needs Referer', 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', @@ -1015,7 +1023,8 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 'duration': 2773, 'thumbnail': r're:^https?://.*\.jpg$', 'uploader_id': 'user22258446', - } + }, + 'skip': 'video gone', }, { 'note': 'Password protected', 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde', @@ -1035,33 +1044,20 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): def _real_initialize(self): self._login() - def _get_config_url(self, webpage_url, video_id, video_password_verified=False): - webpage = self._download_webpage(webpage_url, video_id) - config_url = self._html_search_regex( - r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, - 'config URL', default=None, group='url') - if not config_url: - data = self._parse_json(self._search_regex( - r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data', - default=NO_DEFAULT if video_password_verified else '{}'), video_id) - config = data.get('vimeo_esi', {}).get('config', {}) - config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl']) - if config_url is None: - self._verify_video_password(webpage_url, video_id, webpage) - config_url = self._get_config_url( - webpage_url, video_id, video_password_verified=True) - return config_url - def _real_extract(self, url): page_url, video_id = re.match(self._VALID_URL, url).groups() - config_url = self._get_config_url(url, video_id) + clip_data = self._download_json( + page_url.replace('/review/', '/review/data/'), + video_id)['clipData'] + config_url = clip_data['configUrl'] config = self._download_json(config_url, video_id) info_dict = self._parse_config(config, video_id) - source_format = self._extract_original_format(page_url, video_id) + source_format = self._extract_original_format( + page_url + '/action', video_id) if source_format: info_dict['formats'].append(source_format) self._vimeo_sort_formats(info_dict['formats']) - info_dict['id'] = video_id + info_dict['description'] = clean_html(clip_data.get('description')) return info_dict @@ -1115,94 +1111,17 @@ class VimeoLikesIE(VimeoChannelIE): return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id) -class VHXEmbedIE(InfoExtractor): +class VHXEmbedIE(VimeoBaseInfoExtractor): IE_NAME = 'vhx:embed' _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' - def _call_api(self, video_id, access_token, path='', query=None): - return self._download_json( - 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ - 'Authorization': 'Bearer ' + access_token, - }, query=query) - def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - credentials = self._parse_json(self._search_regex( - r'(?s)credentials\s*:\s*({.+?}),', webpage, - 'config'), video_id, js_to_json) - access_token = credentials['access_token'] - - query = {} - for k, v in credentials.items(): - if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': - if k == 'authUserToken': - query['auth_user_token'] = v - else: - query[k] = v - files = self._call_api(video_id, access_token, '/files', query) - - formats = [] - for f in files: - href = try_get(f, lambda x: x['_links']['source']['href']) - if not href: - continue - method = f.get('method') - if method == 'hls': - formats.extend(self._extract_m3u8_formats( - href, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - elif method == 'dash': - formats.extend(self._extract_mpd_formats( - href, video_id, mpd_id='dash', fatal=False)) - else: - fmt = { - 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), - 'format_id': 'http', - 'preference': 1, - 'url': href, - 'vcodec': f.get('codec'), - } - quality = f.get('quality') - if quality: - fmt.update({ - 'format_id': 'http-' + quality, - 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), - }) - formats.append(fmt) - self._sort_formats(formats) - - video_data = self._call_api(video_id, access_token) - title = video_data.get('title') or video_data['name'] - - subtitles = {} - for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: - lang = subtitle.get('srclang') or subtitle.get('label') - for _link in subtitle.get('_links', {}).values(): - href = _link.get('href') - if not href: - continue - subtitles.setdefault(lang, []).append({ - 'url': href, - }) - - q = qualities(['small', 'medium', 'large', 'source']) - thumbnails = [] - for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): - thumbnails.append({ - 'id': thumbnail_id, - 'url': thumbnail_url, - 'preference': q(thumbnail_id), - }) - - return { - 'id': video_id, - 'title': title, - 'description': video_data.get('description'), - 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), - 'formats': formats, - 'subtitles': subtitles, - 'thumbnails': thumbnails, - 'timestamp': unified_timestamp(video_data.get('created_at')), - 'view_count': int_or_none(video_data.get('plays_count')), - } + config_url = self._parse_json(self._search_regex( + r'window\.OTTData\s*=\s*({.+})', webpage, + 'ott data'), video_id, js_to_json)['config_url'] + config = self._download_json(config_url, video_id) + info = self._parse_config(config, video_id) + self._vimeo_sort_formats(info['formats']) + return info diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 8b6dc0e24..00ec006c4 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import collections +import functools import re from .common import InfoExtractor @@ -11,8 +12,8 @@ from ..utils import ( ExtractorError, get_element_by_class, int_or_none, + OnDemandPagedList, orderedSet, - remove_start, str_or_none, str_to_int, unescapeHTML, @@ -21,6 +22,7 @@ from ..utils import ( urlencode_postdata, ) from .dailymotion import DailymotionIE +from .odnoklassniki import OdnoklassnikiIE from .pladform import PladformIE from .vimeo import VimeoIE from .youtube import YoutubeIE @@ -60,6 +62,18 @@ class VKBaseIE(InfoExtractor): def _real_initialize(self): self._login() + def _download_payload(self, path, video_id, data, fatal=True): + data['al'] = 1 + code, payload = self._download_json( + 'https://vk.com/%s.php' % path, video_id, + data=urlencode_postdata(data), fatal=fatal, + headers={'X-Requested-With': 'XMLHttpRequest'})['payload'] + if code == '3': + self.raise_login_required() + elif code == '8': + raise ExtractorError(clean_html(payload[0][1:-1]), expected=True) + return payload + class VKIE(VKBaseIE): IE_NAME = 'vk' @@ -96,7 +110,6 @@ class VKIE(VKBaseIE): }, { 'url': 'http://vk.com/video205387401_165548505', - 'md5': '6c0aeb2e90396ba97035b9cbde548700', 'info_dict': { 'id': '205387401_165548505', 'ext': 'mp4', @@ -110,18 +123,18 @@ class VKIE(VKBaseIE): }, { 'note': 'Embedded video', - 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1', - 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a', + 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa', + 'md5': '7babad3b85ea2e91948005b1b8b0cb84', 'info_dict': { - 'id': '32194266_162925554', + 'id': '-77521_162222515', 'ext': 'mp4', - 'uploader': 'Vladimir Gavrin', - 'title': 'Lin Dan', - 'duration': 101, - 'upload_date': '20120730', - 'view_count': int, + 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', + 'title': 'ProtivoGunz - Хуёвая песня', + 'duration': 195, + 'upload_date': '20120212', + 'timestamp': 1329049880, + 'uploader_id': '-77521', }, - 'skip': 'This video has been removed from public access.', }, { # VIDEO NOW REMOVED @@ -138,18 +151,19 @@ class VKIE(VKBaseIE): 'upload_date': '20121218', 'view_count': int, }, - 'skip': 'Requires vk account credentials', + 'skip': 'Removed', }, { 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d', - 'md5': '4d7a5ef8cf114dfa09577e57b2993202', 'info_dict': { 'id': '-43215063_168067957', 'ext': 'mp4', - 'uploader': 'Киномания - лучшее из мира кино', + 'uploader': 'Bro Mazter', 'title': ' ', 'duration': 7291, 'upload_date': '20140328', + 'uploader_id': '223413403', + 'timestamp': 1396018030, }, 'skip': 'Requires vk account credentials', }, @@ -165,7 +179,7 @@ class VKIE(VKBaseIE): 'upload_date': '20140626', 'view_count': int, }, - 'skip': 'Only works from Russia', + 'skip': 'Removed', }, { # video (removed?) only available with list id @@ -204,8 +218,7 @@ class VKIE(VKBaseIE): 'id': 'k3lz2cmXyRuJQSjGHUv', 'ext': 'mp4', 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f', - # TODO: fix test by fixing dailymotion description extraction - 'description': 'md5:c651358f03c56f1150b555c26d90a0fd', + 'description': 'md5:424b8e88cc873217f520e582ba28bb36', 'uploader': 'AniLibria.Tv', 'upload_date': '20160914', 'uploader_id': 'x1p5vl5', @@ -247,6 +260,9 @@ class VKIE(VKBaseIE): 'uploader_id': '-387766', 'timestamp': 1475137527, }, + 'params': { + 'skip_download': True, + }, }, { # live stream, hls and rtmp links, most likely already finished live @@ -288,80 +304,94 @@ class VKIE(VKBaseIE): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') + mv_data = {} if video_id: - info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id + data = { + 'act': 'show_inline', + 'video': video_id, + } # Some videos (removed?) can only be downloaded with list id specified list_id = mobj.group('list_id') if list_id: - info_url += '&list=%s' % list_id + data['list'] = list_id + + payload = self._download_payload('al_video', video_id, data) + info_page = payload[1] + opts = payload[-1] + mv_data = opts.get('mvData') or {} + player = opts.get('player') or {} else: - info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query') video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) - info_page = self._download_webpage(info_url, video_id) + info_page = self._download_webpage( + 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) - error_message = self._html_search_regex( - [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', - r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], - info_page, 'error message', default=None) - if error_message: - raise ExtractorError(error_message, expected=True) + error_message = self._html_search_regex( + [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', + r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], + info_page, 'error message', default=None) + if error_message: + raise ExtractorError(error_message, expected=True) - if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): - raise ExtractorError( - 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', - expected=True) + if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): + raise ExtractorError( + 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', + expected=True) - ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' + ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' - ERRORS = { - r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': - ERROR_COPYRIGHT, + ERRORS = { + r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': + ERROR_COPYRIGHT, - r'>The video .*? was removed from public access by request of the copyright holder.<': - ERROR_COPYRIGHT, + r'>The video .*? was removed from public access by request of the copyright holder.<': + ERROR_COPYRIGHT, - r'<!>Please log in or <': - 'Video %s is only available for registered users, ' - 'use --username and --password options to provide account credentials.', + r'<!>Please log in or <': + 'Video %s is only available for registered users, ' + 'use --username and --password options to provide account credentials.', - r'<!>Unknown error': - 'Video %s does not exist.', + r'<!>Unknown error': + 'Video %s does not exist.', - r'<!>Видео временно недоступно': - 'Video %s is temporarily unavailable.', + r'<!>Видео временно недоступно': + 'Video %s is temporarily unavailable.', - r'<!>Access denied': - 'Access denied to video %s.', + r'<!>Access denied': + 'Access denied to video %s.', - r'<!>Видеозапись недоступна, так как её автор был заблокирован.': - 'Video %s is no longer available, because its author has been blocked.', + r'<!>Видеозапись недоступна, так как её автор был заблокирован.': + 'Video %s is no longer available, because its author has been blocked.', - r'<!>This video is no longer available, because its author has been blocked.': - 'Video %s is no longer available, because its author has been blocked.', + r'<!>This video is no longer available, because its author has been blocked.': + 'Video %s is no longer available, because its author has been blocked.', - r'<!>This video is no longer available, because it has been deleted.': - 'Video %s is no longer available, because it has been deleted.', + r'<!>This video is no longer available, because it has been deleted.': + 'Video %s is no longer available, because it has been deleted.', - r'<!>The video .+? is not available in your region.': - 'Video %s is not available in your region.', - } + r'<!>The video .+? is not available in your region.': + 'Video %s is not available in your region.', + } + + for error_re, error_msg in ERRORS.items(): + if re.search(error_re, info_page): + raise ExtractorError(error_msg % video_id, expected=True) - for error_re, error_msg in ERRORS.items(): - if re.search(error_re, info_page): - raise ExtractorError(error_msg % video_id, expected=True) + player = self._parse_json(self._search_regex( + r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', + info_page, 'player params'), video_id) youtube_url = YoutubeIE._extract_url(info_page) if youtube_url: - return self.url_result(youtube_url, ie=YoutubeIE.ie_key()) + return self.url_result(youtube_url, YoutubeIE.ie_key()) vimeo_url = VimeoIE._extract_url(url, info_page) if vimeo_url is not None: - return self.url_result(vimeo_url) + return self.url_result(vimeo_url, VimeoIE.ie_key()) pladform_url = PladformIE._extract_url(info_page) if pladform_url: - return self.url_result(pladform_url) + return self.url_result(pladform_url, PladformIE.ie_key()) m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page) @@ -374,6 +404,10 @@ class VKIE(VKBaseIE): if dailymotion_urls: return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key()) + odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) if m_opts: m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) @@ -383,38 +417,7 @@ class VKIE(VKBaseIE): opts_url = 'http:' + opts_url return self.url_result(opts_url) - # vars does not look to be served anymore since 24.10.2016 - data = self._parse_json( - self._search_regex( - r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'), - video_id, fatal=False) - - # <!json> is served instead - if not data: - data = self._parse_json( - self._search_regex( - [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'], - info_page, 'json', default='{}'), - video_id) - if data: - data = data['player']['params'][0] - - if not data: - data = self._parse_json( - self._search_regex( - r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page, - 'player params', default='{}'), - video_id) - if data: - data = data['params'][0] - - # <!--{...} - if not data: - data = self._parse_json( - self._search_regex( - r'<!--\s*({.+})', info_page, 'payload'), - video_id)['payload'][-1][-1]['player']['params'][0] - + data = player['params'][0] title = unescapeHTML(data['md_title']) # 2 = live @@ -463,12 +466,12 @@ class VKIE(VKBaseIE): 'title': title, 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), - 'uploader_id': str_or_none(data.get('author_id')), - 'duration': data.get('duration'), + 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')), + 'duration': int_or_none(data.get('duration') or mv_data.get('duration')), 'timestamp': timestamp, 'view_count': view_count, - 'like_count': int_or_none(data.get('liked')), - 'dislike_count': int_or_none(data.get('nolikes')), + 'like_count': int_or_none(mv_data.get('likes')), + 'comment_count': int_or_none(mv_data.get('commcount')), 'is_live': is_live, } @@ -476,15 +479,23 @@ class VKIE(VKBaseIE): class VKUserVideosIE(VKBaseIE): IE_NAME = 'vk:uservideos' IE_DESC = "VK - User's Videos" - _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)' + _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)' _TEMPLATE_URL = 'https://vk.com/videos' _TESTS = [{ - 'url': 'http://vk.com/videos205387401', + 'url': 'https://vk.com/videos-767561', + 'info_dict': { + 'id': '-767561_all', + }, + 'playlist_mincount': 1150, + }, { + 'url': 'https://vk.com/videos-767561?section=uploaded', 'info_dict': { - 'id': '205387401', - 'title': "Tom Cruise's Videos", + 'id': '-767561_uploaded', }, - 'playlist_mincount': 4, + 'playlist_mincount': 425, + }, { + 'url': 'http://vk.com/videos205387401', + 'only_matching': True, }, { 'url': 'http://vk.com/videos-77521', 'only_matching': True, @@ -498,22 +509,33 @@ class VKUserVideosIE(VKBaseIE): 'url': 'http://new.vk.com/videos205387401', 'only_matching': True, }] + _PAGE_SIZE = 1000 + _VIDEO = collections.namedtuple('Video', ['owner_id', 'id']) + + def _fetch_page(self, page_id, section, page): + l = self._download_payload('al_video', page_id, { + 'act': 'load_videos_silent', + 'offset': page * self._PAGE_SIZE, + 'oid': page_id, + 'section': section, + })[0][section]['list'] + + for video in l: + v = self._VIDEO._make(video[:2]) + video_id = '%d_%d' % (v.owner_id, v.id) + yield self.url_result( + 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id) def _real_extract(self, url): - page_id = self._match_id(url) - - webpage = self._download_webpage(url, page_id) - - entries = [ - self.url_result( - 'http://vk.com/video' + video_id, 'VK', video_id=video_id) - for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))] + page_id, section = re.match(self._VALID_URL, url).groups() + if not section: + section = 'all' - title = unescapeHTML(self._search_regex( - r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos', - webpage, 'title', default=page_id)) + entries = OnDemandPagedList( + functools.partial(self._fetch_page, page_id, section), + self._PAGE_SIZE) - return self.playlist_result(entries, page_id, title) + return self.playlist_result(entries, '%s_%s' % (page_id, section)) class VKWallPostIE(VKBaseIE): @@ -523,15 +545,15 @@ class VKWallPostIE(VKBaseIE): # public page URL, audio playlist 'url': 'https://vk.com/bs.official?w=wall-23538238_35', 'info_dict': { - 'id': '23538238_35', - 'title': 'Black Shadow - Wall post 23538238_35', + 'id': '-23538238_35', + 'title': 'Black Shadow - Wall post -23538238_35', 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c', }, 'playlist': [{ 'md5': '5ba93864ec5b85f7ce19a9af4af080f6', 'info_dict': { 'id': '135220665_111806521', - 'ext': 'mp3', + 'ext': 'mp4', 'title': 'Black Shadow - Слепое Верование', 'duration': 370, 'uploader': 'Black Shadow', @@ -542,18 +564,16 @@ class VKWallPostIE(VKBaseIE): 'md5': '4cc7e804579122b17ea95af7834c9233', 'info_dict': { 'id': '135220665_111802303', - 'ext': 'mp3', + 'ext': 'mp4', 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!', 'duration': 423, 'uploader': 'Black Shadow', 'artist': 'Black Shadow', 'track': 'Война - Негасимое Бездны Пламя!', }, - 'params': { - 'skip_download': True, - }, }], 'params': { + 'skip_download': True, 'usenetrc': True, }, 'skip': 'Requires vk account credentials', @@ -562,7 +582,7 @@ class VKWallPostIE(VKBaseIE): 'url': 'https://vk.com/wall85155021_6319', 'info_dict': { 'id': '85155021_6319', - 'title': 'Sergey Gorbunov - Wall post 85155021_6319', + 'title': 'Сергей Горбунов - Wall post 85155021_6319', }, 'playlist_count': 1, 'params': { @@ -578,58 +598,72 @@ class VKWallPostIE(VKBaseIE): 'url': 'https://m.vk.com/wall-23538238_35', 'only_matching': True, }] + _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/=' + _AUDIO = collections.namedtuple('Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads']) + + def _decode(self, enc): + dec = '' + e = n = 0 + for c in enc: + r = self._BASE64_CHARS.index(c) + cond = n % 4 + e = 64 * e + r if cond else r + n += 1 + if cond: + dec += chr(255 & e >> (-2 * n & 6)) + return dec + + def _unmask_url(self, mask_url, vk_id): + if 'audio_api_unavailable' in mask_url: + extra = mask_url.split('?extra=')[1].split('#') + func, base = self._decode(extra[1]).split(chr(11)) + mask_url = list(self._decode(extra[0])) + url_len = len(mask_url) + indexes = [None] * url_len + index = int(base) ^ vk_id + for n in range(url_len - 1, -1, -1): + index = (url_len * (n + 1) ^ index + n) % url_len + indexes[n] = index + for n in range(1, url_len): + c = mask_url[n] + index = indexes[url_len - 1 - n] + mask_url[n] = mask_url[index] + mask_url[index] = c + mask_url = ''.join(mask_url) + return mask_url def _real_extract(self, url): post_id = self._match_id(url) - wall_url = 'https://vk.com/wall%s' % post_id - - post_id = remove_start(post_id, '-') - - webpage = self._download_webpage(wall_url, post_id) - - error = self._html_search_regex( - r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)', - webpage, 'error', default=None) - if error: - raise ExtractorError('VK said: %s' % error, expected=True) + webpage = self._download_payload('wkview', post_id, { + 'act': 'show', + 'w': 'wall' + post_id, + })[1] description = clean_html(get_element_by_class('wall_post_text', webpage)) uploader = clean_html(get_element_by_class('author', webpage)) - thumbnail = self._og_search_thumbnail(webpage) entries = [] - audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage) - if audio_ids: - al_audio = self._download_webpage( - 'https://vk.com/al_audio.php', post_id, - note='Downloading audio info', fatal=False, - data=urlencode_postdata({ - 'act': 'reload_audio', - 'al': '1', - 'ids': ','.join(audio_ids) - })) - if al_audio: - Audio = collections.namedtuple( - 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration']) - audios = self._parse_json( - self._search_regex( - r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'), - post_id, fatal=False, transform_source=unescapeHTML) - if isinstance(audios, list): - for audio in audios: - a = Audio._make(audio[:6]) - entries.append({ - 'id': '%s_%s' % (a.user_id, a.id), - 'url': a.url, - 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id, - 'thumbnail': thumbnail, - 'duration': a.duration, - 'uploader': uploader, - 'artist': a.artist, - 'track': a.track, - }) + for audio in re.findall(r'data-audio="([^"]+)', webpage): + audio = self._parse_json(unescapeHTML(audio), post_id) + a = self._AUDIO._make(audio[:16]) + if not a.url: + continue + title = unescapeHTML(a.title) + performer = unescapeHTML(a.performer) + entries.append({ + 'id': '%s_%s' % (a.owner_id, a.id), + 'url': self._unmask_url(a.url, a.ads['vk_id']), + 'title': '%s - %s' % (performer, title) if performer else title, + 'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None, + 'duration': int_or_none(a.duration), + 'uploader': uploader, + 'artist': performer, + 'track': title, + 'ext': 'mp4', + 'protocol': 'm3u8', + }) for video in re.finditer( r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage): diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index c3429f723..f79531e6f 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -6,22 +6,18 @@ import time import itertools from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlencode, - compat_str, -) +from .naver import NaverBaseIE +from ..compat import compat_str from ..utils import ( - dict_get, ExtractorError, - float_or_none, - int_or_none, + merge_dicts, remove_start, try_get, urlencode_postdata, ) -class VLiveIE(InfoExtractor): +class VLiveIE(NaverBaseIE): IE_NAME = 'vlive' _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)' _NETRC_MACHINE = 'vlive' @@ -34,6 +30,7 @@ class VLiveIE(InfoExtractor): 'title': "[V LIVE] Girl's Day's Broadcast", 'creator': "Girl's Day", 'view_count': int, + 'uploader_id': 'muploader_a', }, }, { 'url': 'http://www.vlive.tv/video/16937', @@ -44,6 +41,7 @@ class VLiveIE(InfoExtractor): 'creator': 'EXO', 'view_count': int, 'subtitles': 'mincount:12', + 'uploader_id': 'muploader_j', }, 'params': { 'skip_download': True, @@ -187,45 +185,9 @@ class VLiveIE(InfoExtractor): 'This video is only available for CH+ subscribers') long_video_id, key = video_info['vid'], video_info['inkey'] - playinfo = self._download_json( - 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s' - % compat_urllib_parse_urlencode({ - 'videoId': long_video_id, - 'key': key, - 'ptc': 'http', - 'doct': 'json', # document type (xml or json) - 'cpt': 'vtt', # captions type (vtt or ttml) - }), video_id) - - formats = [{ - 'url': vid['source'], - 'format_id': vid.get('encodingOption', {}).get('name'), - 'abr': float_or_none(vid.get('bitrate', {}).get('audio')), - 'vbr': float_or_none(vid.get('bitrate', {}).get('video')), - 'width': int_or_none(vid.get('encodingOption', {}).get('width')), - 'height': int_or_none(vid.get('encodingOption', {}).get('height')), - 'filesize': int_or_none(vid.get('size')), - } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')] - self._sort_formats(formats) - - view_count = int_or_none(playinfo.get('meta', {}).get('count')) - - subtitles = {} - for caption in playinfo.get('captions', {}).get('list', []): - lang = dict_get(caption, ('locale', 'language', 'country', 'label')) - if lang and caption.get('source'): - subtitles[lang] = [{ - 'ext': 'vtt', - 'url': caption['source']}] - - info = self._get_common_fields(webpage) - info.update({ - 'id': video_id, - 'formats': formats, - 'view_count': view_count, - 'subtitles': subtitles, - }) - return info + return merge_dicts( + self._get_common_fields(webpage), + self._extract_video_info(video_id, long_video_id, key)) def _download_init_page(self, video_id): return self._download_webpage( diff --git a/youtube_dl/extractor/vodplatform.py b/youtube_dl/extractor/vodplatform.py index 239644340..74d2257e7 100644 --- a/youtube_dl/extractor/vodplatform.py +++ b/youtube_dl/extractor/vodplatform.py @@ -6,8 +6,8 @@ from ..utils import unescapeHTML class VODPlatformIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vod-platform\.net/[eE]mbed/(?P<id>[^/?#]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/(?P<id>[^/?#]+)' + _TESTS = [{ # from http://www.lbcgroup.tv/watch/chapter/29143/52844/%D8%A7%D9%84%D9%86%D8%B5%D8%B1%D8%A9-%D9%81%D9%8A-%D8%B6%D9%8A%D8%A7%D9%81%D8%A9-%D8%A7%D9%84%D9%80-cnn/ar 'url': 'http://vod-platform.net/embed/RufMcytHDolTH1MuKHY9Fw', 'md5': '1db2b7249ce383d6be96499006e951fc', @@ -16,7 +16,10 @@ class VODPlatformIE(InfoExtractor): 'ext': 'mp4', 'title': 'LBCi News_ النصرة في ضيافة الـ "سي.أن.أن"', } - } + }, { + 'url': 'http://embed.kwikmotion.com/embed/RufMcytHDolTH1MuKHY9Fw', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/voicerepublic.py b/youtube_dl/extractor/voicerepublic.py index 59e1359c4..a52e40afa 100644 --- a/youtube_dl/extractor/voicerepublic.py +++ b/youtube_dl/extractor/voicerepublic.py @@ -1,17 +1,12 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_urlparse, -) +from ..compat import compat_str from ..utils import ( ExtractorError, determine_ext, int_or_none, - sanitized_Request, + urljoin, ) @@ -26,8 +21,7 @@ class VoiceRepublicIE(InfoExtractor): 'ext': 'm4a', 'title': 'Watching the Watchers: Building a Sousveillance State', 'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.', - 'thumbnail': r're:^https?://.*\.(?:png|jpg)$', - 'duration': 1800, + 'duration': 1556, 'view_count': int, } }, { @@ -38,63 +32,31 @@ class VoiceRepublicIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - req = sanitized_Request( - compat_urlparse.urljoin(url, '/talks/%s' % display_id)) - # Older versions of Firefox get redirected to an "upgrade browser" page - req.add_header('User-Agent', 'youtube-dl') - webpage = self._download_webpage(req, display_id) + webpage = self._download_webpage(url, display_id) if '>Queued for processing, please stand by...<' in webpage: raise ExtractorError( 'Audio is still queued for processing', expected=True) - config = self._search_regex( - r'(?s)return ({.+?});\s*\n', webpage, - 'data', default=None) - data = self._parse_json(config, display_id, fatal=False) if config else None - if data: - title = data['title'] - description = data.get('teaser') - talk_id = compat_str(data.get('talk_id') or display_id) - talk = data['talk'] - duration = int_or_none(talk.get('duration')) - formats = [{ - 'url': compat_urlparse.urljoin(url, talk_url), - 'format_id': format_id, - 'ext': determine_ext(talk_url) or format_id, - 'vcodec': 'none', - } for format_id, talk_url in talk['links'].items()] - else: - title = self._og_search_title(webpage) - description = self._html_search_regex( - r"(?s)<div class='talk-teaser'[^>]*>(.+?)</div>", - webpage, 'description', fatal=False) - talk_id = self._search_regex( - [r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"], - webpage, 'talk id', default=None) or display_id - duration = None - player = self._search_regex( - r"class='vr-player jp-jplayer'([^>]+)>", webpage, 'player') - formats = [{ - 'url': compat_urlparse.urljoin(url, talk_url), - 'format_id': format_id, - 'ext': determine_ext(talk_url) or format_id, - 'vcodec': 'none', - } for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", player)] + talk = self._parse_json(self._search_regex( + r'initialSnapshot\s*=\s*({.+?});', + webpage, 'talk'), display_id)['talk'] + title = talk['title'] + formats = [{ + 'url': urljoin(url, talk_url), + 'format_id': format_id, + 'ext': determine_ext(talk_url) or format_id, + 'vcodec': 'none', + } for format_id, talk_url in talk['media_links'].items()] self._sort_formats(formats) - thumbnail = self._og_search_thumbnail(webpage) - view_count = int_or_none(self._search_regex( - r"class='play-count[^']*'>\s*(\d+) plays", - webpage, 'play count', fatal=False)) - return { - 'id': talk_id, + 'id': compat_str(talk.get('id') or display_id), 'display_id': display_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'view_count': view_count, + 'description': talk.get('teaser'), + 'thumbnail': talk.get('image_url'), + 'duration': int_or_none(talk.get('archived_duration')), + 'view_count': int_or_none(talk.get('play_count')), 'formats': formats, } diff --git a/youtube_dl/extractor/vzaar.py b/youtube_dl/extractor/vzaar.py index 3336e6c15..b7d02fca3 100644 --- a/youtube_dl/extractor/vzaar.py +++ b/youtube_dl/extractor/vzaar.py @@ -33,6 +33,18 @@ class VzaarIE(InfoExtractor): 'title': 'MP3', }, }, { + # hlsAes = true + 'url': 'https://view.vzaar.com/11379930/player', + 'info_dict': { + 'id': '11379930', + 'ext': 'mp4', + 'title': 'Videoaula', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { # with null videoTitle 'url': 'https://view.vzaar.com/20313539/download', 'only_matching': True, @@ -58,6 +70,7 @@ class VzaarIE(InfoExtractor): f = { 'url': source_url, 'format_id': 'http', + 'preference': 1, } if 'audio' in source_url: f.update({ @@ -75,13 +88,17 @@ class VzaarIE(InfoExtractor): video_guid = video_data.get('guid') usp = video_data.get('usp') - if isinstance(video_guid, compat_str) and isinstance(usp, dict): - m3u8_url = ('http://fable.vzaar.com/v4/usp/%s/%s.ism/.m3u8?' - % (video_guid, video_id)) + '&'.join( - '%s=%s' % (k, v) for k, v in usp.items()) - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + if video_data.get('uspEnabled') and isinstance(video_guid, compat_str) and isinstance(usp, dict): + hls_aes = video_data.get('hlsAes') + qs = '&'.join('%s=%s' % (k, v) for k, v in usp.items()) + url_templ = 'http://%%s.vzaar.com/v5/usp%s/%s/%s.ism%%s?' % ('aes' if hls_aes else '', video_guid, video_id) + m3u8_formats = self._extract_m3u8_formats( + url_templ % ('fable', '/.m3u8') + qs, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + if hls_aes: + for f in m3u8_formats: + f['_decryption_key_url'] = url_templ % ('goose', '') + qs + formats.extend(m3u8_formats) self._sort_formats(formats) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index fa142b974..168e5e901 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,9 +12,8 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)' - _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' - _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]{10})' + _EMBED_BASE_URL = 'http://fast.wistia.com/embed/' _TESTS = [{ 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt', @@ -43,33 +42,35 @@ class WistiaIE(InfoExtractor): 'only_matching': True, }] + # https://wistia.com/support/embed-and-share/video-on-your-website @staticmethod def _extract_url(webpage): - match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) - if match: - return unescapeHTML(match.group('url')) + urls = WistiaIE._extract_urls(webpage) + return urls[0] if urls else None - match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) - if match: - return 'wistia:%s' % match.group('id') - - match = re.search( - r'''(?sx) - <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2 - ''', webpage) - if match: - return 'wistia:%s' % match.group('id') + @staticmethod + def _extract_urls(webpage): + urls = [] + for match in re.finditer( + r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage): + urls.append(unescapeHTML(match.group('url'))) + for match in re.finditer( + r'''(?sx) + <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2 + ''', webpage): + urls.append('wistia:%s' % match.group('id')) + for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage): + urls.append('wistia:%s' % match.group('id')) + return urls def _real_extract(self, url): video_id = self._match_id(url) data_json = self._download_json( - self._API_URL % video_id, video_id, + self._EMBED_BASE_URL + 'medias/%s.json' % video_id, video_id, # Some videos require this. headers={ - 'Referer': url if url.startswith('http') else self._IFRAME_URL % video_id, + 'Referer': url if url.startswith('http') else self._EMBED_BASE_URL + 'iframe/' + video_id, }) if data_json.get('error'): @@ -94,27 +95,61 @@ class WistiaIE(InfoExtractor): 'url': aurl, 'width': int_or_none(a.get('width')), 'height': int_or_none(a.get('height')), + 'filesize': int_or_none(a.get('size')), }) else: aext = a.get('ext') - is_m3u8 = a.get('container') == 'm3u8' or aext == 'm3u8' - formats.append({ - 'format_id': atype, + display_name = a.get('display_name') + format_id = atype + if atype and atype.endswith('_video') and display_name: + format_id = '%s-%s' % (atype[:-6], display_name) + f = { + 'format_id': format_id, 'url': aurl, - 'tbr': int_or_none(a.get('bitrate')), - 'vbr': int_or_none(a.get('opt_vbitrate')), - 'width': int_or_none(a.get('width')), - 'height': int_or_none(a.get('height')), - 'filesize': int_or_none(a.get('size')), - 'vcodec': a.get('codec'), - 'container': a.get('container'), - 'ext': 'mp4' if is_m3u8 else aext, - 'protocol': 'm3u8' if is_m3u8 else None, + 'tbr': int_or_none(a.get('bitrate')) or None, 'preference': 1 if atype == 'original' else None, - }) + } + if display_name == 'Audio': + f.update({ + 'vcodec': 'none', + }) + else: + f.update({ + 'width': int_or_none(a.get('width')), + 'height': int_or_none(a.get('height')), + 'vcodec': a.get('codec'), + }) + if a.get('container') == 'm3u8' or aext == 'm3u8': + ts_f = f.copy() + ts_f.update({ + 'ext': 'ts', + 'format_id': f['format_id'].replace('hls-', 'ts-'), + 'url': f['url'].replace('.bin', '.ts'), + }) + formats.append(ts_f) + f.update({ + 'ext': 'mp4', + 'protocol': 'm3u8_native', + }) + else: + f.update({ + 'container': a.get('container'), + 'ext': aext, + 'filesize': int_or_none(a.get('size')), + }) + formats.append(f) self._sort_formats(formats) + subtitles = {} + for caption in data.get('captions', []): + language = caption.get('language') + if not language: + continue + subtitles[language] = [{ + 'url': self._EMBED_BASE_URL + 'captions/' + video_id + '.vtt?language=' + language, + }] + return { 'id': video_id, 'title': title, @@ -123,4 +158,5 @@ class WistiaIE(InfoExtractor): 'thumbnails': thumbnails, 'duration': float_or_none(data.get('duration')), 'timestamp': int_or_none(data.get('createdAt')), + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py index b38c7a7b3..48ef07ed1 100644 --- a/youtube_dl/extractor/xfileshare.py +++ b/youtube_dl/extractor/xfileshare.py @@ -4,37 +4,64 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_chr from ..utils import ( decode_packed_codes, determine_ext, ExtractorError, int_or_none, - NO_DEFAULT, + js_to_json, urlencode_postdata, ) +# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58 +def aa_decode(aa_code): + symbol_table = [ + ('7', '((ﾟｰﾟ) + (o^_^o))'), + ('6', '((o^_^o) +(o^_^o))'), + ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'), + ('2', '((o^_^o) - (ﾟΘﾟ))'), + ('4', '(ﾟｰﾟ)'), + ('3', '(o^_^o)'), + ('1', '(ﾟΘﾟ)'), + ('0', '(c^_^o)'), + ] + delim = '(ﾟДﾟ)[ﾟεﾟ]+' + ret = '' + for aa_char in aa_code.split(delim): + for val, pat in symbol_table: + aa_char = aa_char.replace(pat, val) + aa_char = aa_char.replace('+ ', '') + m = re.match(r'^\d+', aa_char) + if m: + ret += compat_chr(int(m.group(0), 8)) + else: + m = re.match(r'^u([\da-f]+)', aa_char) + if m: + ret += compat_chr(int(m.group(1), 16)) + return ret + + class XFileShareIE(InfoExtractor): _SITES = ( - (r'daclips\.(?:in|com)', 'DaClips'), - (r'filehoot\.com', 'FileHoot'), - (r'gorillavid\.(?:in|com)', 'GorillaVid'), - (r'movpod\.in', 'MovPod'), - (r'powerwatch\.pw', 'PowerWatch'), - (r'rapidvideo\.ws', 'Rapidvideo.ws'), + (r'clipwatching\.com', 'ClipWatching'), + (r'gounlimited\.to', 'GoUnlimited'), + (r'govid\.me', 'GoVid'), + (r'holavid\.com', 'HolaVid'), + (r'streamty\.com', 'Streamty'), (r'thevideobee\.to', 'TheVideoBee'), - (r'vidto\.(?:me|se)', 'Vidto'), - (r'streamin\.to', 'Streamin.To'), - (r'xvidstage\.com', 'XVIDSTAGE'), - (r'vidabc\.com', 'Vid ABC'), + (r'uqload\.com', 'Uqload'), (r'vidbom\.com', 'VidBom'), (r'vidlo\.us', 'vidlo'), - (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'), - (r'fastvideo\.me', 'FastVideo.me'), + (r'vidlocker\.xyz', 'VidLocker'), + (r'vidshare\.tv', 'VidShare'), + (r'vup\.to', 'VUp'), + (r'xvideosharing\.com', 'XVideoSharing'), ) IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1]) - _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' + _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' % '|'.join(site for site in list(zip(*_SITES))[0])) _FILE_NOT_FOUND_REGEXES = ( @@ -43,82 +70,14 @@ class XFileShareIE(InfoExtractor): ) _TESTS = [{ - 'url': 'http://gorillavid.in/06y9juieqpmi', - 'md5': '5ae4a3580620380619678ee4875893ba', - 'info_dict': { - 'id': '06y9juieqpmi', - 'ext': 'mp4', - 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', - 'thumbnail': r're:http://.*\.jpg', - }, - }, { - 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', - 'only_matching': True, - }, { - 'url': 'http://daclips.in/3rso4kdn6f9m', - 'md5': '1ad8fd39bb976eeb66004d3a4895f106', + 'url': 'http://xvideosharing.com/fq65f94nd2ve', + 'md5': '4181f63957e8fe90ac836fa58dc3c8a6', 'info_dict': { - 'id': '3rso4kdn6f9m', + 'id': 'fq65f94nd2ve', 'ext': 'mp4', - 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', + 'title': 'sample', 'thumbnail': r're:http://.*\.jpg', - } - }, { - 'url': 'http://movpod.in/0wguyyxi1yca', - 'only_matching': True, - }, { - 'url': 'http://filehoot.com/3ivfabn7573c.html', - 'info_dict': { - 'id': '3ivfabn7573c', - 'ext': 'mp4', - 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', - 'thumbnail': r're:http://.*\.jpg', - }, - 'skip': 'Video removed', - }, { - 'url': 'http://vidto.me/ku5glz52nqe1.html', - 'info_dict': { - 'id': 'ku5glz52nqe1', - 'ext': 'mp4', - 'title': 'test' - } - }, { - 'url': 'http://powerwatch.pw/duecjibvicbu', - 'info_dict': { - 'id': 'duecjibvicbu', - 'ext': 'mp4', - 'title': 'Big Buck Bunny trailer', - }, - }, { - 'url': 'http://xvidstage.com/e0qcnl03co6z', - 'info_dict': { - 'id': 'e0qcnl03co6z', - 'ext': 'mp4', - 'title': 'Chucky Prank 2015.mp4', - }, - }, { - # removed by administrator - 'url': 'http://xvidstage.com/amfy7atlkx25', - 'only_matching': True, - }, { - 'url': 'http://vidabc.com/i8ybqscrphfv', - 'info_dict': { - 'id': 'i8ybqscrphfv', - 'ext': 'mp4', - 'title': 're:Beauty and the Beast 2017', - }, - 'params': { - 'skip_download': True, }, - }, { - 'url': 'http://www.rapidvideo.cool/b667kprndr8w', - 'only_matching': True, - }, { - 'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html', - 'only_matching': True, - }, { - 'url': 'http://vidto.se/1tx1pf6t12cg.html', - 'only_matching': True, }] @staticmethod @@ -131,10 +90,9 @@ class XFileShareIE(InfoExtractor): webpage)] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + host, video_id = re.match(self._VALID_URL, url).groups() - url = 'http://%s/%s' % (mobj.group('host'), video_id) + url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id) webpage = self._download_webpage(url, video_id) if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES): @@ -142,7 +100,7 @@ class XFileShareIE(InfoExtractor): fields = self._hidden_inputs(webpage) - if fields['op'] == 'download1': + if fields.get('op') == 'download1': countdown = int_or_none(self._search_regex( r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>', webpage, 'countdown', default=None)) @@ -160,13 +118,37 @@ class XFileShareIE(InfoExtractor): (r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'h4-fine[^>]*>([^<]+)<', - r'>Watch (.+) ', + r'>Watch (.+)[ <]', r'<h2 class="video-page-head">([^<]+)</h2>', - r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'), # streamin.to + r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to + r'title\s*:\s*"([^"]+)"'), # govid.me webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or video_id).strip() - def extract_formats(default=NO_DEFAULT): + for regex, func in ( + (r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes), + (r'(ﾟ.+)', aa_decode)): + obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None) + if obf_code: + webpage = webpage.replace(obf_code, func(obf_code)) + + formats = [] + + jwplayer_data = self._search_regex( + [ + r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);', + r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);', + ], webpage, + 'jwplayer data', default=None) + if jwplayer_data: + jwplayer_data = self._parse_json( + jwplayer_data.replace(r"\'", "'"), video_id, js_to_json) + if jwplayer_data: + formats = self._parse_jwplayer_data( + jwplayer_data, video_id, False, + m3u8_id='hls', mpd_id='dash')['formats'] + + if not formats: urls = [] for regex in ( r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1', @@ -177,6 +159,12 @@ class XFileShareIE(InfoExtractor): video_url = mobj.group('url') if video_url not in urls: urls.append(video_url) + + sources = self._search_regex( + r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None) + if sources: + urls.extend(self._parse_json(sources, video_id)) + formats = [] for video_url in urls: if determine_ext(video_url) == 'm3u8': @@ -189,21 +177,13 @@ class XFileShareIE(InfoExtractor): 'url': video_url, 'format_id': 'sd', }) - if not formats and default is not NO_DEFAULT: - return default - self._sort_formats(formats) - return formats - - formats = extract_formats(default=None) - - if not formats: - webpage = decode_packed_codes(self._search_regex( - r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))", - webpage, 'packed code')) - formats = extract_formats() + self._sort_formats(formats) thumbnail = self._search_regex( - r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) + [ + r'<video[^>]+poster="([^"]+)"', + r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],', + ], webpage, 'thumbnail', default=None) return { 'id': video_id, diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index a5b94d279..0f7be6a7d 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -113,7 +113,7 @@ class XHamsterIE(InfoExtractor): display_id = mobj.group('display_id') or mobj.group('display_id_2') desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) - webpage = self._download_webpage(desktop_url, video_id) + webpage, urlh = self._download_webpage_handle(desktop_url, video_id) error = self._html_search_regex( r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>', @@ -161,6 +161,9 @@ class XHamsterIE(InfoExtractor): 'ext': determine_ext(format_url, 'mp4'), 'height': get_height(quality), 'filesize': filesize, + 'http_headers': { + 'Referer': urlh.geturl(), + }, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index c6c0b3291..01b253dcb 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -47,7 +47,7 @@ class XTubeIE(InfoExtractor): 'display_id': 'A-Super-Run-Part-1-YT', 'ext': 'flv', 'title': 'A Super Run - Part 1 (YT)', - 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93', + 'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616', 'uploader': 'tshirtguy59', 'duration': 579, 'view_count': int, @@ -87,10 +87,24 @@ class XTubeIE(InfoExtractor): 'Cookie': 'age_verified=1; cookiesAccepted=1', }) - sources = self._parse_json(self._search_regex( - r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),', - webpage, 'sources', group='sources'), video_id, - transform_source=js_to_json) + title, thumbnail, duration = [None] * 3 + + config = self._parse_json(self._search_regex( + r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', + default='{}'), video_id, transform_source=js_to_json, fatal=False) + if config: + config = config.get('mainRoll') + if isinstance(config, dict): + title = config.get('title') + thumbnail = config.get('poster') + duration = int_or_none(config.get('duration')) + sources = config.get('sources') or config.get('format') + + if not isinstance(sources, dict): + sources = self._parse_json(self._search_regex( + r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) formats = [] for format_id, format_url in sources.items(): @@ -102,20 +116,25 @@ class XTubeIE(InfoExtractor): self._remove_duplicate_formats(formats) self._sort_formats(formats) - title = self._search_regex( - (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), - webpage, 'title', group='title') - description = self._search_regex( + if not title: + title = self._search_regex( + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + webpage, 'title', group='title') + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage, default=None) or self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) uploader = self._search_regex( (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"', r'<span[^>]+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) - duration = parse_duration(self._search_regex( - r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', - webpage, 'duration', fatal=False)) + if not duration: + duration = parse_duration(self._search_regex( + r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', + webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( - r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>', + (r'["\']viewsCount["\'][^>]*>(\d+)\s+views', + r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'), webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( r'>Comments? \(([\d,\.]+)\)<', @@ -126,6 +145,7 @@ class XTubeIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'thumbnail': thumbnail, 'uploader': uploader, 'duration': duration, 'view_count': view_count, @@ -144,7 +164,7 @@ class XTubeUserIE(InfoExtractor): 'id': 'greenshowers-4056496', 'age_limit': 18, }, - 'playlist_mincount': 155, + 'playlist_mincount': 154, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index e5ebdd180..238d9cea0 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -3,453 +3,313 @@ from __future__ import unicode_literals import hashlib import itertools -import json import re from .common import InfoExtractor, SearchInfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urlparse, ) from ..utils import ( clean_html, - determine_ext, - ExtractorError, - extract_attributes, int_or_none, mimetype2ext, + parse_iso8601, smuggle_url, try_get, - unescapeHTML, url_or_none, ) -from .brightcove import ( - BrightcoveLegacyIE, - BrightcoveNewIE, -) -from .nbc import NBCSportsVPlayerIE +from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?P<host>https?://(?:(?P<country>[a-zA-Z]{2})\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?:(?P<display_id>.+)?-)?(?P<id>[0-9]+)(?:-[a-z]+)?(?:\.html)?' - _TESTS = [ - { - 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - 'info_dict': { - 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', - 'ext': 'mp4', - 'title': 'Julian Smith & Travis Legg Watch Julian Smith', - 'description': 'Julian and Travis watch Julian Smith', - 'duration': 6863, - }, + _VALID_URL = r'(?P<url>https?://(?:(?P<country>[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P<id>[^?&#]*-[0-9]+(?:-[a-z]+)?)\.html)' + _TESTS = [{ + 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', + 'info_dict': { + 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', + 'ext': 'mp4', + 'title': 'Julian Smith & Travis Legg Watch Julian Smith', + 'description': 'Julian and Travis watch Julian Smith', + 'duration': 6863, + 'timestamp': 1369812016, + 'upload_date': '20130529', }, - { - 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - 'md5': '251af144a19ebc4a033e8ba91ac726bb', - 'info_dict': { - 'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9', - 'ext': 'mp4', - 'title': 'Codefellas - The Cougar Lies with Spanish Moss', - 'description': 'md5:66b627ab0a282b26352136ca96ce73c1', - 'duration': 151, - }, - 'skip': 'HTTP Error 404', + }, { + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '7993e572fac98e044588d0b5260f4352', + 'info_dict': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + 'duration': 170, + 'timestamp': 1406838636, + 'upload_date': '20140731', }, - { - 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', - 'md5': '7993e572fac98e044588d0b5260f4352', - 'info_dict': { - 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', - 'ext': 'mp4', - 'title': "Yahoo Saves 'Community'", - 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', - 'duration': 170, - } + }, { + 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', + 'md5': '71298482f7c64cbb7fa064e4553ff1c1', + 'info_dict': { + 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', + 'ext': 'webm', + 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', + 'description': 'md5:f66c890e1490f4910a9953c941dee944', + 'duration': 97, + 'timestamp': 1414489862, + 'upload_date': '20141028', + } + }, { + 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + 'md5': '88e209b417f173d86186bef6e4d1f160', + 'info_dict': { + 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', + 'ext': 'mp4', + 'title': 'China Moses Is Crazy About the Blues', + 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', + 'duration': 128, + 'timestamp': 1385722202, + 'upload_date': '20131129', + } + }, { + 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', + 'md5': '2a9752f74cb898af5d1083ea9f661b58', + 'info_dict': { + 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', + 'ext': 'mp4', + 'title': '\'True Story\' Trailer', + 'description': 'True Story', + 'duration': 150, + 'timestamp': 1418919206, + 'upload_date': '20141218', }, - { - 'url': 'https://tw.news.yahoo.com/%E6%95%A2%E5%95%8F%E5%B8%82%E9%95%B7%20%E9%BB%83%E7%A7%80%E9%9C%9C%E6%89%B9%E8%B3%B4%E6%B8%85%E5%BE%B7%20%E9%9D%9E%E5%B8%B8%E9%AB%98%E5%82%B2-034024051.html', - 'md5': '45c024bad51e63e9b6f6fad7a43a8c23', - 'info_dict': { - 'id': 'cac903b3-fcf4-3c14-b632-643ab541712f', - 'ext': 'mp4', - 'title': '敢問市長／黃秀霜批賴清德「非常高傲」', - 'description': '直言台南沒捷運 交通居五都之末', - 'duration': 396, - }, + }, { + 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', + 'only_matching': True, + }, { + 'note': 'NBC Sports embeds', + 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', + 'info_dict': { + 'id': '9CsDKds0kvHI', + 'ext': 'flv', + 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', + 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', + 'upload_date': '20150313', + 'uploader': 'NBCU-SPORTS', + 'timestamp': 1426270238, }, - { - 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', - 'md5': '71298482f7c64cbb7fa064e4553ff1c1', - 'info_dict': { - 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', - 'ext': 'webm', - 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', - 'description': 'md5:f66c890e1490f4910a9953c941dee944', - 'duration': 97, - } + }, { + 'url': 'https://tw.news.yahoo.com/-100120367.html', + 'only_matching': True, + }, { + # Query result is embedded in webpage, but explicit request to video API fails with geo restriction + 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html', + 'md5': '4fbafb9c9b6f07aa8f870629f6671b35', + 'info_dict': { + 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504', + 'ext': 'mp4', + 'title': 'Communitary - Community Episode 1: Ladders', + 'description': 'md5:8fc39608213295748e1e289807838c97', + 'duration': 1646, + 'timestamp': 1440436550, + 'upload_date': '20150824', + 'series': 'Communitary', + 'season_number': 6, + 'episode_number': 1, }, - { - 'url': 'https://ca.sports.yahoo.com/video/program-makes-hockey-more-affordable-013127711.html', - 'md5': '57e06440778b1828a6079d2f744212c4', - 'info_dict': { - 'id': 'c9fa2a36-0d4d-3937-b8f6-cc0fb1881e73', - 'ext': 'mp4', - 'title': 'Program that makes hockey more affordable not offered in Manitoba', - 'description': 'md5:c54a609f4c078d92b74ffb9bf1f496f4', - 'duration': 121, - }, - 'skip': 'Video gone', - }, { - 'url': 'https://ca.finance.yahoo.com/news/hackers-sony-more-trouble-well-154609075.html', - 'info_dict': { - 'id': '154609075', - }, - 'playlist': [{ - 'md5': '000887d0dc609bc3a47c974151a40fb8', - 'info_dict': { - 'id': 'e624c4bc-3389-34de-9dfc-025f74943409', - 'ext': 'mp4', - 'title': '\'The Interview\' TV Spot: War', - 'description': 'The Interview', - 'duration': 30, - }, - }, { - 'md5': '81bc74faf10750fe36e4542f9a184c66', - 'info_dict': { - 'id': '1fc8ada0-718e-3abe-a450-bf31f246d1a9', - 'ext': 'mp4', - 'title': '\'The Interview\' TV Spot: Guys', - 'description': 'The Interview', - 'duration': 30, - }, - }], - }, { - 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', - 'md5': '88e209b417f173d86186bef6e4d1f160', - 'info_dict': { - 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', - 'ext': 'mp4', - 'title': 'China Moses Is Crazy About the Blues', - 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', - 'duration': 128, - } - }, { - 'url': 'https://in.lifestyle.yahoo.com/video/connect-dots-dark-side-virgo-090247395.html', - 'md5': 'd9a083ccf1379127bf25699d67e4791b', - 'info_dict': { - 'id': '52aeeaa3-b3d1-30d8-9ef8-5d0cf05efb7c', - 'ext': 'mp4', - 'title': 'Connect the Dots: Dark Side of Virgo', - 'description': 'md5:1428185051cfd1949807ad4ff6d3686a', - 'duration': 201, - }, - 'skip': 'Domain name in.lifestyle.yahoo.com gone', - }, { - 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', - 'md5': '989396ae73d20c6f057746fb226aa215', - 'info_dict': { - 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', - 'ext': 'mp4', - 'title': '\'True Story\' Trailer', - 'description': 'True Story', - 'duration': 150, - }, - }, { - 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', - 'only_matching': True, - }, { - 'note': 'NBC Sports embeds', - 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', - 'info_dict': { - 'id': '9CsDKds0kvHI', - 'ext': 'flv', - 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', - 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', - 'upload_date': '20150313', - 'uploader': 'NBCU-SPORTS', - 'timestamp': 1426270238, - } - }, { - 'url': 'https://tw.news.yahoo.com/-100120367.html', - 'only_matching': True, - }, { - # Query result is embedded in webpage, but explicit request to video API fails with geo restriction - 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html', - 'md5': '4fbafb9c9b6f07aa8f870629f6671b35', - 'info_dict': { - 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504', - 'ext': 'mp4', - 'title': 'Communitary - Community Episode 1: Ladders', - 'description': 'md5:8fc39608213295748e1e289807838c97', - 'duration': 1646, - }, - }, { - # it uses an alias to get the video_id - 'url': 'https://www.yahoo.com/movies/the-stars-of-daddys-home-have-very-different-212843197.html', - 'info_dict': { - 'id': '40eda9c8-8e5f-3552-8745-830f67d0c737', - 'ext': 'mp4', - 'title': 'Will Ferrell & Mark Wahlberg Are Pro-Spanking', - 'description': 'While they play feuding fathers in \'Daddy\'s Home,\' star Will Ferrell & Mark Wahlberg share their true feelings on parenthood.', - }, + }, { + # ytwnews://cavideo/ + 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', + 'info_dict': { + 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', + 'ext': 'mp4', + 'title': '單車天使 - 中文版預', + 'description': '中文版預', + 'timestamp': 1476696196, + 'upload_date': '20161017', }, - { - # config['models']['applet_model']['data']['sapi'] has no query - 'url': 'https://www.yahoo.com/music/livenation/event/galactic-2016', - 'md5': 'dac0c72d502bc5facda80c9e6d5c98db', - 'info_dict': { - 'id': 'a6015640-e9e5-3efb-bb60-05589a183919', - 'ext': 'mp4', - 'description': 'Galactic', - 'title': 'Dolla Diva (feat. Maggie Koerner)', - }, - 'skip': 'redirect to https://www.yahoo.com/music', + 'params': { + 'skip_download': True, }, - { - # yahoo://article/ - 'url': 'https://www.yahoo.com/movies/video/true-story-trailer-173000497.html', - 'info_dict': { - 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', - 'ext': 'mp4', - 'title': "'True Story' Trailer", - 'description': 'True Story', - }, - 'params': { - 'skip_download': True, - }, + }, { + # Contains both a Yahoo hosted video and multiple Youtube embeds + 'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html', + 'info_dict': { + 'id': '46c5d95a-528f-3d03-b732-732fcadd51de', + 'title': 'Gwen Stefani reveals the pop hit she passed on, assigns it to her \'Voice\' contestant instead', + 'description': 'Gwen decided not to record this hit herself, but she decided it was the perfect fit for Kyndall Inskeep.', }, - { - # ytwnews://cavideo/ - 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', + 'playlist': [{ 'info_dict': { - 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', + 'id': '966d4262-4fd1-3aaa-b45b-049ca6e38ba6', 'ext': 'mp4', - 'title': '單車天使 - 中文版預', - 'description': '中文版預', + 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs', + 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.', + 'timestamp': 1572406500, + 'upload_date': '20191030', }, - 'params': { - 'skip_download': True, - }, - }, - { - # custom brightcove - 'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37083565/clown-entertainers-say-it-is-hurting-their-business/', + }, { 'info_dict': { - 'id': '5575377707001', + 'id': '352CFDOQrKg', 'ext': 'mp4', - 'title': "Clown entertainers say 'It' is hurting their business", - 'description': 'Stephen King s horror film has much to answer for. Jelby and Mr Loopy the Clowns join us.', - 'timestamp': 1505341164, - 'upload_date': '20170913', - 'uploader_id': '2376984109001', - }, - 'params': { - 'skip_download': True, + 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019', + 'description': 'md5:35b61e94c2ae214bc965ff4245f80d11', + 'uploader': 'The Voice', + 'uploader_id': 'NBCTheVoice', + 'upload_date': '20191029', }, + }], + 'params': { + 'playlistend': 2, }, - { - # custom brightcove, geo-restricted to Australia, bypassable - 'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37263964/sunrise-episode-wed-27-sep/', - 'only_matching': True, - } - ] + 'expected_warnings': ['HTTP Error 404'], + }, { + 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html', + 'only_matching': True, + }, { + 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html', + 'only_matching': True, + }, { + 'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - display_id = mobj.group('display_id') or page_id - host = mobj.group('host') - webpage, urlh = self._download_webpage_handle(url, display_id) - if 'err=404' in urlh.geturl(): - raise ExtractorError('Video gone', expected=True) - - # Look for iframed media first - entries = [] - iframe_urls = re.findall(r'<iframe[^>]+src="(/video/.+?-\d+\.html\?format=embed.*?)"', webpage) - for idx, iframe_url in enumerate(iframe_urls): - entries.append(self.url_result(host + iframe_url, 'Yahoo')) - if entries: - return self.playlist_result(entries, page_id) - - # Look for NBCSports iframes - nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage) - if nbc_sports_url: - return self.url_result(nbc_sports_url, NBCSportsVPlayerIE.ie_key()) - - # Look for Brightcove Legacy Studio embeds - bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if bc_url: - return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) - - def brightcove_url_result(bc_url): - return self.url_result( - smuggle_url(bc_url, {'geo_countries': [mobj.group('country')]}), - BrightcoveNewIE.ie_key()) - - # Look for Brightcove New Studio embeds - bc_url = BrightcoveNewIE._extract_url(self, webpage) - if bc_url: - return brightcove_url_result(bc_url) - - brightcove_iframe = self._search_regex( - r'(<iframe[^>]+data-video-id=["\']\d+[^>]+>)', webpage, - 'brightcove iframe', default=None) - if brightcove_iframe: - attr = extract_attributes(brightcove_iframe) - src = attr.get('src') - if src: - parsed_src = compat_urlparse.urlparse(src) - qs = compat_urlparse.parse_qs(parsed_src.query) - account_id = qs.get('accountId', ['2376984109001'])[0] - brightcove_id = attr.get('data-video-id') or qs.get('videoId', [None])[0] - if account_id and brightcove_id: - return brightcove_url_result( - 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' - % (account_id, brightcove_id)) - - # Query result is often embedded in webpage as JSON. Sometimes explicit requests - # to video API results in a failure with geo restriction reason therefore using - # embedded query result when present sounds reasonable. - config_json = self._search_regex( - r'window\.Af\.bootstrap\[[^\]]+\]\s*=\s*({.*?"applet_type"\s*:\s*"td-applet-videoplayer".*?});(?:</script>|$)', - webpage, 'videoplayer applet', default=None) - if config_json: - config = self._parse_json(config_json, display_id, fatal=False) - if config: - sapi = config.get('models', {}).get('applet_model', {}).get('data', {}).get('sapi') - if sapi and 'query' in sapi: - info = self._extract_info(display_id, sapi, webpage) - self._sort_formats(info['formats']) - return info - - items_json = self._search_regex( - r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, - default=None) - if items_json is None: - alias = self._search_regex( - r'"aliases":{"video":"(.*?)"', webpage, 'alias', default=None) - if alias is not None: - alias_info = self._download_json( - 'https://www.yahoo.com/_td/api/resource/VideoService.videos;video_aliases=["%s"]' % alias, - display_id, 'Downloading alias info') - video_id = alias_info[0]['id'] - else: - CONTENT_ID_REGEXES = [ - r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', - r'"first_videoid"\s*:\s*"([^"]+)"', - r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), - r'<article[^>]data-uuid=["\']([^"\']+)', - r'<meta[^<>]+yahoo://article/view\?.*\buuid=([^&"\']+)', - r'<meta[^<>]+["\']ytwnews://cavideo/(?:[^/]+/)+([\da-fA-F-]+)[&"\']', - ] - video_id = self._search_regex( - CONTENT_ID_REGEXES, webpage, 'content ID') + url, country, display_id = re.match(self._VALID_URL, url).groups() + if not country: + country = 'us' else: - items = json.loads(items_json) - info = items['mediaItems']['query']['results']['mediaObj'][0] - # The 'meta' field is not always in the video webpage, we request it - # from another page - video_id = info['id'] - return self._get_info(video_id, display_id, webpage) - - def _extract_info(self, display_id, query, webpage): - info = query['query']['results']['mediaObj'][0] - meta = info.get('meta') - video_id = info.get('id') - - if not meta: - msg = info['status'].get('msg') - if msg: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, msg), expected=True) - raise ExtractorError('Unable to extract media object meta') + country = country.split('-')[0] + api_base = 'https://%s.yahoo.com/_td/api/resource/' % country + + for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]): + content = self._download_json( + api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid, + display_id, 'Downloading content JSON metadata', fatal=i == 1) + if content: + item = content['items'][0] + break + + if item.get('type') != 'video': + entries = [] + + cover = item.get('cover') or {} + if cover.get('type') == 'yvideo': + cover_url = cover.get('url') + if cover_url: + entries.append(self.url_result( + cover_url, 'Yahoo', cover.get('uuid'))) + + for e in item.get('body', []): + if e.get('type') == 'videoIframe': + iframe_url = e.get('url') + if not iframe_url: + continue + entries.append(self.url_result(iframe_url)) + + return self.playlist_result( + entries, item.get('uuid'), + item.get('title'), item.get('summary')) + + video_id = item['uuid'] + video = self._download_json( + api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id, + video_id, 'Downloading video JSON metadata')[0] + title = video['title'] + + if country == 'malaysia': + country = 'my' + is_live = video.get('live_state') == 'live' + fmts = ('m3u8',) if is_live else ('webm', 'mp4') + + urls = [] formats = [] - for s in info['streams']: - tbr = int_or_none(s.get('bitrate')) - format_info = { - 'width': int_or_none(s.get('width')), - 'height': int_or_none(s.get('height')), - 'tbr': tbr, - } - - host = s['host'] - path = s['path'] - if host.startswith('rtmp'): - fmt = 'rtmp' - format_info.update({ - 'url': host, - 'play_path': path, - 'ext': 'flv', - }) - else: - if s.get('format') == 'm3u8_playlist': - fmt = 'hls' - format_info.update({ - 'protocol': 'm3u8_native', - 'ext': 'mp4', - }) - else: - fmt = format_info['ext'] = determine_ext(path) - format_url = compat_urlparse.urljoin(host, path) - format_info['url'] = format_url - format_info['format_id'] = fmt + ('-%d' % tbr if tbr else '') - formats.append(format_info) - - closed_captions = self._html_search_regex( - r'"closedcaptions":(\[[^\]]+\])', webpage, 'closed captions', - default='[]') - - cc_json = self._parse_json(closed_captions, video_id, fatal=False) subtitles = {} - if cc_json: - for closed_caption in cc_json: - lang = closed_caption['lang'] - if lang not in subtitles: - subtitles[lang] = [] - subtitles[lang].append({ - 'url': closed_caption['url'], - 'ext': mimetype2ext(closed_caption['content_type']), + for fmt in fmts: + media_obj = self._download_json( + 'https://video-api.yql.yahoo.com/v1/video/sapi/streams/' + video_id, + video_id, 'Downloading %s JSON metadata' % fmt, + headers=self.geo_verification_headers(), query={ + 'format': fmt, + 'region': country.upper(), + })['query']['results']['mediaObj'][0] + msg = media_obj.get('status', {}).get('msg') + + for s in media_obj.get('streams', []): + host = s.get('host') + path = s.get('path') + if not host or not path: + continue + s_url = host + path + if s.get('format') == 'm3u8': + formats.extend(self._extract_m3u8_formats( + s_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + continue + tbr = int_or_none(s.get('bitrate')) + formats.append({ + 'url': s_url, + 'format_id': fmt + ('-%d' % tbr if tbr else ''), + 'width': int_or_none(s.get('width')), + 'height': int_or_none(s.get('height')), + 'tbr': tbr, + 'fps': int_or_none(s.get('framerate')), + }) + + for cc in media_obj.get('closedcaptions', []): + cc_url = cc.get('url') + if not cc_url or cc_url in urls: + continue + urls.append(cc_url) + subtitles.setdefault(cc.get('lang') or 'en-US', []).append({ + 'url': cc_url, + 'ext': mimetype2ext(cc.get('content_type')), }) + streaming_url = video.get('streaming_url') + if streaming_url and not is_live: + formats.extend(self._extract_m3u8_formats( + streaming_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + + if not formats and msg == 'geo restricted': + self.raise_geo_restricted() + + self._sort_formats(formats) + + thumbnails = [] + for thumb in video.get('thumbnails', []): + thumb_url = thumb.get('url') + if not thumb_url: + continue + thumbnails.append({ + 'id': thumb.get('tag'), + 'url': thumb.get('url'), + 'width': int_or_none(thumb.get('width')), + 'height': int_or_none(thumb.get('height')), + }) + + series_info = video.get('series_info') or {} + return { 'id': video_id, - 'display_id': display_id, - 'title': unescapeHTML(meta['title']), + 'title': self._live_title(title) if is_live else title, 'formats': formats, - 'description': clean_html(meta['description']), - 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), - 'duration': int_or_none(meta.get('duration')), + 'display_id': display_id, + 'thumbnails': thumbnails, + 'description': clean_html(video.get('description')), + 'timestamp': parse_iso8601(video.get('publish_time')), 'subtitles': subtitles, + 'duration': int_or_none(video.get('duration')), + 'view_count': int_or_none(video.get('view_count')), + 'is_live': is_live, + 'series': video.get('show_name'), + 'season_number': int_or_none(series_info.get('season_number')), + 'episode_number': int_or_none(series_info.get('episode_number')), } - def _get_info(self, video_id, display_id, webpage): - region = self._search_regex( - r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', - webpage, 'region', fatal=False, default='US').upper() - formats = [] - info = {} - for fmt in ('webm', 'mp4'): - query_result = self._download_json( - 'https://video.media.yql.yahoo.com/v1/video/sapi/streams/' + video_id, - display_id, 'Downloading %s video info' % fmt, query={ - 'protocol': 'http', - 'region': region, - 'format': fmt, - }) - info = self._extract_info(display_id, query_result, webpage) - formats.extend(info['formats']) - formats.extend(self._extract_m3u8_formats( - 'http://video.media.yql.yahoo.com/v1/hls/%s?region=%s' % (video_id, region), - video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - self._sort_formats(formats) - info['formats'] = formats - return info - class YahooSearchIE(SearchInfoExtractor): IE_DESC = 'Yahoo screen search' @@ -523,7 +383,7 @@ class YahooGyaOPlayerIE(InfoExtractor): 'id': video_id, 'title': video['title'], 'url': smuggle_url( - 'http://players.brightcove.net/4235717419001/default_default/index.html?videoId=' + video['videoId'], + 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video['videoId'], {'geo_countries': ['JP']}), 'description': video.get('longDescription'), 'ie_key': BrightcoveNewIE.ie_key(), diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index dff69fcb7..88aabd272 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -44,7 +44,7 @@ class YouJizzIE(InfoExtractor): encodings = self._parse_json( self._search_regex( - r'encodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', + r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', default='[]'), video_id, fatal=False) for encoding in encodings: diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 8a2d5f63b..98347491e 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( parse_duration, urljoin, @@ -8,9 +9,9 @@ from ..utils import ( class YourPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)' + _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)' _TESTS = [{ - 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', + 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html', 'md5': '6f8682b6464033d87acaa7a8ff0c092e', 'info_dict': { 'id': '57ffcb2e1179b', @@ -33,11 +34,19 @@ class YourPornIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_url = urljoin(url, self._parse_json( + parts = self._parse_json( self._search_regex( r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]).replace('/cdn/', '/cdn5/') + video_id)[video_id].split('/') + + num = 0 + for c in parts[6] + parts[7]: + if c.isnumeric(): + num += int(c) + parts[5] = compat_str(int(parts[5]) - num) + parts[1] += '8' + video_url = urljoin(url, '/'.join(parts)) title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', @@ -54,4 +63,5 @@ class YourPornIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'age_limit': 18, + 'ext': 'mp4', } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 5e397324b..908defecd 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -29,7 +29,6 @@ from ..compat import ( from ..utils import ( bool_or_none, clean_html, - dict_get, error_to_compat_str, extract_attributes, ExtractorError, @@ -69,7 +68,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # If True it will raise an error if no login info is provided _LOGIN_REQUIRED = False - _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}' + _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}' def _set_language(self): self._set_cookie( @@ -372,7 +371,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): _VALID_URL = r"""(?x)^ ( (?:https?://|//) # http(s):// or protocol-independent URL - (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| + (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/| (?:www\.)?deturl\.com/www\.youtube\.com/| (?:www\.)?pwnyoutube\.com/| (?:www\.)?hooktube\.com/| @@ -570,7 +569,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20120506', 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', 'alt_title': 'I Love It (feat. Charli XCX)', - 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', + 'description': 'md5:19a2f98d9032b9311e686ed039564f63', 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', 'iconic ep', 'iconic', 'love', 'it'], @@ -685,12 +684,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', - 'description': 'md5:bec2185232c05479482cb5a9b82719bf', + 'description': 'md5:307195cd21ff7fa352270fe884570ef0', 'duration': 242, 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', - 'creator': 'Taylor Swift', }, 'params': { 'youtube_include_dash_manifest': True, @@ -755,11 +753,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20100430', 'uploader_id': 'deadmau5', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', - 'creator': 'deadmau5', + 'creator': 'Dada Life, deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', 'title': 'Deadmau5 - Some Chords (HD)', - 'alt_title': 'Some Chords', + 'alt_title': 'This Machine Kills Some Chords', }, 'expected_warnings': [ 'DASH manifest missing', @@ -1135,6 +1133,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'skip_download': True, 'youtube_include_dash_manifest': False, }, + 'skip': 'not actual anymore', }, { # Youtube Music Auto-generated description @@ -1145,8 +1144,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Voyeur Girl', 'description': 'md5:7ae382a65843d6df2685993e90a8628f', 'upload_date': '20190312', - 'uploader': 'Various Artists - Topic', - 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw', + 'uploader': 'Stephen - Topic', + 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', 'artist': 'Stephen', 'track': 'Voyeur Girl', 'album': 'it\'s too much love to know my dear', @@ -1210,7 +1209,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': '-hcAI0g-f5M', 'ext': 'mp4', 'title': 'Put It On Me', - 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e', + 'description': 'md5:f6422397c07c4c907c6638e1fee380a5', 'upload_date': '20180426', 'uploader': 'Matt Maeson - Topic', 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ', @@ -1224,6 +1223,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'skip_download': True, }, }, + { + 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', + 'only_matching': True, + }, ] def __init__(self, *args, **kwargs): @@ -1252,7 +1255,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', + r'.*?[-.](?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -1339,6 +1342,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): funcname = self._search_regex( (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', # Obsolete patterns r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', @@ -1703,9 +1707,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def extract_view_count(v_info): return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) - def extract_token(v_info): - return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token')) - def extract_player_response(player_response, video_id): pl_response = str_or_none(player_response) if not pl_response: @@ -1718,6 +1719,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_response = {} # Get video info + video_info = {} embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True @@ -1732,19 +1734,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data - video_info_webpage = self._download_webpage( - video_info_url, video_id, - note='Refetching age-gated info webpage', - errnote='unable to download video info webpage') - video_info = compat_parse_qs(video_info_webpage) - pl_response = video_info.get('player_response', [None])[0] - player_response = extract_player_response(pl_response, video_id) - add_dash_mpd(video_info) - view_count = extract_view_count(video_info) + try: + video_info_webpage = self._download_webpage( + video_info_url, video_id, + note='Refetching age-gated info webpage', + errnote='unable to download video info webpage') + except ExtractorError: + video_info_webpage = None + if video_info_webpage: + video_info = compat_parse_qs(video_info_webpage) + pl_response = video_info.get('player_response', [None])[0] + player_response = extract_player_response(pl_response, video_id) + add_dash_mpd(video_info) + view_count = extract_view_count(video_info) else: age_gate = False - video_info = None - sts = None # Try looking directly into the video webpage ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) if ytplayer_config: @@ -1761,61 +1765,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) if args.get('livestream') == '1' or args.get('live_playback') == 1: is_live = True - sts = ytplayer_config.get('sts') if not player_response: player_response = extract_player_response(args.get('player_response'), video_id) if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): add_dash_mpd_pr(player_response) - # We also try looking in get_video_info since it may contain different dashmpd - # URL that points to a DASH manifest with possibly different itag set (some itags - # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH - # manifest pointed by get_video_info's dashmpd). - # The general idea is to take a union of itags of both DASH manifests (for example - # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093) - self.report_video_info_webpage_download(video_id) - for el in ('embedded', 'detailpage', 'vevo', ''): - query = { - 'video_id': video_id, - 'ps': 'default', - 'eurl': '', - 'gl': 'US', - 'hl': 'en', - } - if el: - query['el'] = el - if sts: - query['sts'] = sts - video_info_webpage = self._download_webpage( - '%s://www.youtube.com/get_video_info' % proto, - video_id, note=False, - errnote='unable to download video info webpage', - fatal=False, query=query) - if not video_info_webpage: - continue - get_video_info = compat_parse_qs(video_info_webpage) - if not player_response: - pl_response = get_video_info.get('player_response', [None])[0] - player_response = extract_player_response(pl_response, video_id) - add_dash_mpd(get_video_info) - if view_count is None: - view_count = extract_view_count(get_video_info) - if not video_info: - video_info = get_video_info - get_token = extract_token(get_video_info) - if get_token: - # Different get_video_info requests may report different results, e.g. - # some may report video unavailability, but some may serve it without - # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362, - # the original webpage as well as el=info and el=embedded get_video_info - # requests report video unavailability due to geo restriction while - # el=detailpage succeeds and returns valid data). This is probably - # due to YouTube measures against IP ranges of hosting providers. - # Working around by preferring the first succeeded video_info containing - # the token if no such video_info yet was found. - token = extract_token(video_info) - if not token: - video_info = get_video_info - break def extract_unavailable_message(): messages = [] @@ -1828,13 +1781,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if messages: return '\n'.join(messages) - if not video_info: + if not video_info and not player_response: unavailable_message = extract_unavailable_message() if not unavailable_message: unavailable_message = 'Unable to extract video data' raise ExtractorError( 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id) + if not isinstance(video_info, dict): + video_info = {} + video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} @@ -2030,7 +1986,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)[-.]([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version @@ -2387,30 +2343,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor): f['stretched_ratio'] = ratio if not formats: - token = extract_token(video_info) - if not token: - if 'reason' in video_info: - if 'The uploader has not made this video available in your country.' in video_info['reason']: - regions_allowed = self._html_search_meta( - 'regionsAllowed', video_webpage, default=None) - countries = regions_allowed.split(',') if regions_allowed else None - self.raise_geo_restricted( - msg=video_info['reason'][0], countries=countries) - reason = video_info['reason'][0] - if 'Invalid parameters' in reason: - unavailable_message = extract_unavailable_message() - if unavailable_message: - reason = unavailable_message - raise ExtractorError( - 'YouTube said: %s' % reason, - expected=True, video_id=video_id) - else: - raise ExtractorError( - '"token" parameter not in video info for unknown reason', - video_id=video_id) - - if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])): - raise ExtractorError('This video is DRM protected.', expected=True) + if 'reason' in video_info: + if 'The uploader has not made this video available in your country.' in video_info['reason']: + regions_allowed = self._html_search_meta( + 'regionsAllowed', video_webpage, default=None) + countries = regions_allowed.split(',') if regions_allowed else None + self.raise_geo_restricted( + msg=video_info['reason'][0], countries=countries) + reason = video_info['reason'][0] + if 'Invalid parameters' in reason: + unavailable_message = extract_unavailable_message() + if unavailable_message: + reason = unavailable_message + raise ExtractorError( + 'YouTube said: %s' % reason, + expected=True, video_id=video_id) + if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']): + raise ExtractorError('This video is DRM protected.', expected=True) self._sort_formats(formats) @@ -2465,7 +2414,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): (?:\w+\.)? (?: (?: - youtube\.com| + youtube(?:kids)?\.com| invidio\.us ) / @@ -2477,7 +2426,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= ) ( - (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,} + (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,} # Top tracks, they can also include dots |(?:MC)[\w\.]* ) @@ -2490,20 +2439,23 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' IE_NAME = 'youtube:playlist' _TESTS = [{ - 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', 'info_dict': { - 'title': 'ytdl test PL', - 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'title': 'youtube-dl public playlist', }, - 'playlist_count': 3, + 'playlist_count': 1, }, { - 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', 'info_dict': { - 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', - 'title': 'YDL_Empty_List', + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', + 'title': 'youtube-dl empty playlist', }, 'playlist_count': 0, - 'skip': 'This playlist is private', }, { 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', @@ -2513,7 +2465,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'uploader': 'Christiaan008', 'uploader_id': 'ChRiStIaAn008', }, - 'playlist_count': 95, + 'playlist_count': 96, }, { 'note': 'issue #673', 'url': 'PLBB231211A4F62143', @@ -2647,6 +2599,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): }, { 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', 'only_matching': True, + }, { + 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', + 'only_matching': True, }] def _real_initialize(self): @@ -2817,7 +2772,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com channels' - _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' + _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' IE_NAME = 'youtube:channel' @@ -2845,6 +2800,9 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): }, { 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', 'only_matching': True, + }, { + 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA', + 'only_matching': True, }] @classmethod diff --git a/youtube_dl/extractor/zapiks.py b/youtube_dl/extractor/zapiks.py index bacb82eee..f6496f516 100644 --- a/youtube_dl/extractor/zapiks.py +++ b/youtube_dl/extractor/zapiks.py @@ -29,7 +29,6 @@ class ZapiksIE(InfoExtractor): 'timestamp': 1359044972, 'upload_date': '20130124', 'view_count': int, - 'comment_count': int, }, }, { diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 145c123a4..656864b2e 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -244,14 +244,14 @@ class ZDFChannelIE(ZDFBaseIE): 'id': 'das-aktuelle-sportstudio', 'title': 'das aktuelle sportstudio | ZDF', }, - 'playlist_count': 21, + 'playlist_mincount': 23, }, { 'url': 'https://www.zdf.de/dokumentation/planet-e', 'info_dict': { 'id': 'planet-e', 'title': 'planet e.', }, - 'playlist_count': 4, + 'playlist_mincount': 50, }, { 'url': 'https://www.zdf.de/filme/taunuskrimi/', 'only_matching': True, diff --git a/youtube_dl/extractor/zype.py b/youtube_dl/extractor/zype.py index 3b16e703b..2e2e97a0c 100644 --- a/youtube_dl/extractor/zype.py +++ b/youtube_dl/extractor/zype.py @@ -4,10 +4,20 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + dict_get, + ExtractorError, + int_or_none, + js_to_json, + parse_iso8601, +) class ZypeIE(InfoExtractor): - _VALID_URL = r'https?://player\.zype\.com/embed/(?P<id>[\da-fA-F]+)\.js\?.*?api_key=[^&]+' + _ID_RE = r'[\da-fA-F]+' + _COMMON_RE = r'//player\.zype\.com/embed/%s\.(?:js|json|html)\?.*?(?:access_token|(?:ap[ip]|player)_key)=' + _VALID_URL = r'https?:%s[^&]+' % (_COMMON_RE % ('(?P<id>%s)' % _ID_RE)) _TEST = { 'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false', 'md5': 'eaee31d474c76a955bdaba02a505c595', @@ -16,6 +26,9 @@ class ZypeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Smoky Barbecue Favorites', 'thumbnail': r're:^https?://.*\.jpe?g', + 'description': 'md5:5ff01e76316bd8d46508af26dc86023b', + 'timestamp': 1504915200, + 'upload_date': '20170909', }, } @@ -24,34 +37,98 @@ class ZypeIE(InfoExtractor): return [ mobj.group('url') for mobj in re.finditer( - r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//player\.zype\.com/embed/[\da-fA-F]+\.js\?.*?api_key=.+?)\1', + r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?%s.+?)\1' % (ZypeIE._COMMON_RE % ZypeIE._ID_RE), webpage)] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + try: + response = self._download_json(re.sub( + r'\.(?:js|html)\?', '.json?', url), video_id)['response'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 403): + raise ExtractorError(self._parse_json( + e.cause.read().decode(), video_id)['message'], expected=True) + raise - title = self._search_regex( - r'video_title\s*[:=]\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, - 'title', group='value') + body = response['body'] + video = response['video'] + title = video['title'] - m3u8_url = self._search_regex( - r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', webpage, - 'm3u8 url', group='url') - - formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls') + if isinstance(body, dict): + formats = [] + for output in body.get('outputs', []): + output_url = output.get('url') + if not output_url: + continue + name = output.get('name') + if name == 'm3u8': + formats = self._extract_m3u8_formats( + output_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + else: + f = { + 'format_id': name, + 'tbr': int_or_none(output.get('bitrate')), + 'url': output_url, + } + if name in ('m4a', 'mp3'): + f['vcodec'] = 'none' + else: + f.update({ + 'height': int_or_none(output.get('height')), + 'width': int_or_none(output.get('width')), + }) + formats.append(f) + text_tracks = body.get('subtitles') or [] + else: + m3u8_url = self._search_regex( + r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', + body, 'm3u8 url', group='url') + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls') + text_tracks = self._search_regex( + r'textTracks\s*:\s*(\[[^]]+\])', + body, 'text tracks', default=None) + if text_tracks: + text_tracks = self._parse_json( + text_tracks, video_id, js_to_json, False) self._sort_formats(formats) - thumbnail = self._search_regex( - r'poster\s*[:=]\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'thumbnail', - default=False, group='url') + subtitles = {} + if text_tracks: + for text_track in text_tracks: + tt_url = dict_get(text_track, ('file', 'src')) + if not tt_url: + continue + subtitles.setdefault(text_track.get('label') or 'English', []).append({ + 'url': tt_url, + }) + + thumbnails = [] + for thumbnail in video.get('thumbnails', []): + thumbnail_url = thumbnail.get('url') + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int_or_none(thumbnail.get('width')), + 'height': int_or_none(thumbnail.get('height')), + }) return { 'id': video_id, + 'display_id': video.get('friendly_title'), 'title': title, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, + 'description': dict_get(video, ('description', 'ott_description', 'short_description')), + 'timestamp': parse_iso8601(video.get('published_at')), + 'duration': int_or_none(video.get('duration')), + 'view_count': int_or_none(video.get('request_count')), + 'average_rating': int_or_none(video.get('rating')), + 'season_number': int_or_none(video.get('season')), + 'episode_number': int_or_none(video.get('episode')), 'formats': formats, + 'subtitles': subtitles, } diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 1ffabc62b..8826b382c 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -134,7 +134,7 @@ def parseOpts(overrideArguments=None): action='help', help='Print this help text and exit') general.add_option( - '-v', '--version', + '--version', action='version', help='Print program version and exit') general.add_option( diff --git a/youtube_dl/postprocessor/embedthumbnail.py b/youtube_dl/postprocessor/embedthumbnail.py index eae266dde..795582259 100644 --- a/youtube_dl/postprocessor/embedthumbnail.py +++ b/youtube_dl/postprocessor/embedthumbnail.py @@ -55,7 +55,15 @@ class EmbedThumbnailPP(FFmpegPostProcessor): os.remove(encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename)) +<<<<<<< HEAD + elif info['ext'] == 'mkv': + os.rename(encodeFilename(thumbnail_filename), encodeFilename('cover.jpg')) + old_thumbnail_filename = thumbnail_filename + thumbnail_filename = 'cover.jpg' + +======= if info['ext'] == 'mkv': +>>>>>>> a0b2ee64dbe6d4bedad9883cc8014aa77cdd0138 options = [ '-c', 'copy', '-attach', thumbnail_filename, '-metadata:s:t', 'mimetype=image/jpeg'] @@ -65,6 +73,11 @@ class EmbedThumbnailPP(FFmpegPostProcessor): if not self._already_have_thumbnail: os.remove(encodeFilename(thumbnail_filename)) +<<<<<<< HEAD + else: + os.rename(encodeFilename(thumbnail_filename), encodeFilename(old_thumbnail_filename)) +======= +>>>>>>> a0b2ee64dbe6d4bedad9883cc8014aa77cdd0138 os.remove(encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename)) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 70416c25e..fd3f921a8 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -393,7 +393,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): sub_ext = sub_info['ext'] if ext != 'webm' or ext == 'webm' and sub_ext == 'vtt': sub_langs.append(lang) - sub_filenames.append(subtitles_filename(filename, lang, sub_ext)) + sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext)) else: if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt': webm_vtt_warn = True @@ -606,9 +606,9 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): self._downloader.to_screen( '[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext) continue - old_file = subtitles_filename(filename, lang, ext) + old_file = subtitles_filename(filename, lang, ext, info.get('ext')) sub_filenames.append(old_file) - new_file = subtitles_filename(filename, lang, new_ext) + new_file = subtitles_filename(filename, lang, new_ext, info.get('ext')) if ext in ('dfxp', 'ttml', 'tt'): self._downloader.report_warning( @@ -616,7 +616,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): 'which results in style information loss') dfxp_file = old_file - srt_file = subtitles_filename(filename, lang, 'srt') + srt_file = subtitles_filename(filename, lang, 'srt', info.get('ext')) with open(dfxp_file, 'rb') as f: srt_data = dfxp2srt(f.read()) diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 002ea7f33..84c964617 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -9,6 +9,7 @@ import subprocess import sys from zipimport import zipimporter +from .compat import compat_realpath from .utils import encode_compat_str from .version import __version__ @@ -84,7 +85,9 @@ def update_self(to_screen, verbose, opener): print_notes(to_screen, versions_info['versions']) # sys.executable is set to the full pathname of the exe-file for py2exe - filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0] + # though symlinks are not followed so that we need to do this manually + # with help of realpath + filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0]) if not os.access(filename, os.W_OK): to_screen('ERROR: no write permissions on %s' % filename) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 798757241..38262bee4 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -46,6 +46,7 @@ from .compat import ( compat_html_entities, compat_html_entities_html5, compat_http_client, + compat_integer_types, compat_kwargs, compat_os_name, compat_parse_qs, @@ -1718,13 +1719,16 @@ DATE_FORMATS = ( '%B %d %Y', '%B %dst %Y', '%B %dnd %Y', + '%B %drd %Y', '%B %dth %Y', '%b %d %Y', '%b %dst %Y', '%b %dnd %Y', + '%b %drd %Y', '%b %dth %Y', '%b %dst %Y %I:%M', '%b %dnd %Y %I:%M', + '%b %drd %Y %I:%M', '%b %dth %Y %I:%M', '%Y %m %d', '%Y-%m-%d', @@ -2725,6 +2729,11 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + """ + See [1] for cookie file format. + + 1. https://curl.haxx.se/docs/http-cookies.html + """ _HTTPONLY_PREFIX = '#HttpOnly_' def save(self, filename=None, ignore_discard=False, ignore_expires=False): @@ -2791,6 +2800,15 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): https_response = http_response +class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler): + if sys.version_info[0] < 3: + def redirect_request(self, req, fp, code, msg, headers, newurl): + # On python 2 urlh.geturl() may sometimes return redirect URL + # as byte string instead of unicode. This workaround allows + # to force it always return unicode. + return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl)) + + def extract_timezone(date_str): m = re.search( r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)', @@ -2906,8 +2924,8 @@ def determine_ext(url, default_ext='unknown_video'): return default_ext -def subtitles_filename(filename, sub_lang, sub_format): - return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format +def subtitles_filename(filename, sub_lang, sub_format, expected_real_ext=None): + return replace_extension(filename, sub_lang + '.' + sub_format, expected_real_ext) def date_from_str(date_str): @@ -3516,10 +3534,11 @@ def str_or_none(v, default=None): def str_to_int(int_str): """ A more relaxed version of int_or_none """ - if int_str is None: - return None - int_str = re.sub(r'[,\.\+]', '', int_str) - return int(int_str) + if isinstance(int_str, compat_integer_types): + return int_str + elif isinstance(int_str, compat_str): + int_str = re.sub(r'[,\.\+]', '', int_str) + return int_or_none(int_str) def float_or_none(v, scale=1, invscale=1, default=None): @@ -4979,7 +4998,7 @@ class ISO3166Utils(object): class GeoUtils(object): # Major IPv4 address blocks per country _country_ip_map = { - 'AD': '85.94.160.0/19', + 'AD': '46.172.224.0/19', 'AE': '94.200.0.0/13', 'AF': '149.54.0.0/17', 'AG': '209.59.64.0/18', @@ -4987,28 +5006,30 @@ class GeoUtils(object): 'AL': '46.99.0.0/16', 'AM': '46.70.0.0/15', 'AO': '105.168.0.0/13', - 'AP': '159.117.192.0/21', + 'AP': '182.50.184.0/21', + 'AQ': '23.154.160.0/24', 'AR': '181.0.0.0/12', 'AS': '202.70.112.0/20', - 'AT': '84.112.0.0/13', + 'AT': '77.116.0.0/14', 'AU': '1.128.0.0/11', 'AW': '181.41.0.0/18', - 'AZ': '5.191.0.0/16', + 'AX': '185.217.4.0/22', + 'AZ': '5.197.0.0/16', 'BA': '31.176.128.0/17', 'BB': '65.48.128.0/17', 'BD': '114.130.0.0/16', 'BE': '57.0.0.0/8', - 'BF': '129.45.128.0/17', + 'BF': '102.178.0.0/15', 'BG': '95.42.0.0/15', 'BH': '37.131.0.0/17', 'BI': '154.117.192.0/18', 'BJ': '137.255.0.0/16', - 'BL': '192.131.134.0/24', + 'BL': '185.212.72.0/23', 'BM': '196.12.64.0/18', 'BN': '156.31.0.0/16', 'BO': '161.56.0.0/16', 'BQ': '161.0.80.0/20', - 'BR': '152.240.0.0/12', + 'BR': '191.128.0.0/12', 'BS': '24.51.64.0/18', 'BT': '119.2.96.0/19', 'BW': '168.167.0.0/16', @@ -5016,20 +5037,20 @@ class GeoUtils(object): 'BZ': '179.42.192.0/18', 'CA': '99.224.0.0/11', 'CD': '41.243.0.0/16', - 'CF': '196.32.200.0/21', - 'CG': '197.214.128.0/17', + 'CF': '197.242.176.0/21', + 'CG': '160.113.0.0/16', 'CH': '85.0.0.0/13', - 'CI': '154.232.0.0/14', + 'CI': '102.136.0.0/14', 'CK': '202.65.32.0/19', 'CL': '152.172.0.0/14', - 'CM': '165.210.0.0/15', + 'CM': '102.244.0.0/14', 'CN': '36.128.0.0/10', 'CO': '181.240.0.0/12', 'CR': '201.192.0.0/12', 'CU': '152.206.0.0/15', 'CV': '165.90.96.0/19', 'CW': '190.88.128.0/17', - 'CY': '46.198.0.0/15', + 'CY': '31.153.0.0/16', 'CZ': '88.100.0.0/14', 'DE': '53.0.0.0/8', 'DJ': '197.241.0.0/17', @@ -5046,6 +5067,7 @@ class GeoUtils(object): 'EU': '2.16.0.0/13', 'FI': '91.152.0.0/13', 'FJ': '144.120.0.0/16', + 'FK': '80.73.208.0/21', 'FM': '119.252.112.0/20', 'FO': '88.85.32.0/19', 'FR': '90.0.0.0/9', @@ -5055,8 +5077,8 @@ class GeoUtils(object): 'GE': '31.146.0.0/16', 'GF': '161.22.64.0/18', 'GG': '62.68.160.0/19', - 'GH': '45.208.0.0/14', - 'GI': '85.115.128.0/19', + 'GH': '154.160.0.0/12', + 'GI': '95.164.0.0/16', 'GL': '88.83.0.0/19', 'GM': '160.182.0.0/15', 'GN': '197.149.192.0/18', @@ -5085,13 +5107,13 @@ class GeoUtils(object): 'JE': '87.244.64.0/18', 'JM': '72.27.0.0/17', 'JO': '176.29.0.0/16', - 'JP': '126.0.0.0/8', + 'JP': '133.0.0.0/8', 'KE': '105.48.0.0/12', 'KG': '158.181.128.0/17', 'KH': '36.37.128.0/17', 'KI': '103.25.140.0/22', 'KM': '197.255.224.0/20', - 'KN': '198.32.32.0/19', + 'KN': '198.167.192.0/19', 'KP': '175.45.176.0/22', 'KR': '175.192.0.0/10', 'KW': '37.36.0.0/14', @@ -5099,10 +5121,10 @@ class GeoUtils(object): 'KZ': '2.72.0.0/13', 'LA': '115.84.64.0/18', 'LB': '178.135.0.0/16', - 'LC': '192.147.231.0/24', + 'LC': '24.92.144.0/20', 'LI': '82.117.0.0/19', 'LK': '112.134.0.0/15', - 'LR': '41.86.0.0/19', + 'LR': '102.183.0.0/16', 'LS': '129.232.0.0/17', 'LT': '78.56.0.0/13', 'LU': '188.42.0.0/16', @@ -5127,7 +5149,7 @@ class GeoUtils(object): 'MT': '46.11.0.0/16', 'MU': '105.16.0.0/12', 'MV': '27.114.128.0/18', - 'MW': '105.234.0.0/16', + 'MW': '102.70.0.0/15', 'MX': '187.192.0.0/11', 'MY': '175.136.0.0/13', 'MZ': '197.218.0.0/15', @@ -5158,23 +5180,23 @@ class GeoUtils(object): 'PW': '202.124.224.0/20', 'PY': '181.120.0.0/14', 'QA': '37.210.0.0/15', - 'RE': '139.26.0.0/16', + 'RE': '102.35.0.0/16', 'RO': '79.112.0.0/13', - 'RS': '178.220.0.0/14', + 'RS': '93.86.0.0/15', 'RU': '5.136.0.0/13', - 'RW': '105.178.0.0/15', + 'RW': '41.186.0.0/16', 'SA': '188.48.0.0/13', 'SB': '202.1.160.0/19', 'SC': '154.192.0.0/11', - 'SD': '154.96.0.0/13', + 'SD': '102.120.0.0/13', 'SE': '78.64.0.0/12', - 'SG': '152.56.0.0/14', + 'SG': '8.128.0.0/10', 'SI': '188.196.0.0/14', 'SK': '78.98.0.0/15', - 'SL': '197.215.0.0/17', + 'SL': '102.143.0.0/17', 'SM': '89.186.32.0/19', 'SN': '41.82.0.0/15', - 'SO': '197.220.64.0/19', + 'SO': '154.115.192.0/18', 'SR': '186.179.128.0/17', 'SS': '105.235.208.0/21', 'ST': '197.159.160.0/19', @@ -5197,15 +5219,15 @@ class GeoUtils(object): 'TV': '202.2.96.0/19', 'TW': '120.96.0.0/11', 'TZ': '156.156.0.0/14', - 'UA': '93.72.0.0/13', - 'UG': '154.224.0.0/13', - 'US': '3.0.0.0/8', + 'UA': '37.52.0.0/14', + 'UG': '102.80.0.0/13', + 'US': '6.0.0.0/8', 'UY': '167.56.0.0/13', - 'UZ': '82.215.64.0/18', + 'UZ': '84.54.64.0/18', 'VA': '212.77.0.0/19', - 'VC': '24.92.144.0/20', + 'VC': '207.191.240.0/21', 'VE': '186.88.0.0/13', - 'VG': '172.103.64.0/18', + 'VG': '66.81.192.0/20', 'VI': '146.226.0.0/16', 'VN': '14.160.0.0/11', 'VU': '202.80.32.0/20', @@ -5214,8 +5236,8 @@ class GeoUtils(object): 'YE': '134.35.0.0/16', 'YT': '41.242.116.0/22', 'ZA': '41.0.0.0/11', - 'ZM': '165.56.0.0/13', - 'ZW': '41.85.192.0/19', + 'ZM': '102.144.0.0/13', + 'ZW': '102.177.192.0/18', } @classmethod @@ -5377,6 +5399,19 @@ def decode_packed_codes(code): obfucasted_code) +def caesar(s, alphabet, shift): + if shift == 0: + return s + l = len(alphabet) + return ''.join( + alphabet[(alphabet.index(c) + shift) % l] if c in alphabet else c + for c in s) + + +def rot47(s): + return caesar(s, r'''!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~''', 47) + + def parse_m3u8_attributes(attrib): info = {} for (key, val) in re.findall(r'(?P<key>[A-Z0-9-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)', attrib): diff --git a/youtube_dl/version.py b/youtube_dl/version.py index c3eafb068..0f768f7c1 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.28' +__version__ = '2020.03.08' |