diff options
| author | Aakash Gajjar <skyqutip@gmail.com> | 2020-08-25 20:23:34 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2020-08-25 20:23:34 +0530 |
| commit | b827ee921fe510a8730a9fab070148ed2b8279b5 (patch) | |
| tree | 4db8b0a8d954cea6fd86188a633850d7139f79c7 /youtube_dl/extractor/ard.py | |
| parent | 89cee32ce9b504bd2b892f6fd2bcda46ae33a10c (diff) | |
| download | hypervideo-pre-b827ee921fe510a8730a9fab070148ed2b8279b5.tar.lz hypervideo-pre-b827ee921fe510a8730a9fab070148ed2b8279b5.tar.xz hypervideo-pre-b827ee921fe510a8730a9fab070148ed2b8279b5.zip | |
pull changes from remote master (#190)
* [scrippsnetworks] Add new extractor(closes #19857)(closes #22981)
* [teachable] Improve locked lessons detection (#23528)
* [teachable] Fail with error message if no video URL found
* [extractors] add missing import for ScrippsNetworksIE
* [brightcove] cache brightcove player policy keys
* [prosiebensat1] improve geo restriction handling(closes #23571)
* [soundcloud] automatically update client id on failing requests
* [spankbang] Fix extraction (closes #23307, closes #23423, closes #23444)
* [spankbang] Improve removed video detection (#23423)
* [brightcove] update policy key on failing requests
* [pornhub] Fix extraction and add support for m3u8 formats (closes #22749, closes #23082)
* [pornhub] Improve locked videos detection (closes #22449, closes #22780)
* [brightcove] invalidate policy key cache on failing requests
* [soundcloud] fix client id extraction for non fatal requests
* [ChangeLog] Actualize
[ci skip]
* [devscripts/create-github-release] Switch to using PAT for authentication
Basic authentication will be deprecated soon
* release 2020.01.01
* [redtube] Detect private videos (#23518)
* [vice] improve extraction(closes #23631)
* [devscripts/create-github-release] Remove unused import
* [wistia] improve format extraction and extract subtitles(closes #22590)
* [nrktv:seriebase] Fix extraction (closes #23625) (#23537)
* [discovery] fix anonymous token extraction(closes #23650)
* [scrippsnetworks] add support for www.discovery.com videos
* [scrippsnetworks] correct test case URL
* [dctp] fix format extraction(closes #23656)
* [pandatv] Remove extractor (#23630)
* [naver] improve extraction
- improve geo-restriction handling
- extract automatic captions
- extract uploader metadata
- extract VLive HLS formats
* [naver] improve metadata extraction
* [cloudflarestream] improve extraction
- add support for bytehighway.net domain
- add support for signed URLs
- extract thumbnail
* [cloudflarestream] import embed URL extraction
* [lego] fix extraction and extract subtitle(closes #23687)
* [safari] Fix kaltura session extraction (closes #23679) (#23670)
* [orf:fm4] Fix extraction (#23599)
* [orf:radio] Clean description and improve extraction
* [twitter] add support for promo_video_website cards(closes #23711)
* [vodplatform] add support for embed.kwikmotion.com domain
* [ndr:base:embed] Improve thumbnails extraction (closes #23731)
* [canvas] Add support for new API endpoint and update tests (closes #17680, closes #18629)
* [travis] Add flake8 job (#23720)
* [yourporn] Fix extraction (closes #21645, closes #22255, closes #23459)
* [ChangeLog] Actualize
[ci skip]
* release 2020.01.15
* [soundcloud] Restore previews extraction (closes #23739)
* [orf:tvthek] Improve geo restricted videos detection (closes #23741)
* [zype] improve extraction
- extract subtitles(closes #21258)
- support URLs with alternative keys/tokens(#21258)
- extract more metadata
* [americastestkitchen] fix extraction
* [nbc] add support for nbc multi network URLs(closes #23049)
* [ard] improve extraction(closes #23761)
- simplify extraction
- extract age limit and series
- bypass geo-restriction
* [ivi:compilation] Fix entries extraction (closes #23770)
* [24video] Add support for 24video.vip (closes #23753)
* [businessinsider] Fix jwplatform id extraction (closes #22929) (#22954)
* [ard] add a missing condition
* [azmedien] fix extraction(closes #23783)
* [voicerepublic] fix extraction
* [stretchinternet] fix extraction(closes #4319)
* [youtube] Fix sigfunc name extraction (closes #23819)
* [ChangeLog] Actualize
[ci skip]
* release 2020.01.24
* [soundcloud] imporve private playlist/set tracks extraction
https://github.com/ytdl-org/youtube-dl/issues/3707#issuecomment-577873539
* [svt] fix article extraction(closes #22897)(closes #22919)
* [svt] fix series extraction(closes #22297)
* [viewlift] improve extraction
- fix extraction(closes #23851)
- add add support for authentication
- add support for more domains
* [vimeo] fix album extraction(closes #23864)
* [tva] Relax _VALID_URL (closes #23903)
* [tv5mondeplus] Fix extraction (closes #23907, closes #23911)
* [twitch:stream] Lowercase channel id for stream request (closes #23917)
* [sportdeutschland] Update to new sportdeutschland API
They switched to SSL, but under a different host AND path...
Remove the old test cases because these videos have become unavailable.
* [popcorntimes] Add extractor (closes #23949)
* [thisoldhouse] fix extraction(closes #23951)
* [toggle] Add support for mewatch.sg (closes #23895) (#23930)
* [compat] Introduce compat_realpath (refs #23991)
* [update] Fix updating via symlinks (closes #23991)
* [nytimes] improve format sorting(closes #24010)
* [abc:iview] Support 720p (#22907) (#22921)
* [nova:embed] Fix extraction (closes #23672)
* [nova:embed] Improve (closes #23690)
* [nova] Improve extraction (refs #23690)
* [jpopsuki] Remove extractor (closes #23858)
* [YoutubeDL] Fix playlist entry indexing with --playlist-items (closes #10591, closes #10622)
* [test_YoutubeDL] Fix get_ids
* [test_YoutubeDL] Add tests for #10591 (closes #23873)
* [24video] Add support for porn.24video.net (closes #23779, closes #23784)
* [npr] Add support for streams (closes #24042)
* [ChangeLog] Actualize
[ci skip]
* release 2020.02.16
* [tv2dk:bornholm:play] Fix extraction (#24076)
* [imdb] Fix extraction (closes #23443)
* [wistia] Add support for multiple generic embeds (closes #8347, closes #11385)
* [teachable] Add support for multiple videos per lecture (closes #24101)
* [pornhd] Fix extraction (closes #24128)
* [options] Remove duplicate short option -v for --version (#24162)
* [extractor/common] Convert ISM manifest to unicode before processing on python 2 (#24152)
* [YoutubeDL] Force redirect URL to unicode on python 2
* Remove no longer needed compat_str around geturl
* [youjizz] Fix extraction (closes #24181)
* [test_subtitles] Remove obsolete test
* [zdf:channel] Fix tests
* [zapiks] Fix test
* [xtube] Fix metadata extraction (closes #21073, closes #22455)
* [xtube:user] Fix test
* [telecinco] Fix extraction (refs #24195)
* [telecinco] Add support for article opening videos
* [franceculture] Fix extraction (closes #24204)
* [xhamster] Fix extraction (closes #24205)
* [ChangeLog] Actualize
[ci skip]
* release 2020.03.01
* [vimeo] Fix subtitles URLs (#24209)
* [servus] Add support for new URL schema (closes #23475, closes #23583, closes #24142)
* [youtube:playlist] Fix tests (closes #23872) (#23885)
* [peertube] Improve extraction
* [peertube] Fix issues and improve extraction (closes #23657)
* [pornhub] Improve title extraction (closes #24184)
* [vimeo] fix showcase password protected video extraction(closes #24224)
* [youtube] Fix age-gated videos support without login (closes #24248)
* [youtube] Fix tests
* [ChangeLog] Actualize
[ci skip]
* release 2020.03.06
* [nhk] update API version(closes #24270)
* [youtube] Improve extraction in 429 error conditions (closes #24283)
* [youtube] Improve age-gated videos extraction in 429 error conditions (refs #24283)
* [youtube] Remove outdated code
Additional get_video_info requests don't seem to provide any extra itags any longer
* [README.md] Clarify 429 error
* [pornhub] Add support for pornhubpremium.com (#24288)
* [utils] Add support for cookies with spaces used instead of tabs
* [ChangeLog] Actualize
[ci skip]
* release 2020.03.08
* Revert "[utils] Add support for cookies with spaces used instead of tabs"
According to [1] TABs must be used as separators between fields.
Files produces by some tools with spaces as separators are considered
malformed.
1. https://curl.haxx.se/docs/http-cookies.html
This reverts commit cff99c91d150df2a4e21962a3ca8d4ae94533b8c.
* [utils] Add reference to cookie file format
* Revert "[vimeo] fix showcase password protected video extraction(closes #24224)"
This reverts commit 12ee431676bb655f04c7dd416a73c1f142ed368d.
* [nhk] Relax _VALID_URL (#24329)
* [nhk] Remove obsolete rtmp formats (closes #24329)
* [nhk] Update m3u8 URL and use native hls (#24329)
* [ndr] Fix extraction (closes #24326)
* [xtube] Fix formats extraction (closes #24348)
* [xtube] Fix typo
* [hellporno] Fix extraction (closes #24399)
* [cbc:watch] Add support for authentication
* [cbc:watch] Fix authenticated device token caching (closes #19160)
* [soundcloud] fix download url extraction(closes #24394)
* [limelight] remove disabled API requests(closes #24255)
* [bilibili] Add support for new URL schema with BV ids (closes #24439, closes #24442)
* [bilibili] Add support for player.bilibili.com (closes #24402)
* [teachable] Extract chapter metadata (closes #24421)
* [generic] Look for teachable embeds before wistia
* [teachable] Update upskillcourses domain
New version does not use teachable platform any longer
* [teachable] Update gns3 domain
* [teachable] Update test
* [ChangeLog] Actualize
[ci skip]
* [ChangeLog] Actualize
[ci skip]
* release 2020.03.24
* [spankwire] Fix extraction (closes #18924, closes #20648)
* [spankwire] Add support for generic embeds (refs #24633)
* [youporn] Add support form generic embeds
* [mofosex] Add support for generic embeds (closes #24633)
* [tele5] Fix extraction (closes #24553)
* [extractor/common] Skip malformed ISM manifest XMLs while extracting ISM formats (#24667)
* [tv4] Fix ISM formats extraction (closes #24667)
* [twitch:clips] Extend _VALID_URL (closes #24290) (#24642)
* [motherless] Fix extraction (closes #24699)
* [nova:embed] Fix extraction (closes #24700)
* [youtube] Skip broken multifeed videos (closes #24711)
* [soundcloud] Extract AAC format
* [soundcloud] Improve AAC format extraction (closes #19173, closes #24708)
* [thisoldhouse] Fix video id extraction (closes #24548)
Added support for:
with of without "www."
and either ".chorus.build" or ".com"
It now validated correctly on older URL's
```
<iframe src="https://thisoldhouse.chorus.build/videos/zype/5e33baec27d2e50001d5f52f
```
and newer ones
```
<iframe src="https://www.thisoldhouse.com/videos/zype/5e2b70e95216cc0001615120
```
* [thisoldhouse] Improve video id extraction (closes #24549)
* [youtube] Fix DRM videos detection (refs #24736)
* [options] Clarify doc on --exec command (closes #19087) (#24883)
* [prosiebensat1] Improve extraction and remove 7tv.de support (#24948)
* [prosiebensat1] Extract series metadata
* [tenplay] Relax _VALID_URL (closes #25001)
* [tvplay] fix Viafree extraction(closes #15189)(closes #24473)(closes #24789)
* [yahoo] fix GYAO Player extraction and relax title URL regex(closes #24178)(closes #24778)
* [youtube] Use redirected video id if any (closes #25063)
* [youtube] Improve player id extraction and add tests
* [extractor/common] Extract multiple JSON-LD entries
* [crunchyroll] Fix and improve extraction (closes #25096, closes #25060)
* [ChangeLog] Actualize
[ci skip]
* release 2020.05.03
* [puhutv] Remove no longer available HTTP formats (closes #25124)
* [utils] Improve cookie files support
+ Add support for UTF-8 in cookie files
* Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
* [dailymotion] Fix typo
* [compat] Introduce compat_cookiejar_Cookie
* [extractor/common] Use compat_cookiejar_Cookie for _set_cookie (closes #23256, closes #24776)
To always ensure cookie name and value are bytestrings on python 2.
* [orf] Add support for more radio stations (closes #24938) (#24968)
* [uol] fix extraction(closes #22007)
* [downloader/http] Finish downloading once received data length matches expected
Always do this if possible, i.e. if Content-Length or expected length is known, not only in test.
This will save unnecessary last extra loop trying to read 0 bytes.
* [downloader/http] Request last data block of exact remaining size
Always request last data block of exact size remaining to download if possible not the current block size.
* [iprima] Improve extraction (closes #25138)
* [youtube] Improve signature cipher extraction (closes #25188)
* [ChangeLog] Actualize
[ci skip]
* release 2020.05.08
* [spike] fix Bellator mgid extraction(closes #25195)
* [bbccouk] PEP8
* [mailru] Fix extraction (closes #24530) (#25239)
* [README.md] flake8 HTTPS URL (#25230)
* [youtube] Add support for yewtu.be (#25226)
* [soundcloud] reduce API playlist page limit(closes #25274)
* [vimeo] improve format extraction and sorting(closes #25285)
* [redtube] Improve title extraction (#25208)
* [indavideo] Switch to HTTPS for API request (#25191)
* [utils] Fix file permissions in write_json_file (closes #12471) (#25122)
* [redtube] Improve formats extraction and extract m3u8 formats (closes #25311, closes #25321)
* [ard] Improve _VALID_URL (closes #25134) (#25198)
* [giantbomb] Extend _VALID_URL (#25222)
* [postprocessor/ffmpeg] Embed series metadata with --add-metadata
* [youtube] Add support for more invidious instances (#25417)
* [ard:beta] Extend _VALID_URL (closes #25405)
* [ChangeLog] Actualize
[ci skip]
* release 2020.05.29
* [jwplatform] Improve embeds extraction (closes #25467)
* [periscope] Fix untitled broadcasts (#25482)
* [twitter:broadcast] Add untitled periscope broadcast test
* [malltv] Add support for sk.mall.tv (#25445)
* [brightcove] Fix subtitles extraction (closes #25540)
* [brightcove] Sort imports
* [twitch] Pass v5 accept header and fix thumbnails extraction (closes #25531)
* [twitch:stream] Fix extraction (closes #25528)
* [twitch:stream] Expect 400 and 410 HTTP errors from API
* [tele5] Prefer jwplatform over nexx (closes #25533)
* [jwplatform] Add support for bypass geo restriction
* [tele5] Bypass geo restriction
* [ChangeLog] Actualize
[ci skip]
* release 2020.06.06
* [kaltura] Add support for multiple embeds on a webpage (closes #25523)
* [youtube] Extract chapters from JSON (closes #24819)
* [facebook] Support single-video ID links
I stumbled upon this at https://www.facebook.com/bwfbadminton/posts/10157127020046316 . No idea how prevalent it is yet.
* [youtube] Fix playlist and feed extraction (closes #25675)
* [youtube] Fix thumbnails extraction and remove uploader id extraction warning (closes #25676)
* [youtube] Fix upload date extraction
* [youtube] Improve view count extraction
* [youtube] Fix uploader id and uploader URL extraction
* [ChangeLog] Actualize
[ci skip]
* release 2020.06.16
* [youtube] Fix categories and improve tags extraction
* [youtube] Force old layout (closes #25682, closes #25683, closes #25680, closes #25686)
* [ChangeLog] Actualize
[ci skip]
* release 2020.06.16.1
* [brightcove] Improve embed detection (closes #25674)
* [bellmedia] add support for cp24.com clip URLs(closes #25764)
* [youtube:playlists] Extend _VALID_URL (closes #25810)
* [youtube] Prevent excess HTTP 301 (#25786)
* [wistia] Restrict embed regex (closes #25969)
* [youtube] Improve description extraction (closes #25937) (#25980)
* [youtube] Fix sigfunc name extraction (closes #26134, closes #26135, closes #26136, closes #26137)
* [ChangeLog] Actualize
[ci skip]
* release 2020.07.28
* [xhamster] Extend _VALID_URL (closes #25789) (#25804)
* [xhamster] Fix extraction (closes #26157) (#26254)
* [xhamster] Extend _VALID_URL (closes #25927)
Co-authored-by: Remita Amine <remitamine@gmail.com>
Co-authored-by: Sergey M․ <dstftw@gmail.com>
Co-authored-by: nmeum <soeren+github@soeren-tempel.net>
Co-authored-by: Roxedus <me@roxedus.dev>
Co-authored-by: Singwai Chan <c.singwai@gmail.com>
Co-authored-by: cdarlint <cdarlint@users.noreply.github.com>
Co-authored-by: Johannes N <31795504+jonolt@users.noreply.github.com>
Co-authored-by: jnozsc <jnozsc@gmail.com>
Co-authored-by: Moritz Patelscheck <moritz.patelscheck@campus.tu-berlin.de>
Co-authored-by: PB <3854688+uno20001@users.noreply.github.com>
Co-authored-by: Philipp Hagemeister <phihag@phihag.de>
Co-authored-by: Xaver Hellauer <software@hellauer.bayern>
Co-authored-by: d2au <d2au.dev@gmail.com>
Co-authored-by: Jan 'Yenda' Trmal <jtrmal@gmail.com>
Co-authored-by: jxu <7989982+jxu@users.noreply.github.com>
Co-authored-by: Martin Ström <name@my-domain.se>
Co-authored-by: The Hatsune Daishi <nao20010128@gmail.com>
Co-authored-by: tsia <github@tsia.de>
Co-authored-by: 3risian <59593325+3risian@users.noreply.github.com>
Co-authored-by: Tristan Waddington <tristan.waddington@gmail.com>
Co-authored-by: Devon Meunier <devon.meunier@gmail.com>
Co-authored-by: Felix Stupp <felix.stupp@outlook.com>
Co-authored-by: tom <tomster954@gmail.com>
Co-authored-by: AndrewMBL <62922222+AndrewMBL@users.noreply.github.com>
Co-authored-by: willbeaufoy <will@willbeaufoy.net>
Co-authored-by: Philipp Stehle <anderschwiedu@googlemail.com>
Co-authored-by: hh0rva1h <61889859+hh0rva1h@users.noreply.github.com>
Co-authored-by: comsomisha <shmelev1996@mail.ru>
Co-authored-by: TotalCaesar659 <14265316+TotalCaesar659@users.noreply.github.com>
Co-authored-by: Juan Francisco Cantero Hurtado <iam@juanfra.info>
Co-authored-by: Dave Loyall <dave@the-good-guys.net>
Co-authored-by: tlsssl <63866177+tlsssl@users.noreply.github.com>
Co-authored-by: Rob <ankenyr@gmail.com>
Co-authored-by: Michael Klein <github@a98shuttle.de>
Co-authored-by: JordanWeatherby <47519158+JordanWeatherby@users.noreply.github.com>
Co-authored-by: striker.sh <19488257+strikersh@users.noreply.github.com>
Co-authored-by: Matej Dujava <mdujava@gmail.com>
Co-authored-by: Glenn Slayden <5589855+glenn-slayden@users.noreply.github.com>
Co-authored-by: MRWITEK <mrvvitek@gmail.com>
Co-authored-by: JChris246 <43832407+JChris246@users.noreply.github.com>
Co-authored-by: TheRealDude2 <the.real.dude@gmx.de>
Diffstat (limited to 'youtube_dl/extractor/ard.py')
| -rw-r--r-- | youtube_dl/extractor/ard.py | 282 |
1 files changed, 152 insertions, 130 deletions
diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 8adae4644..5b7b2dd6d 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) @@ -242,7 +249,7 @@ class ARDMediathekIE(InfoExtractor): class ARDIE(InfoExtractor): - _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html' + _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html' _TESTS = [{ # available till 14.02.2019 'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html', @@ -257,6 +264,9 @@ class ARDIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', }, }, { + 'url': 'https://www.daserste.de/information/reportage-dokumentation/erlebnis-erde/videosextern/woelfe-und-herdenschutzhunde-ungleiche-brueder-102.html', + 'only_matching': True, + }, { 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', 'only_matching': True, }] @@ -302,22 +312,32 @@ 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|video)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)' _TESTS = [{ - 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', - 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', + 'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', + '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', }, }, { + 'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', + 'only_matching': True, + }, { + 'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/', + 'only_matching': True, + }, { + 'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/', + 'only_matching': True, + }, { 'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/', 'only_matching': True, }, { @@ -328,73 +348,75 @@ class ARDBetaMediathekIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) 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, + display_id = mobj.group('display_id') + if display_id: + display_id = display_id.rstrip('/') + if not display_id: + display_id = video_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 |