diff options
| -rw-r--r-- | youtube_dl/extractor/bilibili.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/curiositystream.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/extractors.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 31 | ||||
| -rw-r--r-- | youtube_dl/extractor/liveleak.py | 191 | ||||
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 48 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 32 |
7 files changed, 59 insertions, 254 deletions
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 589fdc1ce..bff6ea194 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -233,7 +233,7 @@ class BiliBiliIE(InfoExtractor): webpage) if uploader_mobj: info.update({ - 'uploader': uploader_mobj.group('name'), + 'uploader': uploader_mobj.group('name').strip(), 'uploader_id': uploader_mobj.group('id'), }) if not info.get('uploader'): diff --git a/youtube_dl/extractor/curiositystream.py b/youtube_dl/extractor/curiositystream.py index ae64a07d7..48ff30432 100644 --- a/youtube_dl/extractor/curiositystream.py +++ b/youtube_dl/extractor/curiositystream.py @@ -145,7 +145,7 @@ class CuriosityStreamIE(CuriosityStreamBaseIE): class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): IE_NAME = 'curiositystream:collection' - _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collections?|series)/(?P<id>\d+)' _TESTS = [{ 'url': 'https://app.curiositystream.com/collection/2', 'info_dict': { @@ -157,6 +157,9 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): }, { 'url': 'https://curiositystream.com/series/2', 'only_matching': True, + }, { + 'url': 'https://curiositystream.com/collections/36', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 402e542ae..6e8fc3961 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -610,10 +610,6 @@ from .linkedin import ( from .linuxacademy import LinuxAcademyIE from .litv import LiTVIE from .livejournal import LiveJournalIE -from .liveleak import ( - LiveLeakIE, - LiveLeakEmbedIE, -) from .livestream import ( LivestreamIE, LivestreamOriginalIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 87594534f..a9c064105 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -84,7 +84,6 @@ from .jwplatform import JWPlatformIE from .digiteka import DigitekaIE from .arkena import ArkenaIE from .instagram import InstagramIE -from .liveleak import LiveLeakIE from .threeqsdn import ThreeQSDNIE from .theplatform import ThePlatformIE from .kaltura import KalturaIE @@ -1629,31 +1628,6 @@ class GenericIE(InfoExtractor): 'upload_date': '20160409', }, }, - # LiveLeak embed - { - 'url': 'http://www.wykop.pl/link/3088787/', - 'md5': '7619da8c820e835bef21a1efa2a0fc71', - 'info_dict': { - 'id': '874_1459135191', - 'ext': 'mp4', - 'title': 'Man shows poor quality of new apartment building', - 'description': 'The wall is like a sand pile.', - 'uploader': 'Lake8737', - }, - 'add_ie': [LiveLeakIE.ie_key()], - }, - # Another LiveLeak embed pattern (#13336) - { - 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/', - 'info_dict': { - 'id': '2eb_1496309988', - 'ext': 'mp4', - 'title': 'Thief robs place where everyone was armed', - 'description': 'md5:694d73ee79e535953cf2488562288eee', - 'uploader': 'brazilwtf', - }, - 'add_ie': [LiveLeakIE.ie_key()], - }, # Duplicated embedded video URLs { 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443', @@ -3179,11 +3153,6 @@ class GenericIE(InfoExtractor): return self.url_result( self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key()) - # Look for LiveLeak embeds - liveleak_urls = LiveLeakIE._extract_urls(webpage) - if liveleak_urls: - return self.playlist_from_matches(liveleak_urls, video_id, video_title) - # Look for 3Q SDN embeds threeqsdn_url = ThreeQSDNIE._extract_url(webpage) if threeqsdn_url: diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py deleted file mode 100644 index 4ac437c8b..000000000 --- a/youtube_dl/extractor/liveleak.py +++ /dev/null @@ -1,191 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import int_or_none - - -class LiveLeakIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?.*?\b[it]=(?P<id>[\w_]+)' - _TESTS = [{ - 'url': 'http://www.liveleak.com/view?i=757_1364311680', - 'md5': '0813c2430bea7a46bf13acf3406992f4', - 'info_dict': { - 'id': '757_1364311680', - 'ext': 'mp4', - 'description': 'extremely bad day for this guy..!', - 'uploader': 'ljfriel2', - 'title': 'Most unlucky car accident', - 'thumbnail': r're:^https?://.*\.jpg$' - } - }, { - 'url': 'http://www.liveleak.com/view?i=f93_1390833151', - 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf', - 'info_dict': { - 'id': 'f93_1390833151', - 'ext': 'mp4', - 'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.', - 'uploader': 'ARD_Stinkt', - 'title': 'German Television does first Edward Snowden Interview (ENGLISH)', - 'thumbnail': r're:^https?://.*\.jpg$' - } - }, { - # Prochan embed - 'url': 'http://www.liveleak.com/view?i=4f7_1392687779', - 'md5': '42c6d97d54f1db107958760788c5f48f', - 'info_dict': { - 'id': '4f7_1392687779', - 'ext': 'mp4', - 'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing... I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.", - 'uploader': 'CapObveus', - 'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck', - 'age_limit': 18, - }, - 'skip': 'Video is dead', - }, { - # Covers https://github.com/ytdl-org/youtube-dl/pull/5983 - # Multiple resolutions - 'url': 'http://www.liveleak.com/view?i=801_1409392012', - 'md5': 'c3a449dbaca5c0d1825caecd52a57d7b', - 'info_dict': { - 'id': '801_1409392012', - 'ext': 'mp4', - 'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.', - 'uploader': 'bony333', - 'title': 'Crazy Hungarian tourist films close call waterspout in Croatia', - 'thumbnail': r're:^https?://.*\.jpg$' - } - }, { - # Covers https://github.com/ytdl-org/youtube-dl/pull/10664#issuecomment-247439521 - 'url': 'http://m.liveleak.com/view?i=763_1473349649', - 'add_ie': ['Youtube'], - 'info_dict': { - 'id': '763_1473349649', - 'ext': 'mp4', - 'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty', - 'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.', - 'uploader': 'Ziz', - 'upload_date': '20160908', - 'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw' - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'https://www.liveleak.com/view?i=677_1439397581', - 'info_dict': { - 'id': '677_1439397581', - 'title': 'Fuel Depot in China Explosion caught on video', - }, - 'playlist_count': 3, - }, { - 'url': 'https://www.liveleak.com/view?t=HvHi_1523016227', - 'only_matching': True, - }, { - # No original video - 'url': 'https://www.liveleak.com/view?t=C26ZZ_1558612804', - 'only_matching': True, - }] - - @staticmethod - def _extract_urls(webpage): - return re.findall( - r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"', - webpage) - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip() - video_description = self._og_search_description(webpage) - video_uploader = self._html_search_regex( - r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False) - age_limit = int_or_none(self._search_regex( - r'you confirm that you are ([0-9]+) years and over.', - webpage, 'age limit', default=None)) - video_thumbnail = self._og_search_thumbnail(webpage) - - entries = self._parse_html5_media_entries(url, webpage, video_id) - if not entries: - # Maybe an embed? - embed_url = self._search_regex( - r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"', - webpage, 'embed URL') - return { - '_type': 'url_transparent', - 'url': embed_url, - 'id': video_id, - 'title': video_title, - 'description': video_description, - 'uploader': video_uploader, - 'age_limit': age_limit, - } - - for idx, info_dict in enumerate(entries): - formats = [] - for a_format in info_dict['formats']: - if not a_format.get('height'): - a_format['height'] = int_or_none(self._search_regex( - r'([0-9]+)p\.mp4', a_format['url'], 'height label', - default=None)) - formats.append(a_format) - - # Removing '.*.mp4' gives the raw video, which is essentially - # the same video without the LiveLeak logo at the top (see - # https://github.com/ytdl-org/youtube-dl/pull/4768) - orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url']) - if a_format['url'] != orig_url: - format_id = a_format.get('format_id') - format_id = 'original' + ('-' + format_id if format_id else '') - if self._is_valid_url(orig_url, video_id, format_id): - formats.append({ - 'format_id': format_id, - 'url': orig_url, - 'preference': 1, - }) - self._sort_formats(formats) - info_dict['formats'] = formats - - # Don't append entry ID for one-video pages to keep backward compatibility - if len(entries) > 1: - info_dict['id'] = '%s_%s' % (video_id, idx + 1) - else: - info_dict['id'] = video_id - - info_dict.update({ - 'title': video_title, - 'description': video_description, - 'uploader': video_uploader, - 'age_limit': age_limit, - 'thumbnail': video_thumbnail, - }) - - return self.playlist_result(entries, video_id, video_title) - - -class LiveLeakEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[ift])=(?P<id>[\w_]+)' - - # See generic.py for actual test cases - _TESTS = [{ - 'url': 'https://www.liveleak.com/ll_embed?i=874_1459135191', - 'only_matching': True, - }, { - 'url': 'https://www.liveleak.com/ll_embed?f=ab065df993c1', - 'only_matching': True, - }] - - def _real_extract(self, url): - kind, video_id = re.match(self._VALID_URL, url).groups() - - if kind == 'f': - webpage = self._download_webpage(url, video_id) - liveleak_url = self._search_regex( - r'(?:logourl\s*:\s*|window\.open\()(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL, - webpage, 'LiveLeak URL', group='url') - else: - liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id) - - return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key()) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 031454600..e2e1500ff 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -30,6 +30,7 @@ from ..utils import ( class PornHubBaseIE(InfoExtractor): _NETRC_MACHINE = 'pornhub' + _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubthbh7ap3u\.onion)' def _download_webpage_handle(self, *args, **kwargs): def dl(*args, **kwargs): @@ -122,11 +123,13 @@ class PornHubIE(PornHubBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)? + %s + /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P<id>[\da-z]+) - ''' + ''' % PornHubBaseIE._PORNHUB_HOST_RE _TESTS = [{ 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', 'md5': 'a6391306d050e4547f62b3f485dd9ba9', @@ -236,6 +239,13 @@ class PornHubIE(PornHubBaseIE): }, { 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3', 'only_matching': True, + }, { + # geo restricted + 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156', + 'only_matching': True, + }, { + 'url': 'http://pornhubthbh7ap3u.onion/view_video.php?viewkey=ph5a9813bfa7156', + 'only_matching': True, }] @staticmethod @@ -275,6 +285,11 @@ class PornHubIE(PornHubBaseIE): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) + if any(re.search(p, webpage) for p in ( + r'class=["\']geoBlocked["\']', + r'>\s*This content is unavailable in your country')): + self.raise_geo_restricted() + # video_title from flashvars contains whitespace instead of non-ASCII (see # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. @@ -408,17 +423,14 @@ class PornHubIE(PornHubBaseIE): format_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) return - tbr = None - mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url) - if mobj: - if not height: - height = int(mobj.group('height')) - tbr = int(mobj.group('tbr')) + if not height: + height = int_or_none(self._search_regex( + r'(?P<height>\d+)[pP]?_\d+[kK]', format_url, 'height', + default=None)) formats.append({ 'url': format_url, 'format_id': '%dp' % height if height else None, 'height': height, - 'tbr': tbr, }) for video_url, height in video_urls: @@ -440,7 +452,8 @@ class PornHubIE(PornHubBaseIE): add_format(video_url, height) continue add_format(video_url) - self._sort_formats(formats) + self._sort_formats( + formats, field_preference=('height', 'width', 'fps', 'format_id')) video_uploader = self._html_search_regex( r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', @@ -513,7 +526,7 @@ class PornHubPlaylistBaseIE(PornHubBaseIE): class PornHubUserIE(PornHubPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph', 'playlist_mincount': 118, @@ -542,6 +555,9 @@ class PornHubUserIE(PornHubPlaylistBaseIE): # Same as before, multi page 'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau', 'only_matching': True, + }, { + 'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph', + 'only_matching': True, }] def _real_extract(self, url): @@ -617,7 +633,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?P<id>(?:[^/]+/)*[^/?#&]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph/videos', 'only_matching': True, @@ -722,6 +738,9 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): }, { 'url': 'https://de.pornhub.com/playlist/4667351', 'only_matching': True, + }, { + 'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph/videos', + 'only_matching': True, }] @classmethod @@ -732,7 +751,7 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE _TESTS = [{ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'info_dict': { @@ -742,4 +761,7 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): }, { 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload', 'only_matching': True, + }, { + 'url': 'http://pornhubthbh7ap3u.onion/pornstar/jenny-blighe/videos/upload', + 'only_matching': True, }] diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 35058950a..dc4bd4a77 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1504,19 +1504,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor): playability_status = player_response.get('playabilityStatus') or {} if playability_status.get('reason') == 'Sign in to confirm your age': - pr = self._parse_json(try_get(compat_parse_qs( - self._download_webpage( - base_url + 'get_video_info', video_id, - 'Refetching age-gated info webpage', - 'unable to download video info webpage', query={ - 'video_id': video_id, - 'eurl': 'https://youtube.googleapis.com/v/' + video_id, - 'html5': 1, - }, fatal=False)), - lambda x: x['player_response'][0], - compat_str) or '{}', video_id) - if pr: - player_response = pr + video_info = self._download_webpage( + base_url + 'get_video_info', video_id, + 'Refetching age-gated info webpage', + 'unable to download video info webpage', query={ + 'video_id': video_id, + 'eurl': 'https://youtube.googleapis.com/v/' + video_id, + 'html5': 1, + # See https://github.com/ytdl-org/youtube-dl/issues/29333#issuecomment-864049544 + 'c': 'TVHTML5', + 'cver': '6.20180913', + }, fatal=False) + if video_info: + pr = self._parse_json( + try_get( + compat_parse_qs(video_info), + lambda x: x['player_response'][0], compat_str) or '{}', + video_id, fatal=False) + if pr and isinstance(pr, dict): + player_response = pr trailer_video_id = try_get( playability_status, |