X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=355067a509fc197c10a2085bad058d4459729bc9;hp=aa04905ed802d7ce5ddc783f10cb7bb0ce6f74a5;hb=562de77f41d0c08df9dbb08cfa86ba6c7d239c5a;hpb=7b393f9cc5dc4790bcb623c768fa4a3046ef80bf diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index aa04905ed..355067a50 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -47,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .tvc import TVCIE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .smotri import SmotriIE from .myvi import MyviIE from .condenast import CondeNastIE @@ -60,6 +60,9 @@ from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE from .tube8 import Tube8IE +from .mofosex import MofosexEmbedIE +from .spankwire import SpankwireIE +from .youporn import YouPornIE from .vimeo import VimeoIE from .dailymotion import DailymotionIE from .dailymail import DailyMailIE @@ -77,11 +80,10 @@ 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 @@ -89,7 +91,6 @@ from .piksel import PikselIE from .videa import VideaIE from .twentymin import TwentyMinutenIE from .ustream import UstreamIE -from .openload import OpenloadIE from .videopress import VideoPressIE from .rutube import RutubeIE from .limelight import LimelightBaseIE @@ -109,9 +110,15 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .teachable import TeachableIE from .indavideo import IndavideoEmbedIE from .apa import APAIE 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): @@ -426,7 +433,7 @@ class GenericIE(InfoExtractor): }, }, { - # https://github.com/rg3/youtube-dl/issues/2253 + # https://github.com/ytdl-org/youtube-dl/issues/2253 'url': 'http://bcove.me/i6nfkrc3', 'md5': '0ba9446db037002366bab3b3eb30c88c', 'info_dict': { @@ -451,7 +458,7 @@ class GenericIE(InfoExtractor): }, }, { - # https://github.com/rg3/youtube-dl/issues/3541 + # https://github.com/ytdl-org/youtube-dl/issues/3541 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', 'info_dict': { @@ -915,7 +922,7 @@ class GenericIE(InfoExtractor): } }, # Multiple brightcove videos - # https://github.com/rg3/youtube-dl/issues/2283 + # https://github.com/ytdl-org/youtube-dl/issues/2283 { 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', 'info_dict': { @@ -1480,16 +1487,18 @@ 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 @@ -1699,6 +1708,15 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Kaltura'], }, + { + # multiple kaltura embeds, nsfw + 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html', + 'info_dict': { + 'id': 'kamila-avec-video-jaime-sadomie', + 'title': "Kamila avec vídeo “J'aime sadomie”", + }, + 'playlist_count': 8, + }, { # Non-standard Vimeo embed 'url': 'https://openclassrooms.com/courses/understanding-the-web', @@ -2059,6 +2077,80 @@ class GenericIE(InfoExtractor): }, 'skip': 'TODO: fix nested playlists processing in tests', }, + { + # Viqeo embeds + 'url': 'https://viqeo.tv/', + 'info_dict': { + 'id': 'viqeo', + 'title': 'All-new video platform', + }, + 'playlist_count': 6, + }, + { + # Squarespace video embed, 2019-08-28 + 'url': 'http://ootboxford.com', + 'info_dict': { + 'id': 'Tc7b_JGdZfw', + 'title': 'Out of the Blue, at Childish Things 10', + 'ext': 'mp4', + 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f', + 'uploader_id': 'helendouglashouse', + 'uploader': 'Helen & Douglas House', + 'upload_date': '20140328', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # Zype embed + 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + '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': { + 'skip_download': True, + }, + }, + { + # videojs embed + 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', + 'info_dict': { + 'id': 'shell', + 'ext': 'mp4', + 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано', + 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Failed to download MPD manifest'], + }, + { + # DailyMotion embed with DM.player + 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804', + 'info_dict': { + 'id': 'k6aKkGHd9FJs4mtJN39', + 'ext': 'mp4', + 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final', + 'description': 'This video is private.', + 'uploader_id': 'x1jf30l', + 'uploader': 'beIN SPORTS USA', + 'upload_date': '20190528', + 'timestamp': 1559062971, + }, + 'params': { + 'skip_download': True, + }, + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -2155,10 +2247,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: @@ -2167,7 +2256,7 @@ class GenericIE(InfoExtractor): default_search = 'fixup_error' if default_search in ('auto', 'auto_warning', 'fixup_error'): - if '/' in url: + if re.match(r'^[^\s/]+\.[^\s/]+/', url): self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) elif default_search != 'fixup_error': @@ -2210,7 +2299,7 @@ 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: @@ -2310,12 +2399,12 @@ 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 @@ -2332,10 +2421,16 @@ class GenericIE(InfoExtractor): return camtasia_res # Sometimes embedded video player is hidden behind percent encoding - # (e.g. https://github.com/rg3/youtube-dl/issues/2448) + # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way webpage = compat_urllib_parse_unquote(webpage) + # Unescape squarespace embeds to be detected by generic extractor, + # see https://github.com/ytdl-org/youtube-dl/issues/21294 + webpage = re.sub( + r']+class=[^>]*?\bsqs-video-wrapper\b[^>]*>', + lambda x: unescapeHTML(x.group(0)), webpage) + # it's tempting to parse this further, but you would # have to take into account all the variations like # Video Title - Site Name @@ -2410,11 +2505,6 @@ 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']+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"', @@ -2458,15 +2548,21 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) + # Look for Teachable embeds, must be before Wistia + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + # 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) @@ -2507,11 +2603,11 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url')) # Look for Ooyala videos - mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) or - re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage) or - re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P.{32})[\'"]', webpage) or - re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P.{32})[\'"]\)', webpage) or - re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P.{32})[\'"]', webpage)) + mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) + or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage) + or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P.{32})[\'"]', webpage) + or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P.{32})[\'"]\)', webpage) + or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P.{32})[\'"]', webpage)) if mobj is not None: embed_token = self._search_regex( r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)', @@ -2541,19 +2637,6 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group(1), 'Mpora') - # Look for embedded NovaMov-based player - mobj = re.search( - r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\']) - (?Phttp://(?:(?:embed|www)\.)? - (?:novamov\.com| - nowvideo\.(?:ch|sx|eu|at|ag|co)| - videoweed\.(?:es|com)| - movshare\.(?:net|sx|ag)| - divxstage\.(?:eu|net|ch|co|at|ag)) - /embed\.php.+?)\1''', webpage) - if mobj is not None: - return self.url_result(mobj.group('url')) - # Look for embedded Facebook player facebook_urls = FacebookIE._extract_urls(webpage) if facebook_urls: @@ -2565,9 +2648,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'VK') # Look for embedded Odnoklassniki player - mobj = re.search(r']+?src=(["\'])(?Phttps?://(?: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']+?src=(["\'])(?Phttps?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) @@ -2610,9 +2693,9 @@ class GenericIE(InfoExtractor): return self.url_result(tvc_url, 'TVC') # Look for embedded SportBox player - sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + sportbox_urls = SportBoxIE._extract_urls(webpage) if sportbox_urls: - return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed') + return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key()) # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) @@ -2644,6 +2727,21 @@ class GenericIE(InfoExtractor): if tube8_urls: return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key()) + # Look for embedded Mofosex player + mofosex_urls = MofosexEmbedIE._extract_urls(webpage) + if mofosex_urls: + return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key()) + + # Look for embedded Spankwire player + spankwire_urls = SpankwireIE._extract_urls(webpage) + if spankwire_urls: + return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key()) + + # Look for embedded YouPorn player + youporn_urls = YouPornIE._extract_urls(webpage) + if youporn_urls: + return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r']+?src=(["\'])(?P(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) @@ -2686,9 +2784,9 @@ 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) @@ -2755,9 +2853,12 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'Zapiks') # Look for Kaltura embeds - kaltura_url = KalturaIE._extract_url(webpage) - if kaltura_url: - return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key()) + kaltura_urls = KalturaIE._extract_urls(webpage) + if kaltura_urls: + return self.playlist_from_matches( + kaltura_urls, video_id, video_title, + getter=lambda x: smuggle_url(x, {'source_url': url}), + ie=KalturaIE.ie_key()) # Look for EaglePlatform embeds eagleplatform_url = EaglePlatformIE._extract_url(webpage) @@ -2831,6 +2932,12 @@ 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: @@ -2892,7 +2999,7 @@ class GenericIE(InfoExtractor): # Look for VODPlatform embeds mobj = re.search( - r']+src=(["\'])(?P(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1', + r']+src=(["\'])(?P(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1', webpage) if mobj is not None: return self.url_result( @@ -2900,10 +3007,14 @@ class GenericIE(InfoExtractor): # Look for Mangomolo embeds mobj = re.search( - r'''(?x)]+src=(["\'])(?P(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/ + r'''(?x)]+src=(["\'])(?P(?:https?:)?// + (?: + admin\.mangomolo\.com/analytics/index\.php/customers/embed| + player\.mangomolo\.com/v1 + )/ (?: video\?.*?\bid=(?P\d+)| - index\?.*?\bchannelid=(?P(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) + (?:index|live)\?.*?\bchannelid=(?P(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) ).+?)\1''', webpage) if mobj is not None: info = { @@ -2972,12 +3083,6 @@ 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 VideoPress embeds videopress_urls = VideoPressIE._extract_urls(webpage) if videopress_urls: @@ -2997,7 +3102,7 @@ class GenericIE(InfoExtractor): wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key()) # Look for Mediaset embeds - mediaset_urls = MediasetIE._extract_urls(webpage) + mediaset_urls = MediasetIE._extract_urls(self, webpage) if mediaset_urls: return self.playlist_from_matches( mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key()) @@ -3086,13 +3191,28 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key()) - sharevideos_urls = [mobj.group('url') for mobj in re.finditer( + sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer( r']+?\bsrc\s*=\s*(["\'])(?P(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] if sharevideos_urls: return self.playlist_from_matches( sharevideos_urls, video_id, video_title) + viqeo_urls = ViqeoIE._extract_urls(webpage) + if viqeo_urls: + return self.playlist_from_matches( + viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + + expressen_urls = ExpressenIE._extract_urls(webpage) + if expressen_urls: + return self.playlist_from_matches( + expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + + zype_urls = ZypeIE._extract_urls(webpage) + if zype_urls: + return self.playlist_from_matches( + zype_urls, video_id, video_title, ie=ZypeIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: @@ -3114,9 +3234,13 @@ class GenericIE(InfoExtractor): jwplayer_data = self._find_jwplayer_data( webpage, video_id, transform_source=js_to_json) if jwplayer_data: - info = self._parse_jwplayer_data( - jwplayer_data, video_id, require_title=False, base_url=url) - return merge_dicts(info, info_dict) + try: + info = self._parse_jwplayer_data( + jwplayer_data, video_id, require_title=False, base_url=url) + return merge_dicts(info, info_dict) + except ExtractorError: + # See https://github.com/ytdl-org/youtube-dl/pull/16735 + pass # Video.js embed mobj = re.search( @@ -3150,8 +3274,8 @@ class GenericIE(InfoExtractor): else: formats.append({ 'url': src, - 'ext': (mimetype2ext(src_type) or - ext if ext in KNOWN_EXTENSIONS else 'mp4'), + 'ext': (mimetype2ext(src_type) + or ext if ext in KNOWN_EXTENSIONS else 'mp4'), }) if formats: self._sort_formats(formats)