3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
12 compat_urllib_parse_unquote,
13 compat_urllib_request,
15 compat_xml_parse_error,
33 from .brightcove import BrightcoveIE
34 from .nbc import NBCSportsVPlayerIE
35 from .ooyala import OoyalaIE
36 from .rutv import RUTVIE
37 from .tvc import TVCIE
38 from .sportbox import SportBoxEmbedIE
39 from .smotri import SmotriIE
40 from .condenast import CondeNastIE
41 from .udn import UDNEmbedIE
42 from .senateisvp import SenateISVPIE
43 from .bliptv import BlipTVIE
44 from .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
49 from .onionstudios import OnionStudiosIE
52 class GenericIE(InfoExtractor):
53 IE_DESC = 'Generic downloader that works on some sites'
57 # Direct link to a video
59 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
60 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
65 'upload_date': '20100513',
68 # Direct link to media delivered compressed (until Accept-Encoding is *)
70 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
71 'md5': '128c42e68b13950268b648275386fc74',
73 'id': 'FictionJunction-Parallel_Hearts',
75 'title': 'FictionJunction-Parallel_Hearts',
76 'upload_date': '20140522',
78 'expected_warnings': [
79 'URL could be a direct video link, returning it as such.'
82 # Direct download with broken HEAD
84 'url': 'http://ai-radio.org:8000/radio.opus',
91 'skip_download': True, # infinite live stream
93 'expected_warnings': [
94 r'501.*Not Implemented'
97 # Direct link with incorrect MIME type
99 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
100 'md5': '4ccbebe5f36706d85221f204d7eb5913',
102 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
103 'id': '5_Lennart_Poettering_-_Systemd',
105 'title': '5_Lennart_Poettering_-_Systemd',
106 'upload_date': '20141120',
108 'expected_warnings': [
109 'URL could be a direct video link, returning it as such.'
114 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
116 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
117 'title': 'Zero Punctuation',
118 'description': 're:.*groundbreaking video review series.*'
120 'playlist_mincount': 11,
122 # RSS feed with enclosure
124 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
126 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
128 'upload_date': '20150228',
129 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
134 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
138 'upload_date': '20130224',
139 'uploader_id': 'TheVerge',
140 'description': 're:^Chris Ziegler takes a look at the\.*',
141 'uploader': 'The Verge',
142 'title': 'First Firefox OS phones side-by-side',
145 'skip_download': False,
149 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
150 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
152 'id': '13601338388002',
154 'uploader': 'www.hodiho.fr',
155 'title': 'R\u00e9gis plante sa Jeep',
158 # bandcamp page with custom domain
160 'add_ie': ['Bandcamp'],
161 'url': 'http://bronyrock.com/track/the-pony-mash',
165 'title': 'The Pony Mash',
166 'uploader': 'M_Pallante',
168 'skip': 'There is a limit of 200 free downloads / month for the test song',
170 # embedded brightcove video
171 # it also tests brightcove videos that need to set the 'Referer' in the
174 'add_ie': ['Brightcove'],
175 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
177 'id': '2765128793001',
179 'title': 'Le cours de bourse : l’analyse technique',
180 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
181 'uploader': 'BFM BUSINESS',
184 'skip_download': True,
188 # https://github.com/rg3/youtube-dl/issues/2253
189 'url': 'http://bcove.me/i6nfkrc3',
190 'md5': '0ba9446db037002366bab3b3eb30c88c',
192 'id': '3101154703001',
194 'title': 'Still no power',
195 'uploader': 'thestar.com',
196 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
198 'add_ie': ['Brightcove'],
201 'url': 'http://www.championat.com/video/football/v/87/87499.html',
202 'md5': 'fb973ecf6e4a78a67453647444222983',
204 'id': '3414141473001',
206 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
207 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
208 'uploader': 'Championat',
212 # https://github.com/rg3/youtube-dl/issues/3541
213 'add_ie': ['Brightcove'],
214 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
216 'id': '3866516442001',
218 'title': 'Leer mij vrouwen kennen: Aflevering 1',
219 'description': 'Leer mij vrouwen kennen: Aflevering 1',
220 'uploader': 'SBS Broadcasting',
222 'skip': 'Restricted to Netherlands',
224 'skip_download': True, # m3u8 download
229 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
230 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
232 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
234 'title': '2cc213299525360.mov', # that's what we get
236 'add_ie': ['Ooyala'],
238 # multiple ooyala embeds on SBN network websites
240 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
242 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
243 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
245 'playlist_mincount': 3,
247 'skip_download': True,
249 'add_ie': ['Ooyala'],
253 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
257 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
258 'upload_date': '20140225',
259 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
260 'uploader': 'Tested',
261 'uploader_id': 'testedcom',
263 # No need to test YoutubeIE here
265 'skip_download': True,
270 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
274 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
275 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
280 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
282 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
284 'playlist_mincount': 18,
288 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
292 'title': 'Охотское море стало целиком российским',
293 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
297 'skip_download': True,
302 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
306 'title': 'Дошкольное воспитание',
311 'url': 'http://www.vestifinance.ru/articles/25753',
314 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
319 'title': 'Госзаказ. День 3',
325 'title': 'Госзаказ. День 2',
331 'title': 'Госзаказ. День 1',
337 'skip_download': True,
342 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
345 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
347 'playlist_mincount': 7,
351 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
352 'md5': '65fdff94098e4a607385a60c5177c638',
356 'title': 'Hidden miracles of the natural world',
357 'uploader': 'Louie Schwartzberg',
358 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
361 # Embeded Ustream video
363 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
364 'md5': '27b99cdb639c9b12a79bca876a073417',
368 'uploader': 'AU SPA: The NSA and Privacy',
369 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
372 # nowvideo embed hidden behind percent encoding
374 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
375 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
377 'id': '06e53103ca9aa',
379 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
380 'description': 'No description',
385 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
386 'md5': '7653032cbb25bf6c80d80f217055fa43',
388 'id': '048195-004_PLUS7-F',
391 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
392 'upload_date': '20140320',
395 'skip_download': 'Requires rtmpdump'
400 'url': 'http://www.wired.com/2014/04/honda-asimo/',
401 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
403 'id': '53501be369702d3275860000',
405 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
410 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
411 'md5': '441aeeb82eb72c422c7f14ec533999cd',
413 'id': 'k2mm4bCdJ6CQ2i7c8o2',
415 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
418 'add_ie': ['Dailymotion'],
422 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
426 'title': 'The NBL Auction 2014',
427 'uploader': 'BADMINTON England',
428 'uploader_id': 'BADMINTONEvents',
429 'upload_date': '20140603',
430 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
432 'add_ie': ['Youtube'],
434 'skip_download': True,
439 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
440 'md5': '35727f82f58c76d996fc188f9755b0d5',
442 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
445 'description': 'Mario\'s life in the fast lane has never looked so good.',
448 # YouTube embed via <data-embed-url="">
450 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
454 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
455 'uploader': 'Gameloft',
456 'uploader_id': 'gameloft',
457 'upload_date': '20140828',
458 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
461 'skip_download': True,
466 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
468 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
470 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
471 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
476 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
478 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
479 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
485 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
490 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
491 'md5': '9d65602bf31c6e20014319c7d07fba27',
493 'id': '5123ea6d5e5a7',
496 'uploader': 'www.handjobhub.com',
497 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
500 # Multiple brightcove videos
501 # https://github.com/rg3/youtube-dl/issues/2283
503 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
505 'id': 'always-never',
506 'title': 'Always / Never - The New Yorker',
510 'extract_flat': False,
511 'skip_download': True,
516 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
517 'md5': '96f09a37e44da40dd083e12d9a683327',
521 'title': 'Ump changes call to ball',
522 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
524 'timestamp': 1401537900,
525 'upload_date': '20140531',
526 'thumbnail': 're:^https?://.*\.jpg$',
531 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
532 'md5': '8788b683c777a5cf25621eaf286d0c23',
536 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
538 'filesize': 182808282,
539 'uploader': 'education-portal.com',
543 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
544 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
548 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
550 'uploader': 'thoughtworks.wistia.com',
555 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
559 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
560 'uploader': 'Sophos Security',
561 'title': 'Chet Chat 171 - Oct 29, 2014',
562 'upload_date': '20141029',
567 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
571 'upload_date': '20141112',
572 'title': 'Rosetta #CometLanding webcast HL 10',
577 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
580 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
582 'playlist_mincount': 2,
586 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
590 'upload_date': '20141126',
591 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
596 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
598 'id': '730m_DandD_1901_512k',
600 'uploader': 'www.abc.net.au',
601 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
604 # embedded viddler video
606 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
610 'uploader': 'deadspin',
611 'title': 'WALL-TO-GORTAT',
612 'timestamp': 1422285291,
613 'upload_date': '20150126',
615 'add_ie': ['Viddler'],
619 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
623 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
624 'description': 'md5:601cb790edd05908957dae8aaa866465',
625 'upload_date': '20150220',
630 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
634 'upload_date': '20150212',
635 'uploader': 'The National Archives UK',
636 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
637 'uploader_id': 'NationalArchives08',
638 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
643 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
644 'playlist_mincount': 5,
646 'id': 'aanslagen-kopenhagen',
647 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
652 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
656 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
661 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
665 'upload_date': '20150226',
666 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
668 'title': 'John Carlson Postgame 2/25/15',
671 # Eagle.Platform embed (generic URL)
673 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
677 'title': 'Навальный вышел на свободу',
678 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
679 'thumbnail': 're:^https?://.*\.jpg$',
685 # ClipYou (Eagle.Platform) embed (custom URL)
687 'url': 'http://muz-tv.ru/play/7129/',
691 'title': "'O Sole Mio",
692 'thumbnail': 're:^https?://.*\.jpg$',
699 'url': 'http://muz-tv.ru/kinozal/view/7400/',
703 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
704 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
705 'thumbnail': 're:^https?://.*\.jpg$',
712 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
716 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
717 'thumbnail': 're:^https?://.*\.png$',
723 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
724 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
728 'title': 'Facebook Creates "On This Day" | Crunch Report',
733 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
737 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
742 # Crooks and Liars embed
744 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
748 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
749 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
750 'timestamp': 1428207000,
751 'upload_date': '20150405',
752 'uploader': 'Heather',
755 # Crooks and Liars external embed
757 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
759 'id': 'MTE3MjUtMzQ2MzA',
761 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
762 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
763 'timestamp': 1265032391,
764 'upload_date': '20100201',
765 'uploader': 'Heather',
768 # NBC Sports vplayer embed
770 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
772 'id': 'ln7x1qSThw4k',
774 'title': "PFT Live: New leader in the 'new-look' defense",
775 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
780 'url': 'http://www.udn.com/news/story/7314/822787',
781 'md5': 'fd2060e988c326991037b9aff9df21a6',
785 'title': '中一中男師變性 全校師生力挺',
786 'thumbnail': 're:^https?://.*\.jpg$',
791 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
793 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
795 'description': 'VIDEO: Index/Match versus VLOOKUP.',
796 'title': 'This is what separates the Excel masters from the wannabes',
800 'skip_download': True,
803 # Contains a SMIL manifest
805 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
809 'title': '+ Football: Lottery Champions League Europe',
810 'uploader': 'www.telewebion.com',
814 'skip_download': True,
817 # Brightcove URL in single quotes
819 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
820 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
822 'id': '4255764656001',
824 'title': 'SN Presents: Russell Martin, World Citizen',
825 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
826 'uploader': 'Rogers Sportsnet',
829 # Dailymotion Cloud video
831 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
832 'md5': '49444254273501a64675a7e68c502681',
834 'id': '5585de919473990de4bee11b',
837 'thumbnail': 're:^https?://.*\.jpe?g$',
842 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
846 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
847 'thumbnail': 're:^https?://.*\.jpe?g$',
848 'uploader': 'ClickHole',
849 'uploader_id': 'clickhole',
854 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
855 'md5': '43662b577c018ad707a63766462b1e87',
859 'title': 'New experience with Acrobat DC',
860 'description': 'New experience with Acrobat DC',
866 def report_following_redirect(self, new_url):
867 """Report information extraction."""
868 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
870 def _extract_rss(self, url, video_id, doc):
871 playlist_title = doc.find('./channel/title').text
872 playlist_desc_el = doc.find('./channel/description')
873 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
876 for it in doc.findall('./channel/item'):
877 next_url = xpath_text(it, 'link', fatal=False)
879 enclosure_nodes = it.findall('./enclosure')
880 for e in enclosure_nodes:
881 next_url = e.attrib.get('url')
891 'title': it.find('title').text,
897 'title': playlist_title,
898 'description': playlist_desc,
902 def _extract_camtasia(self, url, video_id, webpage):
903 """ Returns None if no camtasia video can be found. """
905 camtasia_cfg = self._search_regex(
906 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
907 webpage, 'camtasia configuration file', default=None)
908 if camtasia_cfg is None:
911 title = self._html_search_meta('DC.title', webpage, fatal=True)
913 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
914 camtasia_cfg = self._download_xml(
915 camtasia_url, video_id,
916 note='Downloading camtasia configuration',
917 errnote='Failed to download camtasia configuration')
918 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
921 for n in fileset_node.getchildren():
922 url_n = n.find('./uri')
927 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
928 'title': '%s - %s' % (title, n.tag),
929 'url': compat_urlparse.urljoin(url, url_n.text),
930 'duration': float_or_none(n.find('./duration').text),
939 def _real_extract(self, url):
940 if url.startswith('//'):
943 'url': self.http_scheme() + url,
946 parsed_url = compat_urlparse.urlparse(url)
947 if not parsed_url.scheme:
948 default_search = self._downloader.params.get('default_search')
949 if default_search is None:
950 default_search = 'fixup_error'
952 if default_search in ('auto', 'auto_warning', 'fixup_error'):
954 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
955 return self.url_result('http://' + url)
956 elif default_search != 'fixup_error':
957 if default_search == 'auto_warning':
958 if re.match(r'^(?:url|URL)$', url):
959 raise ExtractorError(
960 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
963 self._downloader.report_warning(
964 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
965 return self.url_result('ytsearch:' + url)
967 if default_search in ('error', 'fixup_error'):
968 raise ExtractorError(
969 '%r is not a valid URL. '
970 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
971 % (url, url), expected=True)
973 if ':' not in default_search:
974 default_search += ':'
975 return self.url_result(default_search + url)
977 url, smuggled_data = unsmuggle_url(url)
979 is_intentional = smuggled_data and smuggled_data.get('to_generic')
980 if smuggled_data and 'force_videoid' in smuggled_data:
981 force_videoid = smuggled_data['force_videoid']
982 video_id = force_videoid
984 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
986 self.to_screen('%s: Requesting header' % video_id)
988 head_req = HEADRequest(url)
989 head_response = self._request_webpage(
991 note=False, errnote='Could not send HEAD request to %s' % url,
994 if head_response is not False:
996 new_url = head_response.geturl()
998 self.report_following_redirect(new_url)
1000 new_url = smuggle_url(
1001 new_url, {'force_videoid': force_videoid})
1002 return self.url_result(new_url)
1004 full_response = None
1005 if head_response is False:
1006 request = compat_urllib_request.Request(url)
1007 request.add_header('Accept-Encoding', '*')
1008 full_response = self._request_webpage(request, video_id)
1009 head_response = full_response
1011 # Check for direct link to a video
1012 content_type = head_response.headers.get('Content-Type', '')
1013 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1015 upload_date = unified_strdate(
1016 head_response.headers.get('Last-Modified'))
1019 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1022 'format_id': m.group('format_id'),
1024 'vcodec': 'none' if m.group('type') == 'audio' else None
1026 'upload_date': upload_date,
1029 if not self._downloader.params.get('test', False) and not is_intentional:
1030 force = self._downloader.params.get('force_generic_extractor', False)
1031 self._downloader.report_warning(
1032 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1034 if not full_response:
1035 request = compat_urllib_request.Request(url)
1036 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1037 # making it impossible to download only chunk of the file (yet we need only 512kB to
1038 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1039 # that will always result in downloading the whole file that is not desirable.
1040 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1041 # to accept raw bytes and being able to download only a chunk.
1042 # It may probably better to solve this by checking Content-Type for application/octet-stream
1043 # after HEAD request finishes, but not sure if we can rely on this.
1044 request.add_header('Accept-Encoding', '*')
1045 full_response = self._request_webpage(request, video_id)
1047 # Maybe it's a direct link to a video?
1048 # Be careful not to download the whole thing!
1049 first_bytes = full_response.read(512)
1050 if not is_html(first_bytes):
1051 self._downloader.report_warning(
1052 'URL could be a direct video link, returning it as such.')
1053 upload_date = unified_strdate(
1054 head_response.headers.get('Last-Modified'))
1057 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1060 'upload_date': upload_date,
1063 webpage = self._webpage_read_content(
1064 full_response, url, video_id, prefix=first_bytes)
1066 self.report_extraction(video_id)
1068 # Is it an RSS feed?
1070 doc = parse_xml(webpage)
1071 if doc.tag == 'rss':
1072 return self._extract_rss(url, video_id, doc)
1073 except compat_xml_parse_error:
1076 # Is it a Camtasia project?
1077 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1078 if camtasia_res is not None:
1081 # Sometimes embedded video player is hidden behind percent encoding
1082 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1083 # Unescaping the whole page allows to handle those cases in a generic way
1084 webpage = compat_urllib_parse.unquote(webpage)
1086 # it's tempting to parse this further, but you would
1087 # have to take into account all the variations like
1088 # Video Title - Site Name
1089 # Site Name | Video Title
1090 # Video Title - Tagline | Site Name
1091 # and so on and so forth; it's just not practical
1092 video_title = self._html_search_regex(
1093 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1096 # Try to detect age limit automatically
1097 age_limit = self._rta_search(webpage)
1098 # And then there are the jokers who advertise that they use RTA,
1099 # but actually don't.
1100 AGE_LIMIT_MARKERS = [
1101 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1103 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1106 # video uploader is domain name
1107 video_uploader = self._search_regex(
1108 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1111 def _playlist_from_matches(matches, getter=None, ie=None):
1113 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1115 return self.playlist_result(
1116 urlrs, playlist_id=video_id, playlist_title=video_title)
1118 # Look for BrightCove:
1119 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1121 self.to_screen('Brightcove video detected.')
1124 'url': smuggle_url(bc_url, {'Referer': url}),
1125 'ie_key': 'Brightcove'
1126 } for bc_url in bc_urls]
1129 '_type': 'playlist',
1130 'title': video_title,
1135 # Look for embedded rtl.nl player
1136 matches = re.findall(
1137 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1140 return _playlist_from_matches(matches, ie='RtlNl')
1142 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1143 if vimeo_url is not None:
1144 return self.url_result(vimeo_url)
1146 # Look for embedded YouTube player
1147 matches = re.findall(r'''(?x)
1156 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1160 return _playlist_from_matches(
1161 matches, lambda m: unescapeHTML(m[1]))
1163 # Look for lazyYT YouTube embed
1164 matches = re.findall(
1165 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1167 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1169 # Look for embedded Dailymotion player
1170 matches = re.findall(
1171 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1173 return _playlist_from_matches(
1174 matches, lambda m: unescapeHTML(m[1]))
1176 # Look for embedded Dailymotion playlist player (#3822)
1178 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1180 playlists = re.findall(
1181 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1183 return _playlist_from_matches(
1184 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1186 # Look for embedded Wistia player
1188 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1190 embed_url = self._proto_relative_url(
1191 unescapeHTML(match.group('url')))
1193 '_type': 'url_transparent',
1196 'uploader': video_uploader,
1197 'title': video_title,
1201 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1204 '_type': 'url_transparent',
1205 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1207 'uploader': video_uploader,
1208 'title': video_title,
1209 'id': match.group('id')
1212 # Look for embedded blip.tv player
1213 bliptv_url = BlipTVIE._extract_url(webpage)
1215 return self.url_result(bliptv_url, 'BlipTV')
1217 # Look for SVT player
1218 svt_url = SVTIE._extract_url(webpage)
1220 return self.url_result(svt_url, 'SVT')
1222 # Look for embedded condenast player
1223 matches = re.findall(
1224 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1228 '_type': 'playlist',
1231 'ie_key': 'CondeNast',
1233 } for ma in matches],
1234 'title': video_title,
1238 # Look for Bandcamp pages with custom domain
1239 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1240 if mobj is not None:
1241 burl = unescapeHTML(mobj.group(1))
1242 # Don't set the extractor because it can be a track url or an album
1243 return self.url_result(burl)
1245 # Look for embedded Vevo player
1247 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1248 if mobj is not None:
1249 return self.url_result(mobj.group('url'))
1251 # Look for embedded Viddler player
1253 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1255 if mobj is not None:
1256 return self.url_result(mobj.group('url'))
1258 # Look for NYTimes player
1260 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1262 if mobj is not None:
1263 return self.url_result(mobj.group('url'))
1265 # Look for Libsyn player
1267 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1268 if mobj is not None:
1269 return self.url_result(mobj.group('url'))
1271 # Look for Ooyala videos
1272 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1273 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1274 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1275 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1276 if mobj is not None:
1277 return OoyalaIE._build_url_result(mobj.group('ec'))
1279 # Look for multiple Ooyala embeds on SBN network websites
1280 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1281 if mobj is not None:
1282 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1284 return _playlist_from_matches(
1285 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1287 # Look for Aparat videos
1288 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1289 if mobj is not None:
1290 return self.url_result(mobj.group(1), 'Aparat')
1292 # Look for MPORA videos
1293 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1294 if mobj is not None:
1295 return self.url_result(mobj.group(1), 'Mpora')
1297 # Look for embedded NovaMov-based player
1299 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1300 (?P<url>http://(?:(?:embed|www)\.)?
1302 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1303 videoweed\.(?:es|com)|
1304 movshare\.(?:net|sx|ag)|
1305 divxstage\.(?:eu|net|ch|co|at|ag))
1306 /embed\.php.+?)\1''', webpage)
1307 if mobj is not None:
1308 return self.url_result(mobj.group('url'))
1310 # Look for embedded Facebook player
1312 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1313 if mobj is not None:
1314 return self.url_result(mobj.group('url'), 'Facebook')
1316 # Look for embedded VK player
1317 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1318 if mobj is not None:
1319 return self.url_result(mobj.group('url'), 'VK')
1321 # Look for embedded ivi player
1322 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1323 if mobj is not None:
1324 return self.url_result(mobj.group('url'), 'Ivi')
1326 # Look for embedded Huffington Post player
1328 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1329 if mobj is not None:
1330 return self.url_result(mobj.group('url'), 'HuffPost')
1333 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1334 if mobj is not None:
1335 return self.url_result(mobj.group('url'))
1336 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1337 if mobj is not None:
1338 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1340 # Look for funnyordie embed
1341 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1343 return _playlist_from_matches(
1344 matches, getter=unescapeHTML, ie='FunnyOrDie')
1346 # Look for BBC iPlayer embed
1347 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1349 return _playlist_from_matches(matches, ie='BBCCoUk')
1351 # Look for embedded RUTV player
1352 rutv_url = RUTVIE._extract_url(webpage)
1354 return self.url_result(rutv_url, 'RUTV')
1356 # Look for embedded TVC player
1357 tvc_url = TVCIE._extract_url(webpage)
1359 return self.url_result(tvc_url, 'TVC')
1361 # Look for embedded SportBox player
1362 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1364 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1366 # Look for embedded PornHub player
1367 pornhub_url = PornHubIE._extract_url(webpage)
1369 return self.url_result(pornhub_url, 'PornHub')
1371 # Look for embedded XHamster player
1372 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1374 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1376 # Look for embedded Tvigle player
1378 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1379 if mobj is not None:
1380 return self.url_result(mobj.group('url'), 'Tvigle')
1382 # Look for embedded TED player
1384 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1385 if mobj is not None:
1386 return self.url_result(mobj.group('url'), 'TED')
1388 # Look for embedded Ustream videos
1390 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1391 if mobj is not None:
1392 return self.url_result(mobj.group('url'), 'Ustream')
1394 # Look for embedded arte.tv player
1396 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1398 if mobj is not None:
1399 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1401 # Look for embedded smotri.com player
1402 smotri_url = SmotriIE._extract_url(webpage)
1404 return self.url_result(smotri_url, 'Smotri')
1406 # Look for embeded soundcloud player
1408 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1410 if mobj is not None:
1411 url = unescapeHTML(mobj.group('url'))
1412 return self.url_result(url)
1414 # Look for embedded vulture.com player
1416 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1418 if mobj is not None:
1419 url = unescapeHTML(mobj.group('url'))
1420 return self.url_result(url, ie='Vulture')
1422 # Look for embedded mtvservices player
1424 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1426 if mobj is not None:
1427 url = unescapeHTML(mobj.group('url'))
1428 return self.url_result(url, ie='MTVServicesEmbedded')
1430 # Look for embedded yahoo player
1432 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1434 if mobj is not None:
1435 return self.url_result(mobj.group('url'), 'Yahoo')
1437 # Look for embedded sbs.com.au player
1441 <meta\s+property="og:video"\s+content=|
1444 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1446 if mobj is not None:
1447 return self.url_result(mobj.group('url'), 'SBS')
1449 # Look for embedded Cinchcast player
1451 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1453 if mobj is not None:
1454 return self.url_result(mobj.group('url'), 'Cinchcast')
1457 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1461 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1463 if mobj is not None:
1464 return self.url_result(mobj.group('url'), 'MLB')
1467 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1469 if mobj is not None:
1470 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1473 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1475 if mobj is not None:
1476 return self.url_result(mobj.group('url'), 'Livestream')
1478 # Look for Zapiks embed
1480 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1481 if mobj is not None:
1482 return self.url_result(mobj.group('url'), 'Zapiks')
1484 # Look for Kaltura embeds
1486 r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
1487 if mobj is not None:
1488 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1490 # Look for Eagle.Platform embeds
1492 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1493 if mobj is not None:
1494 return self.url_result(mobj.group('url'), 'EaglePlatform')
1496 # Look for ClipYou (uses Eagle.Platform) embeds
1498 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1499 if mobj is not None:
1500 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1502 # Look for Pladform embeds
1504 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1505 if mobj is not None:
1506 return self.url_result(mobj.group('url'), 'Pladform')
1508 # Look for Playwire embeds
1510 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1511 if mobj is not None:
1512 return self.url_result(mobj.group('url'))
1514 # Look for 5min embeds
1516 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1517 if mobj is not None:
1518 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1520 # Look for Crooks and Liars embeds
1522 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1523 if mobj is not None:
1524 return self.url_result(mobj.group('url'))
1526 # Look for NBC Sports VPlayer embeds
1527 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1529 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1531 # Look for UDN embeds
1533 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1534 if mobj is not None:
1535 return self.url_result(
1536 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1538 # Look for Senate ISVP iframe
1539 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1541 return self.url_result(senate_isvp_url, 'SenateISVP')
1543 # Look for Dailymotion Cloud videos
1544 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1546 return self.url_result(dmcloud_url, 'DailymotionCloud')
1548 # Look for OnionStudios embeds
1549 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1550 if onionstudios_url:
1551 return self.url_result(onionstudios_url)
1553 # Look for AdobeTVVideo embeds
1555 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1557 if mobj is not None:
1558 return self.url_result(
1559 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1562 def check_video(vurl):
1563 if YoutubeIE.suitable(vurl):
1565 vpath = compat_urlparse.urlparse(vurl).path
1566 vext = determine_ext(vpath)
1567 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1569 def filter_video(urls):
1570 return list(filter(check_video, urls))
1572 # Start with something easy: JW Player in SWFObject
1573 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1575 # Look for gorilla-vid style embedding
1576 found = filter_video(re.findall(r'''(?sx)
1580 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1583 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1585 # Broaden the search a little bit
1586 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1588 # Broaden the findall a little bit: JWPlayer JS loader
1589 found = filter_video(re.findall(
1590 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1593 found = filter_video(re.findall(r'''(?xs)
1594 flowplayer\("[^"]+",\s*
1596 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1597 ["']?url["']?\s*:\s*["']([^"']+)["']
1602 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1604 # Try to find twitter cards info
1605 found = filter_video(re.findall(
1606 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1608 # We look for Open Graph info:
1609 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1610 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1611 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1612 if m_video_type is not None:
1613 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1616 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1618 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1620 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1621 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1624 # Look also in Refresh HTTP header
1625 refresh_header = head_response.headers.get('Refresh')
1627 found = re.search(REDIRECT_REGEX, refresh_header)
1629 new_url = compat_urlparse.urljoin(url, found.group(1))
1630 self.report_following_redirect(new_url)
1636 raise UnsupportedError(url)
1639 for video_url in found:
1640 video_url = compat_urlparse.urljoin(url, video_url)
1641 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1643 # Sometimes, jwplayer extraction will result in a YouTube URL
1644 if YoutubeIE.suitable(video_url):
1645 entries.append(self.url_result(video_url, 'Youtube'))
1648 # here's a fun little line of code for you:
1649 video_id = os.path.splitext(video_id)[0]
1651 if determine_ext(video_url) == 'smil':
1654 'formats': self._extract_smil_formats(video_url, video_id),
1655 'uploader': video_uploader,
1656 'title': video_title,
1657 'age_limit': age_limit,
1663 'uploader': video_uploader,
1664 'title': video_title,
1665 'age_limit': age_limit,
1668 if len(entries) == 1:
1671 for num, e in enumerate(entries, start=1):
1672 # 'url' results don't have a title
1673 if e.get('title') is not None:
1674 e['title'] = '%s (%d)' % (e['title'], num)
1676 '_type': 'playlist',