3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
11 compat_urllib_parse_unquote,
12 compat_urllib_request,
14 compat_xml_parse_error,
32 from .brightcove import BrightcoveIE
33 from .nbc import NBCSportsVPlayerIE
34 from .ooyala import OoyalaIE
35 from .rutv import RUTVIE
36 from .tvc import TVCIE
37 from .sportbox import SportBoxEmbedIE
38 from .smotri import SmotriIE
39 from .myvi import MyviIE
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
50 from .snagfilms import SnagFilmsEmbedIE
53 class GenericIE(InfoExtractor):
54 IE_DESC = 'Generic downloader that works on some sites'
58 # Direct link to a video
60 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
61 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
66 'upload_date': '20100513',
69 # Direct link to media delivered compressed (until Accept-Encoding is *)
71 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
72 'md5': '128c42e68b13950268b648275386fc74',
74 'id': 'FictionJunction-Parallel_Hearts',
76 'title': 'FictionJunction-Parallel_Hearts',
77 'upload_date': '20140522',
79 'expected_warnings': [
80 'URL could be a direct video link, returning it as such.'
83 # Direct download with broken HEAD
85 'url': 'http://ai-radio.org:8000/radio.opus',
92 'skip_download': True, # infinite live stream
94 'expected_warnings': [
95 r'501.*Not Implemented'
98 # Direct link with incorrect MIME type
100 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
101 'md5': '4ccbebe5f36706d85221f204d7eb5913',
103 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
104 'id': '5_Lennart_Poettering_-_Systemd',
106 'title': '5_Lennart_Poettering_-_Systemd',
107 'upload_date': '20141120',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
115 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
117 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'title': 'Zero Punctuation',
119 'description': 're:.*groundbreaking video review series.*'
121 'playlist_mincount': 11,
123 # RSS feed with enclosure
125 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
127 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
129 'upload_date': '20150228',
130 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 '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',
139 'upload_date': '20130224',
140 'uploader_id': 'TheVerge',
141 'description': 're:^Chris Ziegler takes a look at the\.*',
142 'uploader': 'The Verge',
143 'title': 'First Firefox OS phones side-by-side',
146 'skip_download': False,
150 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
151 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
153 'id': '13601338388002',
155 'uploader': 'www.hodiho.fr',
156 'title': 'R\u00e9gis plante sa Jeep',
159 # bandcamp page with custom domain
161 'add_ie': ['Bandcamp'],
162 'url': 'http://bronyrock.com/track/the-pony-mash',
166 'title': 'The Pony Mash',
167 'uploader': 'M_Pallante',
169 'skip': 'There is a limit of 200 free downloads / month for the test song',
171 # embedded brightcove video
172 # it also tests brightcove videos that need to set the 'Referer' in the
175 'add_ie': ['Brightcove'],
176 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
178 'id': '2765128793001',
180 'title': 'Le cours de bourse : l’analyse technique',
181 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
182 'uploader': 'BFM BUSINESS',
185 'skip_download': True,
189 # https://github.com/rg3/youtube-dl/issues/2253
190 'url': 'http://bcove.me/i6nfkrc3',
191 'md5': '0ba9446db037002366bab3b3eb30c88c',
193 'id': '3101154703001',
195 'title': 'Still no power',
196 'uploader': 'thestar.com',
197 '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.',
199 'add_ie': ['Brightcove'],
202 'url': 'http://www.championat.com/video/football/v/87/87499.html',
203 'md5': 'fb973ecf6e4a78a67453647444222983',
205 'id': '3414141473001',
207 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
208 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
209 'uploader': 'Championat',
213 # https://github.com/rg3/youtube-dl/issues/3541
214 'add_ie': ['Brightcove'],
215 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
217 'id': '3866516442001',
219 'title': 'Leer mij vrouwen kennen: Aflevering 1',
220 'description': 'Leer mij vrouwen kennen: Aflevering 1',
221 'uploader': 'SBS Broadcasting',
223 'skip': 'Restricted to Netherlands',
225 'skip_download': True, # m3u8 download
230 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
231 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
233 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
235 'title': '2cc213299525360.mov', # that's what we get
237 'add_ie': ['Ooyala'],
240 # ooyala video embedded with http://player.ooyala.com/iframe.js
241 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
243 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
245 'title': '"Steve Jobs: Man in the Machine" trailer',
246 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
249 'skip_download': True,
252 # multiple ooyala embeds on SBN network websites
254 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
256 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
257 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
259 'playlist_mincount': 3,
261 'skip_download': True,
263 'add_ie': ['Ooyala'],
267 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
271 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
272 'upload_date': '20140225',
273 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
274 'uploader': 'Tested',
275 'uploader_id': 'testedcom',
277 # No need to test YoutubeIE here
279 'skip_download': True,
284 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
288 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
289 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
294 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
298 'title': 'Охотское море стало целиком российским',
299 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
303 'skip_download': True,
308 '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/',
312 'title': 'Дошкольное воспитание',
317 'url': 'http://www.vestifinance.ru/articles/25753',
320 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
325 'title': 'Госзаказ. День 3',
331 'title': 'Госзаказ. День 2',
337 'title': 'Госзаказ. День 1',
343 'skip_download': True,
348 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
350 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
352 'title': 'Ужастики, русский трейлер (2015)',
353 'thumbnail': 're:^https?://.*\.jpg$',
359 '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',
362 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
364 'playlist_mincount': 7,
368 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
369 'md5': '65fdff94098e4a607385a60c5177c638',
373 'title': 'Hidden miracles of the natural world',
374 'uploader': 'Louie Schwartzberg',
375 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
378 # Embeded Ustream video
380 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
381 'md5': '27b99cdb639c9b12a79bca876a073417',
385 'uploader': 'AU SPA: The NSA and Privacy',
386 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
389 # nowvideo embed hidden behind percent encoding
391 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
392 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
394 'id': '06e53103ca9aa',
396 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
397 'description': 'No description',
402 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
403 'md5': '7653032cbb25bf6c80d80f217055fa43',
405 'id': '048195-004_PLUS7-F',
408 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
409 'upload_date': '20140320',
412 'skip_download': 'Requires rtmpdump'
417 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
421 'title': 'Alcaline, le concert avec Calogero',
422 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
423 'upload_date': '20150226',
424 'timestamp': 1424989860,
429 'skip_download': True,
431 'expected_warnings': [
437 'url': 'http://www.wired.com/2014/04/honda-asimo/',
438 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
440 'id': '53501be369702d3275860000',
442 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
447 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
448 'md5': '441aeeb82eb72c422c7f14ec533999cd',
450 'id': 'k2mm4bCdJ6CQ2i7c8o2',
452 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
455 'add_ie': ['Dailymotion'],
459 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
463 'title': 'The NBL Auction 2014',
464 'uploader': 'BADMINTON England',
465 'uploader_id': 'BADMINTONEvents',
466 'upload_date': '20140603',
467 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
469 'add_ie': ['Youtube'],
471 'skip_download': True,
476 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
477 'md5': '35727f82f58c76d996fc188f9755b0d5',
479 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
482 'description': 'Mario\'s life in the fast lane has never looked so good.',
485 # YouTube embed via <data-embed-url="">
487 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
491 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
492 'uploader': 'Gameloft',
493 'uploader_id': 'gameloft',
494 'upload_date': '20140828',
495 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
498 'skip_download': True,
503 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
505 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
507 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
508 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
513 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
515 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
516 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
522 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
527 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
528 'md5': '9d65602bf31c6e20014319c7d07fba27',
530 'id': '5123ea6d5e5a7',
533 'uploader': 'www.handjobhub.com',
534 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
537 # Multiple brightcove videos
538 # https://github.com/rg3/youtube-dl/issues/2283
540 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
542 'id': 'always-never',
543 'title': 'Always / Never - The New Yorker',
547 'extract_flat': False,
548 'skip_download': True,
553 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
554 'md5': '96f09a37e44da40dd083e12d9a683327',
558 'title': 'Ump changes call to ball',
559 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
561 'timestamp': 1401537900,
562 'upload_date': '20140531',
563 'thumbnail': 're:^https?://.*\.jpg$',
568 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
569 'md5': '8788b683c777a5cf25621eaf286d0c23',
573 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
575 'filesize': 182808282,
576 'uploader': 'education-portal.com',
580 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
581 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
585 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
587 'uploader': 'thoughtworks.wistia.com',
592 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
596 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
597 'uploader': 'Sophos Security',
598 'title': 'Chet Chat 171 - Oct 29, 2014',
599 'upload_date': '20141029',
604 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
608 'upload_date': '20141112',
609 'title': 'Rosetta #CometLanding webcast HL 10',
614 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
617 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
619 'playlist_mincount': 2,
623 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
627 'upload_date': '20141126',
628 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
633 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
635 'id': '730m_DandD_1901_512k',
637 'uploader': 'www.abc.net.au',
638 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
641 # embedded viddler video
643 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
647 'uploader': 'deadspin',
648 'title': 'WALL-TO-GORTAT',
649 'timestamp': 1422285291,
650 'upload_date': '20150126',
652 'add_ie': ['Viddler'],
656 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
660 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
661 'description': 'md5:601cb790edd05908957dae8aaa866465',
662 'upload_date': '20150220',
667 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
671 'upload_date': '20150212',
672 'uploader': 'The National Archives UK',
673 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
674 'uploader_id': 'NationalArchives08',
675 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
680 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
681 'playlist_mincount': 5,
683 'id': 'aanslagen-kopenhagen',
684 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
689 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
693 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
698 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
702 'upload_date': '20150226',
703 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
705 'title': 'John Carlson Postgame 2/25/15',
708 # Kaltura embed (different embed code)
710 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
714 'upload_date': '20150127',
715 'uploader_id': 'PremierMedia',
717 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
720 # Eagle.Platform embed (generic URL)
722 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
726 'title': 'Навальный вышел на свободу',
727 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
728 'thumbnail': 're:^https?://.*\.jpg$',
734 # ClipYou (Eagle.Platform) embed (custom URL)
736 'url': 'http://muz-tv.ru/play/7129/',
740 'title': "'O Sole Mio",
741 'thumbnail': 're:^https?://.*\.jpg$',
748 'url': 'http://muz-tv.ru/kinozal/view/7400/',
752 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
753 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
754 'thumbnail': 're:^https?://.*\.jpg$',
761 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
765 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
766 'thumbnail': 're:^https?://.*\.png$',
772 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
773 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
777 'title': 'Facebook Creates "On This Day" | Crunch Report',
782 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
786 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
791 # Crooks and Liars embed
793 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
797 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
798 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
799 'timestamp': 1428207000,
800 'upload_date': '20150405',
801 'uploader': 'Heather',
804 # Crooks and Liars external embed
806 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
808 'id': 'MTE3MjUtMzQ2MzA',
810 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
811 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
812 'timestamp': 1265032391,
813 'upload_date': '20100201',
814 'uploader': 'Heather',
817 # NBC Sports vplayer embed
819 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
821 'id': 'ln7x1qSThw4k',
823 'title': "PFT Live: New leader in the 'new-look' defense",
824 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
829 'url': 'http://www.udn.com/news/story/7314/822787',
830 'md5': 'fd2060e988c326991037b9aff9df21a6',
834 'title': '中一中男師變性 全校師生力挺',
835 'thumbnail': 're:^https?://.*\.jpg$',
840 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
842 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
844 'description': 'VIDEO: Index/Match versus VLOOKUP.',
845 'title': 'This is what separates the Excel masters from the wannabes',
849 'skip_download': True,
852 # Contains a SMIL manifest
854 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
858 'title': '+ Football: Lottery Champions League Europe',
859 'uploader': 'www.telewebion.com',
863 'skip_download': True,
866 # Brightcove URL in single quotes
868 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
869 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
871 'id': '4255764656001',
873 'title': 'SN Presents: Russell Martin, World Citizen',
874 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
875 'uploader': 'Rogers Sportsnet',
878 # Dailymotion Cloud video
880 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
881 'md5': '49444254273501a64675a7e68c502681',
883 'id': '5585de919473990de4bee11b',
886 'thumbnail': 're:^https?://.*\.jpe?g$',
891 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
895 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
896 'thumbnail': 're:^https?://.*\.jpe?g$',
897 'uploader': 'ClickHole',
898 'uploader_id': 'clickhole',
903 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
905 'id': '74849a00-85a9-11e1-9660-123139220831',
907 'title': '#whilewewatch',
912 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
913 'md5': '43662b577c018ad707a63766462b1e87',
917 'title': 'New experience with Acrobat DC',
918 'description': 'New experience with Acrobat DC',
924 def report_following_redirect(self, new_url):
925 """Report information extraction."""
926 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
928 def _extract_rss(self, url, video_id, doc):
929 playlist_title = doc.find('./channel/title').text
930 playlist_desc_el = doc.find('./channel/description')
931 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
934 for it in doc.findall('./channel/item'):
935 next_url = xpath_text(it, 'link', fatal=False)
937 enclosure_nodes = it.findall('./enclosure')
938 for e in enclosure_nodes:
939 next_url = e.attrib.get('url')
949 'title': it.find('title').text,
955 'title': playlist_title,
956 'description': playlist_desc,
960 def _extract_camtasia(self, url, video_id, webpage):
961 """ Returns None if no camtasia video can be found. """
963 camtasia_cfg = self._search_regex(
964 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
965 webpage, 'camtasia configuration file', default=None)
966 if camtasia_cfg is None:
969 title = self._html_search_meta('DC.title', webpage, fatal=True)
971 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
972 camtasia_cfg = self._download_xml(
973 camtasia_url, video_id,
974 note='Downloading camtasia configuration',
975 errnote='Failed to download camtasia configuration')
976 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
979 for n in fileset_node.getchildren():
980 url_n = n.find('./uri')
985 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
986 'title': '%s - %s' % (title, n.tag),
987 'url': compat_urlparse.urljoin(url, url_n.text),
988 'duration': float_or_none(n.find('./duration').text),
997 def _real_extract(self, url):
998 if url.startswith('//'):
1001 'url': self.http_scheme() + url,
1004 parsed_url = compat_urlparse.urlparse(url)
1005 if not parsed_url.scheme:
1006 default_search = self._downloader.params.get('default_search')
1007 if default_search is None:
1008 default_search = 'fixup_error'
1010 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1012 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1013 return self.url_result('http://' + url)
1014 elif default_search != 'fixup_error':
1015 if default_search == 'auto_warning':
1016 if re.match(r'^(?:url|URL)$', url):
1017 raise ExtractorError(
1018 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1021 self._downloader.report_warning(
1022 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1023 return self.url_result('ytsearch:' + url)
1025 if default_search in ('error', 'fixup_error'):
1026 raise ExtractorError(
1027 '%r is not a valid URL. '
1028 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1029 % (url, url), expected=True)
1031 if ':' not in default_search:
1032 default_search += ':'
1033 return self.url_result(default_search + url)
1035 url, smuggled_data = unsmuggle_url(url)
1036 force_videoid = None
1037 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1038 if smuggled_data and 'force_videoid' in smuggled_data:
1039 force_videoid = smuggled_data['force_videoid']
1040 video_id = force_videoid
1042 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1044 self.to_screen('%s: Requesting header' % video_id)
1046 head_req = HEADRequest(url)
1047 head_response = self._request_webpage(
1049 note=False, errnote='Could not send HEAD request to %s' % url,
1052 if head_response is not False:
1053 # Check for redirect
1054 new_url = head_response.geturl()
1056 self.report_following_redirect(new_url)
1058 new_url = smuggle_url(
1059 new_url, {'force_videoid': force_videoid})
1060 return self.url_result(new_url)
1062 full_response = None
1063 if head_response is False:
1064 request = compat_urllib_request.Request(url)
1065 request.add_header('Accept-Encoding', '*')
1066 full_response = self._request_webpage(request, video_id)
1067 head_response = full_response
1069 # Check for direct link to a video
1070 content_type = head_response.headers.get('Content-Type', '')
1071 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1073 upload_date = unified_strdate(
1074 head_response.headers.get('Last-Modified'))
1077 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1080 'format_id': m.group('format_id'),
1082 'vcodec': 'none' if m.group('type') == 'audio' else None
1084 'upload_date': upload_date,
1087 if not self._downloader.params.get('test', False) and not is_intentional:
1088 force = self._downloader.params.get('force_generic_extractor', False)
1089 self._downloader.report_warning(
1090 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1092 if not full_response:
1093 request = compat_urllib_request.Request(url)
1094 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1095 # making it impossible to download only chunk of the file (yet we need only 512kB to
1096 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1097 # that will always result in downloading the whole file that is not desirable.
1098 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1099 # to accept raw bytes and being able to download only a chunk.
1100 # It may probably better to solve this by checking Content-Type for application/octet-stream
1101 # after HEAD request finishes, but not sure if we can rely on this.
1102 request.add_header('Accept-Encoding', '*')
1103 full_response = self._request_webpage(request, video_id)
1105 # Maybe it's a direct link to a video?
1106 # Be careful not to download the whole thing!
1107 first_bytes = full_response.read(512)
1108 if not is_html(first_bytes):
1109 self._downloader.report_warning(
1110 'URL could be a direct video link, returning it as such.')
1111 upload_date = unified_strdate(
1112 head_response.headers.get('Last-Modified'))
1115 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1118 'upload_date': upload_date,
1121 webpage = self._webpage_read_content(
1122 full_response, url, video_id, prefix=first_bytes)
1124 self.report_extraction(video_id)
1126 # Is it an RSS feed?
1128 doc = parse_xml(webpage)
1129 if doc.tag == 'rss':
1130 return self._extract_rss(url, video_id, doc)
1131 except compat_xml_parse_error:
1134 # Is it a Camtasia project?
1135 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1136 if camtasia_res is not None:
1139 # Sometimes embedded video player is hidden behind percent encoding
1140 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1141 # Unescaping the whole page allows to handle those cases in a generic way
1142 webpage = compat_urllib_parse_unquote(webpage)
1144 # it's tempting to parse this further, but you would
1145 # have to take into account all the variations like
1146 # Video Title - Site Name
1147 # Site Name | Video Title
1148 # Video Title - Tagline | Site Name
1149 # and so on and so forth; it's just not practical
1150 video_title = self._html_search_regex(
1151 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1154 # Try to detect age limit automatically
1155 age_limit = self._rta_search(webpage)
1156 # And then there are the jokers who advertise that they use RTA,
1157 # but actually don't.
1158 AGE_LIMIT_MARKERS = [
1159 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1161 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1164 # video uploader is domain name
1165 video_uploader = self._search_regex(
1166 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1169 def _playlist_from_matches(matches, getter=None, ie=None):
1171 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1173 return self.playlist_result(
1174 urlrs, playlist_id=video_id, playlist_title=video_title)
1176 # Look for BrightCove:
1177 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1179 self.to_screen('Brightcove video detected.')
1182 'url': smuggle_url(bc_url, {'Referer': url}),
1183 'ie_key': 'Brightcove'
1184 } for bc_url in bc_urls]
1187 '_type': 'playlist',
1188 'title': video_title,
1193 # Look for embedded rtl.nl player
1194 matches = re.findall(
1195 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1198 return _playlist_from_matches(matches, ie='RtlNl')
1200 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1201 if vimeo_url is not None:
1202 return self.url_result(vimeo_url)
1204 vid_me_embed_url = self._search_regex(
1205 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1206 webpage, 'vid.me embed', default=None)
1207 if vid_me_embed_url is not None:
1208 return self.url_result(vid_me_embed_url, 'Vidme')
1210 # Look for embedded YouTube player
1211 matches = re.findall(r'''(?x)
1220 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1224 return _playlist_from_matches(
1225 matches, lambda m: unescapeHTML(m[1]))
1227 # Look for lazyYT YouTube embed
1228 matches = re.findall(
1229 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1231 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1233 # Look for embedded Dailymotion player
1234 matches = re.findall(
1235 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1237 return _playlist_from_matches(
1238 matches, lambda m: unescapeHTML(m[1]))
1240 # Look for embedded Dailymotion playlist player (#3822)
1242 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1244 playlists = re.findall(
1245 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1247 return _playlist_from_matches(
1248 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1250 # Look for embedded Wistia player
1252 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1254 embed_url = self._proto_relative_url(
1255 unescapeHTML(match.group('url')))
1257 '_type': 'url_transparent',
1260 'uploader': video_uploader,
1261 'title': video_title,
1265 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1268 '_type': 'url_transparent',
1269 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1271 'uploader': video_uploader,
1272 'title': video_title,
1273 'id': match.group('id')
1276 # Look for embedded blip.tv player
1277 bliptv_url = BlipTVIE._extract_url(webpage)
1279 return self.url_result(bliptv_url, 'BlipTV')
1281 # Look for SVT player
1282 svt_url = SVTIE._extract_url(webpage)
1284 return self.url_result(svt_url, 'SVT')
1286 # Look for embedded condenast player
1287 matches = re.findall(
1288 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1292 '_type': 'playlist',
1295 'ie_key': 'CondeNast',
1297 } for ma in matches],
1298 'title': video_title,
1302 # Look for Bandcamp pages with custom domain
1303 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1304 if mobj is not None:
1305 burl = unescapeHTML(mobj.group(1))
1306 # Don't set the extractor because it can be a track url or an album
1307 return self.url_result(burl)
1309 # Look for embedded Vevo player
1311 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1312 if mobj is not None:
1313 return self.url_result(mobj.group('url'))
1315 # Look for embedded Viddler player
1317 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1319 if mobj is not None:
1320 return self.url_result(mobj.group('url'))
1322 # Look for NYTimes player
1324 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1326 if mobj is not None:
1327 return self.url_result(mobj.group('url'))
1329 # Look for Libsyn player
1331 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1332 if mobj is not None:
1333 return self.url_result(mobj.group('url'))
1335 # Look for Ooyala videos
1336 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1337 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1338 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1339 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1340 if mobj is not None:
1341 return OoyalaIE._build_url_result(mobj.group('ec'))
1343 # Look for multiple Ooyala embeds on SBN network websites
1344 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1345 if mobj is not None:
1346 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1348 return _playlist_from_matches(
1349 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1351 # Look for Aparat videos
1352 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1353 if mobj is not None:
1354 return self.url_result(mobj.group(1), 'Aparat')
1356 # Look for MPORA videos
1357 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1358 if mobj is not None:
1359 return self.url_result(mobj.group(1), 'Mpora')
1361 # Look for embedded NovaMov-based player
1363 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1364 (?P<url>http://(?:(?:embed|www)\.)?
1366 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1367 videoweed\.(?:es|com)|
1368 movshare\.(?:net|sx|ag)|
1369 divxstage\.(?:eu|net|ch|co|at|ag))
1370 /embed\.php.+?)\1''', webpage)
1371 if mobj is not None:
1372 return self.url_result(mobj.group('url'))
1374 # Look for embedded Facebook player
1376 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1377 if mobj is not None:
1378 return self.url_result(mobj.group('url'), 'Facebook')
1380 # Look for embedded VK player
1381 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1382 if mobj is not None:
1383 return self.url_result(mobj.group('url'), 'VK')
1385 # Look for embedded ivi player
1386 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1387 if mobj is not None:
1388 return self.url_result(mobj.group('url'), 'Ivi')
1390 # Look for embedded Huffington Post player
1392 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1393 if mobj is not None:
1394 return self.url_result(mobj.group('url'), 'HuffPost')
1397 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1398 if mobj is not None:
1399 return self.url_result(mobj.group('url'))
1400 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1401 if mobj is not None:
1402 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1404 # Look for funnyordie embed
1405 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1407 return _playlist_from_matches(
1408 matches, getter=unescapeHTML, ie='FunnyOrDie')
1410 # Look for BBC iPlayer embed
1411 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1413 return _playlist_from_matches(matches, ie='BBCCoUk')
1415 # Look for embedded RUTV player
1416 rutv_url = RUTVIE._extract_url(webpage)
1418 return self.url_result(rutv_url, 'RUTV')
1420 # Look for embedded TVC player
1421 tvc_url = TVCIE._extract_url(webpage)
1423 return self.url_result(tvc_url, 'TVC')
1425 # Look for embedded SportBox player
1426 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1428 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1430 # Look for embedded PornHub player
1431 pornhub_url = PornHubIE._extract_url(webpage)
1433 return self.url_result(pornhub_url, 'PornHub')
1435 # Look for embedded XHamster player
1436 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1438 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1440 # Look for embedded Tvigle player
1442 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1443 if mobj is not None:
1444 return self.url_result(mobj.group('url'), 'Tvigle')
1446 # Look for embedded TED player
1448 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1449 if mobj is not None:
1450 return self.url_result(mobj.group('url'), 'TED')
1452 # Look for embedded Ustream videos
1454 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1455 if mobj is not None:
1456 return self.url_result(mobj.group('url'), 'Ustream')
1458 # Look for embedded arte.tv player
1460 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1462 if mobj is not None:
1463 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1465 # Look for embedded francetv player
1467 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1469 if mobj is not None:
1470 return self.url_result(mobj.group('url'))
1472 # Look for embedded smotri.com player
1473 smotri_url = SmotriIE._extract_url(webpage)
1475 return self.url_result(smotri_url, 'Smotri')
1477 # Look for embedded Myvi.ru player
1478 myvi_url = MyviIE._extract_url(webpage)
1480 return self.url_result(myvi_url)
1482 # Look for embeded soundcloud player
1484 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1486 if mobj is not None:
1487 url = unescapeHTML(mobj.group('url'))
1488 return self.url_result(url)
1490 # Look for embedded vulture.com player
1492 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1494 if mobj is not None:
1495 url = unescapeHTML(mobj.group('url'))
1496 return self.url_result(url, ie='Vulture')
1498 # Look for embedded mtvservices player
1500 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1502 if mobj is not None:
1503 url = unescapeHTML(mobj.group('url'))
1504 return self.url_result(url, ie='MTVServicesEmbedded')
1506 # Look for embedded yahoo player
1508 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1510 if mobj is not None:
1511 return self.url_result(mobj.group('url'), 'Yahoo')
1513 # Look for embedded sbs.com.au player
1517 <meta\s+property="og:video"\s+content=|
1520 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1522 if mobj is not None:
1523 return self.url_result(mobj.group('url'), 'SBS')
1525 # Look for embedded Cinchcast player
1527 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1529 if mobj is not None:
1530 return self.url_result(mobj.group('url'), 'Cinchcast')
1533 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1537 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1539 if mobj is not None:
1540 return self.url_result(mobj.group('url'), 'MLB')
1543 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1545 if mobj is not None:
1546 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1549 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1551 if mobj is not None:
1552 return self.url_result(mobj.group('url'), 'Livestream')
1554 # Look for Zapiks embed
1556 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1557 if mobj is not None:
1558 return self.url_result(mobj.group('url'), 'Zapiks')
1560 # Look for Kaltura embeds
1561 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1562 re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
1563 if mobj is not None:
1564 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1566 # Look for Eagle.Platform embeds
1568 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1569 if mobj is not None:
1570 return self.url_result(mobj.group('url'), 'EaglePlatform')
1572 # Look for ClipYou (uses Eagle.Platform) embeds
1574 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1575 if mobj is not None:
1576 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1578 # Look for Pladform embeds
1580 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1581 if mobj is not None:
1582 return self.url_result(mobj.group('url'), 'Pladform')
1584 # Look for Playwire embeds
1586 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1587 if mobj is not None:
1588 return self.url_result(mobj.group('url'))
1590 # Look for 5min embeds
1592 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1593 if mobj is not None:
1594 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1596 # Look for Crooks and Liars embeds
1598 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1599 if mobj is not None:
1600 return self.url_result(mobj.group('url'))
1602 # Look for NBC Sports VPlayer embeds
1603 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1605 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1607 # Look for UDN embeds
1609 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1610 if mobj is not None:
1611 return self.url_result(
1612 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1614 # Look for Senate ISVP iframe
1615 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1617 return self.url_result(senate_isvp_url, 'SenateISVP')
1619 # Look for Dailymotion Cloud videos
1620 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1622 return self.url_result(dmcloud_url, 'DailymotionCloud')
1624 # Look for OnionStudios embeds
1625 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1626 if onionstudios_url:
1627 return self.url_result(onionstudios_url)
1629 # Look for SnagFilms embeds
1630 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1632 return self.url_result(snagfilms_url)
1634 # Look for AdobeTVVideo embeds
1636 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1638 if mobj is not None:
1639 return self.url_result(
1640 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1643 def check_video(vurl):
1644 if YoutubeIE.suitable(vurl):
1646 vpath = compat_urlparse.urlparse(vurl).path
1647 vext = determine_ext(vpath)
1648 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1650 def filter_video(urls):
1651 return list(filter(check_video, urls))
1653 # Start with something easy: JW Player in SWFObject
1654 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1656 # Look for gorilla-vid style embedding
1657 found = filter_video(re.findall(r'''(?sx)
1661 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1664 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1666 # Broaden the search a little bit
1667 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1669 # Broaden the findall a little bit: JWPlayer JS loader
1670 found = filter_video(re.findall(
1671 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1674 found = filter_video(re.findall(r'''(?xs)
1675 flowplayer\("[^"]+",\s*
1677 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1678 ["']?url["']?\s*:\s*["']([^"']+)["']
1683 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1685 # Try to find twitter cards info
1686 found = filter_video(re.findall(
1687 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1689 # We look for Open Graph info:
1690 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1691 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1692 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1693 if m_video_type is not None:
1694 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1697 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1699 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1701 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1702 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1705 # Look also in Refresh HTTP header
1706 refresh_header = head_response.headers.get('Refresh')
1708 found = re.search(REDIRECT_REGEX, refresh_header)
1710 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1711 self.report_following_redirect(new_url)
1717 raise UnsupportedError(url)
1720 for video_url in found:
1721 video_url = compat_urlparse.urljoin(url, video_url)
1722 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1724 # Sometimes, jwplayer extraction will result in a YouTube URL
1725 if YoutubeIE.suitable(video_url):
1726 entries.append(self.url_result(video_url, 'Youtube'))
1729 # here's a fun little line of code for you:
1730 video_id = os.path.splitext(video_id)[0]
1732 if determine_ext(video_url) == 'smil':
1735 'formats': self._extract_smil_formats(video_url, video_id),
1736 'uploader': video_uploader,
1737 'title': video_title,
1738 'age_limit': age_limit,
1744 'uploader': video_uploader,
1745 'title': video_title,
1746 'age_limit': age_limit,
1749 if len(entries) == 1:
1752 for num, e in enumerate(entries, start=1):
1753 # 'url' results don't have a title
1754 if e.get('title') is not None:
1755 e['title'] = '%s (%d)' % (e['title'], num)
1757 '_type': 'playlist',