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
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'],
239 # multiple ooyala embeds on SBN network websites
241 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
243 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
244 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
246 'playlist_mincount': 3,
248 'skip_download': True,
250 'add_ie': ['Ooyala'],
254 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
258 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
259 'upload_date': '20140225',
260 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
261 'uploader': 'Tested',
262 'uploader_id': 'testedcom',
264 # No need to test YoutubeIE here
266 'skip_download': True,
271 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
275 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
276 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
281 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
283 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
285 'playlist_mincount': 18,
289 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
293 'title': 'Охотское море стало целиком российским',
294 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
298 'skip_download': True,
303 '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/',
307 'title': 'Дошкольное воспитание',
312 'url': 'http://www.vestifinance.ru/articles/25753',
315 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
320 'title': 'Госзаказ. День 3',
326 'title': 'Госзаказ. День 2',
332 'title': 'Госзаказ. День 1',
338 'skip_download': True,
343 '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',
346 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
348 'playlist_mincount': 7,
352 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
353 'md5': '65fdff94098e4a607385a60c5177c638',
357 'title': 'Hidden miracles of the natural world',
358 'uploader': 'Louie Schwartzberg',
359 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
362 # Embeded Ustream video
364 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
365 'md5': '27b99cdb639c9b12a79bca876a073417',
369 'uploader': 'AU SPA: The NSA and Privacy',
370 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
373 # nowvideo embed hidden behind percent encoding
375 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
376 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
378 'id': '06e53103ca9aa',
380 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
381 'description': 'No description',
386 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
387 'md5': '7653032cbb25bf6c80d80f217055fa43',
389 'id': '048195-004_PLUS7-F',
392 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
393 'upload_date': '20140320',
396 'skip_download': 'Requires rtmpdump'
401 'url': 'http://www.wired.com/2014/04/honda-asimo/',
402 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
404 'id': '53501be369702d3275860000',
406 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
411 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
412 'md5': '441aeeb82eb72c422c7f14ec533999cd',
414 'id': 'k2mm4bCdJ6CQ2i7c8o2',
416 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
419 'add_ie': ['Dailymotion'],
423 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
427 'title': 'The NBL Auction 2014',
428 'uploader': 'BADMINTON England',
429 'uploader_id': 'BADMINTONEvents',
430 'upload_date': '20140603',
431 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
433 'add_ie': ['Youtube'],
435 'skip_download': True,
440 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
441 'md5': '35727f82f58c76d996fc188f9755b0d5',
443 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
446 'description': 'Mario\'s life in the fast lane has never looked so good.',
449 # YouTube embed via <data-embed-url="">
451 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
455 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
456 'uploader': 'Gameloft',
457 'uploader_id': 'gameloft',
458 'upload_date': '20140828',
459 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
462 'skip_download': True,
467 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
469 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
471 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
472 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
477 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
479 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
480 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
486 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
491 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
492 'md5': '9d65602bf31c6e20014319c7d07fba27',
494 'id': '5123ea6d5e5a7',
497 'uploader': 'www.handjobhub.com',
498 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
501 # Multiple brightcove videos
502 # https://github.com/rg3/youtube-dl/issues/2283
504 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
506 'id': 'always-never',
507 'title': 'Always / Never - The New Yorker',
511 'extract_flat': False,
512 'skip_download': True,
517 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
518 'md5': '96f09a37e44da40dd083e12d9a683327',
522 'title': 'Ump changes call to ball',
523 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
525 'timestamp': 1401537900,
526 'upload_date': '20140531',
527 'thumbnail': 're:^https?://.*\.jpg$',
532 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
533 'md5': '8788b683c777a5cf25621eaf286d0c23',
537 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
539 'filesize': 182808282,
540 'uploader': 'education-portal.com',
544 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
545 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
549 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
551 'uploader': 'thoughtworks.wistia.com',
556 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
560 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
561 'uploader': 'Sophos Security',
562 'title': 'Chet Chat 171 - Oct 29, 2014',
563 'upload_date': '20141029',
568 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
572 'upload_date': '20141112',
573 'title': 'Rosetta #CometLanding webcast HL 10',
578 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
581 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
583 'playlist_mincount': 2,
587 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
591 'upload_date': '20141126',
592 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
597 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
599 'id': '730m_DandD_1901_512k',
601 'uploader': 'www.abc.net.au',
602 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
605 # embedded viddler video
607 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
611 'uploader': 'deadspin',
612 'title': 'WALL-TO-GORTAT',
613 'timestamp': 1422285291,
614 'upload_date': '20150126',
616 'add_ie': ['Viddler'],
620 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
624 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
625 'description': 'md5:601cb790edd05908957dae8aaa866465',
626 'upload_date': '20150220',
631 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
635 'upload_date': '20150212',
636 'uploader': 'The National Archives UK',
637 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
638 'uploader_id': 'NationalArchives08',
639 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
644 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
645 'playlist_mincount': 5,
647 'id': 'aanslagen-kopenhagen',
648 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
653 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
657 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
662 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
666 'upload_date': '20150226',
667 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
669 'title': 'John Carlson Postgame 2/25/15',
672 # Kaltura embed (different embed code)
674 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
678 'upload_date': '20150127',
679 'uploader_id': 'PremierMedia',
681 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
684 # Eagle.Platform embed (generic URL)
686 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
690 'title': 'Навальный вышел на свободу',
691 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
692 'thumbnail': 're:^https?://.*\.jpg$',
698 # ClipYou (Eagle.Platform) embed (custom URL)
700 'url': 'http://muz-tv.ru/play/7129/',
704 'title': "'O Sole Mio",
705 'thumbnail': 're:^https?://.*\.jpg$',
712 'url': 'http://muz-tv.ru/kinozal/view/7400/',
716 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
717 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
718 'thumbnail': 're:^https?://.*\.jpg$',
725 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
729 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
730 'thumbnail': 're:^https?://.*\.png$',
736 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
737 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
741 'title': 'Facebook Creates "On This Day" | Crunch Report',
746 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
750 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
755 # Crooks and Liars embed
757 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
761 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
762 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
763 'timestamp': 1428207000,
764 'upload_date': '20150405',
765 'uploader': 'Heather',
768 # Crooks and Liars external embed
770 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
772 'id': 'MTE3MjUtMzQ2MzA',
774 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
775 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
776 'timestamp': 1265032391,
777 'upload_date': '20100201',
778 'uploader': 'Heather',
781 # NBC Sports vplayer embed
783 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
785 'id': 'ln7x1qSThw4k',
787 'title': "PFT Live: New leader in the 'new-look' defense",
788 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
793 'url': 'http://www.udn.com/news/story/7314/822787',
794 'md5': 'fd2060e988c326991037b9aff9df21a6',
798 'title': '中一中男師變性 全校師生力挺',
799 'thumbnail': 're:^https?://.*\.jpg$',
804 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
806 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
808 'description': 'VIDEO: Index/Match versus VLOOKUP.',
809 'title': 'This is what separates the Excel masters from the wannabes',
813 'skip_download': True,
816 # Contains a SMIL manifest
818 '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',
822 'title': '+ Football: Lottery Champions League Europe',
823 'uploader': 'www.telewebion.com',
827 'skip_download': True,
830 # Brightcove URL in single quotes
832 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
833 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
835 'id': '4255764656001',
837 'title': 'SN Presents: Russell Martin, World Citizen',
838 '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.',
839 'uploader': 'Rogers Sportsnet',
842 # Dailymotion Cloud video
844 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
845 'md5': '49444254273501a64675a7e68c502681',
847 'id': '5585de919473990de4bee11b',
850 'thumbnail': 're:^https?://.*\.jpe?g$',
855 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
859 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
860 'thumbnail': 're:^https?://.*\.jpe?g$',
861 'uploader': 'ClickHole',
862 'uploader_id': 'clickhole',
867 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
869 'id': '74849a00-85a9-11e1-9660-123139220831',
871 'title': '#whilewewatch',
876 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
877 'md5': '43662b577c018ad707a63766462b1e87',
881 'title': 'New experience with Acrobat DC',
882 'description': 'New experience with Acrobat DC',
888 def report_following_redirect(self, new_url):
889 """Report information extraction."""
890 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
892 def _extract_rss(self, url, video_id, doc):
893 playlist_title = doc.find('./channel/title').text
894 playlist_desc_el = doc.find('./channel/description')
895 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
898 for it in doc.findall('./channel/item'):
899 next_url = xpath_text(it, 'link', fatal=False)
901 enclosure_nodes = it.findall('./enclosure')
902 for e in enclosure_nodes:
903 next_url = e.attrib.get('url')
913 'title': it.find('title').text,
919 'title': playlist_title,
920 'description': playlist_desc,
924 def _extract_camtasia(self, url, video_id, webpage):
925 """ Returns None if no camtasia video can be found. """
927 camtasia_cfg = self._search_regex(
928 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
929 webpage, 'camtasia configuration file', default=None)
930 if camtasia_cfg is None:
933 title = self._html_search_meta('DC.title', webpage, fatal=True)
935 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
936 camtasia_cfg = self._download_xml(
937 camtasia_url, video_id,
938 note='Downloading camtasia configuration',
939 errnote='Failed to download camtasia configuration')
940 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
943 for n in fileset_node.getchildren():
944 url_n = n.find('./uri')
949 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
950 'title': '%s - %s' % (title, n.tag),
951 'url': compat_urlparse.urljoin(url, url_n.text),
952 'duration': float_or_none(n.find('./duration').text),
961 def _real_extract(self, url):
962 if url.startswith('//'):
965 'url': self.http_scheme() + url,
968 parsed_url = compat_urlparse.urlparse(url)
969 if not parsed_url.scheme:
970 default_search = self._downloader.params.get('default_search')
971 if default_search is None:
972 default_search = 'fixup_error'
974 if default_search in ('auto', 'auto_warning', 'fixup_error'):
976 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
977 return self.url_result('http://' + url)
978 elif default_search != 'fixup_error':
979 if default_search == 'auto_warning':
980 if re.match(r'^(?:url|URL)$', url):
981 raise ExtractorError(
982 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
985 self._downloader.report_warning(
986 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
987 return self.url_result('ytsearch:' + url)
989 if default_search in ('error', 'fixup_error'):
990 raise ExtractorError(
991 '%r is not a valid URL. '
992 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
993 % (url, url), expected=True)
995 if ':' not in default_search:
996 default_search += ':'
997 return self.url_result(default_search + url)
999 url, smuggled_data = unsmuggle_url(url)
1000 force_videoid = None
1001 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1002 if smuggled_data and 'force_videoid' in smuggled_data:
1003 force_videoid = smuggled_data['force_videoid']
1004 video_id = force_videoid
1006 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1008 self.to_screen('%s: Requesting header' % video_id)
1010 head_req = HEADRequest(url)
1011 head_response = self._request_webpage(
1013 note=False, errnote='Could not send HEAD request to %s' % url,
1016 if head_response is not False:
1017 # Check for redirect
1018 new_url = head_response.geturl()
1020 self.report_following_redirect(new_url)
1022 new_url = smuggle_url(
1023 new_url, {'force_videoid': force_videoid})
1024 return self.url_result(new_url)
1026 full_response = None
1027 if head_response is False:
1028 request = compat_urllib_request.Request(url)
1029 request.add_header('Accept-Encoding', '*')
1030 full_response = self._request_webpage(request, video_id)
1031 head_response = full_response
1033 # Check for direct link to a video
1034 content_type = head_response.headers.get('Content-Type', '')
1035 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1037 upload_date = unified_strdate(
1038 head_response.headers.get('Last-Modified'))
1041 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1044 'format_id': m.group('format_id'),
1046 'vcodec': 'none' if m.group('type') == 'audio' else None
1048 'upload_date': upload_date,
1051 if not self._downloader.params.get('test', False) and not is_intentional:
1052 force = self._downloader.params.get('force_generic_extractor', False)
1053 self._downloader.report_warning(
1054 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1056 if not full_response:
1057 request = compat_urllib_request.Request(url)
1058 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1059 # making it impossible to download only chunk of the file (yet we need only 512kB to
1060 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1061 # that will always result in downloading the whole file that is not desirable.
1062 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1063 # to accept raw bytes and being able to download only a chunk.
1064 # It may probably better to solve this by checking Content-Type for application/octet-stream
1065 # after HEAD request finishes, but not sure if we can rely on this.
1066 request.add_header('Accept-Encoding', '*')
1067 full_response = self._request_webpage(request, video_id)
1069 # Maybe it's a direct link to a video?
1070 # Be careful not to download the whole thing!
1071 first_bytes = full_response.read(512)
1072 if not is_html(first_bytes):
1073 self._downloader.report_warning(
1074 'URL could be a direct video link, returning it as such.')
1075 upload_date = unified_strdate(
1076 head_response.headers.get('Last-Modified'))
1079 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1082 'upload_date': upload_date,
1085 webpage = self._webpage_read_content(
1086 full_response, url, video_id, prefix=first_bytes)
1088 self.report_extraction(video_id)
1090 # Is it an RSS feed?
1092 doc = parse_xml(webpage)
1093 if doc.tag == 'rss':
1094 return self._extract_rss(url, video_id, doc)
1095 except compat_xml_parse_error:
1098 # Is it a Camtasia project?
1099 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1100 if camtasia_res is not None:
1103 # Sometimes embedded video player is hidden behind percent encoding
1104 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1105 # Unescaping the whole page allows to handle those cases in a generic way
1106 webpage = compat_urllib_parse.unquote(webpage)
1108 # it's tempting to parse this further, but you would
1109 # have to take into account all the variations like
1110 # Video Title - Site Name
1111 # Site Name | Video Title
1112 # Video Title - Tagline | Site Name
1113 # and so on and so forth; it's just not practical
1114 video_title = self._html_search_regex(
1115 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1118 # Try to detect age limit automatically
1119 age_limit = self._rta_search(webpage)
1120 # And then there are the jokers who advertise that they use RTA,
1121 # but actually don't.
1122 AGE_LIMIT_MARKERS = [
1123 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1125 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1128 # video uploader is domain name
1129 video_uploader = self._search_regex(
1130 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1133 def _playlist_from_matches(matches, getter=None, ie=None):
1135 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1137 return self.playlist_result(
1138 urlrs, playlist_id=video_id, playlist_title=video_title)
1140 # Look for BrightCove:
1141 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1143 self.to_screen('Brightcove video detected.')
1146 'url': smuggle_url(bc_url, {'Referer': url}),
1147 'ie_key': 'Brightcove'
1148 } for bc_url in bc_urls]
1151 '_type': 'playlist',
1152 'title': video_title,
1157 # Look for embedded rtl.nl player
1158 matches = re.findall(
1159 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1162 return _playlist_from_matches(matches, ie='RtlNl')
1164 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1165 if vimeo_url is not None:
1166 return self.url_result(vimeo_url)
1168 # Look for embedded YouTube player
1169 matches = re.findall(r'''(?x)
1178 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1182 return _playlist_from_matches(
1183 matches, lambda m: unescapeHTML(m[1]))
1185 # Look for lazyYT YouTube embed
1186 matches = re.findall(
1187 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1189 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1191 # Look for embedded Dailymotion player
1192 matches = re.findall(
1193 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1195 return _playlist_from_matches(
1196 matches, lambda m: unescapeHTML(m[1]))
1198 # Look for embedded Dailymotion playlist player (#3822)
1200 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1202 playlists = re.findall(
1203 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1205 return _playlist_from_matches(
1206 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1208 # Look for embedded Wistia player
1210 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1212 embed_url = self._proto_relative_url(
1213 unescapeHTML(match.group('url')))
1215 '_type': 'url_transparent',
1218 'uploader': video_uploader,
1219 'title': video_title,
1223 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1226 '_type': 'url_transparent',
1227 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1229 'uploader': video_uploader,
1230 'title': video_title,
1231 'id': match.group('id')
1234 # Look for embedded blip.tv player
1235 bliptv_url = BlipTVIE._extract_url(webpage)
1237 return self.url_result(bliptv_url, 'BlipTV')
1239 # Look for SVT player
1240 svt_url = SVTIE._extract_url(webpage)
1242 return self.url_result(svt_url, 'SVT')
1244 # Look for embedded condenast player
1245 matches = re.findall(
1246 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1250 '_type': 'playlist',
1253 'ie_key': 'CondeNast',
1255 } for ma in matches],
1256 'title': video_title,
1260 # Look for Bandcamp pages with custom domain
1261 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1262 if mobj is not None:
1263 burl = unescapeHTML(mobj.group(1))
1264 # Don't set the extractor because it can be a track url or an album
1265 return self.url_result(burl)
1267 # Look for embedded Vevo player
1269 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1270 if mobj is not None:
1271 return self.url_result(mobj.group('url'))
1273 # Look for embedded Viddler player
1275 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1277 if mobj is not None:
1278 return self.url_result(mobj.group('url'))
1280 # Look for NYTimes player
1282 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1284 if mobj is not None:
1285 return self.url_result(mobj.group('url'))
1287 # Look for Libsyn player
1289 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1290 if mobj is not None:
1291 return self.url_result(mobj.group('url'))
1293 # Look for Ooyala videos
1294 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1295 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1296 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1297 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1298 if mobj is not None:
1299 return OoyalaIE._build_url_result(mobj.group('ec'))
1301 # Look for multiple Ooyala embeds on SBN network websites
1302 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1303 if mobj is not None:
1304 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1306 return _playlist_from_matches(
1307 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1309 # Look for Aparat videos
1310 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1311 if mobj is not None:
1312 return self.url_result(mobj.group(1), 'Aparat')
1314 # Look for MPORA videos
1315 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1316 if mobj is not None:
1317 return self.url_result(mobj.group(1), 'Mpora')
1319 # Look for embedded NovaMov-based player
1321 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1322 (?P<url>http://(?:(?:embed|www)\.)?
1324 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1325 videoweed\.(?:es|com)|
1326 movshare\.(?:net|sx|ag)|
1327 divxstage\.(?:eu|net|ch|co|at|ag))
1328 /embed\.php.+?)\1''', webpage)
1329 if mobj is not None:
1330 return self.url_result(mobj.group('url'))
1332 # Look for embedded Facebook player
1334 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1335 if mobj is not None:
1336 return self.url_result(mobj.group('url'), 'Facebook')
1338 # Look for embedded VK player
1339 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1340 if mobj is not None:
1341 return self.url_result(mobj.group('url'), 'VK')
1343 # Look for embedded ivi player
1344 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1345 if mobj is not None:
1346 return self.url_result(mobj.group('url'), 'Ivi')
1348 # Look for embedded Huffington Post player
1350 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1351 if mobj is not None:
1352 return self.url_result(mobj.group('url'), 'HuffPost')
1355 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1356 if mobj is not None:
1357 return self.url_result(mobj.group('url'))
1358 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1359 if mobj is not None:
1360 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1362 # Look for funnyordie embed
1363 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1365 return _playlist_from_matches(
1366 matches, getter=unescapeHTML, ie='FunnyOrDie')
1368 # Look for BBC iPlayer embed
1369 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1371 return _playlist_from_matches(matches, ie='BBCCoUk')
1373 # Look for embedded RUTV player
1374 rutv_url = RUTVIE._extract_url(webpage)
1376 return self.url_result(rutv_url, 'RUTV')
1378 # Look for embedded TVC player
1379 tvc_url = TVCIE._extract_url(webpage)
1381 return self.url_result(tvc_url, 'TVC')
1383 # Look for embedded SportBox player
1384 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1386 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1388 # Look for embedded PornHub player
1389 pornhub_url = PornHubIE._extract_url(webpage)
1391 return self.url_result(pornhub_url, 'PornHub')
1393 # Look for embedded XHamster player
1394 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1396 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1398 # Look for embedded Tvigle player
1400 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1401 if mobj is not None:
1402 return self.url_result(mobj.group('url'), 'Tvigle')
1404 # Look for embedded TED player
1406 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1407 if mobj is not None:
1408 return self.url_result(mobj.group('url'), 'TED')
1410 # Look for embedded Ustream videos
1412 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1413 if mobj is not None:
1414 return self.url_result(mobj.group('url'), 'Ustream')
1416 # Look for embedded arte.tv player
1418 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1420 if mobj is not None:
1421 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1423 # Look for embedded smotri.com player
1424 smotri_url = SmotriIE._extract_url(webpage)
1426 return self.url_result(smotri_url, 'Smotri')
1428 # Look for embeded soundcloud player
1430 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1432 if mobj is not None:
1433 url = unescapeHTML(mobj.group('url'))
1434 return self.url_result(url)
1436 # Look for embedded vulture.com player
1438 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1440 if mobj is not None:
1441 url = unescapeHTML(mobj.group('url'))
1442 return self.url_result(url, ie='Vulture')
1444 # Look for embedded mtvservices player
1446 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1448 if mobj is not None:
1449 url = unescapeHTML(mobj.group('url'))
1450 return self.url_result(url, ie='MTVServicesEmbedded')
1452 # Look for embedded yahoo player
1454 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1456 if mobj is not None:
1457 return self.url_result(mobj.group('url'), 'Yahoo')
1459 # Look for embedded sbs.com.au player
1463 <meta\s+property="og:video"\s+content=|
1466 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1468 if mobj is not None:
1469 return self.url_result(mobj.group('url'), 'SBS')
1471 # Look for embedded Cinchcast player
1473 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1475 if mobj is not None:
1476 return self.url_result(mobj.group('url'), 'Cinchcast')
1479 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1483 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1485 if mobj is not None:
1486 return self.url_result(mobj.group('url'), 'MLB')
1489 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1491 if mobj is not None:
1492 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1495 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1497 if mobj is not None:
1498 return self.url_result(mobj.group('url'), 'Livestream')
1500 # Look for Zapiks embed
1502 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1503 if mobj is not None:
1504 return self.url_result(mobj.group('url'), 'Zapiks')
1506 # Look for Kaltura embeds
1507 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1508 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))
1509 if mobj is not None:
1510 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1512 # Look for Eagle.Platform embeds
1514 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1515 if mobj is not None:
1516 return self.url_result(mobj.group('url'), 'EaglePlatform')
1518 # Look for ClipYou (uses Eagle.Platform) embeds
1520 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1521 if mobj is not None:
1522 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1524 # Look for Pladform embeds
1526 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1527 if mobj is not None:
1528 return self.url_result(mobj.group('url'), 'Pladform')
1530 # Look for Playwire embeds
1532 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1533 if mobj is not None:
1534 return self.url_result(mobj.group('url'))
1536 # Look for 5min embeds
1538 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1539 if mobj is not None:
1540 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1542 # Look for Crooks and Liars embeds
1544 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1545 if mobj is not None:
1546 return self.url_result(mobj.group('url'))
1548 # Look for NBC Sports VPlayer embeds
1549 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1551 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1553 # Look for UDN embeds
1555 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1556 if mobj is not None:
1557 return self.url_result(
1558 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1560 # Look for Senate ISVP iframe
1561 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1563 return self.url_result(senate_isvp_url, 'SenateISVP')
1565 # Look for Dailymotion Cloud videos
1566 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1568 return self.url_result(dmcloud_url, 'DailymotionCloud')
1570 # Look for OnionStudios embeds
1571 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1572 if onionstudios_url:
1573 return self.url_result(onionstudios_url)
1575 # Look for SnagFilms embeds
1576 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1578 return self.url_result(snagfilms_url)
1580 # Look for AdobeTVVideo embeds
1582 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1584 if mobj is not None:
1585 return self.url_result(
1586 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1589 def check_video(vurl):
1590 if YoutubeIE.suitable(vurl):
1592 vpath = compat_urlparse.urlparse(vurl).path
1593 vext = determine_ext(vpath)
1594 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1596 def filter_video(urls):
1597 return list(filter(check_video, urls))
1599 # Start with something easy: JW Player in SWFObject
1600 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1602 # Look for gorilla-vid style embedding
1603 found = filter_video(re.findall(r'''(?sx)
1607 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1610 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1612 # Broaden the search a little bit
1613 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1615 # Broaden the findall a little bit: JWPlayer JS loader
1616 found = filter_video(re.findall(
1617 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1620 found = filter_video(re.findall(r'''(?xs)
1621 flowplayer\("[^"]+",\s*
1623 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1624 ["']?url["']?\s*:\s*["']([^"']+)["']
1629 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1631 # Try to find twitter cards info
1632 found = filter_video(re.findall(
1633 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1635 # We look for Open Graph info:
1636 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1637 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1638 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1639 if m_video_type is not None:
1640 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1643 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1645 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1647 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1648 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1651 # Look also in Refresh HTTP header
1652 refresh_header = head_response.headers.get('Refresh')
1654 found = re.search(REDIRECT_REGEX, refresh_header)
1656 new_url = compat_urlparse.urljoin(url, found.group(1))
1657 self.report_following_redirect(new_url)
1663 raise UnsupportedError(url)
1666 for video_url in found:
1667 video_url = compat_urlparse.urljoin(url, video_url)
1668 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1670 # Sometimes, jwplayer extraction will result in a YouTube URL
1671 if YoutubeIE.suitable(video_url):
1672 entries.append(self.url_result(video_url, 'Youtube'))
1675 # here's a fun little line of code for you:
1676 video_id = os.path.splitext(video_id)[0]
1678 if determine_ext(video_url) == 'smil':
1681 'formats': self._extract_smil_formats(video_url, video_id),
1682 'uploader': video_uploader,
1683 'title': video_title,
1684 'age_limit': age_limit,
1690 'uploader': video_uploader,
1691 'title': video_title,
1692 'age_limit': age_limit,
1695 if len(entries) == 1:
1698 for num, e in enumerate(entries, start=1):
1699 # 'url' results don't have a title
1700 if e.get('title') is not None:
1701 e['title'] = '%s (%d)' % (e['title'], num)
1703 '_type': 'playlist',