3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .vimeo import VimeoIE
51 from .dailymotion import DailymotionCloudIE
52 from .onionstudios import OnionStudiosIE
53 from .snagfilms import SnagFilmsEmbedIE
54 from .screenwavemedia import ScreenwaveMediaIE
55 from .mtv import MTVServicesEmbeddedIE
56 from .pladform import PladformIE
57 from .googledrive import GoogleDriveIE
58 from .jwplatform import JWPlatformIE
59 from .ultimedia import UltimediaIE
62 class GenericIE(InfoExtractor):
63 IE_DESC = 'Generic downloader that works on some sites'
67 # Direct link to a video
69 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
70 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
75 'upload_date': '20100513',
78 # Direct link to media delivered compressed (until Accept-Encoding is *)
80 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
81 'md5': '128c42e68b13950268b648275386fc74',
83 'id': 'FictionJunction-Parallel_Hearts',
85 'title': 'FictionJunction-Parallel_Hearts',
86 'upload_date': '20140522',
88 'expected_warnings': [
89 'URL could be a direct video link, returning it as such.'
92 # Direct download with broken HEAD
94 'url': 'http://ai-radio.org:8000/radio.opus',
101 'skip_download': True, # infinite live stream
103 'expected_warnings': [
104 r'501.*Not Implemented'
107 # Direct link with incorrect MIME type
109 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
110 'md5': '4ccbebe5f36706d85221f204d7eb5913',
112 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
113 'id': '5_Lennart_Poettering_-_Systemd',
115 'title': '5_Lennart_Poettering_-_Systemd',
116 'upload_date': '20141120',
118 'expected_warnings': [
119 'URL could be a direct video link, returning it as such.'
124 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
126 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
127 'title': 'Zero Punctuation',
128 'description': 're:.*groundbreaking video review series.*'
130 'playlist_mincount': 11,
132 # RSS feed with enclosure
134 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
136 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
138 'upload_date': '20150228',
139 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
142 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
144 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
148 'title': 'Automatics, robotics and biocybernetics',
149 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
150 'upload_date': '20130627',
151 'formats': 'mincount:16',
152 'subtitles': 'mincount:1',
155 'force_generic_extractor': True,
156 'skip_download': True,
159 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
161 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
166 'formats': 'mincount:1',
169 'skip_download': True,
172 # SMIL from https://www.restudy.dk/video/play/id/1637
174 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
178 'title': 'video_1637',
179 'formats': 'mincount:3',
182 'skip_download': True,
185 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
187 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
189 'id': 'smil-service',
191 'title': 'smil-service',
192 'formats': 'mincount:1',
195 'skip_download': True,
198 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
200 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
204 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
205 'formats': 'mincount:3',
208 'skip_download': True,
211 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
213 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
215 'id': 'mZlp2ctYIUEB',
217 'title': 'Tikibad ontruimd wegens brand',
218 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
219 'thumbnail': 're:^https?://.*\.jpg$',
223 'skip_download': True,
228 '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',
232 'upload_date': '20130224',
233 'uploader_id': 'TheVerge',
234 'description': 're:^Chris Ziegler takes a look at the\.*',
235 'uploader': 'The Verge',
236 'title': 'First Firefox OS phones side-by-side',
239 'skip_download': False,
243 # redirect in Refresh HTTP header
244 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
248 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
249 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
250 'upload_date': '20150917',
251 'uploader_id': 'brtvofficial',
252 'uploader': 'Boiler Room',
255 'skip_download': False,
259 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
260 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
262 'id': '13601338388002',
264 'uploader': 'www.hodiho.fr',
265 'title': 'R\u00e9gis plante sa Jeep',
268 # bandcamp page with custom domain
270 'add_ie': ['Bandcamp'],
271 'url': 'http://bronyrock.com/track/the-pony-mash',
275 'title': 'The Pony Mash',
276 'uploader': 'M_Pallante',
278 'skip': 'There is a limit of 200 free downloads / month for the test song',
280 # embedded brightcove video
281 # it also tests brightcove videos that need to set the 'Referer' in the
284 'add_ie': ['BrightcoveLegacy'],
285 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
287 'id': '2765128793001',
289 'title': 'Le cours de bourse : l’analyse technique',
290 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
291 'uploader': 'BFM BUSINESS',
294 'skip_download': True,
298 # https://github.com/rg3/youtube-dl/issues/2253
299 'url': 'http://bcove.me/i6nfkrc3',
300 'md5': '0ba9446db037002366bab3b3eb30c88c',
302 'id': '3101154703001',
304 'title': 'Still no power',
305 'uploader': 'thestar.com',
306 '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.',
308 'add_ie': ['BrightcoveLegacy'],
311 'url': 'http://www.championat.com/video/football/v/87/87499.html',
312 'md5': 'fb973ecf6e4a78a67453647444222983',
314 'id': '3414141473001',
316 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
317 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
318 'uploader': 'Championat',
322 # https://github.com/rg3/youtube-dl/issues/3541
323 'add_ie': ['BrightcoveLegacy'],
324 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
326 'id': '3866516442001',
328 'title': 'Leer mij vrouwen kennen: Aflevering 1',
329 'description': 'Leer mij vrouwen kennen: Aflevering 1',
330 'uploader': 'SBS Broadcasting',
332 'skip': 'Restricted to Netherlands',
334 'skip_download': True, # m3u8 download
339 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
340 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
342 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
344 'title': '2cc213299525360.mov', # that's what we get
347 'add_ie': ['Ooyala'],
350 # ooyala video embedded with http://player.ooyala.com/iframe.js
351 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
353 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
355 'title': '"Steve Jobs: Man in the Machine" trailer',
356 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
360 'skip_download': True,
363 # multiple ooyala embeds on SBN network websites
365 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
367 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
368 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
370 'playlist_mincount': 3,
372 'skip_download': True,
374 'add_ie': ['Ooyala'],
378 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
382 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
383 'upload_date': '20140225',
384 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
385 'uploader': 'Tested',
386 'uploader_id': 'testedcom',
388 # No need to test YoutubeIE here
390 'skip_download': True,
395 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
399 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
400 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
405 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
409 'title': 'Охотское море стало целиком российским',
410 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
414 'skip_download': True,
419 '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/',
423 'title': 'Дошкольное воспитание',
428 'url': 'http://www.vestifinance.ru/articles/25753',
431 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
436 'title': 'Госзаказ. День 3',
442 'title': 'Госзаказ. День 2',
448 'title': 'Госзаказ. День 1',
454 'skip_download': True,
459 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
461 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
463 'title': 'Ужастики, русский трейлер (2015)',
464 'thumbnail': 're:^https?://.*\.jpg$',
470 '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',
473 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
475 'playlist_mincount': 7,
479 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
480 'md5': '65fdff94098e4a607385a60c5177c638',
484 'title': 'Hidden miracles of the natural world',
485 'uploader': 'Louie Schwartzberg',
486 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
489 # Embeded Ustream video
491 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
492 'md5': '27b99cdb639c9b12a79bca876a073417',
496 'uploader': 'AU SPA: The NSA and Privacy',
497 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
500 # nowvideo embed hidden behind percent encoding
502 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
503 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
505 'id': '06e53103ca9aa',
507 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
508 'description': 'No description',
513 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
514 'md5': '7653032cbb25bf6c80d80f217055fa43',
516 'id': '048195-004_PLUS7-F',
519 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
520 'upload_date': '20140320',
523 'skip_download': 'Requires rtmpdump'
528 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
532 'title': 'Alcaline, le concert avec Calogero',
533 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
534 'upload_date': '20150226',
535 'timestamp': 1424989860,
540 'skip_download': True,
542 'expected_warnings': [
548 'url': 'http://www.wired.com/2014/04/honda-asimo/',
549 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
551 'id': '53501be369702d3275860000',
553 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
558 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
559 'md5': '441aeeb82eb72c422c7f14ec533999cd',
561 'id': 'k2mm4bCdJ6CQ2i7c8o2',
563 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
566 'add_ie': ['Dailymotion'],
570 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
574 'title': 'The NBL Auction 2014',
575 'uploader': 'BADMINTON England',
576 'uploader_id': 'BADMINTONEvents',
577 'upload_date': '20140603',
578 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
580 'add_ie': ['Youtube'],
582 'skip_download': True,
587 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
588 'md5': '35727f82f58c76d996fc188f9755b0d5',
590 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
593 'description': 'Mario\'s life in the fast lane has never looked so good.',
596 # YouTube embed via <data-embed-url="">
598 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
602 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
603 'uploader': 'Gameloft',
604 'uploader_id': 'gameloft',
605 'upload_date': '20140828',
606 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
609 'skip_download': True,
614 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
616 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
618 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
619 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
624 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
626 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
627 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
633 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
638 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
639 'md5': '9d65602bf31c6e20014319c7d07fba27',
641 'id': '5123ea6d5e5a7',
644 'uploader': 'www.handjobhub.com',
645 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
648 # Multiple brightcove videos
649 # https://github.com/rg3/youtube-dl/issues/2283
651 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
653 'id': 'always-never',
654 'title': 'Always / Never - The New Yorker',
658 'extract_flat': False,
659 'skip_download': True,
664 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
665 'md5': '96f09a37e44da40dd083e12d9a683327',
669 'title': 'Ump changes call to ball',
670 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
672 'timestamp': 1401537900,
673 'upload_date': '20140531',
674 'thumbnail': 're:^https?://.*\.jpg$',
679 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
680 'md5': '8788b683c777a5cf25621eaf286d0c23',
684 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
686 'filesize': 182808282,
687 'uploader': 'education-portal.com',
691 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
692 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
696 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
698 'uploader': 'thoughtworks.wistia.com',
703 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
707 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
708 'uploader': 'Sophos Security',
709 'title': 'Chet Chat 171 - Oct 29, 2014',
710 'upload_date': '20141029',
715 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
719 'upload_date': '20141112',
720 'title': 'Rosetta #CometLanding webcast HL 10',
725 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
728 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
730 'playlist_mincount': 2,
734 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
738 'upload_date': '20141126',
739 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
744 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
746 'id': '730m_DandD_1901_512k',
748 'uploader': 'www.abc.net.au',
749 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
752 # embedded viddler video
754 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
758 'uploader': 'deadspin',
759 'title': 'WALL-TO-GORTAT',
760 'timestamp': 1422285291,
761 'upload_date': '20150126',
763 'add_ie': ['Viddler'],
767 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
771 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
772 'description': 'md5:601cb790edd05908957dae8aaa866465',
773 'upload_date': '20150220',
778 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
782 'upload_date': '20150212',
783 'uploader': 'The National Archives UK',
784 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
785 'uploader_id': 'NationalArchives08',
786 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
791 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
792 'playlist_mincount': 5,
794 'id': 'aanslagen-kopenhagen',
795 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
800 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
804 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
809 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
813 'upload_date': '20150226',
814 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
816 'title': 'John Carlson Postgame 2/25/15',
819 # Kaltura embed (different embed code)
821 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
825 'upload_date': '20150127',
826 'uploader_id': 'PremierMedia',
828 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
831 # Kaltura embed protected with referrer
833 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
837 'title': 'Violetta - Achter De Schermen - Ruggero',
838 'description': 'Achter de schermen met Ruggero',
839 'timestamp': 1435133761,
840 'upload_date': '20150624',
841 'uploader_id': 'echojecka',
844 # Eagle.Platform embed (generic URL)
846 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
850 'title': 'Навальный вышел на свободу',
851 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
852 'thumbnail': 're:^https?://.*\.jpg$',
858 # ClipYou (Eagle.Platform) embed (custom URL)
860 'url': 'http://muz-tv.ru/play/7129/',
864 'title': "'O Sole Mio",
865 'thumbnail': 're:^https?://.*\.jpg$',
872 'url': 'http://muz-tv.ru/kinozal/view/7400/',
876 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
877 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
878 'thumbnail': 're:^https?://.*\.jpg$',
885 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
889 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
890 'thumbnail': 're:^https?://.*\.png$',
896 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
897 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
901 'title': 'Facebook Creates "On This Day" | Crunch Report',
906 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
910 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
915 # Crooks and Liars embed
917 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
921 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
922 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
923 'timestamp': 1428207000,
924 'upload_date': '20150405',
925 'uploader': 'Heather',
928 # Crooks and Liars external embed
930 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
932 'id': 'MTE3MjUtMzQ2MzA',
934 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
935 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
936 'timestamp': 1265032391,
937 'upload_date': '20100201',
938 'uploader': 'Heather',
941 # NBC Sports vplayer embed
943 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
945 'id': 'ln7x1qSThw4k',
947 'title': "PFT Live: New leader in the 'new-look' defense",
948 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
953 'url': 'http://www.udn.com/news/story/7314/822787',
954 'md5': 'fd2060e988c326991037b9aff9df21a6',
958 'title': '中一中男師變性 全校師生力挺',
959 'thumbnail': 're:^https?://.*\.jpg$',
964 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
966 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
968 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
969 'title': 'This is what separates the Excel masters from the wannabes',
974 'skip_download': True,
977 # Contains a SMIL manifest
979 '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',
983 'title': '+ Football: Lottery Champions League Europe',
984 'uploader': 'www.telewebion.com',
988 'skip_download': True,
991 # Brightcove URL in single quotes
993 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
994 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
996 'id': '4255764656001',
998 'title': 'SN Presents: Russell Martin, World Citizen',
999 '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.',
1000 'uploader': 'Rogers Sportsnet',
1003 # Dailymotion Cloud video
1005 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1006 'md5': '49444254273501a64675a7e68c502681',
1008 'id': '5585de919473990de4bee11b',
1010 'title': 'Le débat',
1011 'thumbnail': 're:^https?://.*\.jpe?g$',
1014 # OnionStudios embed
1016 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1020 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1021 'thumbnail': 're:^https?://.*\.jpe?g$',
1022 'uploader': 'ClickHole',
1023 'uploader_id': 'clickhole',
1028 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1030 'id': '74849a00-85a9-11e1-9660-123139220831',
1032 'title': '#whilewewatch',
1035 # AdobeTVVideo embed
1037 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1038 'md5': '43662b577c018ad707a63766462b1e87',
1042 'title': 'New experience with Acrobat DC',
1043 'description': 'New experience with Acrobat DC',
1044 'duration': 248.667,
1047 # ScreenwaveMedia embed
1049 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1050 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1052 'id': 'cinemasnob-55d26273809dd',
1054 'title': 'cinemasnob',
1057 # BrightcoveInPageEmbed embed
1059 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1061 'id': '4238694884001',
1063 'title': 'Tabletop: Dread, Last Thoughts',
1064 'description': 'Tabletop: Dread, Last Thoughts',
1068 # JWPlayer with M3U8
1070 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1074 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1075 'uploader': 'ren.tv',
1079 'skip_download': True,
1084 def report_following_redirect(self, new_url):
1085 """Report information extraction."""
1086 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1088 def _extract_rss(self, url, video_id, doc):
1089 playlist_title = doc.find('./channel/title').text
1090 playlist_desc_el = doc.find('./channel/description')
1091 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1094 for it in doc.findall('./channel/item'):
1095 next_url = xpath_text(it, 'link', fatal=False)
1097 enclosure_nodes = it.findall('./enclosure')
1098 for e in enclosure_nodes:
1099 next_url = e.attrib.get('url')
1109 'title': it.find('title').text,
1113 '_type': 'playlist',
1115 'title': playlist_title,
1116 'description': playlist_desc,
1120 def _extract_camtasia(self, url, video_id, webpage):
1121 """ Returns None if no camtasia video can be found. """
1123 camtasia_cfg = self._search_regex(
1124 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1125 webpage, 'camtasia configuration file', default=None)
1126 if camtasia_cfg is None:
1129 title = self._html_search_meta('DC.title', webpage, fatal=True)
1131 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1132 camtasia_cfg = self._download_xml(
1133 camtasia_url, video_id,
1134 note='Downloading camtasia configuration',
1135 errnote='Failed to download camtasia configuration')
1136 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1139 for n in fileset_node.getchildren():
1140 url_n = n.find('./uri')
1145 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1146 'title': '%s - %s' % (title, n.tag),
1147 'url': compat_urlparse.urljoin(url, url_n.text),
1148 'duration': float_or_none(n.find('./duration').text),
1152 '_type': 'playlist',
1157 def _real_extract(self, url):
1158 if url.startswith('//'):
1161 'url': self.http_scheme() + url,
1164 parsed_url = compat_urlparse.urlparse(url)
1165 if not parsed_url.scheme:
1166 default_search = self._downloader.params.get('default_search')
1167 if default_search is None:
1168 default_search = 'fixup_error'
1170 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1172 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1173 return self.url_result('http://' + url)
1174 elif default_search != 'fixup_error':
1175 if default_search == 'auto_warning':
1176 if re.match(r'^(?:url|URL)$', url):
1177 raise ExtractorError(
1178 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1181 self._downloader.report_warning(
1182 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1183 return self.url_result('ytsearch:' + url)
1185 if default_search in ('error', 'fixup_error'):
1186 raise ExtractorError(
1187 '%r is not a valid URL. '
1188 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1189 % (url, url), expected=True)
1191 if ':' not in default_search:
1192 default_search += ':'
1193 return self.url_result(default_search + url)
1195 url, smuggled_data = unsmuggle_url(url)
1196 force_videoid = None
1197 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1198 if smuggled_data and 'force_videoid' in smuggled_data:
1199 force_videoid = smuggled_data['force_videoid']
1200 video_id = force_videoid
1202 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1204 self.to_screen('%s: Requesting header' % video_id)
1206 head_req = HEADRequest(url)
1207 head_response = self._request_webpage(
1209 note=False, errnote='Could not send HEAD request to %s' % url,
1212 if head_response is not False:
1213 # Check for redirect
1214 new_url = head_response.geturl()
1216 self.report_following_redirect(new_url)
1218 new_url = smuggle_url(
1219 new_url, {'force_videoid': force_videoid})
1220 return self.url_result(new_url)
1222 full_response = None
1223 if head_response is False:
1224 request = sanitized_Request(url)
1225 request.add_header('Accept-Encoding', '*')
1226 full_response = self._request_webpage(request, video_id)
1227 head_response = full_response
1229 # Check for direct link to a video
1230 content_type = head_response.headers.get('Content-Type', '')
1231 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1233 upload_date = unified_strdate(
1234 head_response.headers.get('Last-Modified'))
1237 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1240 'format_id': m.group('format_id'),
1242 'vcodec': 'none' if m.group('type') == 'audio' else None
1244 'upload_date': upload_date,
1247 if not self._downloader.params.get('test', False) and not is_intentional:
1248 force = self._downloader.params.get('force_generic_extractor', False)
1249 self._downloader.report_warning(
1250 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1252 if not full_response:
1253 request = sanitized_Request(url)
1254 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1255 # making it impossible to download only chunk of the file (yet we need only 512kB to
1256 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1257 # that will always result in downloading the whole file that is not desirable.
1258 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1259 # to accept raw bytes and being able to download only a chunk.
1260 # It may probably better to solve this by checking Content-Type for application/octet-stream
1261 # after HEAD request finishes, but not sure if we can rely on this.
1262 request.add_header('Accept-Encoding', '*')
1263 full_response = self._request_webpage(request, video_id)
1265 # Maybe it's a direct link to a video?
1266 # Be careful not to download the whole thing!
1267 first_bytes = full_response.read(512)
1268 if not is_html(first_bytes):
1269 self._downloader.report_warning(
1270 'URL could be a direct video link, returning it as such.')
1271 upload_date = unified_strdate(
1272 head_response.headers.get('Last-Modified'))
1275 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1278 'upload_date': upload_date,
1281 webpage = self._webpage_read_content(
1282 full_response, url, video_id, prefix=first_bytes)
1284 self.report_extraction(video_id)
1286 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1288 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1289 if doc.tag == 'rss':
1290 return self._extract_rss(url, video_id, doc)
1291 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1292 return self._parse_smil(doc, url, video_id)
1293 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1294 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1295 except compat_xml_parse_error:
1298 # Is it a Camtasia project?
1299 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1300 if camtasia_res is not None:
1303 # Sometimes embedded video player is hidden behind percent encoding
1304 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1305 # Unescaping the whole page allows to handle those cases in a generic way
1306 webpage = compat_urllib_parse_unquote(webpage)
1308 # it's tempting to parse this further, but you would
1309 # have to take into account all the variations like
1310 # Video Title - Site Name
1311 # Site Name | Video Title
1312 # Video Title - Tagline | Site Name
1313 # and so on and so forth; it's just not practical
1314 video_title = self._html_search_regex(
1315 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1318 # Try to detect age limit automatically
1319 age_limit = self._rta_search(webpage)
1320 # And then there are the jokers who advertise that they use RTA,
1321 # but actually don't.
1322 AGE_LIMIT_MARKERS = [
1323 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1325 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1328 # video uploader is domain name
1329 video_uploader = self._search_regex(
1330 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1333 def _playlist_from_matches(matches, getter=None, ie=None):
1335 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1337 return self.playlist_result(
1338 urlrs, playlist_id=video_id, playlist_title=video_title)
1340 # Look for Brightcove Legacy Studio embeds
1341 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1343 self.to_screen('Brightcove video detected.')
1346 'url': smuggle_url(bc_url, {'Referer': url}),
1347 'ie_key': 'BrightcoveLegacy'
1348 } for bc_url in bc_urls]
1351 '_type': 'playlist',
1352 'title': video_title,
1357 # Look for Brightcove New Studio embeds
1358 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1360 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1362 # Look for embedded rtl.nl player
1363 matches = re.findall(
1364 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1367 return _playlist_from_matches(matches, ie='RtlNl')
1369 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1370 if vimeo_url is not None:
1371 return self.url_result(vimeo_url)
1373 vid_me_embed_url = self._search_regex(
1374 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1375 webpage, 'vid.me embed', default=None)
1376 if vid_me_embed_url is not None:
1377 return self.url_result(vid_me_embed_url, 'Vidme')
1379 # Look for embedded YouTube player
1380 matches = re.findall(r'''(?x)
1389 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1393 return _playlist_from_matches(
1394 matches, lambda m: unescapeHTML(m[1]))
1396 # Look for lazyYT YouTube embed
1397 matches = re.findall(
1398 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1400 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1402 # Look for embedded Dailymotion player
1403 matches = re.findall(
1404 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1406 return _playlist_from_matches(
1407 matches, lambda m: unescapeHTML(m[1]))
1409 # Look for embedded Dailymotion playlist player (#3822)
1411 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1413 playlists = re.findall(
1414 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1416 return _playlist_from_matches(
1417 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1419 # Look for embedded Wistia player
1421 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1423 embed_url = self._proto_relative_url(
1424 unescapeHTML(match.group('url')))
1426 '_type': 'url_transparent',
1429 'uploader': video_uploader,
1430 'title': video_title,
1434 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1437 '_type': 'url_transparent',
1438 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1440 'uploader': video_uploader,
1441 'title': video_title,
1442 'id': match.group('id')
1445 # Look for SVT player
1446 svt_url = SVTIE._extract_url(webpage)
1448 return self.url_result(svt_url, 'SVT')
1450 # Look for embedded condenast player
1451 matches = re.findall(
1452 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1456 '_type': 'playlist',
1459 'ie_key': 'CondeNast',
1461 } for ma in matches],
1462 'title': video_title,
1466 # Look for Bandcamp pages with custom domain
1467 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1468 if mobj is not None:
1469 burl = unescapeHTML(mobj.group(1))
1470 # Don't set the extractor because it can be a track url or an album
1471 return self.url_result(burl)
1473 # Look for embedded Vevo player
1475 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1476 if mobj is not None:
1477 return self.url_result(mobj.group('url'))
1479 # Look for embedded Viddler player
1481 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1483 if mobj is not None:
1484 return self.url_result(mobj.group('url'))
1486 # Look for NYTimes player
1488 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1490 if mobj is not None:
1491 return self.url_result(mobj.group('url'))
1493 # Look for Libsyn player
1495 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1496 if mobj is not None:
1497 return self.url_result(mobj.group('url'))
1499 # Look for Ooyala videos
1500 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1501 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1502 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1503 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1504 if mobj is not None:
1505 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1507 # Look for multiple Ooyala embeds on SBN network websites
1508 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1509 if mobj is not None:
1510 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1512 return _playlist_from_matches(
1513 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1515 # Look for Aparat videos
1516 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1517 if mobj is not None:
1518 return self.url_result(mobj.group(1), 'Aparat')
1520 # Look for MPORA videos
1521 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1522 if mobj is not None:
1523 return self.url_result(mobj.group(1), 'Mpora')
1525 # Look for embedded NovaMov-based player
1527 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1528 (?P<url>http://(?:(?:embed|www)\.)?
1530 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1531 videoweed\.(?:es|com)|
1532 movshare\.(?:net|sx|ag)|
1533 divxstage\.(?:eu|net|ch|co|at|ag))
1534 /embed\.php.+?)\1''', webpage)
1535 if mobj is not None:
1536 return self.url_result(mobj.group('url'))
1538 # Look for embedded Facebook player
1540 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1541 if mobj is not None:
1542 return self.url_result(mobj.group('url'), 'Facebook')
1544 # Look for embedded VK player
1545 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1546 if mobj is not None:
1547 return self.url_result(mobj.group('url'), 'VK')
1549 # Look for embedded ivi player
1550 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1551 if mobj is not None:
1552 return self.url_result(mobj.group('url'), 'Ivi')
1554 # Look for embedded Huffington Post player
1556 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1557 if mobj is not None:
1558 return self.url_result(mobj.group('url'), 'HuffPost')
1561 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1562 if mobj is not None:
1563 return self.url_result(mobj.group('url'))
1564 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1565 if mobj is not None:
1566 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1568 # Look for funnyordie embed
1569 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1571 return _playlist_from_matches(
1572 matches, getter=unescapeHTML, ie='FunnyOrDie')
1574 # Look for BBC iPlayer embed
1575 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1577 return _playlist_from_matches(matches, ie='BBCCoUk')
1579 # Look for embedded RUTV player
1580 rutv_url = RUTVIE._extract_url(webpage)
1582 return self.url_result(rutv_url, 'RUTV')
1584 # Look for embedded TVC player
1585 tvc_url = TVCIE._extract_url(webpage)
1587 return self.url_result(tvc_url, 'TVC')
1589 # Look for embedded SportBox player
1590 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1592 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1594 # Look for embedded PornHub player
1595 pornhub_url = PornHubIE._extract_url(webpage)
1597 return self.url_result(pornhub_url, 'PornHub')
1599 # Look for embedded XHamster player
1600 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1602 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1604 # Look for embedded Tvigle player
1606 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1607 if mobj is not None:
1608 return self.url_result(mobj.group('url'), 'Tvigle')
1610 # Look for embedded TED player
1612 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1613 if mobj is not None:
1614 return self.url_result(mobj.group('url'), 'TED')
1616 # Look for embedded Ustream videos
1618 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1619 if mobj is not None:
1620 return self.url_result(mobj.group('url'), 'Ustream')
1622 # Look for embedded arte.tv player
1624 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1626 if mobj is not None:
1627 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1629 # Look for embedded francetv player
1631 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1633 if mobj is not None:
1634 return self.url_result(mobj.group('url'))
1636 # Look for embedded smotri.com player
1637 smotri_url = SmotriIE._extract_url(webpage)
1639 return self.url_result(smotri_url, 'Smotri')
1641 # Look for embedded Myvi.ru player
1642 myvi_url = MyviIE._extract_url(webpage)
1644 return self.url_result(myvi_url)
1646 # Look for embeded soundcloud player
1648 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1650 if mobj is not None:
1651 url = unescapeHTML(mobj.group('url'))
1652 return self.url_result(url)
1654 # Look for embedded vulture.com player
1656 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1658 if mobj is not None:
1659 url = unescapeHTML(mobj.group('url'))
1660 return self.url_result(url, ie='Vulture')
1662 # Look for embedded mtvservices player
1663 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1665 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1667 # Look for embedded yahoo player
1669 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1671 if mobj is not None:
1672 return self.url_result(mobj.group('url'), 'Yahoo')
1674 # Look for embedded sbs.com.au player
1678 <meta\s+property="og:video"\s+content=|
1681 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'), 'SBS')
1686 # Look for embedded Cinchcast player
1688 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1690 if mobj is not None:
1691 return self.url_result(mobj.group('url'), 'Cinchcast')
1694 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1698 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1700 if mobj is not None:
1701 return self.url_result(mobj.group('url'), 'MLB')
1704 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1706 if mobj is not None:
1707 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1710 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1712 if mobj is not None:
1713 return self.url_result(mobj.group('url'), 'Livestream')
1715 # Look for Zapiks embed
1717 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1718 if mobj is not None:
1719 return self.url_result(mobj.group('url'), 'Zapiks')
1721 # Look for Kaltura embeds
1722 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1723 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1724 if mobj is not None:
1725 return self.url_result(smuggle_url(
1726 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1727 {'source_url': url}), 'Kaltura')
1729 # Look for Eagle.Platform embeds
1731 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1732 if mobj is not None:
1733 return self.url_result(mobj.group('url'), 'EaglePlatform')
1735 # Look for ClipYou (uses Eagle.Platform) embeds
1737 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1738 if mobj is not None:
1739 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1741 # Look for Pladform embeds
1742 pladform_url = PladformIE._extract_url(webpage)
1744 return self.url_result(pladform_url)
1746 # Look for Playwire embeds
1748 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1749 if mobj is not None:
1750 return self.url_result(mobj.group('url'))
1752 # Look for 5min embeds
1754 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1755 if mobj is not None:
1756 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1758 # Look for Crooks and Liars embeds
1760 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1761 if mobj is not None:
1762 return self.url_result(mobj.group('url'))
1764 # Look for NBC Sports VPlayer embeds
1765 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1767 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1769 # Look for Google Drive embeds
1770 google_drive_url = GoogleDriveIE._extract_url(webpage)
1771 if google_drive_url:
1772 return self.url_result(google_drive_url, 'GoogleDrive')
1774 # Look for UDN embeds
1776 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1777 if mobj is not None:
1778 return self.url_result(
1779 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1781 # Look for Senate ISVP iframe
1782 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1784 return self.url_result(senate_isvp_url, 'SenateISVP')
1786 # Look for Dailymotion Cloud videos
1787 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1789 return self.url_result(dmcloud_url, 'DailymotionCloud')
1791 # Look for OnionStudios embeds
1792 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1793 if onionstudios_url:
1794 return self.url_result(onionstudios_url)
1796 # Look for SnagFilms embeds
1797 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1799 return self.url_result(snagfilms_url)
1801 # Look for JWPlatform embeds
1802 jwplatform_url = JWPlatformIE._extract_url(webpage)
1804 return self.url_result(jwplatform_url, 'JWPlatform')
1806 # Look for ScreenwaveMedia embeds
1807 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1808 if mobj is not None:
1809 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1811 # Look for Ulltimedia embeds
1812 ultimedia_url = UltimediaIE._extract_url(webpage)
1814 return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia')
1816 # Look for AdobeTVVideo embeds
1818 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1820 if mobj is not None:
1821 return self.url_result(
1822 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1825 def check_video(vurl):
1826 if YoutubeIE.suitable(vurl):
1828 vpath = compat_urlparse.urlparse(vurl).path
1829 vext = determine_ext(vpath)
1830 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1832 def filter_video(urls):
1833 return list(filter(check_video, urls))
1835 # Start with something easy: JW Player in SWFObject
1836 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1838 # Look for gorilla-vid style embedding
1839 found = filter_video(re.findall(r'''(?sx)
1843 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1846 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1848 # Broaden the search a little bit
1849 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1851 # Broaden the findall a little bit: JWPlayer JS loader
1852 found = filter_video(re.findall(
1853 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1856 found = filter_video(re.findall(r'''(?xs)
1857 flowplayer\("[^"]+",\s*
1859 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1860 ["']?url["']?\s*:\s*["']([^"']+)["']
1865 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1867 # Try to find twitter cards info
1868 found = filter_video(re.findall(
1869 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1871 # We look for Open Graph info:
1872 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1873 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1874 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1875 if m_video_type is not None:
1876 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1879 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1881 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1883 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1884 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1887 # Look also in Refresh HTTP header
1888 refresh_header = head_response.headers.get('Refresh')
1890 # In python 2 response HTTP headers are bytestrings
1891 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1892 refresh_header = refresh_header.decode('iso-8859-1')
1893 found = re.search(REDIRECT_REGEX, refresh_header)
1895 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1896 self.report_following_redirect(new_url)
1902 raise UnsupportedError(url)
1905 for video_url in found:
1906 video_url = video_url.replace('\\/', '/')
1907 video_url = compat_urlparse.urljoin(url, video_url)
1908 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1910 # Sometimes, jwplayer extraction will result in a YouTube URL
1911 if YoutubeIE.suitable(video_url):
1912 entries.append(self.url_result(video_url, 'Youtube'))
1915 # here's a fun little line of code for you:
1916 video_id = os.path.splitext(video_id)[0]
1920 'uploader': video_uploader,
1921 'title': video_title,
1922 'age_limit': age_limit,
1925 ext = determine_ext(video_url)
1927 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1929 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1931 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1933 entry_info_dict['url'] = video_url
1935 entries.append(entry_info_dict)
1937 if len(entries) == 1:
1940 for num, e in enumerate(entries, start=1):
1941 # 'url' results don't have a title
1942 if e.get('title') is not None:
1943 e['title'] = '%s (%d)' % (e['title'], num)
1945 '_type': 'playlist',