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,
14 compat_urllib_request,
16 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 .bliptv import BlipTVIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .snagfilms import SnagFilmsEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
59 class GenericIE(InfoExtractor):
60 IE_DESC = 'Generic downloader that works on some sites'
64 # Direct link to a video
66 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
67 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
72 'upload_date': '20100513',
75 # Direct link to media delivered compressed (until Accept-Encoding is *)
77 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
78 'md5': '128c42e68b13950268b648275386fc74',
80 'id': 'FictionJunction-Parallel_Hearts',
82 'title': 'FictionJunction-Parallel_Hearts',
83 'upload_date': '20140522',
85 'expected_warnings': [
86 'URL could be a direct video link, returning it as such.'
89 # Direct download with broken HEAD
91 'url': 'http://ai-radio.org:8000/radio.opus',
98 'skip_download': True, # infinite live stream
100 'expected_warnings': [
101 r'501.*Not Implemented'
104 # Direct link with incorrect MIME type
106 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
107 'md5': '4ccbebe5f36706d85221f204d7eb5913',
109 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
110 'id': '5_Lennart_Poettering_-_Systemd',
112 'title': '5_Lennart_Poettering_-_Systemd',
113 'upload_date': '20141120',
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
121 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
123 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
124 'title': 'Zero Punctuation',
125 'description': 're:.*groundbreaking video review series.*'
127 'playlist_mincount': 11,
129 # RSS feed with enclosure
131 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
133 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 'upload_date': '20150228',
136 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
139 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
141 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
145 'title': 'Automatics, robotics and biocybernetics',
146 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
147 'upload_date': '20130627',
148 'formats': 'mincount:16',
149 'subtitles': 'mincount:1',
152 'force_generic_extractor': True,
153 'skip_download': True,
156 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
158 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
163 'formats': 'mincount:1',
166 'skip_download': True,
169 # SMIL from https://www.restudy.dk/video/play/id/1637
171 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
175 'title': 'video_1637',
176 'formats': 'mincount:3',
179 'skip_download': True,
182 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
184 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
186 'id': 'smil-service',
188 'title': 'smil-service',
189 'formats': 'mincount:1',
192 'skip_download': True,
195 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
197 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
201 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
202 'formats': 'mincount:3',
205 'skip_download': True,
208 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
210 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
212 'id': 'mZlp2ctYIUEB',
214 'title': 'Tikibad ontruimd wegens brand',
215 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
216 'thumbnail': 're:^https?://.*\.jpg$',
220 'skip_download': True,
225 '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',
229 'upload_date': '20130224',
230 'uploader_id': 'TheVerge',
231 'description': 're:^Chris Ziegler takes a look at the\.*',
232 'uploader': 'The Verge',
233 'title': 'First Firefox OS phones side-by-side',
236 'skip_download': False,
240 # redirect in Refresh HTTP header
241 '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',
245 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
246 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
247 'upload_date': '20150917',
248 'uploader_id': 'brtvofficial',
249 'uploader': 'Boiler Room',
252 'skip_download': False,
256 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
257 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
259 'id': '13601338388002',
261 'uploader': 'www.hodiho.fr',
262 'title': 'R\u00e9gis plante sa Jeep',
265 # bandcamp page with custom domain
267 'add_ie': ['Bandcamp'],
268 'url': 'http://bronyrock.com/track/the-pony-mash',
272 'title': 'The Pony Mash',
273 'uploader': 'M_Pallante',
275 'skip': 'There is a limit of 200 free downloads / month for the test song',
277 # embedded brightcove video
278 # it also tests brightcove videos that need to set the 'Referer' in the
281 'add_ie': ['BrightcoveLegacy'],
282 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
284 'id': '2765128793001',
286 'title': 'Le cours de bourse : l’analyse technique',
287 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
288 'uploader': 'BFM BUSINESS',
291 'skip_download': True,
295 # https://github.com/rg3/youtube-dl/issues/2253
296 'url': 'http://bcove.me/i6nfkrc3',
297 'md5': '0ba9446db037002366bab3b3eb30c88c',
299 'id': '3101154703001',
301 'title': 'Still no power',
302 'uploader': 'thestar.com',
303 '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.',
305 'add_ie': ['BrightcoveLegacy'],
308 'url': 'http://www.championat.com/video/football/v/87/87499.html',
309 'md5': 'fb973ecf6e4a78a67453647444222983',
311 'id': '3414141473001',
313 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
314 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
315 'uploader': 'Championat',
319 # https://github.com/rg3/youtube-dl/issues/3541
320 'add_ie': ['BrightcoveLegacy'],
321 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
323 'id': '3866516442001',
325 'title': 'Leer mij vrouwen kennen: Aflevering 1',
326 'description': 'Leer mij vrouwen kennen: Aflevering 1',
327 'uploader': 'SBS Broadcasting',
329 'skip': 'Restricted to Netherlands',
331 'skip_download': True, # m3u8 download
336 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
337 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
339 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
341 'title': '2cc213299525360.mov', # that's what we get
343 'add_ie': ['Ooyala'],
346 # ooyala video embedded with http://player.ooyala.com/iframe.js
347 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
349 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
351 'title': '"Steve Jobs: Man in the Machine" trailer',
352 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
355 'skip_download': True,
358 # multiple ooyala embeds on SBN network websites
360 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
362 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
363 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
365 'playlist_mincount': 3,
367 'skip_download': True,
369 'add_ie': ['Ooyala'],
373 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
377 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
378 'upload_date': '20140225',
379 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
380 'uploader': 'Tested',
381 'uploader_id': 'testedcom',
383 # No need to test YoutubeIE here
385 'skip_download': True,
390 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
394 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
395 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
400 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
404 'title': 'Охотское море стало целиком российским',
405 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
409 'skip_download': True,
414 '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/',
418 'title': 'Дошкольное воспитание',
423 'url': 'http://www.vestifinance.ru/articles/25753',
426 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
431 'title': 'Госзаказ. День 3',
437 'title': 'Госзаказ. День 2',
443 'title': 'Госзаказ. День 1',
449 'skip_download': True,
454 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
456 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
458 'title': 'Ужастики, русский трейлер (2015)',
459 'thumbnail': 're:^https?://.*\.jpg$',
465 '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',
468 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
470 'playlist_mincount': 7,
474 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
475 'md5': '65fdff94098e4a607385a60c5177c638',
479 'title': 'Hidden miracles of the natural world',
480 'uploader': 'Louie Schwartzberg',
481 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
484 # Embeded Ustream video
486 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
487 'md5': '27b99cdb639c9b12a79bca876a073417',
491 'uploader': 'AU SPA: The NSA and Privacy',
492 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
495 # nowvideo embed hidden behind percent encoding
497 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
498 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
500 'id': '06e53103ca9aa',
502 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
503 'description': 'No description',
508 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
509 'md5': '7653032cbb25bf6c80d80f217055fa43',
511 'id': '048195-004_PLUS7-F',
514 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
515 'upload_date': '20140320',
518 'skip_download': 'Requires rtmpdump'
523 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
527 'title': 'Alcaline, le concert avec Calogero',
528 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
529 'upload_date': '20150226',
530 'timestamp': 1424989860,
535 'skip_download': True,
537 'expected_warnings': [
543 'url': 'http://www.wired.com/2014/04/honda-asimo/',
544 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
546 'id': '53501be369702d3275860000',
548 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
553 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
554 'md5': '441aeeb82eb72c422c7f14ec533999cd',
556 'id': 'k2mm4bCdJ6CQ2i7c8o2',
558 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
561 'add_ie': ['Dailymotion'],
565 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
569 'title': 'The NBL Auction 2014',
570 'uploader': 'BADMINTON England',
571 'uploader_id': 'BADMINTONEvents',
572 'upload_date': '20140603',
573 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
575 'add_ie': ['Youtube'],
577 'skip_download': True,
582 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
583 'md5': '35727f82f58c76d996fc188f9755b0d5',
585 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
588 'description': 'Mario\'s life in the fast lane has never looked so good.',
591 # YouTube embed via <data-embed-url="">
593 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
597 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
598 'uploader': 'Gameloft',
599 'uploader_id': 'gameloft',
600 'upload_date': '20140828',
601 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
604 'skip_download': True,
609 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
611 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
613 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
614 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
619 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
621 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
622 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
628 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
633 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
634 'md5': '9d65602bf31c6e20014319c7d07fba27',
636 'id': '5123ea6d5e5a7',
639 'uploader': 'www.handjobhub.com',
640 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
643 # Multiple brightcove videos
644 # https://github.com/rg3/youtube-dl/issues/2283
646 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
648 'id': 'always-never',
649 'title': 'Always / Never - The New Yorker',
653 'extract_flat': False,
654 'skip_download': True,
659 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
660 'md5': '96f09a37e44da40dd083e12d9a683327',
664 'title': 'Ump changes call to ball',
665 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
667 'timestamp': 1401537900,
668 'upload_date': '20140531',
669 'thumbnail': 're:^https?://.*\.jpg$',
674 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
675 'md5': '8788b683c777a5cf25621eaf286d0c23',
679 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
681 'filesize': 182808282,
682 'uploader': 'education-portal.com',
686 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
687 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
691 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
693 'uploader': 'thoughtworks.wistia.com',
698 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
702 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
703 'uploader': 'Sophos Security',
704 'title': 'Chet Chat 171 - Oct 29, 2014',
705 'upload_date': '20141029',
710 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
714 'upload_date': '20141112',
715 'title': 'Rosetta #CometLanding webcast HL 10',
720 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
723 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
725 'playlist_mincount': 2,
729 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
733 'upload_date': '20141126',
734 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
739 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
741 'id': '730m_DandD_1901_512k',
743 'uploader': 'www.abc.net.au',
744 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
747 # embedded viddler video
749 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
753 'uploader': 'deadspin',
754 'title': 'WALL-TO-GORTAT',
755 'timestamp': 1422285291,
756 'upload_date': '20150126',
758 'add_ie': ['Viddler'],
762 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
766 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
767 'description': 'md5:601cb790edd05908957dae8aaa866465',
768 'upload_date': '20150220',
773 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
777 'upload_date': '20150212',
778 'uploader': 'The National Archives UK',
779 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
780 'uploader_id': 'NationalArchives08',
781 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
786 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
787 'playlist_mincount': 5,
789 'id': 'aanslagen-kopenhagen',
790 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
795 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
799 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
804 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
808 'upload_date': '20150226',
809 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
811 'title': 'John Carlson Postgame 2/25/15',
814 # Kaltura embed (different embed code)
816 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
820 'upload_date': '20150127',
821 'uploader_id': 'PremierMedia',
823 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
826 # Kaltura embed protected with referrer
828 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
832 'title': 'Violetta - Achter De Schermen - Ruggero',
833 'description': 'Achter de schermen met Ruggero',
834 'timestamp': 1435133761,
835 'upload_date': '20150624',
836 'uploader_id': 'echojecka',
839 # Eagle.Platform embed (generic URL)
841 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
845 'title': 'Навальный вышел на свободу',
846 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
847 'thumbnail': 're:^https?://.*\.jpg$',
853 # ClipYou (Eagle.Platform) embed (custom URL)
855 'url': 'http://muz-tv.ru/play/7129/',
859 'title': "'O Sole Mio",
860 'thumbnail': 're:^https?://.*\.jpg$',
867 'url': 'http://muz-tv.ru/kinozal/view/7400/',
871 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
872 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
873 'thumbnail': 're:^https?://.*\.jpg$',
880 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
884 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
885 'thumbnail': 're:^https?://.*\.png$',
891 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
892 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
896 'title': 'Facebook Creates "On This Day" | Crunch Report',
901 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
905 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
910 # Crooks and Liars embed
912 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
916 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
917 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
918 'timestamp': 1428207000,
919 'upload_date': '20150405',
920 'uploader': 'Heather',
923 # Crooks and Liars external embed
925 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
927 'id': 'MTE3MjUtMzQ2MzA',
929 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
930 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
931 'timestamp': 1265032391,
932 'upload_date': '20100201',
933 'uploader': 'Heather',
936 # NBC Sports vplayer embed
938 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
940 'id': 'ln7x1qSThw4k',
942 'title': "PFT Live: New leader in the 'new-look' defense",
943 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
948 'url': 'http://www.udn.com/news/story/7314/822787',
949 'md5': 'fd2060e988c326991037b9aff9df21a6',
953 'title': '中一中男師變性 全校師生力挺',
954 'thumbnail': 're:^https?://.*\.jpg$',
959 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
961 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
963 'description': 'VIDEO: Index/Match versus VLOOKUP.',
964 'title': 'This is what separates the Excel masters from the wannabes',
968 'skip_download': True,
971 # Contains a SMIL manifest
973 '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',
977 'title': '+ Football: Lottery Champions League Europe',
978 'uploader': 'www.telewebion.com',
982 'skip_download': True,
985 # Brightcove URL in single quotes
987 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
988 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
990 'id': '4255764656001',
992 'title': 'SN Presents: Russell Martin, World Citizen',
993 '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.',
994 'uploader': 'Rogers Sportsnet',
997 # Dailymotion Cloud video
999 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1000 'md5': '49444254273501a64675a7e68c502681',
1002 'id': '5585de919473990de4bee11b',
1004 'title': 'Le débat',
1005 'thumbnail': 're:^https?://.*\.jpe?g$',
1008 # OnionStudios embed
1010 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1014 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1015 'thumbnail': 're:^https?://.*\.jpe?g$',
1016 'uploader': 'ClickHole',
1017 'uploader_id': 'clickhole',
1022 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1024 'id': '74849a00-85a9-11e1-9660-123139220831',
1026 'title': '#whilewewatch',
1029 # AdobeTVVideo embed
1031 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1032 'md5': '43662b577c018ad707a63766462b1e87',
1036 'title': 'New experience with Acrobat DC',
1037 'description': 'New experience with Acrobat DC',
1038 'duration': 248.667,
1041 # ScreenwaveMedia embed
1043 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1044 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1046 'id': 'cinemasnob-55d26273809dd',
1048 'title': 'cinemasnob',
1051 # BrightcoveInPageEmbed embed
1053 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1055 'id': '4238694884001',
1057 'title': 'Tabletop: Dread, Last Thoughts',
1058 'description': 'Tabletop: Dread, Last Thoughts',
1064 def report_following_redirect(self, new_url):
1065 """Report information extraction."""
1066 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1068 def _extract_rss(self, url, video_id, doc):
1069 playlist_title = doc.find('./channel/title').text
1070 playlist_desc_el = doc.find('./channel/description')
1071 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1074 for it in doc.findall('./channel/item'):
1075 next_url = xpath_text(it, 'link', fatal=False)
1077 enclosure_nodes = it.findall('./enclosure')
1078 for e in enclosure_nodes:
1079 next_url = e.attrib.get('url')
1089 'title': it.find('title').text,
1093 '_type': 'playlist',
1095 'title': playlist_title,
1096 'description': playlist_desc,
1100 def _extract_camtasia(self, url, video_id, webpage):
1101 """ Returns None if no camtasia video can be found. """
1103 camtasia_cfg = self._search_regex(
1104 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1105 webpage, 'camtasia configuration file', default=None)
1106 if camtasia_cfg is None:
1109 title = self._html_search_meta('DC.title', webpage, fatal=True)
1111 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1112 camtasia_cfg = self._download_xml(
1113 camtasia_url, video_id,
1114 note='Downloading camtasia configuration',
1115 errnote='Failed to download camtasia configuration')
1116 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1119 for n in fileset_node.getchildren():
1120 url_n = n.find('./uri')
1125 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1126 'title': '%s - %s' % (title, n.tag),
1127 'url': compat_urlparse.urljoin(url, url_n.text),
1128 'duration': float_or_none(n.find('./duration').text),
1132 '_type': 'playlist',
1137 def _real_extract(self, url):
1138 if url.startswith('//'):
1141 'url': self.http_scheme() + url,
1144 parsed_url = compat_urlparse.urlparse(url)
1145 if not parsed_url.scheme:
1146 default_search = self._downloader.params.get('default_search')
1147 if default_search is None:
1148 default_search = 'fixup_error'
1150 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1152 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1153 return self.url_result('http://' + url)
1154 elif default_search != 'fixup_error':
1155 if default_search == 'auto_warning':
1156 if re.match(r'^(?:url|URL)$', url):
1157 raise ExtractorError(
1158 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1161 self._downloader.report_warning(
1162 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1163 return self.url_result('ytsearch:' + url)
1165 if default_search in ('error', 'fixup_error'):
1166 raise ExtractorError(
1167 '%r is not a valid URL. '
1168 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1169 % (url, url), expected=True)
1171 if ':' not in default_search:
1172 default_search += ':'
1173 return self.url_result(default_search + url)
1175 url, smuggled_data = unsmuggle_url(url)
1176 force_videoid = None
1177 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1178 if smuggled_data and 'force_videoid' in smuggled_data:
1179 force_videoid = smuggled_data['force_videoid']
1180 video_id = force_videoid
1182 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1184 self.to_screen('%s: Requesting header' % video_id)
1186 head_req = HEADRequest(url)
1187 head_response = self._request_webpage(
1189 note=False, errnote='Could not send HEAD request to %s' % url,
1192 if head_response is not False:
1193 # Check for redirect
1194 new_url = head_response.geturl()
1196 self.report_following_redirect(new_url)
1198 new_url = smuggle_url(
1199 new_url, {'force_videoid': force_videoid})
1200 return self.url_result(new_url)
1202 full_response = None
1203 if head_response is False:
1204 request = compat_urllib_request.Request(url)
1205 request.add_header('Accept-Encoding', '*')
1206 full_response = self._request_webpage(request, video_id)
1207 head_response = full_response
1209 # Check for direct link to a video
1210 content_type = head_response.headers.get('Content-Type', '')
1211 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1213 upload_date = unified_strdate(
1214 head_response.headers.get('Last-Modified'))
1217 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1220 'format_id': m.group('format_id'),
1222 'vcodec': 'none' if m.group('type') == 'audio' else None
1224 'upload_date': upload_date,
1227 if not self._downloader.params.get('test', False) and not is_intentional:
1228 force = self._downloader.params.get('force_generic_extractor', False)
1229 self._downloader.report_warning(
1230 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1232 if not full_response:
1233 request = compat_urllib_request.Request(url)
1234 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1235 # making it impossible to download only chunk of the file (yet we need only 512kB to
1236 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1237 # that will always result in downloading the whole file that is not desirable.
1238 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1239 # to accept raw bytes and being able to download only a chunk.
1240 # It may probably better to solve this by checking Content-Type for application/octet-stream
1241 # after HEAD request finishes, but not sure if we can rely on this.
1242 request.add_header('Accept-Encoding', '*')
1243 full_response = self._request_webpage(request, video_id)
1245 # Maybe it's a direct link to a video?
1246 # Be careful not to download the whole thing!
1247 first_bytes = full_response.read(512)
1248 if not is_html(first_bytes):
1249 self._downloader.report_warning(
1250 'URL could be a direct video link, returning it as such.')
1251 upload_date = unified_strdate(
1252 head_response.headers.get('Last-Modified'))
1255 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1258 'upload_date': upload_date,
1261 webpage = self._webpage_read_content(
1262 full_response, url, video_id, prefix=first_bytes)
1264 self.report_extraction(video_id)
1266 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1268 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1269 if doc.tag == 'rss':
1270 return self._extract_rss(url, video_id, doc)
1271 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1272 return self._parse_smil(doc, url, video_id)
1273 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1274 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1275 except compat_xml_parse_error:
1278 # Is it a Camtasia project?
1279 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1280 if camtasia_res is not None:
1283 # Sometimes embedded video player is hidden behind percent encoding
1284 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1285 # Unescaping the whole page allows to handle those cases in a generic way
1286 webpage = compat_urllib_parse_unquote(webpage)
1288 # it's tempting to parse this further, but you would
1289 # have to take into account all the variations like
1290 # Video Title - Site Name
1291 # Site Name | Video Title
1292 # Video Title - Tagline | Site Name
1293 # and so on and so forth; it's just not practical
1294 video_title = self._html_search_regex(
1295 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1298 # Try to detect age limit automatically
1299 age_limit = self._rta_search(webpage)
1300 # And then there are the jokers who advertise that they use RTA,
1301 # but actually don't.
1302 AGE_LIMIT_MARKERS = [
1303 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1305 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1308 # video uploader is domain name
1309 video_uploader = self._search_regex(
1310 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1313 def _playlist_from_matches(matches, getter=None, ie=None):
1315 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1317 return self.playlist_result(
1318 urlrs, playlist_id=video_id, playlist_title=video_title)
1320 # Look for Brightcove Legacy Studio embeds
1321 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1323 self.to_screen('Brightcove video detected.')
1326 'url': smuggle_url(bc_url, {'Referer': url}),
1327 'ie_key': 'BrightcoveLegacy'
1328 } for bc_url in bc_urls]
1331 '_type': 'playlist',
1332 'title': video_title,
1337 # Look for Brightcove New Studio embeds
1338 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1340 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1342 # Look for embedded rtl.nl player
1343 matches = re.findall(
1344 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1347 return _playlist_from_matches(matches, ie='RtlNl')
1349 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1350 if vimeo_url is not None:
1351 return self.url_result(vimeo_url)
1353 vid_me_embed_url = self._search_regex(
1354 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1355 webpage, 'vid.me embed', default=None)
1356 if vid_me_embed_url is not None:
1357 return self.url_result(vid_me_embed_url, 'Vidme')
1359 # Look for embedded YouTube player
1360 matches = re.findall(r'''(?x)
1369 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1373 return _playlist_from_matches(
1374 matches, lambda m: unescapeHTML(m[1]))
1376 # Look for lazyYT YouTube embed
1377 matches = re.findall(
1378 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1380 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1382 # Look for embedded Dailymotion player
1383 matches = re.findall(
1384 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1386 return _playlist_from_matches(
1387 matches, lambda m: unescapeHTML(m[1]))
1389 # Look for embedded Dailymotion playlist player (#3822)
1391 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1393 playlists = re.findall(
1394 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1396 return _playlist_from_matches(
1397 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1399 # Look for embedded Wistia player
1401 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1403 embed_url = self._proto_relative_url(
1404 unescapeHTML(match.group('url')))
1406 '_type': 'url_transparent',
1409 'uploader': video_uploader,
1410 'title': video_title,
1414 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1417 '_type': 'url_transparent',
1418 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1420 'uploader': video_uploader,
1421 'title': video_title,
1422 'id': match.group('id')
1425 # Look for embedded blip.tv player
1426 bliptv_url = BlipTVIE._extract_url(webpage)
1428 return self.url_result(bliptv_url, 'BlipTV')
1430 # Look for SVT player
1431 svt_url = SVTIE._extract_url(webpage)
1433 return self.url_result(svt_url, 'SVT')
1435 # Look for embedded condenast player
1436 matches = re.findall(
1437 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1441 '_type': 'playlist',
1444 'ie_key': 'CondeNast',
1446 } for ma in matches],
1447 'title': video_title,
1451 # Look for Bandcamp pages with custom domain
1452 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1453 if mobj is not None:
1454 burl = unescapeHTML(mobj.group(1))
1455 # Don't set the extractor because it can be a track url or an album
1456 return self.url_result(burl)
1458 # Look for embedded Vevo player
1460 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1461 if mobj is not None:
1462 return self.url_result(mobj.group('url'))
1464 # Look for embedded Viddler player
1466 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1468 if mobj is not None:
1469 return self.url_result(mobj.group('url'))
1471 # Look for NYTimes player
1473 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1475 if mobj is not None:
1476 return self.url_result(mobj.group('url'))
1478 # Look for Libsyn player
1480 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1481 if mobj is not None:
1482 return self.url_result(mobj.group('url'))
1484 # Look for Ooyala videos
1485 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1486 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1487 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1488 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1489 if mobj is not None:
1490 return OoyalaIE._build_url_result(mobj.group('ec'))
1492 # Look for multiple Ooyala embeds on SBN network websites
1493 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1494 if mobj is not None:
1495 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1497 return _playlist_from_matches(
1498 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1500 # Look for Aparat videos
1501 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1502 if mobj is not None:
1503 return self.url_result(mobj.group(1), 'Aparat')
1505 # Look for MPORA videos
1506 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1507 if mobj is not None:
1508 return self.url_result(mobj.group(1), 'Mpora')
1510 # Look for embedded NovaMov-based player
1512 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1513 (?P<url>http://(?:(?:embed|www)\.)?
1515 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1516 videoweed\.(?:es|com)|
1517 movshare\.(?:net|sx|ag)|
1518 divxstage\.(?:eu|net|ch|co|at|ag))
1519 /embed\.php.+?)\1''', webpage)
1520 if mobj is not None:
1521 return self.url_result(mobj.group('url'))
1523 # Look for embedded Facebook player
1525 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1526 if mobj is not None:
1527 return self.url_result(mobj.group('url'), 'Facebook')
1529 # Look for embedded VK player
1530 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1531 if mobj is not None:
1532 return self.url_result(mobj.group('url'), 'VK')
1534 # Look for embedded ivi player
1535 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1536 if mobj is not None:
1537 return self.url_result(mobj.group('url'), 'Ivi')
1539 # Look for embedded Huffington Post player
1541 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1542 if mobj is not None:
1543 return self.url_result(mobj.group('url'), 'HuffPost')
1546 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1547 if mobj is not None:
1548 return self.url_result(mobj.group('url'))
1549 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1550 if mobj is not None:
1551 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1553 # Look for funnyordie embed
1554 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1556 return _playlist_from_matches(
1557 matches, getter=unescapeHTML, ie='FunnyOrDie')
1559 # Look for BBC iPlayer embed
1560 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1562 return _playlist_from_matches(matches, ie='BBCCoUk')
1564 # Look for embedded RUTV player
1565 rutv_url = RUTVIE._extract_url(webpage)
1567 return self.url_result(rutv_url, 'RUTV')
1569 # Look for embedded TVC player
1570 tvc_url = TVCIE._extract_url(webpage)
1572 return self.url_result(tvc_url, 'TVC')
1574 # Look for embedded SportBox player
1575 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1577 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1579 # Look for embedded PornHub player
1580 pornhub_url = PornHubIE._extract_url(webpage)
1582 return self.url_result(pornhub_url, 'PornHub')
1584 # Look for embedded XHamster player
1585 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1587 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1589 # Look for embedded Tvigle player
1591 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1592 if mobj is not None:
1593 return self.url_result(mobj.group('url'), 'Tvigle')
1595 # Look for embedded TED player
1597 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1598 if mobj is not None:
1599 return self.url_result(mobj.group('url'), 'TED')
1601 # Look for embedded Ustream videos
1603 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1604 if mobj is not None:
1605 return self.url_result(mobj.group('url'), 'Ustream')
1607 # Look for embedded arte.tv player
1609 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1611 if mobj is not None:
1612 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1614 # Look for embedded francetv player
1616 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1618 if mobj is not None:
1619 return self.url_result(mobj.group('url'))
1621 # Look for embedded smotri.com player
1622 smotri_url = SmotriIE._extract_url(webpage)
1624 return self.url_result(smotri_url, 'Smotri')
1626 # Look for embedded Myvi.ru player
1627 myvi_url = MyviIE._extract_url(webpage)
1629 return self.url_result(myvi_url)
1631 # Look for embeded soundcloud player
1633 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1635 if mobj is not None:
1636 url = unescapeHTML(mobj.group('url'))
1637 return self.url_result(url)
1639 # Look for embedded vulture.com player
1641 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1643 if mobj is not None:
1644 url = unescapeHTML(mobj.group('url'))
1645 return self.url_result(url, ie='Vulture')
1647 # Look for embedded mtvservices player
1648 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1650 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1652 # Look for embedded yahoo player
1654 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1656 if mobj is not None:
1657 return self.url_result(mobj.group('url'), 'Yahoo')
1659 # Look for embedded sbs.com.au player
1663 <meta\s+property="og:video"\s+content=|
1666 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1668 if mobj is not None:
1669 return self.url_result(mobj.group('url'), 'SBS')
1671 # Look for embedded Cinchcast player
1673 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1675 if mobj is not None:
1676 return self.url_result(mobj.group('url'), 'Cinchcast')
1679 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1683 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1685 if mobj is not None:
1686 return self.url_result(mobj.group('url'), 'MLB')
1689 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1691 if mobj is not None:
1692 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1695 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'Livestream')
1700 # Look for Zapiks embed
1702 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1703 if mobj is not None:
1704 return self.url_result(mobj.group('url'), 'Zapiks')
1706 # Look for Kaltura embeds
1707 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1708 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))
1709 if mobj is not None:
1710 return self.url_result(smuggle_url(
1711 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1712 {'source_url': url}), 'Kaltura')
1714 # Look for Eagle.Platform embeds
1716 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1717 if mobj is not None:
1718 return self.url_result(mobj.group('url'), 'EaglePlatform')
1720 # Look for ClipYou (uses Eagle.Platform) embeds
1722 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1723 if mobj is not None:
1724 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1726 # Look for Pladform embeds
1728 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1729 if mobj is not None:
1730 return self.url_result(mobj.group('url'), 'Pladform')
1732 # Look for Playwire embeds
1734 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1735 if mobj is not None:
1736 return self.url_result(mobj.group('url'))
1738 # Look for 5min embeds
1740 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1741 if mobj is not None:
1742 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1744 # Look for Crooks and Liars embeds
1746 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1747 if mobj is not None:
1748 return self.url_result(mobj.group('url'))
1750 # Look for NBC Sports VPlayer embeds
1751 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1753 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1755 # Look for UDN embeds
1757 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1758 if mobj is not None:
1759 return self.url_result(
1760 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1762 # Look for Senate ISVP iframe
1763 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1765 return self.url_result(senate_isvp_url, 'SenateISVP')
1767 # Look for Dailymotion Cloud videos
1768 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1770 return self.url_result(dmcloud_url, 'DailymotionCloud')
1772 # Look for OnionStudios embeds
1773 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1774 if onionstudios_url:
1775 return self.url_result(onionstudios_url)
1777 # Look for SnagFilms embeds
1778 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1780 return self.url_result(snagfilms_url)
1782 # Look for ScreenwaveMedia embeds
1783 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1784 if mobj is not None:
1785 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1787 # Look for AdobeTVVideo embeds
1789 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1791 if mobj is not None:
1792 return self.url_result(
1793 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1796 def check_video(vurl):
1797 if YoutubeIE.suitable(vurl):
1799 vpath = compat_urlparse.urlparse(vurl).path
1800 vext = determine_ext(vpath)
1801 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1803 def filter_video(urls):
1804 return list(filter(check_video, urls))
1806 # Start with something easy: JW Player in SWFObject
1807 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1809 # Look for gorilla-vid style embedding
1810 found = filter_video(re.findall(r'''(?sx)
1814 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1817 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1819 # Broaden the search a little bit
1820 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1822 # Broaden the findall a little bit: JWPlayer JS loader
1823 found = filter_video(re.findall(
1824 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1827 found = filter_video(re.findall(r'''(?xs)
1828 flowplayer\("[^"]+",\s*
1830 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1831 ["']?url["']?\s*:\s*["']([^"']+)["']
1836 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1838 # Try to find twitter cards info
1839 found = filter_video(re.findall(
1840 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1842 # We look for Open Graph info:
1843 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1844 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1845 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1846 if m_video_type is not None:
1847 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1850 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1852 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1854 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1855 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1858 # Look also in Refresh HTTP header
1859 refresh_header = head_response.headers.get('Refresh')
1861 # In python 2 response HTTP headers are bytestrings
1862 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1863 refresh_header = refresh_header.decode('iso-8859-1')
1864 found = re.search(REDIRECT_REGEX, refresh_header)
1866 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1867 self.report_following_redirect(new_url)
1873 raise UnsupportedError(url)
1876 for video_url in found:
1877 video_url = video_url.replace('\\/', '/')
1878 video_url = compat_urlparse.urljoin(url, video_url)
1879 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1881 # Sometimes, jwplayer extraction will result in a YouTube URL
1882 if YoutubeIE.suitable(video_url):
1883 entries.append(self.url_result(video_url, 'Youtube'))
1886 # here's a fun little line of code for you:
1887 video_id = os.path.splitext(video_id)[0]
1891 'uploader': video_uploader,
1892 'title': video_title,
1893 'age_limit': age_limit,
1896 ext = determine_ext(video_url)
1898 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1900 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1902 entry_info_dict['url'] = video_url
1904 entries.append(entry_info_dict)
1906 if len(entries) == 1:
1909 for num, e in enumerate(entries, start=1):
1910 # 'url' results don't have a title
1911 if e.get('title') is not None:
1912 e['title'] = '%s (%d)' % (e['title'], num)
1914 '_type': 'playlist',