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 .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .viewlift import ViewLiftEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
64 from .threeqsdn import ThreeQSDNIE
65 from .theplatform import ThePlatformIE
68 class GenericIE(InfoExtractor):
69 IE_DESC = 'Generic downloader that works on some sites'
73 # Direct link to a video
75 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
76 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
81 'upload_date': '20100513',
84 # Direct link to media delivered compressed (until Accept-Encoding is *)
86 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
87 'md5': '128c42e68b13950268b648275386fc74',
89 'id': 'FictionJunction-Parallel_Hearts',
91 'title': 'FictionJunction-Parallel_Hearts',
92 'upload_date': '20140522',
94 'expected_warnings': [
95 'URL could be a direct video link, returning it as such.'
98 # Direct download with broken HEAD
100 'url': 'http://ai-radio.org:8000/radio.opus',
107 'skip_download': True, # infinite live stream
109 'expected_warnings': [
110 r'501.*Not Implemented',
114 # Direct link with incorrect MIME type
116 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
117 'md5': '4ccbebe5f36706d85221f204d7eb5913',
119 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
120 'id': '5_Lennart_Poettering_-_Systemd',
122 'title': '5_Lennart_Poettering_-_Systemd',
123 'upload_date': '20141120',
125 'expected_warnings': [
126 'URL could be a direct video link, returning it as such.'
131 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
133 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
134 'title': 'Zero Punctuation',
135 'description': 're:.*groundbreaking video review series.*'
137 'playlist_mincount': 11,
139 # RSS feed with enclosure
141 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
143 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
145 'upload_date': '20150228',
146 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
149 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
151 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
155 'title': 'Automatics, robotics and biocybernetics',
156 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
157 'upload_date': '20130627',
158 'formats': 'mincount:16',
159 'subtitles': 'mincount:1',
162 'force_generic_extractor': True,
163 'skip_download': True,
166 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
168 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
173 'formats': 'mincount:1',
176 'skip_download': True,
179 # SMIL from https://www.restudy.dk/video/play/id/1637
181 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
185 'title': 'video_1637',
186 'formats': 'mincount:3',
189 'skip_download': True,
192 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
194 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
196 'id': 'smil-service',
198 'title': 'smil-service',
199 'formats': 'mincount:1',
202 'skip_download': True,
205 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
207 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
211 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
212 'formats': 'mincount:3',
215 'skip_download': True,
218 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
220 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
222 'id': 'mZlp2ctYIUEB',
224 'title': 'Tikibad ontruimd wegens brand',
225 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
226 'thumbnail': 're:^https?://.*\.jpg$',
230 'skip_download': True,
233 # MPD from http://dash-mse-test.appspot.com/media.html
235 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
236 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
238 'id': 'car-20120827-manifest',
240 'title': 'car-20120827-manifest',
241 'formats': 'mincount:9',
242 'upload_date': '20130904',
245 'format': 'bestvideo',
248 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
250 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
255 'formats': 'mincount:8',
259 'skip_download': True,
262 # m3u8 served with Content-Type: text/plain
264 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
269 'upload_date': '20140720',
270 'formats': 'mincount:11',
274 'skip_download': True,
279 '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',
283 'upload_date': '20130224',
284 'uploader_id': 'TheVerge',
285 'description': 're:^Chris Ziegler takes a look at the\.*',
286 'uploader': 'The Verge',
287 'title': 'First Firefox OS phones side-by-side',
290 'skip_download': False,
294 # redirect in Refresh HTTP header
295 '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',
299 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
300 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
301 'upload_date': '20150917',
302 'uploader_id': 'brtvofficial',
303 'uploader': 'Boiler Room',
306 'skip_download': False,
310 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
311 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
313 'id': '13601338388002',
315 'uploader': 'www.hodiho.fr',
316 'title': 'R\u00e9gis plante sa Jeep',
319 # bandcamp page with custom domain
321 'add_ie': ['Bandcamp'],
322 'url': 'http://bronyrock.com/track/the-pony-mash',
326 'title': 'The Pony Mash',
327 'uploader': 'M_Pallante',
329 'skip': 'There is a limit of 200 free downloads / month for the test song',
331 # embedded brightcove video
332 # it also tests brightcove videos that need to set the 'Referer' in the
335 'add_ie': ['BrightcoveLegacy'],
336 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
338 'id': '2765128793001',
340 'title': 'Le cours de bourse : l’analyse technique',
341 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
342 'uploader': 'BFM BUSINESS',
345 'skip_download': True,
349 # https://github.com/rg3/youtube-dl/issues/2253
350 'url': 'http://bcove.me/i6nfkrc3',
351 'md5': '0ba9446db037002366bab3b3eb30c88c',
353 'id': '3101154703001',
355 'title': 'Still no power',
356 'uploader': 'thestar.com',
357 '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.',
359 'add_ie': ['BrightcoveLegacy'],
362 'url': 'http://www.championat.com/video/football/v/87/87499.html',
363 'md5': 'fb973ecf6e4a78a67453647444222983',
365 'id': '3414141473001',
367 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
368 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
369 'uploader': 'Championat',
373 # https://github.com/rg3/youtube-dl/issues/3541
374 'add_ie': ['BrightcoveLegacy'],
375 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
377 'id': '3866516442001',
379 'title': 'Leer mij vrouwen kennen: Aflevering 1',
380 'description': 'Leer mij vrouwen kennen: Aflevering 1',
381 'uploader': 'SBS Broadcasting',
383 'skip': 'Restricted to Netherlands',
385 'skip_download': True, # m3u8 download
390 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
391 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
393 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
395 'title': '2cc213299525360.mov', # that's what we get
398 'add_ie': ['Ooyala'],
401 # ooyala video embedded with http://player.ooyala.com/iframe.js
402 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
404 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
406 'title': '"Steve Jobs: Man in the Machine" trailer',
407 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
411 'skip_download': True,
416 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
420 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
421 'upload_date': '20140225',
422 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
423 'uploader': 'Tested',
424 'uploader_id': 'testedcom',
426 # No need to test YoutubeIE here
428 'skip_download': True,
433 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
437 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
438 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
443 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
447 'title': 'Охотское море стало целиком российским',
448 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
452 'skip_download': True,
457 '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/',
461 'title': 'Дошкольное воспитание',
466 'url': 'http://www.vestifinance.ru/articles/25753',
469 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
474 'title': 'Госзаказ. День 3',
480 'title': 'Госзаказ. День 2',
486 'title': 'Госзаказ. День 1',
492 'skip_download': True,
497 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
499 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
501 'title': 'Ужастики, русский трейлер (2015)',
502 'thumbnail': 're:^https?://.*\.jpg$',
508 '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',
511 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
513 'playlist_mincount': 7,
517 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
518 'md5': '65fdff94098e4a607385a60c5177c638',
522 'title': 'Hidden miracles of the natural world',
523 'uploader': 'Louie Schwartzberg',
524 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
527 # Embedded Ustream video
529 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
530 'md5': '27b99cdb639c9b12a79bca876a073417',
534 'uploader': 'AU SPA: The NSA and Privacy',
535 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
538 # nowvideo embed hidden behind percent encoding
540 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
541 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
543 'id': '06e53103ca9aa',
545 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
546 'description': 'No description',
551 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
552 'md5': '7653032cbb25bf6c80d80f217055fa43',
554 'id': '048195-004_PLUS7-F',
557 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
558 'upload_date': '20140320',
561 'skip_download': 'Requires rtmpdump'
566 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
570 'title': 'Alcaline, le concert avec Calogero',
571 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
572 'upload_date': '20150226',
573 'timestamp': 1424989860,
578 'skip_download': True,
580 'expected_warnings': [
586 'url': 'http://www.wired.com/2014/04/honda-asimo/',
587 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
589 'id': '53501be369702d3275860000',
591 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
596 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
597 'md5': '441aeeb82eb72c422c7f14ec533999cd',
599 'id': 'k2mm4bCdJ6CQ2i7c8o2',
601 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
602 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
604 'uploader_id': 'xgditw',
605 'upload_date': '20140425',
606 'timestamp': 1398441542,
608 'add_ie': ['Dailymotion'],
612 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
616 'title': 'The NBL Auction 2014',
617 'uploader': 'BADMINTON England',
618 'uploader_id': 'BADMINTONEvents',
619 'upload_date': '20140603',
620 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
622 'add_ie': ['Youtube'],
624 'skip_download': True,
629 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
630 'md5': '35727f82f58c76d996fc188f9755b0d5',
632 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
635 'description': 'Mario\'s life in the fast lane has never looked so good.',
638 # YouTube embed via <data-embed-url="">
640 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
644 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
645 'uploader': 'Gameloft',
646 'uploader_id': 'gameloft',
647 'upload_date': '20140828',
648 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
651 'skip_download': True,
656 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
658 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
660 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
661 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
666 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
668 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
669 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
675 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
680 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
681 'md5': '9d65602bf31c6e20014319c7d07fba27',
683 'id': '5123ea6d5e5a7',
686 'uploader': 'www.handjobhub.com',
687 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
690 # Multiple brightcove videos
691 # https://github.com/rg3/youtube-dl/issues/2283
693 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
695 'id': 'always-never',
696 'title': 'Always / Never - The New Yorker',
700 'extract_flat': False,
701 'skip_download': True,
706 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
707 'md5': '96f09a37e44da40dd083e12d9a683327',
711 'title': 'Ump changes call to ball',
712 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
714 'timestamp': 1401537900,
715 'upload_date': '20140531',
716 'thumbnail': 're:^https?://.*\.jpg$',
721 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
722 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
726 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
727 'description': 'a Paywall Videos video from Remilon',
729 'uploader': 'study.com',
730 'timestamp': 1459678540,
731 'upload_date': '20160403',
732 'filesize': 24687186,
736 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
737 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
741 'title': 'Conversation about Hexagonal Rails Part 1',
742 'description': 'a Martin Fowler video from ThoughtWorks',
744 'uploader': 'thoughtworks.wistia.com',
745 'timestamp': 1401832161,
746 'upload_date': '20140603',
749 # Wistia standard embed (async)
751 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
755 'title': 'Drip Brennan Dunn Workshop',
756 'description': 'a JV Webinars video from getdrip-1',
758 'timestamp': 1463607249,
759 'upload_date': '20160518',
762 'skip_download': True,
767 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
771 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
772 'uploader': 'Sophos Security',
773 'title': 'Chet Chat 171 - Oct 29, 2014',
774 'upload_date': '20141029',
779 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
783 'upload_date': '20141112',
784 'title': 'Rosetta #CometLanding webcast HL 10',
789 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
792 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
794 'playlist_mincount': 2,
798 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
802 'upload_date': '20141126',
803 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
808 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
810 'id': '730m_DandD_1901_512k',
812 'uploader': 'www.abc.net.au',
813 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
816 # embedded viddler video
818 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
822 'uploader': 'deadspin',
823 'title': 'WALL-TO-GORTAT',
824 'timestamp': 1422285291,
825 'upload_date': '20150126',
827 'add_ie': ['Viddler'],
831 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
835 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
836 'description': 'md5:601cb790edd05908957dae8aaa866465',
837 'upload_date': '20150220',
842 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
846 'upload_date': '20150212',
847 'uploader': 'The National Archives UK',
848 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
849 'uploader_id': 'NationalArchives08',
850 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
855 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
856 'playlist_mincount': 5,
858 'id': 'aanslagen-kopenhagen',
859 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
864 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
868 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
873 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
877 'upload_date': '20150226',
878 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
880 'title': 'John Carlson Postgame 2/25/15',
883 # Kaltura embed (different embed code)
885 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
889 'upload_date': '20150127',
890 'uploader_id': 'PremierMedia',
892 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
895 # Kaltura embed protected with referrer
897 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
901 'title': 'Violetta - Achter De Schermen - Ruggero',
902 'description': 'Achter de schermen met Ruggero',
903 'timestamp': 1435133761,
904 'upload_date': '20150624',
905 'uploader_id': 'echojecka',
908 # Eagle.Platform embed (generic URL)
910 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
911 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
915 'title': 'Навальный вышел на свободу',
916 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
917 'thumbnail': 're:^https?://.*\.jpg$',
923 # ClipYou (Eagle.Platform) embed (custom URL)
925 'url': 'http://muz-tv.ru/play/7129/',
926 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
930 'title': "'O Sole Mio",
931 'thumbnail': 're:^https?://.*\.jpg$',
938 'url': 'http://muz-tv.ru/kinozal/view/7400/',
942 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
943 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
944 'thumbnail': 're:^https?://.*\.jpg$',
951 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
955 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
956 'thumbnail': 're:^https?://.*\.png$',
962 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
963 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
967 'title': 'Facebook Creates "On This Day" | Crunch Report',
972 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
976 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
981 # Crooks and Liars embed
983 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
987 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
988 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
989 'timestamp': 1428207000,
990 'upload_date': '20150405',
991 'uploader': 'Heather',
994 # Crooks and Liars external embed
996 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
998 'id': 'MTE3MjUtMzQ2MzA',
1000 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1001 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1002 'timestamp': 1265032391,
1003 'upload_date': '20100201',
1004 'uploader': 'Heather',
1007 # NBC Sports vplayer embed
1009 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1011 'id': 'ln7x1qSThw4k',
1013 'title': "PFT Live: New leader in the 'new-look' defense",
1014 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1015 'uploader': 'NBCU-SPORTS',
1016 'upload_date': '20140107',
1017 'timestamp': 1389118457,
1022 'url': 'http://www.udn.com/news/story/7314/822787',
1023 'md5': 'fd2060e988c326991037b9aff9df21a6',
1027 'title': '中一中男師變性 全校師生力挺',
1028 'thumbnail': 're:^https?://.*\.jpg$',
1033 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1035 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1037 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1038 'title': 'This is what separates the Excel masters from the wannabes',
1039 'duration': 191.933,
1043 'skip_download': True,
1046 # Contains a SMIL manifest
1048 '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',
1052 'title': '+ Football: Lottery Champions League Europe',
1053 'uploader': 'www.telewebion.com',
1057 'skip_download': True,
1060 # Brightcove URL in single quotes
1062 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1063 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1065 'id': '4255764656001',
1067 'title': 'SN Presents: Russell Martin, World Citizen',
1068 '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.',
1069 'uploader': 'Rogers Sportsnet',
1070 'uploader_id': '1704050871',
1071 'upload_date': '20150525',
1072 'timestamp': 1432570283,
1075 # Dailymotion Cloud video
1077 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1078 'md5': '49444254273501a64675a7e68c502681',
1080 'id': '5585de919473990de4bee11b',
1082 'title': 'Le débat',
1083 'thumbnail': 're:^https?://.*\.jpe?g$',
1086 # OnionStudios embed
1088 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1092 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1093 'thumbnail': 're:^https?://.*\.jpe?g$',
1094 'uploader': 'ClickHole',
1095 'uploader_id': 'clickhole',
1100 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1102 'id': '74849a00-85a9-11e1-9660-123139220831',
1104 'title': '#whilewewatch',
1107 # AdobeTVVideo embed
1109 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1110 'md5': '43662b577c018ad707a63766462b1e87',
1114 'title': 'New experience with Acrobat DC',
1115 'description': 'New experience with Acrobat DC',
1116 'duration': 248.667,
1119 # ScreenwaveMedia embed
1121 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1122 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1124 'id': 'cinemasnob-55d26273809dd',
1126 'title': 'cinemasnob',
1129 # BrightcoveInPageEmbed embed
1131 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1133 'id': '4238694884001',
1135 'title': 'Tabletop: Dread, Last Thoughts',
1136 'description': 'Tabletop: Dread, Last Thoughts',
1140 # JWPlayer with M3U8
1142 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1146 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1147 'uploader': 'ren.tv',
1151 'skip_download': True,
1154 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1155 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1157 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1159 'id': '4785848093001',
1161 'title': 'The Cardinal Pell Interview',
1162 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1163 'uploader': 'GlobeCast Australia - GlobeStream',
1164 'uploader_id': '2733773828001',
1165 'upload_date': '20160304',
1166 'timestamp': 1457083087,
1170 'skip_download': True,
1173 # Another form of arte.tv embed
1175 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1176 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1178 'id': '030273-562_PLUS7-F',
1180 'title': 'ARTE Reportage - Nulle part, en France',
1181 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1182 'upload_date': '20160409',
1187 'url': 'http://www.wykop.pl/link/3088787/',
1188 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1190 'id': '874_1459135191',
1192 'title': 'Man shows poor quality of new apartment building',
1193 'description': 'The wall is like a sand pile.',
1194 'uploader': 'Lake8737',
1199 def report_following_redirect(self, new_url):
1200 """Report information extraction."""
1201 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1203 def _extract_rss(self, url, video_id, doc):
1204 playlist_title = doc.find('./channel/title').text
1205 playlist_desc_el = doc.find('./channel/description')
1206 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1209 for it in doc.findall('./channel/item'):
1210 next_url = xpath_text(it, 'link', fatal=False)
1212 enclosure_nodes = it.findall('./enclosure')
1213 for e in enclosure_nodes:
1214 next_url = e.attrib.get('url')
1224 'title': it.find('title').text,
1228 '_type': 'playlist',
1230 'title': playlist_title,
1231 'description': playlist_desc,
1235 def _extract_camtasia(self, url, video_id, webpage):
1236 """ Returns None if no camtasia video can be found. """
1238 camtasia_cfg = self._search_regex(
1239 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1240 webpage, 'camtasia configuration file', default=None)
1241 if camtasia_cfg is None:
1244 title = self._html_search_meta('DC.title', webpage, fatal=True)
1246 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1247 camtasia_cfg = self._download_xml(
1248 camtasia_url, video_id,
1249 note='Downloading camtasia configuration',
1250 errnote='Failed to download camtasia configuration')
1251 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1254 for n in fileset_node.getchildren():
1255 url_n = n.find('./uri')
1260 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1261 'title': '%s - %s' % (title, n.tag),
1262 'url': compat_urlparse.urljoin(url, url_n.text),
1263 'duration': float_or_none(n.find('./duration').text),
1267 '_type': 'playlist',
1272 def _real_extract(self, url):
1273 if url.startswith('//'):
1276 'url': self.http_scheme() + url,
1279 parsed_url = compat_urlparse.urlparse(url)
1280 if not parsed_url.scheme:
1281 default_search = self._downloader.params.get('default_search')
1282 if default_search is None:
1283 default_search = 'fixup_error'
1285 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1287 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1288 return self.url_result('http://' + url)
1289 elif default_search != 'fixup_error':
1290 if default_search == 'auto_warning':
1291 if re.match(r'^(?:url|URL)$', url):
1292 raise ExtractorError(
1293 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1296 self._downloader.report_warning(
1297 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1298 return self.url_result('ytsearch:' + url)
1300 if default_search in ('error', 'fixup_error'):
1301 raise ExtractorError(
1302 '%r is not a valid URL. '
1303 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1304 % (url, url), expected=True)
1306 if ':' not in default_search:
1307 default_search += ':'
1308 return self.url_result(default_search + url)
1310 url, smuggled_data = unsmuggle_url(url)
1311 force_videoid = None
1312 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1313 if smuggled_data and 'force_videoid' in smuggled_data:
1314 force_videoid = smuggled_data['force_videoid']
1315 video_id = force_videoid
1317 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1319 self.to_screen('%s: Requesting header' % video_id)
1321 head_req = HEADRequest(url)
1322 head_response = self._request_webpage(
1324 note=False, errnote='Could not send HEAD request to %s' % url,
1327 if head_response is not False:
1328 # Check for redirect
1329 new_url = head_response.geturl()
1331 self.report_following_redirect(new_url)
1333 new_url = smuggle_url(
1334 new_url, {'force_videoid': force_videoid})
1335 return self.url_result(new_url)
1337 full_response = None
1338 if head_response is False:
1339 request = sanitized_Request(url)
1340 request.add_header('Accept-Encoding', '*')
1341 full_response = self._request_webpage(request, video_id)
1342 head_response = full_response
1346 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1347 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1350 # Check for direct link to a video
1351 content_type = head_response.headers.get('Content-Type', '').lower()
1352 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1354 format_id = m.group('format_id')
1355 if format_id.endswith('mpegurl'):
1356 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1357 elif format_id == 'f4m':
1358 formats = self._extract_f4m_formats(url, video_id)
1361 'format_id': m.group('format_id'),
1363 'vcodec': 'none' if m.group('type') == 'audio' else None
1365 info_dict['direct'] = True
1366 self._sort_formats(formats)
1367 info_dict['formats'] = formats
1370 if not self._downloader.params.get('test', False) and not is_intentional:
1371 force = self._downloader.params.get('force_generic_extractor', False)
1372 self._downloader.report_warning(
1373 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1375 if not full_response:
1376 request = sanitized_Request(url)
1377 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1378 # making it impossible to download only chunk of the file (yet we need only 512kB to
1379 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1380 # that will always result in downloading the whole file that is not desirable.
1381 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1382 # to accept raw bytes and being able to download only a chunk.
1383 # It may probably better to solve this by checking Content-Type for application/octet-stream
1384 # after HEAD request finishes, but not sure if we can rely on this.
1385 request.add_header('Accept-Encoding', '*')
1386 full_response = self._request_webpage(request, video_id)
1388 first_bytes = full_response.read(512)
1390 # Is it an M3U playlist?
1391 if first_bytes.startswith(b'#EXTM3U'):
1392 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1393 self._sort_formats(info_dict['formats'])
1396 # Maybe it's a direct link to a video?
1397 # Be careful not to download the whole thing!
1398 if not is_html(first_bytes):
1399 self._downloader.report_warning(
1400 'URL could be a direct video link, returning it as such.')
1407 webpage = self._webpage_read_content(
1408 full_response, url, video_id, prefix=first_bytes)
1410 self.report_extraction(video_id)
1412 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1414 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1415 if doc.tag == 'rss':
1416 return self._extract_rss(url, video_id, doc)
1417 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1418 smil = self._parse_smil(doc, url, video_id)
1419 self._sort_formats(smil['formats'])
1421 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1422 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1423 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1424 info_dict['formats'] = self._parse_mpd_formats(
1425 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1426 self._sort_formats(info_dict['formats'])
1428 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1429 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1430 self._sort_formats(info_dict['formats'])
1432 except compat_xml_parse_error:
1435 # Is it a Camtasia project?
1436 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1437 if camtasia_res is not None:
1440 # Sometimes embedded video player is hidden behind percent encoding
1441 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1442 # Unescaping the whole page allows to handle those cases in a generic way
1443 webpage = compat_urllib_parse_unquote(webpage)
1445 # it's tempting to parse this further, but you would
1446 # have to take into account all the variations like
1447 # Video Title - Site Name
1448 # Site Name | Video Title
1449 # Video Title - Tagline | Site Name
1450 # and so on and so forth; it's just not practical
1451 video_title = self._og_search_title(
1452 webpage, default=None) or self._html_search_regex(
1453 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1456 # Try to detect age limit automatically
1457 age_limit = self._rta_search(webpage)
1458 # And then there are the jokers who advertise that they use RTA,
1459 # but actually don't.
1460 AGE_LIMIT_MARKERS = [
1461 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1463 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1466 # video uploader is domain name
1467 video_uploader = self._search_regex(
1468 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1470 video_description = self._og_search_description(webpage, default=None)
1471 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1474 def _playlist_from_matches(matches, getter=None, ie=None):
1476 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1478 return self.playlist_result(
1479 urlrs, playlist_id=video_id, playlist_title=video_title)
1481 # Look for Brightcove Legacy Studio embeds
1482 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1484 self.to_screen('Brightcove video detected.')
1487 'url': smuggle_url(bc_url, {'Referer': url}),
1488 'ie_key': 'BrightcoveLegacy'
1489 } for bc_url in bc_urls]
1492 '_type': 'playlist',
1493 'title': video_title,
1498 # Look for Brightcove New Studio embeds
1499 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1501 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1503 # Look for ThePlatform embeds
1504 tp_urls = ThePlatformIE._extract_urls(webpage)
1506 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1508 # Look for embedded rtl.nl player
1509 matches = re.findall(
1510 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1513 return _playlist_from_matches(matches, ie='RtlNl')
1515 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1516 if vimeo_url is not None:
1517 return self.url_result(vimeo_url)
1519 vid_me_embed_url = self._search_regex(
1520 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1521 webpage, 'vid.me embed', default=None)
1522 if vid_me_embed_url is not None:
1523 return self.url_result(vid_me_embed_url, 'Vidme')
1525 # Look for embedded YouTube player
1526 matches = re.findall(r'''(?x)
1535 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1539 return _playlist_from_matches(
1540 matches, lambda m: unescapeHTML(m[1]))
1542 # Look for lazyYT YouTube embed
1543 matches = re.findall(
1544 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1546 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1548 # Look for embedded Dailymotion player
1549 matches = re.findall(
1550 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1552 return _playlist_from_matches(
1553 matches, lambda m: unescapeHTML(m[1]))
1555 # Look for embedded Dailymotion playlist player (#3822)
1557 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1559 playlists = re.findall(
1560 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1562 return _playlist_from_matches(
1563 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1565 # Look for embedded Wistia player
1567 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1569 embed_url = self._proto_relative_url(
1570 unescapeHTML(match.group('url')))
1572 '_type': 'url_transparent',
1575 'uploader': video_uploader,
1578 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1581 '_type': 'url_transparent',
1582 'url': 'wistia:%s' % match.group('id'),
1584 'uploader': video_uploader,
1589 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1590 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1593 return self.url_result(self._proto_relative_url(
1594 'wistia:%s' % match.group('id')), 'Wistia')
1596 # Look for SVT player
1597 svt_url = SVTIE._extract_url(webpage)
1599 return self.url_result(svt_url, 'SVT')
1601 # Look for embedded condenast player
1602 matches = re.findall(
1603 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1607 '_type': 'playlist',
1610 'ie_key': 'CondeNast',
1612 } for ma in matches],
1613 'title': video_title,
1617 # Look for Bandcamp pages with custom domain
1618 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1619 if mobj is not None:
1620 burl = unescapeHTML(mobj.group(1))
1621 # Don't set the extractor because it can be a track url or an album
1622 return self.url_result(burl)
1624 # Look for embedded Vevo player
1626 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'))
1630 # Look for embedded Viddler player
1632 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1634 if mobj is not None:
1635 return self.url_result(mobj.group('url'))
1637 # Look for NYTimes player
1639 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1641 if mobj is not None:
1642 return self.url_result(mobj.group('url'))
1644 # Look for Libsyn player
1646 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1647 if mobj is not None:
1648 return self.url_result(mobj.group('url'))
1650 # Look for Ooyala videos
1651 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1652 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1653 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1654 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1655 if mobj is not None:
1656 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1658 # Look for multiple Ooyala embeds on SBN network websites
1659 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1660 if mobj is not None:
1661 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1663 return _playlist_from_matches(
1664 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1666 # Look for Aparat videos
1667 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1668 if mobj is not None:
1669 return self.url_result(mobj.group(1), 'Aparat')
1671 # Look for MPORA videos
1672 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1673 if mobj is not None:
1674 return self.url_result(mobj.group(1), 'Mpora')
1676 # Look for embedded NovaMov-based player
1678 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1679 (?P<url>http://(?:(?:embed|www)\.)?
1681 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1682 videoweed\.(?:es|com)|
1683 movshare\.(?:net|sx|ag)|
1684 divxstage\.(?:eu|net|ch|co|at|ag))
1685 /embed\.php.+?)\1''', webpage)
1686 if mobj is not None:
1687 return self.url_result(mobj.group('url'))
1689 # Look for embedded Facebook player
1691 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1692 if mobj is not None:
1693 return self.url_result(mobj.group('url'), 'Facebook')
1695 # Look for embedded VK player
1696 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'VK')
1700 # Look for embedded Odnoklassniki player
1701 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1702 if mobj is not None:
1703 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1705 # Look for embedded ivi player
1706 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1707 if mobj is not None:
1708 return self.url_result(mobj.group('url'), 'Ivi')
1710 # Look for embedded Huffington Post player
1712 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1713 if mobj is not None:
1714 return self.url_result(mobj.group('url'), 'HuffPost')
1717 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1718 if mobj is not None:
1719 return self.url_result(mobj.group('url'))
1720 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1721 if mobj is not None:
1722 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1724 # Look for funnyordie embed
1725 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1727 return _playlist_from_matches(
1728 matches, getter=unescapeHTML, ie='FunnyOrDie')
1730 # Look for BBC iPlayer embed
1731 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1733 return _playlist_from_matches(matches, ie='BBCCoUk')
1735 # Look for embedded RUTV player
1736 rutv_url = RUTVIE._extract_url(webpage)
1738 return self.url_result(rutv_url, 'RUTV')
1740 # Look for embedded TVC player
1741 tvc_url = TVCIE._extract_url(webpage)
1743 return self.url_result(tvc_url, 'TVC')
1745 # Look for embedded SportBox player
1746 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1748 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1750 # Look for embedded PornHub player
1751 pornhub_url = PornHubIE._extract_url(webpage)
1753 return self.url_result(pornhub_url, 'PornHub')
1755 # Look for embedded XHamster player
1756 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1758 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1760 # Look for embedded TNAFlixNetwork player
1761 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1763 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1765 # Look for embedded Tvigle player
1767 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'), 'Tvigle')
1771 # Look for embedded TED player
1773 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1774 if mobj is not None:
1775 return self.url_result(mobj.group('url'), 'TED')
1777 # Look for embedded Ustream videos
1779 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1780 if mobj is not None:
1781 return self.url_result(mobj.group('url'), 'Ustream')
1783 # Look for embedded arte.tv player
1785 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1787 if mobj is not None:
1788 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1790 # Look for embedded francetv player
1792 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1794 if mobj is not None:
1795 return self.url_result(mobj.group('url'))
1797 # Look for embedded smotri.com player
1798 smotri_url = SmotriIE._extract_url(webpage)
1800 return self.url_result(smotri_url, 'Smotri')
1802 # Look for embedded Myvi.ru player
1803 myvi_url = MyviIE._extract_url(webpage)
1805 return self.url_result(myvi_url)
1807 # Look for embedded soundcloud player
1809 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1811 if mobj is not None:
1812 url = unescapeHTML(mobj.group('url'))
1813 return self.url_result(url)
1815 # Look for embedded vulture.com player
1817 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1819 if mobj is not None:
1820 url = unescapeHTML(mobj.group('url'))
1821 return self.url_result(url, ie='Vulture')
1823 # Look for embedded mtvservices player
1824 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1826 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1828 # Look for embedded yahoo player
1830 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1832 if mobj is not None:
1833 return self.url_result(mobj.group('url'), 'Yahoo')
1835 # Look for embedded sbs.com.au player
1839 <meta\s+property="og:video"\s+content=|
1842 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1844 if mobj is not None:
1845 return self.url_result(mobj.group('url'), 'SBS')
1847 # Look for embedded Cinchcast player
1849 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1851 if mobj is not None:
1852 return self.url_result(mobj.group('url'), 'Cinchcast')
1855 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1859 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1861 if mobj is not None:
1862 return self.url_result(mobj.group('url'), 'MLB')
1865 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1867 if mobj is not None:
1868 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1871 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1873 if mobj is not None:
1874 return self.url_result(mobj.group('url'), 'Livestream')
1876 # Look for Zapiks embed
1878 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1879 if mobj is not None:
1880 return self.url_result(mobj.group('url'), 'Zapiks')
1882 # Look for Kaltura embeds
1883 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1884 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))
1885 if mobj is not None:
1886 return self.url_result(smuggle_url(
1887 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1888 {'source_url': url}), 'Kaltura')
1890 # Look for Eagle.Platform embeds
1892 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1893 if mobj is not None:
1894 return self.url_result(mobj.group('url'), 'EaglePlatform')
1896 # Look for ClipYou (uses Eagle.Platform) embeds
1898 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1899 if mobj is not None:
1900 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1902 # Look for Pladform embeds
1903 pladform_url = PladformIE._extract_url(webpage)
1905 return self.url_result(pladform_url)
1907 # Look for Videomore embeds
1908 videomore_url = VideomoreIE._extract_url(webpage)
1910 return self.url_result(videomore_url)
1912 # Look for Playwire embeds
1914 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1915 if mobj is not None:
1916 return self.url_result(mobj.group('url'))
1918 # Look for 5min embeds
1920 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1921 if mobj is not None:
1922 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1924 # Look for Crooks and Liars embeds
1926 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1927 if mobj is not None:
1928 return self.url_result(mobj.group('url'))
1930 # Look for NBC Sports VPlayer embeds
1931 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1933 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1935 # Look for Google Drive embeds
1936 google_drive_url = GoogleDriveIE._extract_url(webpage)
1937 if google_drive_url:
1938 return self.url_result(google_drive_url, 'GoogleDrive')
1940 # Look for UDN embeds
1942 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1943 if mobj is not None:
1944 return self.url_result(
1945 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1947 # Look for Senate ISVP iframe
1948 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1950 return self.url_result(senate_isvp_url, 'SenateISVP')
1952 # Look for Dailymotion Cloud videos
1953 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1955 return self.url_result(dmcloud_url, 'DailymotionCloud')
1957 # Look for OnionStudios embeds
1958 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1959 if onionstudios_url:
1960 return self.url_result(onionstudios_url)
1962 # Look for ViewLift embeds
1963 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1965 return self.url_result(viewlift_url)
1967 # Look for JWPlatform embeds
1968 jwplatform_url = JWPlatformIE._extract_url(webpage)
1970 return self.url_result(jwplatform_url, 'JWPlatform')
1972 # Look for ScreenwaveMedia embeds
1973 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1974 if mobj is not None:
1975 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1977 # Look for Digiteka embeds
1978 digiteka_url = DigitekaIE._extract_url(webpage)
1980 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1982 # Look for Limelight embeds
1983 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1987 'Channel': 'channel',
1988 'ChannelList': 'channel_list',
1990 return self.url_result('limelight:%s:%s' % (
1991 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1993 # Look for AdobeTVVideo embeds
1995 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1997 if mobj is not None:
1998 return self.url_result(
1999 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2002 # Look for Vine embeds
2004 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2006 if mobj is not None:
2007 return self.url_result(
2008 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2010 # Look for Instagram embeds
2011 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2012 if instagram_embed_url is not None:
2013 return self.url_result(
2014 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2016 # Look for LiveLeak embeds
2017 liveleak_url = LiveLeakIE._extract_url(webpage)
2019 return self.url_result(liveleak_url, 'LiveLeak')
2021 # Look for 3Q SDN embeds
2022 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2025 '_type': 'url_transparent',
2026 'ie_key': ThreeQSDNIE.ie_key(),
2027 'url': self._proto_relative_url(threeqsdn_url),
2028 'title': video_title,
2029 'description': video_description,
2030 'thumbnail': video_thumbnail,
2031 'uploader': video_uploader,
2034 def check_video(vurl):
2035 if YoutubeIE.suitable(vurl):
2037 vpath = compat_urlparse.urlparse(vurl).path
2038 vext = determine_ext(vpath)
2039 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2041 def filter_video(urls):
2042 return list(filter(check_video, urls))
2044 # Start with something easy: JW Player in SWFObject
2045 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2047 # Look for gorilla-vid style embedding
2048 found = filter_video(re.findall(r'''(?sx)
2052 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2055 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2057 # Broaden the search a little bit
2058 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2060 # Broaden the findall a little bit: JWPlayer JS loader
2061 found = filter_video(re.findall(
2062 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2065 found = filter_video(re.findall(r'''(?xs)
2066 flowplayer\("[^"]+",\s*
2068 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2069 ["']?url["']?\s*:\s*["']([^"']+)["']
2074 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2076 # Try to find twitter cards info
2077 found = filter_video(re.findall(
2078 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2080 # We look for Open Graph info:
2081 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2082 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2083 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2084 if m_video_type is not None:
2085 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2088 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2090 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2092 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2093 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2096 # Look also in Refresh HTTP header
2097 refresh_header = head_response.headers.get('Refresh')
2099 # In python 2 response HTTP headers are bytestrings
2100 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2101 refresh_header = refresh_header.decode('iso-8859-1')
2102 found = re.search(REDIRECT_REGEX, refresh_header)
2104 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2105 self.report_following_redirect(new_url)
2111 raise UnsupportedError(url)
2114 for video_url in found:
2115 video_url = unescapeHTML(video_url)
2116 video_url = video_url.replace('\\/', '/')
2117 video_url = compat_urlparse.urljoin(url, video_url)
2118 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2120 # Sometimes, jwplayer extraction will result in a YouTube URL
2121 if YoutubeIE.suitable(video_url):
2122 entries.append(self.url_result(video_url, 'Youtube'))
2125 # here's a fun little line of code for you:
2126 video_id = os.path.splitext(video_id)[0]
2130 'uploader': video_uploader,
2131 'title': video_title,
2132 'age_limit': age_limit,
2135 ext = determine_ext(video_url)
2137 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2139 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2141 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2143 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2145 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2147 entry_info_dict['url'] = video_url
2149 if entry_info_dict.get('formats'):
2150 self._sort_formats(entry_info_dict['formats'])
2152 entries.append(entry_info_dict)
2154 if len(entries) == 1:
2157 for num, e in enumerate(entries, start=1):
2158 # 'url' results don't have a title
2159 if e.get('title') is not None:
2160 e['title'] = '%s (%d)' % (e['title'], num)
2162 '_type': 'playlist',