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 (
56 from .onionstudios import OnionStudiosIE
57 from .viewlift import ViewLiftEmbedIE
58 from .screenwavemedia import ScreenwaveMediaIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .googledrive import GoogleDriveIE
63 from .jwplatform import JWPlatformIE
64 from .digiteka import DigitekaIE
65 from .instagram import InstagramIE
66 from .liveleak import LiveLeakIE
67 from .threeqsdn import ThreeQSDNIE
68 from .theplatform import ThePlatformIE
69 from .vessel import VesselIE
70 from .kaltura import KalturaIE
71 from .eagleplatform import EaglePlatformIE
72 from .facebook import FacebookIE
75 class GenericIE(InfoExtractor):
76 IE_DESC = 'Generic downloader that works on some sites'
80 # Direct link to a video
82 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
83 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
88 'upload_date': '20100513',
91 # Direct link to media delivered compressed (until Accept-Encoding is *)
93 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
94 'md5': '128c42e68b13950268b648275386fc74',
96 'id': 'FictionJunction-Parallel_Hearts',
98 'title': 'FictionJunction-Parallel_Hearts',
99 'upload_date': '20140522',
101 'expected_warnings': [
102 'URL could be a direct video link, returning it as such.'
105 # Direct download with broken HEAD
107 'url': 'http://ai-radio.org:8000/radio.opus',
114 'skip_download': True, # infinite live stream
116 'expected_warnings': [
117 r'501.*Not Implemented',
121 # Direct link with incorrect MIME type
123 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
124 'md5': '4ccbebe5f36706d85221f204d7eb5913',
126 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
127 'id': '5_Lennart_Poettering_-_Systemd',
129 'title': '5_Lennart_Poettering_-_Systemd',
130 'upload_date': '20141120',
132 'expected_warnings': [
133 'URL could be a direct video link, returning it as such.'
138 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
140 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
141 'title': 'Zero Punctuation',
142 'description': 're:.*groundbreaking video review series.*'
144 'playlist_mincount': 11,
146 # RSS feed with enclosure
148 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
150 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
152 'upload_date': '20150228',
153 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
156 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
158 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
162 'title': 'Automatics, robotics and biocybernetics',
163 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
164 'upload_date': '20130627',
165 'formats': 'mincount:16',
166 'subtitles': 'mincount:1',
169 'force_generic_extractor': True,
170 'skip_download': True,
173 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
175 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
180 'formats': 'mincount:1',
183 'skip_download': True,
186 # SMIL from https://www.restudy.dk/video/play/id/1637
188 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
192 'title': 'video_1637',
193 'formats': 'mincount:3',
196 'skip_download': True,
199 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
201 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
203 'id': 'smil-service',
205 'title': 'smil-service',
206 'formats': 'mincount:1',
209 'skip_download': True,
212 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
214 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
218 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
219 'formats': 'mincount:3',
222 'skip_download': True,
225 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
227 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
229 'id': 'mZlp2ctYIUEB',
231 'title': 'Tikibad ontruimd wegens brand',
232 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
233 'thumbnail': 're:^https?://.*\.jpg$',
237 'skip_download': True,
240 # MPD from http://dash-mse-test.appspot.com/media.html
242 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
243 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
245 'id': 'car-20120827-manifest',
247 'title': 'car-20120827-manifest',
248 'formats': 'mincount:9',
249 'upload_date': '20130904',
252 'format': 'bestvideo',
255 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
257 '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',
262 'formats': 'mincount:8',
266 'skip_download': True,
269 # m3u8 served with Content-Type: text/plain
271 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
276 'upload_date': '20140720',
277 'formats': 'mincount:11',
281 'skip_download': True,
286 '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',
290 'upload_date': '20130224',
291 'uploader_id': 'TheVerge',
292 'description': 're:^Chris Ziegler takes a look at the\.*',
293 'uploader': 'The Verge',
294 'title': 'First Firefox OS phones side-by-side',
297 'skip_download': False,
301 # redirect in Refresh HTTP header
302 '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',
306 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
307 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
308 'upload_date': '20150917',
309 'uploader_id': 'brtvofficial',
310 'uploader': 'Boiler Room',
313 'skip_download': False,
317 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
318 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
320 'id': '13601338388002',
322 'uploader': 'www.hodiho.fr',
323 'title': 'R\u00e9gis plante sa Jeep',
326 # bandcamp page with custom domain
328 'add_ie': ['Bandcamp'],
329 'url': 'http://bronyrock.com/track/the-pony-mash',
333 'title': 'The Pony Mash',
334 'uploader': 'M_Pallante',
336 'skip': 'There is a limit of 200 free downloads / month for the test song',
338 # embedded brightcove video
339 # it also tests brightcove videos that need to set the 'Referer' in the
342 'add_ie': ['BrightcoveLegacy'],
343 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
345 'id': '2765128793001',
347 'title': 'Le cours de bourse : l’analyse technique',
348 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
349 'uploader': 'BFM BUSINESS',
352 'skip_download': True,
356 # https://github.com/rg3/youtube-dl/issues/2253
357 'url': 'http://bcove.me/i6nfkrc3',
358 'md5': '0ba9446db037002366bab3b3eb30c88c',
360 'id': '3101154703001',
362 'title': 'Still no power',
363 'uploader': 'thestar.com',
364 '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.',
366 'add_ie': ['BrightcoveLegacy'],
369 'url': 'http://www.championat.com/video/football/v/87/87499.html',
370 'md5': 'fb973ecf6e4a78a67453647444222983',
372 'id': '3414141473001',
374 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
375 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
376 'uploader': 'Championat',
380 # https://github.com/rg3/youtube-dl/issues/3541
381 'add_ie': ['BrightcoveLegacy'],
382 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
384 'id': '3866516442001',
386 'title': 'Leer mij vrouwen kennen: Aflevering 1',
387 'description': 'Leer mij vrouwen kennen: Aflevering 1',
388 'uploader': 'SBS Broadcasting',
390 'skip': 'Restricted to Netherlands',
392 'skip_download': True, # m3u8 download
397 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
398 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
400 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
402 'title': '2cc213299525360.mov', # that's what we get
405 'add_ie': ['Ooyala'],
408 # ooyala video embedded with http://player.ooyala.com/iframe.js
409 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
411 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
413 'title': '"Steve Jobs: Man in the Machine" trailer',
414 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
418 'skip_download': True,
423 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
427 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
428 'upload_date': '20140225',
429 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
430 'uploader': 'Tested',
431 'uploader_id': 'testedcom',
433 # No need to test YoutubeIE here
435 'skip_download': True,
440 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
444 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
445 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
450 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
454 'title': 'Охотское море стало целиком российским',
455 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
459 'skip_download': True,
464 '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/',
468 'title': 'Дошкольное воспитание',
473 'url': 'http://www.vestifinance.ru/articles/25753',
476 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
481 'title': 'Госзаказ. День 3',
487 'title': 'Госзаказ. День 2',
493 'title': 'Госзаказ. День 1',
499 'skip_download': True,
504 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
506 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
508 'title': 'Ужастики, русский трейлер (2015)',
509 'thumbnail': 're:^https?://.*\.jpg$',
515 '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',
518 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
520 'playlist_mincount': 7,
524 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
525 'md5': '65fdff94098e4a607385a60c5177c638',
529 'title': 'Hidden miracles of the natural world',
530 'uploader': 'Louie Schwartzberg',
531 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
534 # Embedded Ustream video
536 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
537 'md5': '27b99cdb639c9b12a79bca876a073417',
541 'uploader': 'AU SPA: The NSA and Privacy',
542 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
545 # nowvideo embed hidden behind percent encoding
547 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
548 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
550 'id': '06e53103ca9aa',
552 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
553 'description': 'No description',
558 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
559 'md5': '7653032cbb25bf6c80d80f217055fa43',
561 'id': '048195-004_PLUS7-F',
564 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
565 'upload_date': '20140320',
568 'skip_download': 'Requires rtmpdump'
573 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
577 'title': 'Alcaline, le concert avec Calogero',
578 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
579 'upload_date': '20150226',
580 'timestamp': 1424989860,
585 'skip_download': True,
587 'expected_warnings': [
593 'url': 'http://www.wired.com/2014/04/honda-asimo/',
594 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
596 'id': '53501be369702d3275860000',
598 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
603 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
604 'md5': '441aeeb82eb72c422c7f14ec533999cd',
606 'id': 'k2mm4bCdJ6CQ2i7c8o2',
608 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
609 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
611 'uploader_id': 'xgditw',
612 'upload_date': '20140425',
613 'timestamp': 1398441542,
615 'add_ie': ['Dailymotion'],
619 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
623 'title': 'The NBL Auction 2014',
624 'uploader': 'BADMINTON England',
625 'uploader_id': 'BADMINTONEvents',
626 'upload_date': '20140603',
627 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
629 'add_ie': ['Youtube'],
631 'skip_download': True,
636 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
637 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
639 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
641 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
642 'description': 'Two valets share their love for movie star Liam Neesons.',
645 # YouTube embed via <data-embed-url="">
647 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
651 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
652 'uploader': 'Gameloft',
653 'uploader_id': 'gameloft',
654 'upload_date': '20140828',
655 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
658 'skip_download': True,
663 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
665 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
667 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
668 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
673 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
675 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
676 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
682 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
687 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
688 'md5': '9d65602bf31c6e20014319c7d07fba27',
690 'id': '5123ea6d5e5a7',
693 'uploader': 'www.handjobhub.com',
694 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
697 # Multiple brightcove videos
698 # https://github.com/rg3/youtube-dl/issues/2283
700 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
702 'id': 'always-never',
703 'title': 'Always / Never - The New Yorker',
707 'extract_flat': False,
708 'skip_download': True,
713 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
714 'md5': '96f09a37e44da40dd083e12d9a683327',
718 'title': 'Ump changes call to ball',
719 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
721 'timestamp': 1401537900,
722 'upload_date': '20140531',
723 'thumbnail': 're:^https?://.*\.jpg$',
728 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
729 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
733 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
734 'description': 'a Paywall Videos video from Remilon',
736 'uploader': 'study.com',
737 'timestamp': 1459678540,
738 'upload_date': '20160403',
739 'filesize': 24687186,
743 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
744 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
748 'title': 'Conversation about Hexagonal Rails Part 1',
749 'description': 'a Martin Fowler video from ThoughtWorks',
751 'uploader': 'thoughtworks.wistia.com',
752 'timestamp': 1401832161,
753 'upload_date': '20140603',
756 # Wistia standard embed (async)
758 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
762 'title': 'Drip Brennan Dunn Workshop',
763 'description': 'a JV Webinars video from getdrip-1',
765 'timestamp': 1463607249,
766 'upload_date': '20160518',
769 'skip_download': True,
774 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
778 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
779 'uploader': 'Sophos Security',
780 'title': 'Chet Chat 171 - Oct 29, 2014',
781 'upload_date': '20141029',
786 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
790 'upload_date': '20141112',
791 'title': 'Rosetta #CometLanding webcast HL 10',
794 # Another Livestream embed, without 'new.' in URL
796 'url': 'https://www.freespeech.org/',
800 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
804 'skip_download': True,
809 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
812 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
814 'playlist_mincount': 2,
818 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
822 'upload_date': '20141126',
823 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
828 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
830 'id': '730m_DandD_1901_512k',
832 'uploader': 'www.abc.net.au',
833 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
836 # embedded viddler video
838 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
842 'uploader': 'deadspin',
843 'title': 'WALL-TO-GORTAT',
844 'timestamp': 1422285291,
845 'upload_date': '20150126',
847 'add_ie': ['Viddler'],
851 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
855 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
856 'description': 'md5:601cb790edd05908957dae8aaa866465',
857 'upload_date': '20150220',
862 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
866 'upload_date': '20150212',
867 'uploader': 'The National Archives UK',
868 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
869 'uploader_id': 'NationalArchives08',
870 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
875 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
876 'playlist_mincount': 5,
878 'id': 'aanslagen-kopenhagen',
879 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
884 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
888 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
891 # Kaltura embed (different embed code)
893 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
897 'upload_date': '20150127',
898 'uploader_id': 'PremierMedia',
900 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
903 # Kaltura embed protected with referrer
905 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
909 'title': 'Violetta - Achter De Schermen - Ruggero',
910 'description': 'Achter de schermen met Ruggero',
911 'timestamp': 1435133761,
912 'upload_date': '20150624',
913 'uploader_id': 'echojecka',
916 # Kaltura embed with single quotes
918 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
923 'timestamp': 1355743100,
924 'upload_date': '20121217',
925 'uploader_id': 'batchUser',
927 'add_ie': ['Kaltura'],
930 # Kaltura embedded via quoted entry_id
931 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
935 'title': '06_matthew_brender_raj_dutt',
936 'timestamp': 1466638791,
937 'upload_date': '20160622',
939 'add_ie': ['Kaltura'],
940 'expected_warnings': [
941 'Could not send HEAD request'
944 'skip_download': True,
947 # Eagle.Platform embed (generic URL)
949 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
950 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
954 'title': 'Навальный вышел на свободу',
955 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
956 'thumbnail': 're:^https?://.*\.jpg$',
962 # ClipYou (Eagle.Platform) embed (custom URL)
964 'url': 'http://muz-tv.ru/play/7129/',
965 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
969 'title': "'O Sole Mio",
970 'thumbnail': 're:^https?://.*\.jpg$',
977 'url': 'http://muz-tv.ru/kinozal/view/7400/',
981 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
982 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
983 'thumbnail': 're:^https?://.*\.jpg$',
990 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
994 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
995 'thumbnail': 're:^https?://.*\.png$',
1001 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1002 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1006 'title': 'Facebook Creates "On This Day" | Crunch Report',
1011 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1015 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1020 # Crooks and Liars embed
1022 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1026 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1027 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1028 'timestamp': 1428207000,
1029 'upload_date': '20150405',
1030 'uploader': 'Heather',
1033 # Crooks and Liars external embed
1035 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1037 'id': 'MTE3MjUtMzQ2MzA',
1039 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1040 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1041 'timestamp': 1265032391,
1042 'upload_date': '20100201',
1043 'uploader': 'Heather',
1046 # NBC Sports vplayer embed
1048 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1050 'id': 'ln7x1qSThw4k',
1052 'title': "PFT Live: New leader in the 'new-look' defense",
1053 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1054 'uploader': 'NBCU-SPORTS',
1055 'upload_date': '20140107',
1056 'timestamp': 1389118457,
1061 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1062 'md5': '1aa589c675898ae6d37a17913cf68d66',
1064 'id': '701714499682',
1066 'title': 'PREVIEW: On Assignment: David Letterman',
1067 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1072 'url': 'https://video.udn.com/news/300346',
1073 'md5': 'fd2060e988c326991037b9aff9df21a6',
1077 'title': '中一中男師變性 全校師生力挺',
1078 'thumbnail': 're:^https?://.*\.jpg$',
1082 'skip_download': True,
1087 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1089 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1091 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1092 'title': 'This is what separates the Excel masters from the wannabes',
1093 'duration': 191.933,
1097 'skip_download': True,
1100 # Brightcove URL in single quotes
1102 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1103 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1105 'id': '4255764656001',
1107 'title': 'SN Presents: Russell Martin, World Citizen',
1108 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1109 'uploader': 'Rogers Sportsnet',
1110 'uploader_id': '1704050871',
1111 'upload_date': '20150525',
1112 'timestamp': 1432570283,
1115 # Dailymotion Cloud video
1117 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1118 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1122 'title': 'Sauvons les abeilles ! - Le débat',
1123 'description': 'md5:d9082128b1c5277987825d684939ca26',
1124 'thumbnail': 're:^https?://.*\.jpe?g$',
1125 'timestamp': 1434970506,
1126 'upload_date': '20150622',
1127 'uploader': 'Public Sénat',
1128 'uploader_id': 'xa9gza',
1131 # OnionStudios embed
1133 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1137 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1138 'thumbnail': 're:^https?://.*\.jpe?g$',
1139 'uploader': 'ClickHole',
1140 'uploader_id': 'clickhole',
1145 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1147 'id': '74849a00-85a9-11e1-9660-123139220831',
1149 'title': '#whilewewatch',
1152 # AdobeTVVideo embed
1154 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1155 'md5': '43662b577c018ad707a63766462b1e87',
1159 'title': 'New experience with Acrobat DC',
1160 'description': 'New experience with Acrobat DC',
1161 'duration': 248.667,
1164 # ScreenwaveMedia embed
1166 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1167 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1169 'id': 'cinemasnob-55d26273809dd',
1171 'title': 'cinemasnob',
1174 # BrightcoveInPageEmbed embed
1176 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1178 'id': '4238694884001',
1180 'title': 'Tabletop: Dread, Last Thoughts',
1181 'description': 'Tabletop: Dread, Last Thoughts',
1185 # JWPlayer with M3U8
1187 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1191 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1192 'uploader': 'ren.tv',
1196 'skip_download': True,
1199 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1200 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1202 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1204 'id': '4785848093001',
1206 'title': 'The Cardinal Pell Interview',
1207 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1208 'uploader': 'GlobeCast Australia - GlobeStream',
1209 'uploader_id': '2733773828001',
1210 'upload_date': '20160304',
1211 'timestamp': 1457083087,
1215 'skip_download': True,
1218 # Another form of arte.tv embed
1220 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1221 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1223 'id': '030273-562_PLUS7-F',
1225 'title': 'ARTE Reportage - Nulle part, en France',
1226 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1227 'upload_date': '20160409',
1232 'url': 'http://www.wykop.pl/link/3088787/',
1233 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1235 'id': '874_1459135191',
1237 'title': 'Man shows poor quality of new apartment building',
1238 'description': 'The wall is like a sand pile.',
1239 'uploader': 'Lake8737',
1242 # Duplicated embedded video URLs
1244 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1246 'id': '149298443_480_16c25b74_2',
1248 'title': 'vs. Blue Orange Spring Game',
1249 'uploader': 'www.hudl.com',
1252 # twitter:player:stream embed
1254 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1258 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1259 'uploader': 'www.rtl.be',
1263 'skip_download': True,
1266 # twitter:player embed
1268 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1269 'md5': 'a3e0df96369831de324f0778e126653c',
1271 'id': '4909620399001',
1273 'title': 'What Do Black Holes Sound Like?',
1274 'description': 'what do black holes sound like',
1275 'upload_date': '20160524',
1276 'uploader_id': '29913724001',
1277 'timestamp': 1464107587,
1278 'uploader': 'TheAtlantic',
1280 'add_ie': ['BrightcoveLegacy'],
1282 # Facebook <iframe> embed
1284 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1285 'md5': 'fbcde74f534176ecb015849146dd3aee',
1287 'id': '599637780109885',
1289 'title': 'Facebook video #599637780109885',
1292 # Facebook API embed
1294 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1295 'md5': 'a47372ee61b39a7b90287094d447d94e',
1297 'id': '10153467542406923',
1299 'title': 'Facebook video #10153467542406923',
1302 # Wordpress "YouTube Video Importer" plugin
1304 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1305 'md5': 'd16797741b560b485194eddda8121b48',
1307 'id': 'HNTXWDXV9Is',
1309 'title': 'Blue Devils Drumline Stanford lot 2016',
1310 'upload_date': '20160627',
1311 'uploader_id': 'GENOCIDE8GENERAL10',
1312 'uploader': 'cylus cyrus',
1316 # video stored on custom kaltura server
1317 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1318 'md5': '537617d06e64dfed891fa1593c4b30cc',
1322 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1323 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1324 'uploader_id': 'videos.expansion@el-mundo.net',
1325 'upload_date': '20150429',
1326 'timestamp': 1430303472,
1328 'add_ie': ['Kaltura'],
1331 # Non-standard Vimeo embed
1332 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1333 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1337 'title': 'Understanding the web - Teaser',
1338 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1339 'upload_date': '20151214',
1340 'uploader': 'OpenClassrooms',
1341 'uploader_id': 'openclassrooms',
1343 'add_ie': ['Vimeo'],
1346 # # TODO: find another test
1347 # # http://schema.org/VideoObject
1348 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1349 # 'md5': '888dcf08b7ea671381f00fab74692755',
1351 # 'id': 'nyvTSJMKId',
1353 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1354 # 'description': '#love for cats.',
1355 # 'timestamp': 1461244995,
1356 # 'upload_date': '20160421',
1359 # 'force_generic_extractor': True,
1364 def report_following_redirect(self, new_url):
1365 """Report information extraction."""
1366 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1368 def _extract_rss(self, url, video_id, doc):
1369 playlist_title = doc.find('./channel/title').text
1370 playlist_desc_el = doc.find('./channel/description')
1371 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1374 for it in doc.findall('./channel/item'):
1375 next_url = xpath_text(it, 'link', fatal=False)
1377 enclosure_nodes = it.findall('./enclosure')
1378 for e in enclosure_nodes:
1379 next_url = e.attrib.get('url')
1389 'title': it.find('title').text,
1393 '_type': 'playlist',
1395 'title': playlist_title,
1396 'description': playlist_desc,
1400 def _extract_camtasia(self, url, video_id, webpage):
1401 """ Returns None if no camtasia video can be found. """
1403 camtasia_cfg = self._search_regex(
1404 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1405 webpage, 'camtasia configuration file', default=None)
1406 if camtasia_cfg is None:
1409 title = self._html_search_meta('DC.title', webpage, fatal=True)
1411 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1412 camtasia_cfg = self._download_xml(
1413 camtasia_url, video_id,
1414 note='Downloading camtasia configuration',
1415 errnote='Failed to download camtasia configuration')
1416 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1419 for n in fileset_node.getchildren():
1420 url_n = n.find('./uri')
1425 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1426 'title': '%s - %s' % (title, n.tag),
1427 'url': compat_urlparse.urljoin(url, url_n.text),
1428 'duration': float_or_none(n.find('./duration').text),
1432 '_type': 'playlist',
1437 def _real_extract(self, url):
1438 if url.startswith('//'):
1441 'url': self.http_scheme() + url,
1444 parsed_url = compat_urlparse.urlparse(url)
1445 if not parsed_url.scheme:
1446 default_search = self._downloader.params.get('default_search')
1447 if default_search is None:
1448 default_search = 'fixup_error'
1450 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1452 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1453 return self.url_result('http://' + url)
1454 elif default_search != 'fixup_error':
1455 if default_search == 'auto_warning':
1456 if re.match(r'^(?:url|URL)$', url):
1457 raise ExtractorError(
1458 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1461 self._downloader.report_warning(
1462 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1463 return self.url_result('ytsearch:' + url)
1465 if default_search in ('error', 'fixup_error'):
1466 raise ExtractorError(
1467 '%r is not a valid URL. '
1468 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1469 % (url, url), expected=True)
1471 if ':' not in default_search:
1472 default_search += ':'
1473 return self.url_result(default_search + url)
1475 url, smuggled_data = unsmuggle_url(url)
1476 force_videoid = None
1477 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1478 if smuggled_data and 'force_videoid' in smuggled_data:
1479 force_videoid = smuggled_data['force_videoid']
1480 video_id = force_videoid
1482 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1484 self.to_screen('%s: Requesting header' % video_id)
1486 head_req = HEADRequest(url)
1487 head_response = self._request_webpage(
1489 note=False, errnote='Could not send HEAD request to %s' % url,
1492 if head_response is not False:
1493 # Check for redirect
1494 new_url = head_response.geturl()
1496 self.report_following_redirect(new_url)
1498 new_url = smuggle_url(
1499 new_url, {'force_videoid': force_videoid})
1500 return self.url_result(new_url)
1502 full_response = None
1503 if head_response is False:
1504 request = sanitized_Request(url)
1505 request.add_header('Accept-Encoding', '*')
1506 full_response = self._request_webpage(request, video_id)
1507 head_response = full_response
1511 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1512 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1515 # Check for direct link to a video
1516 content_type = head_response.headers.get('Content-Type', '').lower()
1517 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1519 format_id = m.group('format_id')
1520 if format_id.endswith('mpegurl'):
1521 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1522 elif format_id == 'f4m':
1523 formats = self._extract_f4m_formats(url, video_id)
1526 'format_id': m.group('format_id'),
1528 'vcodec': 'none' if m.group('type') == 'audio' else None
1530 info_dict['direct'] = True
1531 self._sort_formats(formats)
1532 info_dict['formats'] = formats
1535 if not self._downloader.params.get('test', False) and not is_intentional:
1536 force = self._downloader.params.get('force_generic_extractor', False)
1537 self._downloader.report_warning(
1538 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1540 if not full_response:
1541 request = sanitized_Request(url)
1542 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1543 # making it impossible to download only chunk of the file (yet we need only 512kB to
1544 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1545 # that will always result in downloading the whole file that is not desirable.
1546 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1547 # to accept raw bytes and being able to download only a chunk.
1548 # It may probably better to solve this by checking Content-Type for application/octet-stream
1549 # after HEAD request finishes, but not sure if we can rely on this.
1550 request.add_header('Accept-Encoding', '*')
1551 full_response = self._request_webpage(request, video_id)
1553 first_bytes = full_response.read(512)
1555 # Is it an M3U playlist?
1556 if first_bytes.startswith(b'#EXTM3U'):
1557 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1558 self._sort_formats(info_dict['formats'])
1561 # Maybe it's a direct link to a video?
1562 # Be careful not to download the whole thing!
1563 if not is_html(first_bytes):
1564 self._downloader.report_warning(
1565 'URL could be a direct video link, returning it as such.')
1572 webpage = self._webpage_read_content(
1573 full_response, url, video_id, prefix=first_bytes)
1575 self.report_extraction(video_id)
1577 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1579 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1580 if doc.tag == 'rss':
1581 return self._extract_rss(url, video_id, doc)
1582 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1583 smil = self._parse_smil(doc, url, video_id)
1584 self._sort_formats(smil['formats'])
1586 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1587 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1588 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1589 info_dict['formats'] = self._parse_mpd_formats(
1590 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1591 self._sort_formats(info_dict['formats'])
1593 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1594 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1595 self._sort_formats(info_dict['formats'])
1597 except compat_xml_parse_error:
1600 # Is it a Camtasia project?
1601 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1602 if camtasia_res is not None:
1605 # Sometimes embedded video player is hidden behind percent encoding
1606 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1607 # Unescaping the whole page allows to handle those cases in a generic way
1608 webpage = compat_urllib_parse_unquote(webpage)
1610 # it's tempting to parse this further, but you would
1611 # have to take into account all the variations like
1612 # Video Title - Site Name
1613 # Site Name | Video Title
1614 # Video Title - Tagline | Site Name
1615 # and so on and so forth; it's just not practical
1616 video_title = self._og_search_title(
1617 webpage, default=None) or self._html_search_regex(
1618 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1621 # Try to detect age limit automatically
1622 age_limit = self._rta_search(webpage)
1623 # And then there are the jokers who advertise that they use RTA,
1624 # but actually don't.
1625 AGE_LIMIT_MARKERS = [
1626 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1628 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1631 # video uploader is domain name
1632 video_uploader = self._search_regex(
1633 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1635 video_description = self._og_search_description(webpage, default=None)
1636 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1639 def _playlist_from_matches(matches, getter=None, ie=None):
1641 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1643 return self.playlist_result(
1644 urlrs, playlist_id=video_id, playlist_title=video_title)
1646 # Look for Brightcove Legacy Studio embeds
1647 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1649 self.to_screen('Brightcove video detected.')
1652 'url': smuggle_url(bc_url, {'Referer': url}),
1653 'ie_key': 'BrightcoveLegacy'
1654 } for bc_url in bc_urls]
1657 '_type': 'playlist',
1658 'title': video_title,
1663 # Look for Brightcove New Studio embeds
1664 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1666 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1668 # Look for ThePlatform embeds
1669 tp_urls = ThePlatformIE._extract_urls(webpage)
1671 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1673 # Look for Vessel embeds
1674 vessel_urls = VesselIE._extract_urls(webpage)
1676 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1678 # Look for embedded rtl.nl player
1679 matches = re.findall(
1680 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1683 return _playlist_from_matches(matches, ie='RtlNl')
1685 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1686 if vimeo_url is not None:
1687 return self.url_result(vimeo_url)
1689 vid_me_embed_url = self._search_regex(
1690 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1691 webpage, 'vid.me embed', default=None)
1692 if vid_me_embed_url is not None:
1693 return self.url_result(vid_me_embed_url, 'Vidme')
1695 # Look for embedded YouTube player
1696 matches = re.findall(r'''(?x)
1705 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1709 return _playlist_from_matches(
1710 matches, lambda m: unescapeHTML(m[1]))
1712 # Look for lazyYT YouTube embed
1713 matches = re.findall(
1714 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1716 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1718 # Look for Wordpress "YouTube Video Importer" plugin
1719 matches = re.findall(r'''(?x)<div[^>]+
1720 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1721 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1723 return _playlist_from_matches(matches, lambda m: m[-1])
1725 matches = DailymotionIE._extract_urls(webpage)
1727 return _playlist_from_matches(matches)
1729 # Look for embedded Dailymotion playlist player (#3822)
1731 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1733 playlists = re.findall(
1734 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1736 return _playlist_from_matches(
1737 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1739 # Look for embedded Wistia player
1741 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1743 embed_url = self._proto_relative_url(
1744 unescapeHTML(match.group('url')))
1746 '_type': 'url_transparent',
1749 'uploader': video_uploader,
1752 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1755 '_type': 'url_transparent',
1756 'url': 'wistia:%s' % match.group('id'),
1758 'uploader': video_uploader,
1763 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1764 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1767 return self.url_result(self._proto_relative_url(
1768 'wistia:%s' % match.group('id')), 'Wistia')
1770 # Look for SVT player
1771 svt_url = SVTIE._extract_url(webpage)
1773 return self.url_result(svt_url, 'SVT')
1775 # Look for embedded condenast player
1776 matches = re.findall(
1777 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1781 '_type': 'playlist',
1784 'ie_key': 'CondeNast',
1786 } for ma in matches],
1787 'title': video_title,
1791 # Look for Bandcamp pages with custom domain
1792 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1793 if mobj is not None:
1794 burl = unescapeHTML(mobj.group(1))
1795 # Don't set the extractor because it can be a track url or an album
1796 return self.url_result(burl)
1798 # Look for embedded Vevo player
1800 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1801 if mobj is not None:
1802 return self.url_result(mobj.group('url'))
1804 # Look for embedded Viddler player
1806 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1808 if mobj is not None:
1809 return self.url_result(mobj.group('url'))
1811 # Look for NYTimes player
1813 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1815 if mobj is not None:
1816 return self.url_result(mobj.group('url'))
1818 # Look for Libsyn player
1820 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1821 if mobj is not None:
1822 return self.url_result(mobj.group('url'))
1824 # Look for Ooyala videos
1825 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1826 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1827 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1828 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1829 if mobj is not None:
1830 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1832 # Look for multiple Ooyala embeds on SBN network websites
1833 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1834 if mobj is not None:
1835 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1837 return _playlist_from_matches(
1838 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1840 # Look for Aparat videos
1841 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1842 if mobj is not None:
1843 return self.url_result(mobj.group(1), 'Aparat')
1845 # Look for MPORA videos
1846 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1847 if mobj is not None:
1848 return self.url_result(mobj.group(1), 'Mpora')
1850 # Look for embedded NovaMov-based player
1852 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1853 (?P<url>http://(?:(?:embed|www)\.)?
1855 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1856 videoweed\.(?:es|com)|
1857 movshare\.(?:net|sx|ag)|
1858 divxstage\.(?:eu|net|ch|co|at|ag))
1859 /embed\.php.+?)\1''', webpage)
1860 if mobj is not None:
1861 return self.url_result(mobj.group('url'))
1863 # Look for embedded Facebook player
1864 facebook_url = FacebookIE._extract_url(webpage)
1865 if facebook_url is not None:
1866 return self.url_result(facebook_url, 'Facebook')
1868 # Look for embedded VK player
1869 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1870 if mobj is not None:
1871 return self.url_result(mobj.group('url'), 'VK')
1873 # Look for embedded Odnoklassniki player
1874 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1875 if mobj is not None:
1876 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1878 # Look for embedded ivi player
1879 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1880 if mobj is not None:
1881 return self.url_result(mobj.group('url'), 'Ivi')
1883 # Look for embedded Huffington Post player
1885 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1886 if mobj is not None:
1887 return self.url_result(mobj.group('url'), 'HuffPost')
1890 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1891 if mobj is not None:
1892 return self.url_result(mobj.group('url'))
1893 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1894 if mobj is not None:
1895 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1897 # Look for funnyordie embed
1898 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1900 return _playlist_from_matches(
1901 matches, getter=unescapeHTML, ie='FunnyOrDie')
1903 # Look for BBC iPlayer embed
1904 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1906 return _playlist_from_matches(matches, ie='BBCCoUk')
1908 # Look for embedded RUTV player
1909 rutv_url = RUTVIE._extract_url(webpage)
1911 return self.url_result(rutv_url, 'RUTV')
1913 # Look for embedded TVC player
1914 tvc_url = TVCIE._extract_url(webpage)
1916 return self.url_result(tvc_url, 'TVC')
1918 # Look for embedded SportBox player
1919 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1921 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1923 # Look for embedded PornHub player
1924 pornhub_url = PornHubIE._extract_url(webpage)
1926 return self.url_result(pornhub_url, 'PornHub')
1928 # Look for embedded XHamster player
1929 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1931 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1933 # Look for embedded TNAFlixNetwork player
1934 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1936 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1938 # Look for embedded Tvigle player
1940 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1941 if mobj is not None:
1942 return self.url_result(mobj.group('url'), 'Tvigle')
1944 # Look for embedded TED player
1946 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1947 if mobj is not None:
1948 return self.url_result(mobj.group('url'), 'TED')
1950 # Look for embedded Ustream videos
1952 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1953 if mobj is not None:
1954 return self.url_result(mobj.group('url'), 'Ustream')
1956 # Look for embedded arte.tv player
1958 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1960 if mobj is not None:
1961 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1963 # Look for embedded francetv player
1965 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1967 if mobj is not None:
1968 return self.url_result(mobj.group('url'))
1970 # Look for embedded smotri.com player
1971 smotri_url = SmotriIE._extract_url(webpage)
1973 return self.url_result(smotri_url, 'Smotri')
1975 # Look for embedded Myvi.ru player
1976 myvi_url = MyviIE._extract_url(webpage)
1978 return self.url_result(myvi_url)
1980 # Look for embedded soundcloud player
1982 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1984 if mobj is not None:
1985 url = unescapeHTML(mobj.group('url'))
1986 return self.url_result(url)
1988 # Look for embedded mtvservices player
1989 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1991 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1993 # Look for embedded yahoo player
1995 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1997 if mobj is not None:
1998 return self.url_result(mobj.group('url'), 'Yahoo')
2000 # Look for embedded sbs.com.au player
2004 <meta\s+property="og:video"\s+content=|
2007 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2009 if mobj is not None:
2010 return self.url_result(mobj.group('url'), 'SBS')
2012 # Look for embedded Cinchcast player
2014 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2016 if mobj is not None:
2017 return self.url_result(mobj.group('url'), 'Cinchcast')
2020 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2024 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2026 if mobj is not None:
2027 return self.url_result(mobj.group('url'), 'MLB')
2030 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2032 if mobj is not None:
2033 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2036 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2038 if mobj is not None:
2039 return self.url_result(mobj.group('url'), 'Livestream')
2041 # Look for Zapiks embed
2043 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2044 if mobj is not None:
2045 return self.url_result(mobj.group('url'), 'Zapiks')
2047 # Look for Kaltura embeds
2048 kaltura_url = KalturaIE._extract_url(webpage)
2050 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2052 # Look for Eagle.Platform embeds
2053 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2054 if eagleplatform_url:
2055 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2057 # Look for ClipYou (uses Eagle.Platform) embeds
2059 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2060 if mobj is not None:
2061 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2063 # Look for Pladform embeds
2064 pladform_url = PladformIE._extract_url(webpage)
2066 return self.url_result(pladform_url)
2068 # Look for Videomore embeds
2069 videomore_url = VideomoreIE._extract_url(webpage)
2071 return self.url_result(videomore_url)
2073 # Look for Playwire embeds
2075 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2076 if mobj is not None:
2077 return self.url_result(mobj.group('url'))
2079 # Look for 5min embeds
2081 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2082 if mobj is not None:
2083 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2085 # Look for Crooks and Liars embeds
2087 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2088 if mobj is not None:
2089 return self.url_result(mobj.group('url'))
2091 # Look for NBC Sports VPlayer embeds
2092 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2094 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2096 # Look for NBC News embeds
2097 nbc_news_embed_url = re.search(
2098 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2099 if nbc_news_embed_url:
2100 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2102 # Look for Google Drive embeds
2103 google_drive_url = GoogleDriveIE._extract_url(webpage)
2104 if google_drive_url:
2105 return self.url_result(google_drive_url, 'GoogleDrive')
2107 # Look for UDN embeds
2109 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2110 if mobj is not None:
2111 return self.url_result(
2112 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2114 # Look for Senate ISVP iframe
2115 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2117 return self.url_result(senate_isvp_url, 'SenateISVP')
2119 # Look for Dailymotion Cloud videos
2120 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2122 return self.url_result(dmcloud_url, 'DailymotionCloud')
2124 # Look for OnionStudios embeds
2125 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2126 if onionstudios_url:
2127 return self.url_result(onionstudios_url)
2129 # Look for ViewLift embeds
2130 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2132 return self.url_result(viewlift_url)
2134 # Look for JWPlatform embeds
2135 jwplatform_url = JWPlatformIE._extract_url(webpage)
2137 return self.url_result(jwplatform_url, 'JWPlatform')
2139 # Look for ScreenwaveMedia embeds
2140 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2141 if mobj is not None:
2142 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2144 # Look for Digiteka embeds
2145 digiteka_url = DigitekaIE._extract_url(webpage)
2147 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2149 # Look for Limelight embeds
2150 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2154 'Channel': 'channel',
2155 'ChannelList': 'channel_list',
2157 return self.url_result('limelight:%s:%s' % (
2158 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2160 # Look for AdobeTVVideo embeds
2162 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2164 if mobj is not None:
2165 return self.url_result(
2166 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2169 # Look for Vine embeds
2171 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2173 if mobj is not None:
2174 return self.url_result(
2175 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2177 # Look for Instagram embeds
2178 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2179 if instagram_embed_url is not None:
2180 return self.url_result(
2181 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2183 # Look for LiveLeak embeds
2184 liveleak_url = LiveLeakIE._extract_url(webpage)
2186 return self.url_result(liveleak_url, 'LiveLeak')
2188 # Look for 3Q SDN embeds
2189 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2192 '_type': 'url_transparent',
2193 'ie_key': ThreeQSDNIE.ie_key(),
2194 'url': self._proto_relative_url(threeqsdn_url),
2195 'title': video_title,
2196 'description': video_description,
2197 'thumbnail': video_thumbnail,
2198 'uploader': video_uploader,
2201 # Looking for http://schema.org/VideoObject
2202 json_ld = self._search_json_ld(
2203 webpage, video_id, default=None, expected_type='VideoObject')
2204 if json_ld and json_ld.get('url'):
2206 'title': video_title or info_dict['title'],
2207 'description': video_description,
2208 'thumbnail': video_thumbnail,
2209 'age_limit': age_limit
2211 info_dict.update(json_ld)
2214 def check_video(vurl):
2215 if YoutubeIE.suitable(vurl):
2217 vpath = compat_urlparse.urlparse(vurl).path
2218 vext = determine_ext(vpath)
2219 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2221 def filter_video(urls):
2222 return list(filter(check_video, urls))
2224 # Start with something easy: JW Player in SWFObject
2225 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2227 # Look for gorilla-vid style embedding
2228 found = filter_video(re.findall(r'''(?sx)
2232 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2235 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2237 # Broaden the search a little bit
2238 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2240 # Broaden the findall a little bit: JWPlayer JS loader
2241 found = filter_video(re.findall(
2242 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2245 found = filter_video(re.findall(r'''(?xs)
2246 flowplayer\("[^"]+",\s*
2248 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2249 ["']?url["']?\s*:\s*["']([^"']+)["']
2254 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2256 # Try to find twitter cards info
2257 # twitter:player:stream should be checked before twitter:player since
2258 # it is expected to contain a raw stream (see
2259 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2260 found = filter_video(re.findall(
2261 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2263 # We look for Open Graph info:
2264 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2265 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2266 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2267 if m_video_type is not None:
2268 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2271 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2273 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2275 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2276 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2279 # Look also in Refresh HTTP header
2280 refresh_header = head_response.headers.get('Refresh')
2282 # In python 2 response HTTP headers are bytestrings
2283 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2284 refresh_header = refresh_header.decode('iso-8859-1')
2285 found = re.search(REDIRECT_REGEX, refresh_header)
2287 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2288 self.report_following_redirect(new_url)
2295 # twitter:player is a https URL to iframe player that may or may not
2296 # be supported by youtube-dl thus this is checked the very last (see
2297 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2298 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2300 return self.url_result(embed_url)
2303 raise UnsupportedError(url)
2306 for video_url in orderedSet(found):
2307 video_url = unescapeHTML(video_url)
2308 video_url = video_url.replace('\\/', '/')
2309 video_url = compat_urlparse.urljoin(url, video_url)
2310 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2312 # Sometimes, jwplayer extraction will result in a YouTube URL
2313 if YoutubeIE.suitable(video_url):
2314 entries.append(self.url_result(video_url, 'Youtube'))
2317 # here's a fun little line of code for you:
2318 video_id = os.path.splitext(video_id)[0]
2322 'uploader': video_uploader,
2323 'title': video_title,
2324 'age_limit': age_limit,
2327 ext = determine_ext(video_url)
2329 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2331 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2333 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2335 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2337 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2339 entry_info_dict['url'] = video_url
2341 if entry_info_dict.get('formats'):
2342 self._sort_formats(entry_info_dict['formats'])
2344 entries.append(entry_info_dict)
2346 if len(entries) == 1:
2349 for num, e in enumerate(entries, start=1):
2350 # 'url' results don't have a title
2351 if e.get('title') is not None:
2352 e['title'] = '%s (%d)' % (e['title'], num)
2354 '_type': 'playlist',