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
66 from .vessel import VesselIE
67 from .kaltura import KalturaIE
68 from .eagleplatform import EaglePlatformIE
69 from .facebook import FacebookIE
72 class GenericIE(InfoExtractor):
73 IE_DESC = 'Generic downloader that works on some sites'
77 # Direct link to a video
79 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
80 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
85 'upload_date': '20100513',
88 # Direct link to media delivered compressed (until Accept-Encoding is *)
90 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
91 'md5': '128c42e68b13950268b648275386fc74',
93 'id': 'FictionJunction-Parallel_Hearts',
95 'title': 'FictionJunction-Parallel_Hearts',
96 'upload_date': '20140522',
98 'expected_warnings': [
99 'URL could be a direct video link, returning it as such.'
102 # Direct download with broken HEAD
104 'url': 'http://ai-radio.org:8000/radio.opus',
111 'skip_download': True, # infinite live stream
113 'expected_warnings': [
114 r'501.*Not Implemented',
118 # Direct link with incorrect MIME type
120 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
121 'md5': '4ccbebe5f36706d85221f204d7eb5913',
123 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
124 'id': '5_Lennart_Poettering_-_Systemd',
126 'title': '5_Lennart_Poettering_-_Systemd',
127 'upload_date': '20141120',
129 'expected_warnings': [
130 'URL could be a direct video link, returning it as such.'
135 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
137 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
138 'title': 'Zero Punctuation',
139 'description': 're:.*groundbreaking video review series.*'
141 'playlist_mincount': 11,
143 # RSS feed with enclosure
145 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
147 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
149 'upload_date': '20150228',
150 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
153 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
155 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
159 'title': 'Automatics, robotics and biocybernetics',
160 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
161 'upload_date': '20130627',
162 'formats': 'mincount:16',
163 'subtitles': 'mincount:1',
166 'force_generic_extractor': True,
167 'skip_download': True,
170 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
172 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
177 'formats': 'mincount:1',
180 'skip_download': True,
183 # SMIL from https://www.restudy.dk/video/play/id/1637
185 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
189 'title': 'video_1637',
190 'formats': 'mincount:3',
193 'skip_download': True,
196 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
198 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
200 'id': 'smil-service',
202 'title': 'smil-service',
203 'formats': 'mincount:1',
206 'skip_download': True,
209 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
211 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
215 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
216 'formats': 'mincount:3',
219 'skip_download': True,
222 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
224 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
226 'id': 'mZlp2ctYIUEB',
228 'title': 'Tikibad ontruimd wegens brand',
229 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
230 'thumbnail': 're:^https?://.*\.jpg$',
234 'skip_download': True,
237 # MPD from http://dash-mse-test.appspot.com/media.html
239 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
240 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
242 'id': 'car-20120827-manifest',
244 'title': 'car-20120827-manifest',
245 'formats': 'mincount:9',
246 'upload_date': '20130904',
249 'format': 'bestvideo',
252 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
254 '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',
259 'formats': 'mincount:8',
263 'skip_download': True,
266 # m3u8 served with Content-Type: text/plain
268 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
273 'upload_date': '20140720',
274 'formats': 'mincount:11',
278 'skip_download': True,
283 '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',
287 'upload_date': '20130224',
288 'uploader_id': 'TheVerge',
289 'description': 're:^Chris Ziegler takes a look at the\.*',
290 'uploader': 'The Verge',
291 'title': 'First Firefox OS phones side-by-side',
294 'skip_download': False,
298 # redirect in Refresh HTTP header
299 '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',
303 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
304 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
305 'upload_date': '20150917',
306 'uploader_id': 'brtvofficial',
307 'uploader': 'Boiler Room',
310 'skip_download': False,
314 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
315 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
317 'id': '13601338388002',
319 'uploader': 'www.hodiho.fr',
320 'title': 'R\u00e9gis plante sa Jeep',
323 # bandcamp page with custom domain
325 'add_ie': ['Bandcamp'],
326 'url': 'http://bronyrock.com/track/the-pony-mash',
330 'title': 'The Pony Mash',
331 'uploader': 'M_Pallante',
333 'skip': 'There is a limit of 200 free downloads / month for the test song',
335 # embedded brightcove video
336 # it also tests brightcove videos that need to set the 'Referer' in the
339 'add_ie': ['BrightcoveLegacy'],
340 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
342 'id': '2765128793001',
344 'title': 'Le cours de bourse : l’analyse technique',
345 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
346 'uploader': 'BFM BUSINESS',
349 'skip_download': True,
353 # https://github.com/rg3/youtube-dl/issues/2253
354 'url': 'http://bcove.me/i6nfkrc3',
355 'md5': '0ba9446db037002366bab3b3eb30c88c',
357 'id': '3101154703001',
359 'title': 'Still no power',
360 'uploader': 'thestar.com',
361 '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.',
363 'add_ie': ['BrightcoveLegacy'],
366 'url': 'http://www.championat.com/video/football/v/87/87499.html',
367 'md5': 'fb973ecf6e4a78a67453647444222983',
369 'id': '3414141473001',
371 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
372 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
373 'uploader': 'Championat',
377 # https://github.com/rg3/youtube-dl/issues/3541
378 'add_ie': ['BrightcoveLegacy'],
379 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
381 'id': '3866516442001',
383 'title': 'Leer mij vrouwen kennen: Aflevering 1',
384 'description': 'Leer mij vrouwen kennen: Aflevering 1',
385 'uploader': 'SBS Broadcasting',
387 'skip': 'Restricted to Netherlands',
389 'skip_download': True, # m3u8 download
394 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
395 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
397 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
399 'title': '2cc213299525360.mov', # that's what we get
402 'add_ie': ['Ooyala'],
405 # ooyala video embedded with http://player.ooyala.com/iframe.js
406 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
408 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
410 'title': '"Steve Jobs: Man in the Machine" trailer',
411 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
415 'skip_download': True,
420 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
424 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
425 'upload_date': '20140225',
426 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
427 'uploader': 'Tested',
428 'uploader_id': 'testedcom',
430 # No need to test YoutubeIE here
432 'skip_download': True,
437 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
441 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
442 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
447 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
451 'title': 'Охотское море стало целиком российским',
452 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
456 'skip_download': True,
461 '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/',
465 'title': 'Дошкольное воспитание',
470 'url': 'http://www.vestifinance.ru/articles/25753',
473 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
478 'title': 'Госзаказ. День 3',
484 'title': 'Госзаказ. День 2',
490 'title': 'Госзаказ. День 1',
496 'skip_download': True,
501 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
503 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
505 'title': 'Ужастики, русский трейлер (2015)',
506 'thumbnail': 're:^https?://.*\.jpg$',
512 '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',
515 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
517 'playlist_mincount': 7,
521 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
522 'md5': '65fdff94098e4a607385a60c5177c638',
526 'title': 'Hidden miracles of the natural world',
527 'uploader': 'Louie Schwartzberg',
528 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
531 # Embedded Ustream video
533 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
534 'md5': '27b99cdb639c9b12a79bca876a073417',
538 'uploader': 'AU SPA: The NSA and Privacy',
539 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
542 # nowvideo embed hidden behind percent encoding
544 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
545 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
547 'id': '06e53103ca9aa',
549 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
550 'description': 'No description',
555 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
556 'md5': '7653032cbb25bf6c80d80f217055fa43',
558 'id': '048195-004_PLUS7-F',
561 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
562 'upload_date': '20140320',
565 'skip_download': 'Requires rtmpdump'
570 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
574 'title': 'Alcaline, le concert avec Calogero',
575 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
576 'upload_date': '20150226',
577 'timestamp': 1424989860,
582 'skip_download': True,
584 'expected_warnings': [
590 'url': 'http://www.wired.com/2014/04/honda-asimo/',
591 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
593 'id': '53501be369702d3275860000',
595 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
600 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
601 'md5': '441aeeb82eb72c422c7f14ec533999cd',
603 'id': 'k2mm4bCdJ6CQ2i7c8o2',
605 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
606 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
608 'uploader_id': 'xgditw',
609 'upload_date': '20140425',
610 'timestamp': 1398441542,
612 'add_ie': ['Dailymotion'],
616 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
620 'title': 'The NBL Auction 2014',
621 'uploader': 'BADMINTON England',
622 'uploader_id': 'BADMINTONEvents',
623 'upload_date': '20140603',
624 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
626 'add_ie': ['Youtube'],
628 'skip_download': True,
633 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
634 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
636 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
638 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
639 'description': 'Two valets share their love for movie star Liam Neesons.',
642 # YouTube embed via <data-embed-url="">
644 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
648 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
649 'uploader': 'Gameloft',
650 'uploader_id': 'gameloft',
651 'upload_date': '20140828',
652 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
655 'skip_download': True,
660 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
662 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
664 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
665 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
670 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
672 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
673 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
679 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
684 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
685 'md5': '9d65602bf31c6e20014319c7d07fba27',
687 'id': '5123ea6d5e5a7',
690 'uploader': 'www.handjobhub.com',
691 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
694 # Multiple brightcove videos
695 # https://github.com/rg3/youtube-dl/issues/2283
697 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
699 'id': 'always-never',
700 'title': 'Always / Never - The New Yorker',
704 'extract_flat': False,
705 'skip_download': True,
710 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
711 'md5': '96f09a37e44da40dd083e12d9a683327',
715 'title': 'Ump changes call to ball',
716 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
718 'timestamp': 1401537900,
719 'upload_date': '20140531',
720 'thumbnail': 're:^https?://.*\.jpg$',
725 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
726 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
730 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
731 'description': 'a Paywall Videos video from Remilon',
733 'uploader': 'study.com',
734 'timestamp': 1459678540,
735 'upload_date': '20160403',
736 'filesize': 24687186,
740 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
741 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
745 'title': 'Conversation about Hexagonal Rails Part 1',
746 'description': 'a Martin Fowler video from ThoughtWorks',
748 'uploader': 'thoughtworks.wistia.com',
749 'timestamp': 1401832161,
750 'upload_date': '20140603',
753 # Wistia standard embed (async)
755 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
759 'title': 'Drip Brennan Dunn Workshop',
760 'description': 'a JV Webinars video from getdrip-1',
762 'timestamp': 1463607249,
763 'upload_date': '20160518',
766 'skip_download': True,
771 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
775 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
776 'uploader': 'Sophos Security',
777 'title': 'Chet Chat 171 - Oct 29, 2014',
778 'upload_date': '20141029',
783 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
787 'upload_date': '20141112',
788 'title': 'Rosetta #CometLanding webcast HL 10',
791 # Another Livestream embed, without 'new.' in URL
793 'url': 'https://www.freespeech.org/',
797 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
801 'skip_download': True,
806 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
809 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
811 'playlist_mincount': 2,
815 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
819 'upload_date': '20141126',
820 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
825 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
827 'id': '730m_DandD_1901_512k',
829 'uploader': 'www.abc.net.au',
830 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
833 # embedded viddler video
835 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
839 'uploader': 'deadspin',
840 'title': 'WALL-TO-GORTAT',
841 'timestamp': 1422285291,
842 'upload_date': '20150126',
844 'add_ie': ['Viddler'],
848 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
852 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
853 'description': 'md5:601cb790edd05908957dae8aaa866465',
854 'upload_date': '20150220',
859 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
863 'upload_date': '20150212',
864 'uploader': 'The National Archives UK',
865 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
866 'uploader_id': 'NationalArchives08',
867 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
872 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
873 'playlist_mincount': 5,
875 'id': 'aanslagen-kopenhagen',
876 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
881 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
885 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
888 # Kaltura embed (different embed code)
890 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
894 'upload_date': '20150127',
895 'uploader_id': 'PremierMedia',
897 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
900 # Kaltura embed protected with referrer
902 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
906 'title': 'Violetta - Achter De Schermen - Ruggero',
907 'description': 'Achter de schermen met Ruggero',
908 'timestamp': 1435133761,
909 'upload_date': '20150624',
910 'uploader_id': 'echojecka',
913 # Kaltura embed with single quotes
915 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
920 'timestamp': 1355743100,
921 'upload_date': '20121217',
922 'uploader_id': 'batchUser',
924 'add_ie': ['Kaltura'],
927 # Kaltura embedded via quoted entry_id
928 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
932 'title': '06_matthew_brender_raj_dutt',
933 'timestamp': 1466638791,
934 'upload_date': '20160622',
936 'add_ie': ['Kaltura'],
937 'expected_warnings': [
938 'Could not send HEAD request'
941 'skip_download': True,
944 # Eagle.Platform embed (generic URL)
946 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
947 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
951 'title': 'Навальный вышел на свободу',
952 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
953 'thumbnail': 're:^https?://.*\.jpg$',
959 # ClipYou (Eagle.Platform) embed (custom URL)
961 'url': 'http://muz-tv.ru/play/7129/',
962 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
966 'title': "'O Sole Mio",
967 'thumbnail': 're:^https?://.*\.jpg$',
974 'url': 'http://muz-tv.ru/kinozal/view/7400/',
978 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
979 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
980 'thumbnail': 're:^https?://.*\.jpg$',
987 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
991 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
992 'thumbnail': 're:^https?://.*\.png$',
998 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
999 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1003 'title': 'Facebook Creates "On This Day" | Crunch Report',
1008 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1012 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1017 # Crooks and Liars embed
1019 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1023 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1024 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1025 'timestamp': 1428207000,
1026 'upload_date': '20150405',
1027 'uploader': 'Heather',
1030 # Crooks and Liars external embed
1032 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1034 'id': 'MTE3MjUtMzQ2MzA',
1036 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1037 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1038 'timestamp': 1265032391,
1039 'upload_date': '20100201',
1040 'uploader': 'Heather',
1043 # NBC Sports vplayer embed
1045 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1047 'id': 'ln7x1qSThw4k',
1049 'title': "PFT Live: New leader in the 'new-look' defense",
1050 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1051 'uploader': 'NBCU-SPORTS',
1052 'upload_date': '20140107',
1053 'timestamp': 1389118457,
1058 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1059 'md5': '1aa589c675898ae6d37a17913cf68d66',
1061 'id': '701714499682',
1063 'title': 'PREVIEW: On Assignment: David Letterman',
1064 '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.',
1069 'url': 'https://video.udn.com/news/300346',
1070 'md5': 'fd2060e988c326991037b9aff9df21a6',
1074 'title': '中一中男師變性 全校師生力挺',
1075 'thumbnail': 're:^https?://.*\.jpg$',
1079 'skip_download': True,
1084 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1086 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1088 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1089 'title': 'This is what separates the Excel masters from the wannabes',
1090 'duration': 191.933,
1094 'skip_download': True,
1097 # Brightcove URL in single quotes
1099 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1100 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1102 'id': '4255764656001',
1104 'title': 'SN Presents: Russell Martin, World Citizen',
1105 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1106 'uploader': 'Rogers Sportsnet',
1107 'uploader_id': '1704050871',
1108 'upload_date': '20150525',
1109 'timestamp': 1432570283,
1112 # Dailymotion Cloud video
1114 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1115 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1119 'title': 'Sauvons les abeilles ! - Le débat',
1120 'description': 'md5:d9082128b1c5277987825d684939ca26',
1121 'thumbnail': 're:^https?://.*\.jpe?g$',
1122 'timestamp': 1434970506,
1123 'upload_date': '20150622',
1124 'uploader': 'Public Sénat',
1125 'uploader_id': 'xa9gza',
1128 # OnionStudios embed
1130 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1134 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1135 'thumbnail': 're:^https?://.*\.jpe?g$',
1136 'uploader': 'ClickHole',
1137 'uploader_id': 'clickhole',
1142 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1144 'id': '74849a00-85a9-11e1-9660-123139220831',
1146 'title': '#whilewewatch',
1149 # AdobeTVVideo embed
1151 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1152 'md5': '43662b577c018ad707a63766462b1e87',
1156 'title': 'New experience with Acrobat DC',
1157 'description': 'New experience with Acrobat DC',
1158 'duration': 248.667,
1161 # ScreenwaveMedia embed
1163 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1164 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1166 'id': 'cinemasnob-55d26273809dd',
1168 'title': 'cinemasnob',
1171 # BrightcoveInPageEmbed embed
1173 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1175 'id': '4238694884001',
1177 'title': 'Tabletop: Dread, Last Thoughts',
1178 'description': 'Tabletop: Dread, Last Thoughts',
1182 # JWPlayer with M3U8
1184 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1188 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1189 'uploader': 'ren.tv',
1193 'skip_download': True,
1196 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1197 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1199 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1201 'id': '4785848093001',
1203 'title': 'The Cardinal Pell Interview',
1204 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1205 'uploader': 'GlobeCast Australia - GlobeStream',
1206 'uploader_id': '2733773828001',
1207 'upload_date': '20160304',
1208 'timestamp': 1457083087,
1212 'skip_download': True,
1215 # Another form of arte.tv embed
1217 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1218 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1220 'id': '030273-562_PLUS7-F',
1222 'title': 'ARTE Reportage - Nulle part, en France',
1223 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1224 'upload_date': '20160409',
1229 'url': 'http://www.wykop.pl/link/3088787/',
1230 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1232 'id': '874_1459135191',
1234 'title': 'Man shows poor quality of new apartment building',
1235 'description': 'The wall is like a sand pile.',
1236 'uploader': 'Lake8737',
1239 # Duplicated embedded video URLs
1241 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1243 'id': '149298443_480_16c25b74_2',
1245 'title': 'vs. Blue Orange Spring Game',
1246 'uploader': 'www.hudl.com',
1249 # twitter:player embed
1251 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1252 'md5': 'a3e0df96369831de324f0778e126653c',
1254 'id': '4909620399001',
1256 'title': 'What Do Black Holes Sound Like?',
1257 'description': 'what do black holes sound like',
1258 'upload_date': '20160524',
1259 'uploader_id': '29913724001',
1260 'timestamp': 1464107587,
1261 'uploader': 'TheAtlantic',
1263 'add_ie': ['BrightcoveLegacy'],
1265 # Facebook <iframe> embed
1267 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1269 'id': '599637780109885',
1271 'title': 'Facebook video #599637780109885',
1274 # Facebook API embed
1276 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1278 'id': '10153467542406923',
1280 'title': 'Facebook video #10153467542406923',
1283 # Wordpress "YouTube Video Importer" plugin
1285 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1287 'id': 'HNTXWDXV9Is',
1289 'title': 'Blue Devils Drumline Stanford lot 2016',
1290 'upload_date': '20160627',
1291 'uploader_id': 'GENOCIDE8GENERAL10',
1292 'uploader': 'cylus cyrus',
1297 def report_following_redirect(self, new_url):
1298 """Report information extraction."""
1299 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1301 def _extract_rss(self, url, video_id, doc):
1302 playlist_title = doc.find('./channel/title').text
1303 playlist_desc_el = doc.find('./channel/description')
1304 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1307 for it in doc.findall('./channel/item'):
1308 next_url = xpath_text(it, 'link', fatal=False)
1310 enclosure_nodes = it.findall('./enclosure')
1311 for e in enclosure_nodes:
1312 next_url = e.attrib.get('url')
1322 'title': it.find('title').text,
1326 '_type': 'playlist',
1328 'title': playlist_title,
1329 'description': playlist_desc,
1333 def _extract_camtasia(self, url, video_id, webpage):
1334 """ Returns None if no camtasia video can be found. """
1336 camtasia_cfg = self._search_regex(
1337 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1338 webpage, 'camtasia configuration file', default=None)
1339 if camtasia_cfg is None:
1342 title = self._html_search_meta('DC.title', webpage, fatal=True)
1344 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1345 camtasia_cfg = self._download_xml(
1346 camtasia_url, video_id,
1347 note='Downloading camtasia configuration',
1348 errnote='Failed to download camtasia configuration')
1349 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1352 for n in fileset_node.getchildren():
1353 url_n = n.find('./uri')
1358 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1359 'title': '%s - %s' % (title, n.tag),
1360 'url': compat_urlparse.urljoin(url, url_n.text),
1361 'duration': float_or_none(n.find('./duration').text),
1365 '_type': 'playlist',
1370 def _real_extract(self, url):
1371 if url.startswith('//'):
1374 'url': self.http_scheme() + url,
1377 parsed_url = compat_urlparse.urlparse(url)
1378 if not parsed_url.scheme:
1379 default_search = self._downloader.params.get('default_search')
1380 if default_search is None:
1381 default_search = 'fixup_error'
1383 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1385 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1386 return self.url_result('http://' + url)
1387 elif default_search != 'fixup_error':
1388 if default_search == 'auto_warning':
1389 if re.match(r'^(?:url|URL)$', url):
1390 raise ExtractorError(
1391 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1394 self._downloader.report_warning(
1395 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1396 return self.url_result('ytsearch:' + url)
1398 if default_search in ('error', 'fixup_error'):
1399 raise ExtractorError(
1400 '%r is not a valid URL. '
1401 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1402 % (url, url), expected=True)
1404 if ':' not in default_search:
1405 default_search += ':'
1406 return self.url_result(default_search + url)
1408 url, smuggled_data = unsmuggle_url(url)
1409 force_videoid = None
1410 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1411 if smuggled_data and 'force_videoid' in smuggled_data:
1412 force_videoid = smuggled_data['force_videoid']
1413 video_id = force_videoid
1415 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1417 self.to_screen('%s: Requesting header' % video_id)
1419 head_req = HEADRequest(url)
1420 head_response = self._request_webpage(
1422 note=False, errnote='Could not send HEAD request to %s' % url,
1425 if head_response is not False:
1426 # Check for redirect
1427 new_url = head_response.geturl()
1429 self.report_following_redirect(new_url)
1431 new_url = smuggle_url(
1432 new_url, {'force_videoid': force_videoid})
1433 return self.url_result(new_url)
1435 full_response = None
1436 if head_response is False:
1437 request = sanitized_Request(url)
1438 request.add_header('Accept-Encoding', '*')
1439 full_response = self._request_webpage(request, video_id)
1440 head_response = full_response
1444 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1445 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1448 # Check for direct link to a video
1449 content_type = head_response.headers.get('Content-Type', '').lower()
1450 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1452 format_id = m.group('format_id')
1453 if format_id.endswith('mpegurl'):
1454 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1455 elif format_id == 'f4m':
1456 formats = self._extract_f4m_formats(url, video_id)
1459 'format_id': m.group('format_id'),
1461 'vcodec': 'none' if m.group('type') == 'audio' else None
1463 info_dict['direct'] = True
1464 self._sort_formats(formats)
1465 info_dict['formats'] = formats
1468 if not self._downloader.params.get('test', False) and not is_intentional:
1469 force = self._downloader.params.get('force_generic_extractor', False)
1470 self._downloader.report_warning(
1471 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1473 if not full_response:
1474 request = sanitized_Request(url)
1475 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1476 # making it impossible to download only chunk of the file (yet we need only 512kB to
1477 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1478 # that will always result in downloading the whole file that is not desirable.
1479 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1480 # to accept raw bytes and being able to download only a chunk.
1481 # It may probably better to solve this by checking Content-Type for application/octet-stream
1482 # after HEAD request finishes, but not sure if we can rely on this.
1483 request.add_header('Accept-Encoding', '*')
1484 full_response = self._request_webpage(request, video_id)
1486 first_bytes = full_response.read(512)
1488 # Is it an M3U playlist?
1489 if first_bytes.startswith(b'#EXTM3U'):
1490 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1491 self._sort_formats(info_dict['formats'])
1494 # Maybe it's a direct link to a video?
1495 # Be careful not to download the whole thing!
1496 if not is_html(first_bytes):
1497 self._downloader.report_warning(
1498 'URL could be a direct video link, returning it as such.')
1505 webpage = self._webpage_read_content(
1506 full_response, url, video_id, prefix=first_bytes)
1508 self.report_extraction(video_id)
1510 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1512 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1513 if doc.tag == 'rss':
1514 return self._extract_rss(url, video_id, doc)
1515 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1516 smil = self._parse_smil(doc, url, video_id)
1517 self._sort_formats(smil['formats'])
1519 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1520 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1521 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1522 info_dict['formats'] = self._parse_mpd_formats(
1523 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1524 self._sort_formats(info_dict['formats'])
1526 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1527 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1528 self._sort_formats(info_dict['formats'])
1530 except compat_xml_parse_error:
1533 # Is it a Camtasia project?
1534 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1535 if camtasia_res is not None:
1538 # Sometimes embedded video player is hidden behind percent encoding
1539 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1540 # Unescaping the whole page allows to handle those cases in a generic way
1541 webpage = compat_urllib_parse_unquote(webpage)
1543 # it's tempting to parse this further, but you would
1544 # have to take into account all the variations like
1545 # Video Title - Site Name
1546 # Site Name | Video Title
1547 # Video Title - Tagline | Site Name
1548 # and so on and so forth; it's just not practical
1549 video_title = self._og_search_title(
1550 webpage, default=None) or self._html_search_regex(
1551 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1554 # Try to detect age limit automatically
1555 age_limit = self._rta_search(webpage)
1556 # And then there are the jokers who advertise that they use RTA,
1557 # but actually don't.
1558 AGE_LIMIT_MARKERS = [
1559 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1561 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1564 # video uploader is domain name
1565 video_uploader = self._search_regex(
1566 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1568 video_description = self._og_search_description(webpage, default=None)
1569 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1572 def _playlist_from_matches(matches, getter=None, ie=None):
1574 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1576 return self.playlist_result(
1577 urlrs, playlist_id=video_id, playlist_title=video_title)
1579 # Look for Brightcove Legacy Studio embeds
1580 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1582 self.to_screen('Brightcove video detected.')
1585 'url': smuggle_url(bc_url, {'Referer': url}),
1586 'ie_key': 'BrightcoveLegacy'
1587 } for bc_url in bc_urls]
1590 '_type': 'playlist',
1591 'title': video_title,
1596 # Look for Brightcove New Studio embeds
1597 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1599 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1601 # Look for ThePlatform embeds
1602 tp_urls = ThePlatformIE._extract_urls(webpage)
1604 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1606 # Look for Vessel embeds
1607 vessel_urls = VesselIE._extract_urls(webpage)
1609 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1611 # Look for embedded rtl.nl player
1612 matches = re.findall(
1613 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1616 return _playlist_from_matches(matches, ie='RtlNl')
1618 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1619 if vimeo_url is not None:
1620 return self.url_result(vimeo_url)
1622 vid_me_embed_url = self._search_regex(
1623 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1624 webpage, 'vid.me embed', default=None)
1625 if vid_me_embed_url is not None:
1626 return self.url_result(vid_me_embed_url, 'Vidme')
1628 # Look for embedded YouTube player
1629 matches = re.findall(r'''(?x)
1638 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1642 return _playlist_from_matches(
1643 matches, lambda m: unescapeHTML(m[1]))
1645 # Look for lazyYT YouTube embed
1646 matches = re.findall(
1647 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1649 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1651 # Look for Wordpress "YouTube Video Importer" plugin
1652 matches = re.findall(r'''(?x)<div[^>]+
1653 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1654 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1656 return _playlist_from_matches(matches, lambda m: m[-1])
1658 # Look for embedded Dailymotion player
1659 matches = re.findall(
1660 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1662 return _playlist_from_matches(
1663 matches, lambda m: unescapeHTML(m[1]))
1665 # Look for embedded Dailymotion playlist player (#3822)
1667 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1669 playlists = re.findall(
1670 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1672 return _playlist_from_matches(
1673 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1675 # Look for embedded Wistia player
1677 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1679 embed_url = self._proto_relative_url(
1680 unescapeHTML(match.group('url')))
1682 '_type': 'url_transparent',
1685 'uploader': video_uploader,
1688 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1691 '_type': 'url_transparent',
1692 'url': 'wistia:%s' % match.group('id'),
1694 'uploader': video_uploader,
1699 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1700 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1703 return self.url_result(self._proto_relative_url(
1704 'wistia:%s' % match.group('id')), 'Wistia')
1706 # Look for SVT player
1707 svt_url = SVTIE._extract_url(webpage)
1709 return self.url_result(svt_url, 'SVT')
1711 # Look for embedded condenast player
1712 matches = re.findall(
1713 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1717 '_type': 'playlist',
1720 'ie_key': 'CondeNast',
1722 } for ma in matches],
1723 'title': video_title,
1727 # Look for Bandcamp pages with custom domain
1728 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1729 if mobj is not None:
1730 burl = unescapeHTML(mobj.group(1))
1731 # Don't set the extractor because it can be a track url or an album
1732 return self.url_result(burl)
1734 # Look for embedded Vevo player
1736 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1737 if mobj is not None:
1738 return self.url_result(mobj.group('url'))
1740 # Look for embedded Viddler player
1742 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1744 if mobj is not None:
1745 return self.url_result(mobj.group('url'))
1747 # Look for NYTimes player
1749 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1751 if mobj is not None:
1752 return self.url_result(mobj.group('url'))
1754 # Look for Libsyn player
1756 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1757 if mobj is not None:
1758 return self.url_result(mobj.group('url'))
1760 # Look for Ooyala videos
1761 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1762 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1763 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1764 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1765 if mobj is not None:
1766 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1768 # Look for multiple Ooyala embeds on SBN network websites
1769 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1770 if mobj is not None:
1771 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1773 return _playlist_from_matches(
1774 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1776 # Look for Aparat videos
1777 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1778 if mobj is not None:
1779 return self.url_result(mobj.group(1), 'Aparat')
1781 # Look for MPORA videos
1782 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1783 if mobj is not None:
1784 return self.url_result(mobj.group(1), 'Mpora')
1786 # Look for embedded NovaMov-based player
1788 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1789 (?P<url>http://(?:(?:embed|www)\.)?
1791 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1792 videoweed\.(?:es|com)|
1793 movshare\.(?:net|sx|ag)|
1794 divxstage\.(?:eu|net|ch|co|at|ag))
1795 /embed\.php.+?)\1''', webpage)
1796 if mobj is not None:
1797 return self.url_result(mobj.group('url'))
1799 # Look for embedded Facebook player
1800 facebook_url = FacebookIE._extract_url(webpage)
1801 if facebook_url is not None:
1802 return self.url_result(facebook_url, 'Facebook')
1804 # Look for embedded VK player
1805 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1806 if mobj is not None:
1807 return self.url_result(mobj.group('url'), 'VK')
1809 # Look for embedded Odnoklassniki player
1810 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1811 if mobj is not None:
1812 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1814 # Look for embedded ivi player
1815 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1816 if mobj is not None:
1817 return self.url_result(mobj.group('url'), 'Ivi')
1819 # Look for embedded Huffington Post player
1821 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1822 if mobj is not None:
1823 return self.url_result(mobj.group('url'), 'HuffPost')
1826 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1827 if mobj is not None:
1828 return self.url_result(mobj.group('url'))
1829 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1830 if mobj is not None:
1831 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1833 # Look for funnyordie embed
1834 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1836 return _playlist_from_matches(
1837 matches, getter=unescapeHTML, ie='FunnyOrDie')
1839 # Look for BBC iPlayer embed
1840 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1842 return _playlist_from_matches(matches, ie='BBCCoUk')
1844 # Look for embedded RUTV player
1845 rutv_url = RUTVIE._extract_url(webpage)
1847 return self.url_result(rutv_url, 'RUTV')
1849 # Look for embedded TVC player
1850 tvc_url = TVCIE._extract_url(webpage)
1852 return self.url_result(tvc_url, 'TVC')
1854 # Look for embedded SportBox player
1855 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1857 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1859 # Look for embedded PornHub player
1860 pornhub_url = PornHubIE._extract_url(webpage)
1862 return self.url_result(pornhub_url, 'PornHub')
1864 # Look for embedded XHamster player
1865 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1867 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1869 # Look for embedded TNAFlixNetwork player
1870 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1872 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1874 # Look for embedded Tvigle player
1876 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1877 if mobj is not None:
1878 return self.url_result(mobj.group('url'), 'Tvigle')
1880 # Look for embedded TED player
1882 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1883 if mobj is not None:
1884 return self.url_result(mobj.group('url'), 'TED')
1886 # Look for embedded Ustream videos
1888 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1889 if mobj is not None:
1890 return self.url_result(mobj.group('url'), 'Ustream')
1892 # Look for embedded arte.tv player
1894 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1896 if mobj is not None:
1897 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1899 # Look for embedded francetv player
1901 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1903 if mobj is not None:
1904 return self.url_result(mobj.group('url'))
1906 # Look for embedded smotri.com player
1907 smotri_url = SmotriIE._extract_url(webpage)
1909 return self.url_result(smotri_url, 'Smotri')
1911 # Look for embedded Myvi.ru player
1912 myvi_url = MyviIE._extract_url(webpage)
1914 return self.url_result(myvi_url)
1916 # Look for embedded soundcloud player
1918 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1920 if mobj is not None:
1921 url = unescapeHTML(mobj.group('url'))
1922 return self.url_result(url)
1924 # Look for embedded mtvservices player
1925 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1927 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1929 # Look for embedded yahoo player
1931 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1933 if mobj is not None:
1934 return self.url_result(mobj.group('url'), 'Yahoo')
1936 # Look for embedded sbs.com.au player
1940 <meta\s+property="og:video"\s+content=|
1943 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1945 if mobj is not None:
1946 return self.url_result(mobj.group('url'), 'SBS')
1948 # Look for embedded Cinchcast player
1950 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1952 if mobj is not None:
1953 return self.url_result(mobj.group('url'), 'Cinchcast')
1956 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1960 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1962 if mobj is not None:
1963 return self.url_result(mobj.group('url'), 'MLB')
1966 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1968 if mobj is not None:
1969 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1972 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1974 if mobj is not None:
1975 return self.url_result(mobj.group('url'), 'Livestream')
1977 # Look for Zapiks embed
1979 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1980 if mobj is not None:
1981 return self.url_result(mobj.group('url'), 'Zapiks')
1983 # Look for Kaltura embeds
1984 kaltura_url = KalturaIE._extract_url(webpage)
1986 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
1988 # Look for Eagle.Platform embeds
1989 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
1990 if eagleplatform_url:
1991 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
1993 # Look for ClipYou (uses Eagle.Platform) embeds
1995 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1996 if mobj is not None:
1997 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1999 # Look for Pladform embeds
2000 pladform_url = PladformIE._extract_url(webpage)
2002 return self.url_result(pladform_url)
2004 # Look for Videomore embeds
2005 videomore_url = VideomoreIE._extract_url(webpage)
2007 return self.url_result(videomore_url)
2009 # Look for Playwire embeds
2011 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2012 if mobj is not None:
2013 return self.url_result(mobj.group('url'))
2015 # Look for 5min embeds
2017 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2018 if mobj is not None:
2019 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2021 # Look for Crooks and Liars embeds
2023 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2024 if mobj is not None:
2025 return self.url_result(mobj.group('url'))
2027 # Look for NBC Sports VPlayer embeds
2028 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2030 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2032 # Look for NBC News embeds
2033 nbc_news_embed_url = re.search(
2034 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2035 if nbc_news_embed_url:
2036 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2038 # Look for Google Drive embeds
2039 google_drive_url = GoogleDriveIE._extract_url(webpage)
2040 if google_drive_url:
2041 return self.url_result(google_drive_url, 'GoogleDrive')
2043 # Look for UDN embeds
2045 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2046 if mobj is not None:
2047 return self.url_result(
2048 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2050 # Look for Senate ISVP iframe
2051 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2053 return self.url_result(senate_isvp_url, 'SenateISVP')
2055 # Look for Dailymotion Cloud videos
2056 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2058 return self.url_result(dmcloud_url, 'DailymotionCloud')
2060 # Look for OnionStudios embeds
2061 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2062 if onionstudios_url:
2063 return self.url_result(onionstudios_url)
2065 # Look for ViewLift embeds
2066 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2068 return self.url_result(viewlift_url)
2070 # Look for JWPlatform embeds
2071 jwplatform_url = JWPlatformIE._extract_url(webpage)
2073 return self.url_result(jwplatform_url, 'JWPlatform')
2075 # Look for ScreenwaveMedia embeds
2076 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2077 if mobj is not None:
2078 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2080 # Look for Digiteka embeds
2081 digiteka_url = DigitekaIE._extract_url(webpage)
2083 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2085 # Look for Limelight embeds
2086 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2090 'Channel': 'channel',
2091 'ChannelList': 'channel_list',
2093 return self.url_result('limelight:%s:%s' % (
2094 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2096 # Look for AdobeTVVideo embeds
2098 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2100 if mobj is not None:
2101 return self.url_result(
2102 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2105 # Look for Vine embeds
2107 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2109 if mobj is not None:
2110 return self.url_result(
2111 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2113 # Look for Instagram embeds
2114 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2115 if instagram_embed_url is not None:
2116 return self.url_result(
2117 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2119 # Look for LiveLeak embeds
2120 liveleak_url = LiveLeakIE._extract_url(webpage)
2122 return self.url_result(liveleak_url, 'LiveLeak')
2124 # Look for 3Q SDN embeds
2125 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2128 '_type': 'url_transparent',
2129 'ie_key': ThreeQSDNIE.ie_key(),
2130 'url': self._proto_relative_url(threeqsdn_url),
2131 'title': video_title,
2132 'description': video_description,
2133 'thumbnail': video_thumbnail,
2134 'uploader': video_uploader,
2137 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
2138 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2140 return self.url_result(embed_url)
2142 def check_video(vurl):
2143 if YoutubeIE.suitable(vurl):
2145 vpath = compat_urlparse.urlparse(vurl).path
2146 vext = determine_ext(vpath)
2147 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2149 def filter_video(urls):
2150 return list(filter(check_video, urls))
2152 # Start with something easy: JW Player in SWFObject
2153 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2155 # Look for gorilla-vid style embedding
2156 found = filter_video(re.findall(r'''(?sx)
2160 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2163 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2165 # Broaden the search a little bit
2166 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2168 # Broaden the findall a little bit: JWPlayer JS loader
2169 found = filter_video(re.findall(
2170 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2173 found = filter_video(re.findall(r'''(?xs)
2174 flowplayer\("[^"]+",\s*
2176 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2177 ["']?url["']?\s*:\s*["']([^"']+)["']
2182 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2184 # Try to find twitter cards info
2185 found = filter_video(re.findall(
2186 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2188 # We look for Open Graph info:
2189 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2190 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2191 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2192 if m_video_type is not None:
2193 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2196 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2198 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2200 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2201 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2204 # Look also in Refresh HTTP header
2205 refresh_header = head_response.headers.get('Refresh')
2207 # In python 2 response HTTP headers are bytestrings
2208 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2209 refresh_header = refresh_header.decode('iso-8859-1')
2210 found = re.search(REDIRECT_REGEX, refresh_header)
2212 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2213 self.report_following_redirect(new_url)
2219 raise UnsupportedError(url)
2222 for video_url in orderedSet(found):
2223 video_url = unescapeHTML(video_url)
2224 video_url = video_url.replace('\\/', '/')
2225 video_url = compat_urlparse.urljoin(url, video_url)
2226 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2228 # Sometimes, jwplayer extraction will result in a YouTube URL
2229 if YoutubeIE.suitable(video_url):
2230 entries.append(self.url_result(video_url, 'Youtube'))
2233 # here's a fun little line of code for you:
2234 video_id = os.path.splitext(video_id)[0]
2238 'uploader': video_uploader,
2239 'title': video_title,
2240 'age_limit': age_limit,
2243 ext = determine_ext(video_url)
2245 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2247 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2249 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2251 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2253 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2255 entry_info_dict['url'] = video_url
2257 if entry_info_dict.get('formats'):
2258 self._sort_formats(entry_info_dict['formats'])
2260 entries.append(entry_info_dict)
2262 if len(entries) == 1:
2265 for num, e in enumerate(entries, start=1):
2266 # 'url' results don't have a title
2267 if e.get('title') is not None:
2268 e['title'] = '%s (%d)' % (e['title'], num)
2270 '_type': 'playlist',