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',
1285 def report_following_redirect(self, new_url):
1286 """Report information extraction."""
1287 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1289 def _extract_rss(self, url, video_id, doc):
1290 playlist_title = doc.find('./channel/title').text
1291 playlist_desc_el = doc.find('./channel/description')
1292 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1295 for it in doc.findall('./channel/item'):
1296 next_url = xpath_text(it, 'link', fatal=False)
1298 enclosure_nodes = it.findall('./enclosure')
1299 for e in enclosure_nodes:
1300 next_url = e.attrib.get('url')
1310 'title': it.find('title').text,
1314 '_type': 'playlist',
1316 'title': playlist_title,
1317 'description': playlist_desc,
1321 def _extract_camtasia(self, url, video_id, webpage):
1322 """ Returns None if no camtasia video can be found. """
1324 camtasia_cfg = self._search_regex(
1325 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1326 webpage, 'camtasia configuration file', default=None)
1327 if camtasia_cfg is None:
1330 title = self._html_search_meta('DC.title', webpage, fatal=True)
1332 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1333 camtasia_cfg = self._download_xml(
1334 camtasia_url, video_id,
1335 note='Downloading camtasia configuration',
1336 errnote='Failed to download camtasia configuration')
1337 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1340 for n in fileset_node.getchildren():
1341 url_n = n.find('./uri')
1346 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1347 'title': '%s - %s' % (title, n.tag),
1348 'url': compat_urlparse.urljoin(url, url_n.text),
1349 'duration': float_or_none(n.find('./duration').text),
1353 '_type': 'playlist',
1358 def _real_extract(self, url):
1359 if url.startswith('//'):
1362 'url': self.http_scheme() + url,
1365 parsed_url = compat_urlparse.urlparse(url)
1366 if not parsed_url.scheme:
1367 default_search = self._downloader.params.get('default_search')
1368 if default_search is None:
1369 default_search = 'fixup_error'
1371 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1373 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1374 return self.url_result('http://' + url)
1375 elif default_search != 'fixup_error':
1376 if default_search == 'auto_warning':
1377 if re.match(r'^(?:url|URL)$', url):
1378 raise ExtractorError(
1379 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1382 self._downloader.report_warning(
1383 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1384 return self.url_result('ytsearch:' + url)
1386 if default_search in ('error', 'fixup_error'):
1387 raise ExtractorError(
1388 '%r is not a valid URL. '
1389 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1390 % (url, url), expected=True)
1392 if ':' not in default_search:
1393 default_search += ':'
1394 return self.url_result(default_search + url)
1396 url, smuggled_data = unsmuggle_url(url)
1397 force_videoid = None
1398 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1399 if smuggled_data and 'force_videoid' in smuggled_data:
1400 force_videoid = smuggled_data['force_videoid']
1401 video_id = force_videoid
1403 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1405 self.to_screen('%s: Requesting header' % video_id)
1407 head_req = HEADRequest(url)
1408 head_response = self._request_webpage(
1410 note=False, errnote='Could not send HEAD request to %s' % url,
1413 if head_response is not False:
1414 # Check for redirect
1415 new_url = head_response.geturl()
1417 self.report_following_redirect(new_url)
1419 new_url = smuggle_url(
1420 new_url, {'force_videoid': force_videoid})
1421 return self.url_result(new_url)
1423 full_response = None
1424 if head_response is False:
1425 request = sanitized_Request(url)
1426 request.add_header('Accept-Encoding', '*')
1427 full_response = self._request_webpage(request, video_id)
1428 head_response = full_response
1432 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1433 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1436 # Check for direct link to a video
1437 content_type = head_response.headers.get('Content-Type', '').lower()
1438 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1440 format_id = m.group('format_id')
1441 if format_id.endswith('mpegurl'):
1442 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1443 elif format_id == 'f4m':
1444 formats = self._extract_f4m_formats(url, video_id)
1447 'format_id': m.group('format_id'),
1449 'vcodec': 'none' if m.group('type') == 'audio' else None
1451 info_dict['direct'] = True
1452 self._sort_formats(formats)
1453 info_dict['formats'] = formats
1456 if not self._downloader.params.get('test', False) and not is_intentional:
1457 force = self._downloader.params.get('force_generic_extractor', False)
1458 self._downloader.report_warning(
1459 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1461 if not full_response:
1462 request = sanitized_Request(url)
1463 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1464 # making it impossible to download only chunk of the file (yet we need only 512kB to
1465 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1466 # that will always result in downloading the whole file that is not desirable.
1467 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1468 # to accept raw bytes and being able to download only a chunk.
1469 # It may probably better to solve this by checking Content-Type for application/octet-stream
1470 # after HEAD request finishes, but not sure if we can rely on this.
1471 request.add_header('Accept-Encoding', '*')
1472 full_response = self._request_webpage(request, video_id)
1474 first_bytes = full_response.read(512)
1476 # Is it an M3U playlist?
1477 if first_bytes.startswith(b'#EXTM3U'):
1478 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1479 self._sort_formats(info_dict['formats'])
1482 # Maybe it's a direct link to a video?
1483 # Be careful not to download the whole thing!
1484 if not is_html(first_bytes):
1485 self._downloader.report_warning(
1486 'URL could be a direct video link, returning it as such.')
1493 webpage = self._webpage_read_content(
1494 full_response, url, video_id, prefix=first_bytes)
1496 self.report_extraction(video_id)
1498 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1500 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1501 if doc.tag == 'rss':
1502 return self._extract_rss(url, video_id, doc)
1503 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1504 smil = self._parse_smil(doc, url, video_id)
1505 self._sort_formats(smil['formats'])
1507 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1508 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1509 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1510 info_dict['formats'] = self._parse_mpd_formats(
1511 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1512 self._sort_formats(info_dict['formats'])
1514 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1515 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1516 self._sort_formats(info_dict['formats'])
1518 except compat_xml_parse_error:
1521 # Is it a Camtasia project?
1522 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1523 if camtasia_res is not None:
1526 # Sometimes embedded video player is hidden behind percent encoding
1527 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1528 # Unescaping the whole page allows to handle those cases in a generic way
1529 webpage = compat_urllib_parse_unquote(webpage)
1531 # it's tempting to parse this further, but you would
1532 # have to take into account all the variations like
1533 # Video Title - Site Name
1534 # Site Name | Video Title
1535 # Video Title - Tagline | Site Name
1536 # and so on and so forth; it's just not practical
1537 video_title = self._og_search_title(
1538 webpage, default=None) or self._html_search_regex(
1539 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1542 # Try to detect age limit automatically
1543 age_limit = self._rta_search(webpage)
1544 # And then there are the jokers who advertise that they use RTA,
1545 # but actually don't.
1546 AGE_LIMIT_MARKERS = [
1547 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1549 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1552 # video uploader is domain name
1553 video_uploader = self._search_regex(
1554 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1556 video_description = self._og_search_description(webpage, default=None)
1557 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1560 def _playlist_from_matches(matches, getter=None, ie=None):
1562 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1564 return self.playlist_result(
1565 urlrs, playlist_id=video_id, playlist_title=video_title)
1567 # Look for Brightcove Legacy Studio embeds
1568 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1570 self.to_screen('Brightcove video detected.')
1573 'url': smuggle_url(bc_url, {'Referer': url}),
1574 'ie_key': 'BrightcoveLegacy'
1575 } for bc_url in bc_urls]
1578 '_type': 'playlist',
1579 'title': video_title,
1584 # Look for Brightcove New Studio embeds
1585 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1587 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1589 # Look for ThePlatform embeds
1590 tp_urls = ThePlatformIE._extract_urls(webpage)
1592 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1594 # Look for Vessel embeds
1595 vessel_urls = VesselIE._extract_urls(webpage)
1597 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1599 # Look for embedded rtl.nl player
1600 matches = re.findall(
1601 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1604 return _playlist_from_matches(matches, ie='RtlNl')
1606 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1607 if vimeo_url is not None:
1608 return self.url_result(vimeo_url)
1610 vid_me_embed_url = self._search_regex(
1611 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1612 webpage, 'vid.me embed', default=None)
1613 if vid_me_embed_url is not None:
1614 return self.url_result(vid_me_embed_url, 'Vidme')
1616 # Look for embedded YouTube player
1617 matches = re.findall(r'''(?x)
1626 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1630 return _playlist_from_matches(
1631 matches, lambda m: unescapeHTML(m[1]))
1633 # Look for lazyYT YouTube embed
1634 matches = re.findall(
1635 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1637 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1639 # Look for embedded Dailymotion player
1640 matches = re.findall(
1641 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1643 return _playlist_from_matches(
1644 matches, lambda m: unescapeHTML(m[1]))
1646 # Look for embedded Dailymotion playlist player (#3822)
1648 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1650 playlists = re.findall(
1651 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1653 return _playlist_from_matches(
1654 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1656 # Look for embedded Wistia player
1658 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1660 embed_url = self._proto_relative_url(
1661 unescapeHTML(match.group('url')))
1663 '_type': 'url_transparent',
1666 'uploader': video_uploader,
1669 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1672 '_type': 'url_transparent',
1673 'url': 'wistia:%s' % match.group('id'),
1675 'uploader': video_uploader,
1680 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1681 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1684 return self.url_result(self._proto_relative_url(
1685 'wistia:%s' % match.group('id')), 'Wistia')
1687 # Look for SVT player
1688 svt_url = SVTIE._extract_url(webpage)
1690 return self.url_result(svt_url, 'SVT')
1692 # Look for embedded condenast player
1693 matches = re.findall(
1694 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1698 '_type': 'playlist',
1701 'ie_key': 'CondeNast',
1703 } for ma in matches],
1704 'title': video_title,
1708 # Look for Bandcamp pages with custom domain
1709 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1710 if mobj is not None:
1711 burl = unescapeHTML(mobj.group(1))
1712 # Don't set the extractor because it can be a track url or an album
1713 return self.url_result(burl)
1715 # Look for embedded Vevo player
1717 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1718 if mobj is not None:
1719 return self.url_result(mobj.group('url'))
1721 # Look for embedded Viddler player
1723 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1725 if mobj is not None:
1726 return self.url_result(mobj.group('url'))
1728 # Look for NYTimes player
1730 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1732 if mobj is not None:
1733 return self.url_result(mobj.group('url'))
1735 # Look for Libsyn player
1737 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1738 if mobj is not None:
1739 return self.url_result(mobj.group('url'))
1741 # Look for Ooyala videos
1742 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1743 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1744 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1745 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1746 if mobj is not None:
1747 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1749 # Look for multiple Ooyala embeds on SBN network websites
1750 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1751 if mobj is not None:
1752 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1754 return _playlist_from_matches(
1755 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1757 # Look for Aparat videos
1758 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1759 if mobj is not None:
1760 return self.url_result(mobj.group(1), 'Aparat')
1762 # Look for MPORA videos
1763 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1764 if mobj is not None:
1765 return self.url_result(mobj.group(1), 'Mpora')
1767 # Look for embedded NovaMov-based player
1769 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1770 (?P<url>http://(?:(?:embed|www)\.)?
1772 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1773 videoweed\.(?:es|com)|
1774 movshare\.(?:net|sx|ag)|
1775 divxstage\.(?:eu|net|ch|co|at|ag))
1776 /embed\.php.+?)\1''', webpage)
1777 if mobj is not None:
1778 return self.url_result(mobj.group('url'))
1780 # Look for embedded Facebook player
1781 facebook_url = FacebookIE._extract_url(webpage)
1782 if facebook_url is not None:
1783 return self.url_result(facebook_url, 'Facebook')
1785 # Look for embedded VK player
1786 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1787 if mobj is not None:
1788 return self.url_result(mobj.group('url'), 'VK')
1790 # Look for embedded Odnoklassniki player
1791 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1792 if mobj is not None:
1793 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1795 # Look for embedded ivi player
1796 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1797 if mobj is not None:
1798 return self.url_result(mobj.group('url'), 'Ivi')
1800 # Look for embedded Huffington Post player
1802 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1803 if mobj is not None:
1804 return self.url_result(mobj.group('url'), 'HuffPost')
1807 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1808 if mobj is not None:
1809 return self.url_result(mobj.group('url'))
1810 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1811 if mobj is not None:
1812 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1814 # Look for funnyordie embed
1815 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1817 return _playlist_from_matches(
1818 matches, getter=unescapeHTML, ie='FunnyOrDie')
1820 # Look for BBC iPlayer embed
1821 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1823 return _playlist_from_matches(matches, ie='BBCCoUk')
1825 # Look for embedded RUTV player
1826 rutv_url = RUTVIE._extract_url(webpage)
1828 return self.url_result(rutv_url, 'RUTV')
1830 # Look for embedded TVC player
1831 tvc_url = TVCIE._extract_url(webpage)
1833 return self.url_result(tvc_url, 'TVC')
1835 # Look for embedded SportBox player
1836 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1838 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1840 # Look for embedded PornHub player
1841 pornhub_url = PornHubIE._extract_url(webpage)
1843 return self.url_result(pornhub_url, 'PornHub')
1845 # Look for embedded XHamster player
1846 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1848 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1850 # Look for embedded TNAFlixNetwork player
1851 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1853 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1855 # Look for embedded Tvigle player
1857 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1858 if mobj is not None:
1859 return self.url_result(mobj.group('url'), 'Tvigle')
1861 # Look for embedded TED player
1863 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1864 if mobj is not None:
1865 return self.url_result(mobj.group('url'), 'TED')
1867 # Look for embedded Ustream videos
1869 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1870 if mobj is not None:
1871 return self.url_result(mobj.group('url'), 'Ustream')
1873 # Look for embedded arte.tv player
1875 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1877 if mobj is not None:
1878 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1880 # Look for embedded francetv player
1882 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1884 if mobj is not None:
1885 return self.url_result(mobj.group('url'))
1887 # Look for embedded smotri.com player
1888 smotri_url = SmotriIE._extract_url(webpage)
1890 return self.url_result(smotri_url, 'Smotri')
1892 # Look for embedded Myvi.ru player
1893 myvi_url = MyviIE._extract_url(webpage)
1895 return self.url_result(myvi_url)
1897 # Look for embedded soundcloud player
1899 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1901 if mobj is not None:
1902 url = unescapeHTML(mobj.group('url'))
1903 return self.url_result(url)
1905 # Look for embedded mtvservices player
1906 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1908 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1910 # Look for embedded yahoo player
1912 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1914 if mobj is not None:
1915 return self.url_result(mobj.group('url'), 'Yahoo')
1917 # Look for embedded sbs.com.au player
1921 <meta\s+property="og:video"\s+content=|
1924 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1926 if mobj is not None:
1927 return self.url_result(mobj.group('url'), 'SBS')
1929 # Look for embedded Cinchcast player
1931 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1933 if mobj is not None:
1934 return self.url_result(mobj.group('url'), 'Cinchcast')
1937 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1941 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1943 if mobj is not None:
1944 return self.url_result(mobj.group('url'), 'MLB')
1947 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1949 if mobj is not None:
1950 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1953 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1955 if mobj is not None:
1956 return self.url_result(mobj.group('url'), 'Livestream')
1958 # Look for Zapiks embed
1960 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1961 if mobj is not None:
1962 return self.url_result(mobj.group('url'), 'Zapiks')
1964 # Look for Kaltura embeds
1965 kaltura_url = KalturaIE._extract_url(webpage)
1967 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
1969 # Look for Eagle.Platform embeds
1970 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
1971 if eagleplatform_url:
1972 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
1974 # Look for ClipYou (uses Eagle.Platform) embeds
1976 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1977 if mobj is not None:
1978 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1980 # Look for Pladform embeds
1981 pladform_url = PladformIE._extract_url(webpage)
1983 return self.url_result(pladform_url)
1985 # Look for Videomore embeds
1986 videomore_url = VideomoreIE._extract_url(webpage)
1988 return self.url_result(videomore_url)
1990 # Look for Playwire embeds
1992 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1993 if mobj is not None:
1994 return self.url_result(mobj.group('url'))
1996 # Look for 5min embeds
1998 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1999 if mobj is not None:
2000 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2002 # Look for Crooks and Liars embeds
2004 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2005 if mobj is not None:
2006 return self.url_result(mobj.group('url'))
2008 # Look for NBC Sports VPlayer embeds
2009 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2011 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2013 # Look for NBC News embeds
2014 nbc_news_embed_url = re.search(
2015 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2016 if nbc_news_embed_url:
2017 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2019 # Look for Google Drive embeds
2020 google_drive_url = GoogleDriveIE._extract_url(webpage)
2021 if google_drive_url:
2022 return self.url_result(google_drive_url, 'GoogleDrive')
2024 # Look for UDN embeds
2026 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2027 if mobj is not None:
2028 return self.url_result(
2029 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2031 # Look for Senate ISVP iframe
2032 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2034 return self.url_result(senate_isvp_url, 'SenateISVP')
2036 # Look for Dailymotion Cloud videos
2037 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2039 return self.url_result(dmcloud_url, 'DailymotionCloud')
2041 # Look for OnionStudios embeds
2042 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2043 if onionstudios_url:
2044 return self.url_result(onionstudios_url)
2046 # Look for ViewLift embeds
2047 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2049 return self.url_result(viewlift_url)
2051 # Look for JWPlatform embeds
2052 jwplatform_url = JWPlatformIE._extract_url(webpage)
2054 return self.url_result(jwplatform_url, 'JWPlatform')
2056 # Look for ScreenwaveMedia embeds
2057 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2058 if mobj is not None:
2059 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2061 # Look for Digiteka embeds
2062 digiteka_url = DigitekaIE._extract_url(webpage)
2064 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2066 # Look for Limelight embeds
2067 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2071 'Channel': 'channel',
2072 'ChannelList': 'channel_list',
2074 return self.url_result('limelight:%s:%s' % (
2075 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2077 # Look for AdobeTVVideo embeds
2079 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2081 if mobj is not None:
2082 return self.url_result(
2083 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2086 # Look for Vine embeds
2088 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2090 if mobj is not None:
2091 return self.url_result(
2092 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2094 # Look for Instagram embeds
2095 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2096 if instagram_embed_url is not None:
2097 return self.url_result(
2098 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2100 # Look for LiveLeak embeds
2101 liveleak_url = LiveLeakIE._extract_url(webpage)
2103 return self.url_result(liveleak_url, 'LiveLeak')
2105 # Look for 3Q SDN embeds
2106 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2109 '_type': 'url_transparent',
2110 'ie_key': ThreeQSDNIE.ie_key(),
2111 'url': self._proto_relative_url(threeqsdn_url),
2112 'title': video_title,
2113 'description': video_description,
2114 'thumbnail': video_thumbnail,
2115 'uploader': video_uploader,
2118 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
2119 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2121 return self.url_result(embed_url)
2123 def check_video(vurl):
2124 if YoutubeIE.suitable(vurl):
2126 vpath = compat_urlparse.urlparse(vurl).path
2127 vext = determine_ext(vpath)
2128 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2130 def filter_video(urls):
2131 return list(filter(check_video, urls))
2133 # Start with something easy: JW Player in SWFObject
2134 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2136 # Look for gorilla-vid style embedding
2137 found = filter_video(re.findall(r'''(?sx)
2141 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2144 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2146 # Broaden the search a little bit
2147 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2149 # Broaden the findall a little bit: JWPlayer JS loader
2150 found = filter_video(re.findall(
2151 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2154 found = filter_video(re.findall(r'''(?xs)
2155 flowplayer\("[^"]+",\s*
2157 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2158 ["']?url["']?\s*:\s*["']([^"']+)["']
2163 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2165 # Try to find twitter cards info
2166 found = filter_video(re.findall(
2167 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2169 # We look for Open Graph info:
2170 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2171 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2172 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2173 if m_video_type is not None:
2174 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2177 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2179 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2181 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2182 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2185 # Look also in Refresh HTTP header
2186 refresh_header = head_response.headers.get('Refresh')
2188 # In python 2 response HTTP headers are bytestrings
2189 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2190 refresh_header = refresh_header.decode('iso-8859-1')
2191 found = re.search(REDIRECT_REGEX, refresh_header)
2193 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2194 self.report_following_redirect(new_url)
2200 raise UnsupportedError(url)
2203 for video_url in orderedSet(found):
2204 video_url = unescapeHTML(video_url)
2205 video_url = video_url.replace('\\/', '/')
2206 video_url = compat_urlparse.urljoin(url, video_url)
2207 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2209 # Sometimes, jwplayer extraction will result in a YouTube URL
2210 if YoutubeIE.suitable(video_url):
2211 entries.append(self.url_result(video_url, 'Youtube'))
2214 # here's a fun little line of code for you:
2215 video_id = os.path.splitext(video_id)[0]
2219 'uploader': video_uploader,
2220 'title': video_title,
2221 'age_limit': age_limit,
2224 ext = determine_ext(video_url)
2226 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2228 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2230 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2232 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2234 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2236 entry_info_dict['url'] = video_url
2238 if entry_info_dict.get('formats'):
2239 self._sort_formats(entry_info_dict['formats'])
2241 entries.append(entry_info_dict)
2243 if len(entries) == 1:
2246 for num, e in enumerate(entries, start=1):
2247 # 'url' results don't have a title
2248 if e.get('title') is not None:
2249 e['title'] = '%s (%d)' % (e['title'], num)
2251 '_type': 'playlist',