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,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .drtuber import DrTuberIE
51 from .redtube import RedTubeIE
52 from .vimeo import VimeoIE
53 from .dailymotion import (
57 from .onionstudios import OnionStudiosIE
58 from .viewlift import ViewLiftEmbedIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .webcaster import WebcasterFeedIE
63 from .googledrive import GoogleDriveIE
64 from .jwplatform import JWPlatformIE
65 from .digiteka import DigitekaIE
66 from .arkena import ArkenaIE
67 from .instagram import InstagramIE
68 from .liveleak import LiveLeakIE
69 from .threeqsdn import ThreeQSDNIE
70 from .theplatform import ThePlatformIE
71 from .vessel import VesselIE
72 from .kaltura import KalturaIE
73 from .eagleplatform import EaglePlatformIE
74 from .facebook import FacebookIE
75 from .soundcloud import SoundcloudIE
76 from .vbox7 import Vbox7IE
77 from .dbtv import DBTVIE
78 from .piksel import PikselIE
81 class GenericIE(InfoExtractor):
82 IE_DESC = 'Generic downloader that works on some sites'
86 # Direct link to a video
88 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
89 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
94 'upload_date': '20100513',
97 # Direct link to media delivered compressed (until Accept-Encoding is *)
99 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
100 'md5': '128c42e68b13950268b648275386fc74',
102 'id': 'FictionJunction-Parallel_Hearts',
104 'title': 'FictionJunction-Parallel_Hearts',
105 'upload_date': '20140522',
107 'expected_warnings': [
108 'URL could be a direct video link, returning it as such.'
110 'skip': 'URL invalid',
112 # Direct download with broken HEAD
114 'url': 'http://ai-radio.org:8000/radio.opus',
121 'skip_download': True, # infinite live stream
123 'expected_warnings': [
124 r'501.*Not Implemented',
128 # Direct link with incorrect MIME type
130 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
131 'md5': '4ccbebe5f36706d85221f204d7eb5913',
133 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
134 'id': '5_Lennart_Poettering_-_Systemd',
136 'title': '5_Lennart_Poettering_-_Systemd',
137 'upload_date': '20141120',
139 'expected_warnings': [
140 'URL could be a direct video link, returning it as such.'
145 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
147 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
148 'title': 'Zero Punctuation',
149 'description': 're:.*groundbreaking video review series.*'
151 'playlist_mincount': 11,
153 # RSS feed with enclosure
155 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
157 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
159 'upload_date': '20150228',
160 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
163 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
165 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
169 'title': 'Automatics, robotics and biocybernetics',
170 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
171 'upload_date': '20130627',
172 'formats': 'mincount:16',
173 'subtitles': 'mincount:1',
176 'force_generic_extractor': True,
177 'skip_download': True,
180 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
182 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
187 'formats': 'mincount:1',
190 'skip_download': True,
193 # SMIL from https://www.restudy.dk/video/play/id/1637
195 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
199 'title': 'video_1637',
200 'formats': 'mincount:3',
203 'skip_download': True,
206 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
208 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
210 'id': 'smil-service',
212 'title': 'smil-service',
213 'formats': 'mincount:1',
216 'skip_download': True,
219 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
221 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
225 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
226 'formats': 'mincount:3',
229 'skip_download': True,
232 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
234 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
236 'id': 'mZlp2ctYIUEB',
238 'title': 'Tikibad ontruimd wegens brand',
239 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
240 'thumbnail': 're:^https?://.*\.jpg$',
244 'skip_download': True,
247 # MPD from http://dash-mse-test.appspot.com/media.html
249 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
250 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
252 'id': 'car-20120827-manifest',
254 'title': 'car-20120827-manifest',
255 'formats': 'mincount:9',
256 'upload_date': '20130904',
259 'format': 'bestvideo',
262 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
264 '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',
269 'formats': 'mincount:8',
273 'skip_download': True,
275 'skip': 'video gone',
277 # m3u8 served with Content-Type: text/plain
279 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
284 'upload_date': '20140720',
285 'formats': 'mincount:11',
289 'skip_download': True,
291 'skip': 'video gone',
295 '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',
299 'upload_date': '20130224',
300 'uploader_id': 'TheVerge',
301 'description': 're:^Chris Ziegler takes a look at the\.*',
302 'uploader': 'The Verge',
303 'title': 'First Firefox OS phones side-by-side',
306 'skip_download': False,
310 # redirect in Refresh HTTP header
311 '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',
315 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
316 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
317 'upload_date': '20150917',
318 'uploader_id': 'brtvofficial',
319 'uploader': 'Boiler Room',
322 'skip_download': False,
326 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
327 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
329 'id': '13601338388002',
331 'uploader': 'www.hodiho.fr',
332 'title': 'R\u00e9gis plante sa Jeep',
335 # bandcamp page with custom domain
337 'add_ie': ['Bandcamp'],
338 'url': 'http://bronyrock.com/track/the-pony-mash',
342 'title': 'The Pony Mash',
343 'uploader': 'M_Pallante',
345 'skip': 'There is a limit of 200 free downloads / month for the test song',
348 # embedded brightcove video
349 # it also tests brightcove videos that need to set the 'Referer'
350 # in the http requests
351 'add_ie': ['BrightcoveLegacy'],
352 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
354 'id': '2765128793001',
356 'title': 'Le cours de bourse : l’analyse technique',
357 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
358 'uploader': 'BFM BUSINESS',
361 'skip_download': True,
365 # embedded with itemprop embedURL and video id spelled as `idVideo`
366 'add_id': ['BrightcoveLegacy'],
367 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
369 'id': '5255628253001',
371 'title': 'md5:37c519b1128915607601e75a87995fc0',
372 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
373 'uploader': 'BFM BUSINESS',
374 'uploader_id': '876450612001',
375 'timestamp': 1482255315,
376 'upload_date': '20161220',
379 'skip_download': True,
383 # https://github.com/rg3/youtube-dl/issues/2253
384 'url': 'http://bcove.me/i6nfkrc3',
385 'md5': '0ba9446db037002366bab3b3eb30c88c',
387 'id': '3101154703001',
389 'title': 'Still no power',
390 'uploader': 'thestar.com',
391 '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.',
393 'add_ie': ['BrightcoveLegacy'],
394 'skip': 'video gone',
397 'url': 'http://www.championat.com/video/football/v/87/87499.html',
398 'md5': 'fb973ecf6e4a78a67453647444222983',
400 'id': '3414141473001',
402 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
403 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
404 'uploader': 'Championat',
408 # https://github.com/rg3/youtube-dl/issues/3541
409 'add_ie': ['BrightcoveLegacy'],
410 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
412 'id': '3866516442001',
414 'title': 'Leer mij vrouwen kennen: Aflevering 1',
415 'description': 'Leer mij vrouwen kennen: Aflevering 1',
416 'uploader': 'SBS Broadcasting',
418 'skip': 'Restricted to Netherlands',
420 'skip_download': True, # m3u8 download
425 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
426 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
428 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
430 'title': '2cc213299525360.mov', # that's what we get
433 'add_ie': ['Ooyala'],
436 # ooyala video embedded with http://player.ooyala.com/iframe.js
437 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
439 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
441 'title': '"Steve Jobs: Man in the Machine" trailer',
442 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
446 'skip_download': True,
448 'skip': 'movie expired',
452 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
456 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
457 'upload_date': '20140225',
458 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
459 'uploader': 'Tested',
460 'uploader_id': 'testedcom',
462 # No need to test YoutubeIE here
464 'skip_download': True,
469 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
473 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
474 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
476 # HEAD requests lead to endless 301, while GET is OK
477 'expected_warnings': ['301'],
481 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
485 'title': 'Охотское море стало целиком российским',
486 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
490 'skip_download': True,
495 '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/',
499 'title': 'Дошкольное воспитание',
504 'url': 'http://www.vestifinance.ru/articles/25753',
507 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
512 'title': 'Госзаказ. День 3',
518 'title': 'Госзаказ. День 2',
524 'title': 'Госзаказ. День 1',
530 'skip_download': True,
535 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
537 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
539 'title': 'Ужастики, русский трейлер (2015)',
540 'thumbnail': 're:^https?://.*\.jpg$',
546 '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',
549 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
551 'playlist_mincount': 7,
552 # This forum does not allow <iframe> syntaxes anymore
553 # Now HTML tags are displayed as-is
554 'skip': 'No videos on this page',
558 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
559 'md5': '65fdff94098e4a607385a60c5177c638',
563 'title': 'Hidden miracles of the natural world',
564 'uploader': 'Louie Schwartzberg',
565 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
568 # Embedded Ustream video
570 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
571 'md5': '27b99cdb639c9b12a79bca876a073417',
575 'uploader': 'AU SPA: The NSA and Privacy',
576 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
579 # nowvideo embed hidden behind percent encoding
581 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
582 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
584 'id': '06e53103ca9aa',
586 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
587 'description': 'No description',
592 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
593 'md5': '7653032cbb25bf6c80d80f217055fa43',
595 'id': '048195-004_PLUS7-F',
598 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
599 'upload_date': '20140320',
602 'skip_download': 'Requires rtmpdump'
604 'skip': 'video gone',
608 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
612 'title': 'Alcaline, le concert avec Calogero',
613 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
614 'upload_date': '20150226',
615 'timestamp': 1424989860,
620 'skip_download': True,
622 'expected_warnings': [
628 'url': 'http://www.wired.com/2014/04/honda-asimo/',
629 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
631 'id': '53501be369702d3275860000',
633 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
638 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
639 'md5': '441aeeb82eb72c422c7f14ec533999cd',
641 'id': 'k2mm4bCdJ6CQ2i7c8o2',
643 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
644 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
646 'uploader_id': 'xgditw',
647 'upload_date': '20140425',
648 'timestamp': 1398441542,
650 'add_ie': ['Dailymotion'],
654 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
658 'title': 'The NBL Auction 2014',
659 'uploader': 'BADMINTON England',
660 'uploader_id': 'BADMINTONEvents',
661 'upload_date': '20140603',
662 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
664 'add_ie': ['Youtube'],
666 'skip_download': True,
671 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
672 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
674 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
676 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
677 'description': 'Two valets share their love for movie star Liam Neesons.',
678 'timestamp': 1349922600,
679 'upload_date': '20121011',
682 # YouTube embed via <data-embed-url="">
684 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
688 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
689 'uploader': 'Gameloft',
690 'uploader_id': 'gameloft',
691 'upload_date': '20140828',
692 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
695 'skip_download': True,
700 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
702 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
704 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
705 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
710 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
712 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
713 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
719 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
724 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
725 'md5': '9d65602bf31c6e20014319c7d07fba27',
727 'id': '5123ea6d5e5a7',
730 'uploader': 'www.handjobhub.com',
731 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
734 # Multiple brightcove videos
735 # https://github.com/rg3/youtube-dl/issues/2283
737 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
739 'id': 'always-never',
740 'title': 'Always / Never - The New Yorker',
744 'extract_flat': False,
745 'skip_download': True,
750 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
751 'md5': '96f09a37e44da40dd083e12d9a683327',
755 'title': 'Ump changes call to ball',
756 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
758 'timestamp': 1401537900,
759 'upload_date': '20140531',
760 'thumbnail': 're:^https?://.*\.jpg$',
765 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
766 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
770 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
771 'description': 'a Paywall Videos video from Remilon',
773 'uploader': 'study.com',
774 'timestamp': 1459678540,
775 'upload_date': '20160403',
776 'filesize': 24687186,
780 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
781 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
785 'title': 'Conversation about Hexagonal Rails Part 1',
786 'description': 'a Martin Fowler video from ThoughtWorks',
788 'uploader': 'thoughtworks.wistia.com',
789 'timestamp': 1401832161,
790 'upload_date': '20140603',
793 # Wistia standard embed (async)
795 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
799 'title': 'Drip Brennan Dunn Workshop',
800 'description': 'a JV Webinars video from getdrip-1',
802 'timestamp': 1463607249,
803 'upload_date': '20160518',
806 'skip_download': True,
811 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
815 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
816 'uploader': 'Sophos Security',
817 'title': 'Chet Chat 171 - Oct 29, 2014',
818 'upload_date': '20141029',
821 # Soundcloud multiple embeds
823 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
826 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
828 'playlist_mincount': 7,
832 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
836 'upload_date': '20141112',
837 'title': 'Rosetta #CometLanding webcast HL 10',
840 # Another Livestream embed, without 'new.' in URL
842 'url': 'https://www.freespeech.org/',
846 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
850 'skip_download': True,
855 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
858 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
860 'playlist_mincount': 2,
864 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
868 'upload_date': '20141126',
869 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
874 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
876 'id': '730m_DandD_1901_512k',
878 'uploader': 'www.abc.net.au',
879 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
882 # embedded viddler video
884 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
888 'uploader': 'deadspin',
889 'title': 'WALL-TO-GORTAT',
890 'timestamp': 1422285291,
891 'upload_date': '20150126',
893 'add_ie': ['Viddler'],
897 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
901 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
902 'description': 'md5:601cb790edd05908957dae8aaa866465',
903 'upload_date': '20150220',
905 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
909 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
913 'upload_date': '20150212',
914 'uploader': 'The National Archives UK',
915 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
916 'uploader_id': 'NationalArchives08',
917 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
922 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
923 'playlist_mincount': 5,
925 'id': 'aanslagen-kopenhagen',
926 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
931 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
935 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
938 # Kaltura embed (different embed code)
940 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
944 'upload_date': '20150127',
945 'uploader_id': 'PremierMedia',
947 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
950 # Kaltura embed protected with referrer
952 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
956 'title': 'Violetta - Achter De Schermen - Ruggero',
957 'description': 'Achter de schermen met Ruggero',
958 'timestamp': 1435133761,
959 'upload_date': '20150624',
960 'uploader_id': 'echojecka',
963 # Kaltura embed with single quotes
965 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
970 'timestamp': 1355743100,
971 'upload_date': '20121217',
972 'uploader_id': 'batchUser',
974 'add_ie': ['Kaltura'],
977 # Kaltura embedded via quoted entry_id
978 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
982 'title': '06_matthew_brender_raj_dutt',
983 'timestamp': 1466638791,
984 'upload_date': '20160622',
986 'add_ie': ['Kaltura'],
987 'expected_warnings': [
988 'Could not send HEAD request'
991 'skip_download': True,
995 # Kaltura embedded, some fileExt broken (#11480)
996 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1000 'title': 'Our "Standard Models" of particle physics and cosmology',
1001 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1002 'timestamp': 1321158993,
1003 'upload_date': '20111113',
1004 'uploader_id': 'kps1',
1006 'add_ie': ['Kaltura'],
1008 # Eagle.Platform embed (generic URL)
1010 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1011 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1015 'title': 'Навальный вышел на свободу',
1016 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1017 'thumbnail': 're:^https?://.*\.jpg$',
1023 # ClipYou (Eagle.Platform) embed (custom URL)
1025 'url': 'http://muz-tv.ru/play/7129/',
1026 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1030 'title': "'O Sole Mio",
1031 'thumbnail': 're:^https?://.*\.jpg$',
1038 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1042 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1043 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1044 'thumbnail': 're:^https?://.*\.jpg$',
1051 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1055 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1056 'thumbnail': 're:^https?://.*\.png$',
1062 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1063 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1067 'title': 'Facebook Creates "On This Day" | Crunch Report',
1072 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1076 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1081 # Crooks and Liars embed
1083 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1087 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1088 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1089 'timestamp': 1428207000,
1090 'upload_date': '20150405',
1091 'uploader': 'Heather',
1094 # Crooks and Liars external embed
1096 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1098 'id': 'MTE3MjUtMzQ2MzA',
1100 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1101 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1102 'timestamp': 1265032391,
1103 'upload_date': '20100201',
1104 'uploader': 'Heather',
1107 # NBC Sports vplayer embed
1109 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1111 'id': 'ln7x1qSThw4k',
1113 'title': "PFT Live: New leader in the 'new-look' defense",
1114 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1115 'uploader': 'NBCU-SPORTS',
1116 'upload_date': '20140107',
1117 'timestamp': 1389118457,
1122 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1123 'md5': '1aa589c675898ae6d37a17913cf68d66',
1125 'id': '701714499682',
1127 'title': 'PREVIEW: On Assignment: David Letterman',
1128 '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.',
1133 'url': 'https://video.udn.com/news/300346',
1134 'md5': 'fd2060e988c326991037b9aff9df21a6',
1138 'title': '中一中男師變性 全校師生力挺',
1139 'thumbnail': 're:^https?://.*\.jpg$',
1143 'skip_download': True,
1148 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1150 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1152 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1153 'title': 'This is what separates the Excel masters from the wannabes',
1154 'duration': 191.933,
1158 'skip_download': True,
1161 # Brightcove URL in single quotes
1163 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1164 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1166 'id': '4255764656001',
1168 'title': 'SN Presents: Russell Martin, World Citizen',
1169 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1170 'uploader': 'Rogers Sportsnet',
1171 'uploader_id': '1704050871',
1172 'upload_date': '20150525',
1173 'timestamp': 1432570283,
1176 # Dailymotion Cloud video
1178 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1179 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1183 'title': 'Sauvons les abeilles ! - Le débat',
1184 'description': 'md5:d9082128b1c5277987825d684939ca26',
1185 'thumbnail': 're:^https?://.*\.jpe?g$',
1186 'timestamp': 1434970506,
1187 'upload_date': '20150622',
1188 'uploader': 'Public Sénat',
1189 'uploader_id': 'xa9gza',
1192 # OnionStudios embed
1194 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1198 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1199 'thumbnail': 're:^https?://.*\.jpe?g$',
1200 'uploader': 'ClickHole',
1201 'uploader_id': 'clickhole',
1206 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1208 'id': '74849a00-85a9-11e1-9660-123139220831',
1210 'title': '#whilewewatch',
1213 # AdobeTVVideo embed
1215 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1216 'md5': '43662b577c018ad707a63766462b1e87',
1220 'title': 'New experience with Acrobat DC',
1221 'description': 'New experience with Acrobat DC',
1222 'duration': 248.667,
1225 # BrightcoveInPageEmbed embed
1227 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1229 'id': '4238694884001',
1231 'title': 'Tabletop: Dread, Last Thoughts',
1232 'description': 'Tabletop: Dread, Last Thoughts',
1236 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1237 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1239 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1241 'id': '4785848093001',
1243 'title': 'The Cardinal Pell Interview',
1244 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1245 'uploader': 'GlobeCast Australia - GlobeStream',
1246 'uploader_id': '2733773828001',
1247 'upload_date': '20160304',
1248 'timestamp': 1457083087,
1252 'skip_download': True,
1255 # Another form of arte.tv embed
1257 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1258 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1260 'id': '030273-562_PLUS7-F',
1262 'title': 'ARTE Reportage - Nulle part, en France',
1263 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1264 'upload_date': '20160409',
1269 'url': 'http://www.wykop.pl/link/3088787/',
1270 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1272 'id': '874_1459135191',
1274 'title': 'Man shows poor quality of new apartment building',
1275 'description': 'The wall is like a sand pile.',
1276 'uploader': 'Lake8737',
1279 # Duplicated embedded video URLs
1281 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1283 'id': '149298443_480_16c25b74_2',
1285 'title': 'vs. Blue Orange Spring Game',
1286 'uploader': 'www.hudl.com',
1289 # twitter:player:stream embed
1291 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1295 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1296 'uploader': 'www.rtl.be',
1300 'skip_download': True,
1303 # twitter:player embed
1305 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1306 'md5': 'a3e0df96369831de324f0778e126653c',
1308 'id': '4909620399001',
1310 'title': 'What Do Black Holes Sound Like?',
1311 'description': 'what do black holes sound like',
1312 'upload_date': '20160524',
1313 'uploader_id': '29913724001',
1314 'timestamp': 1464107587,
1315 'uploader': 'TheAtlantic',
1317 'add_ie': ['BrightcoveLegacy'],
1319 # Facebook <iframe> embed
1321 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1322 'md5': 'fbcde74f534176ecb015849146dd3aee',
1324 'id': '599637780109885',
1326 'title': 'Facebook video #599637780109885',
1329 # Facebook API embed
1331 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1332 'md5': 'a47372ee61b39a7b90287094d447d94e',
1334 'id': '10153467542406923',
1336 'title': 'Facebook video #10153467542406923',
1339 # Wordpress "YouTube Video Importer" plugin
1341 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1342 'md5': 'd16797741b560b485194eddda8121b48',
1344 'id': 'HNTXWDXV9Is',
1346 'title': 'Blue Devils Drumline Stanford lot 2016',
1347 'upload_date': '20160627',
1348 'uploader_id': 'GENOCIDE8GENERAL10',
1349 'uploader': 'cylus cyrus',
1353 # video stored on custom kaltura server
1354 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1355 'md5': '537617d06e64dfed891fa1593c4b30cc',
1359 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1360 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1361 'uploader_id': 'videos.expansion@el-mundo.net',
1362 'upload_date': '20150429',
1363 'timestamp': 1430303472,
1365 'add_ie': ['Kaltura'],
1368 # Non-standard Vimeo embed
1369 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1370 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1374 'title': 'Understanding the web - Teaser',
1375 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1376 'upload_date': '20151214',
1377 'uploader': 'OpenClassrooms',
1378 'uploader_id': 'openclassrooms',
1380 'add_ie': ['Vimeo'],
1383 # generic vimeo embed that requires original URL passed as Referer
1384 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1385 'only_matching': True,
1388 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1389 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1391 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1393 'title': 'Big Buck Bunny',
1394 'description': 'Royalty free test video',
1395 'timestamp': 1432816365,
1396 'upload_date': '20150528',
1400 'skip_download': True,
1402 'add_ie': [ArkenaIE.ie_key()],
1405 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1409 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1412 'skip_download': True,
1414 'add_ie': [Vbox7IE.ie_key()],
1418 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1421 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1423 'playlist_mincount': 3,
1426 # # TODO: find another test
1427 # # http://schema.org/VideoObject
1428 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1429 # 'md5': '888dcf08b7ea671381f00fab74692755',
1431 # 'id': 'nyvTSJMKId',
1433 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1434 # 'description': '#love for cats.',
1435 # 'timestamp': 1461244995,
1436 # 'upload_date': '20160421',
1439 # 'force_generic_extractor': True,
1444 def report_following_redirect(self, new_url):
1445 """Report information extraction."""
1446 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1448 def _extract_rss(self, url, video_id, doc):
1449 playlist_title = doc.find('./channel/title').text
1450 playlist_desc_el = doc.find('./channel/description')
1451 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1454 for it in doc.findall('./channel/item'):
1455 next_url = xpath_text(it, 'link', fatal=False)
1457 enclosure_nodes = it.findall('./enclosure')
1458 for e in enclosure_nodes:
1459 next_url = e.attrib.get('url')
1469 'title': it.find('title').text,
1473 '_type': 'playlist',
1475 'title': playlist_title,
1476 'description': playlist_desc,
1480 def _extract_camtasia(self, url, video_id, webpage):
1481 """ Returns None if no camtasia video can be found. """
1483 camtasia_cfg = self._search_regex(
1484 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1485 webpage, 'camtasia configuration file', default=None)
1486 if camtasia_cfg is None:
1489 title = self._html_search_meta('DC.title', webpage, fatal=True)
1491 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1492 camtasia_cfg = self._download_xml(
1493 camtasia_url, video_id,
1494 note='Downloading camtasia configuration',
1495 errnote='Failed to download camtasia configuration')
1496 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1499 for n in fileset_node.getchildren():
1500 url_n = n.find('./uri')
1505 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1506 'title': '%s - %s' % (title, n.tag),
1507 'url': compat_urlparse.urljoin(url, url_n.text),
1508 'duration': float_or_none(n.find('./duration').text),
1512 '_type': 'playlist',
1517 def _real_extract(self, url):
1518 if url.startswith('//'):
1521 'url': self.http_scheme() + url,
1524 parsed_url = compat_urlparse.urlparse(url)
1525 if not parsed_url.scheme:
1526 default_search = self._downloader.params.get('default_search')
1527 if default_search is None:
1528 default_search = 'fixup_error'
1530 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1532 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1533 return self.url_result('http://' + url)
1534 elif default_search != 'fixup_error':
1535 if default_search == 'auto_warning':
1536 if re.match(r'^(?:url|URL)$', url):
1537 raise ExtractorError(
1538 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1541 self._downloader.report_warning(
1542 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1543 return self.url_result('ytsearch:' + url)
1545 if default_search in ('error', 'fixup_error'):
1546 raise ExtractorError(
1547 '%r is not a valid URL. '
1548 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1549 % (url, url), expected=True)
1551 if ':' not in default_search:
1552 default_search += ':'
1553 return self.url_result(default_search + url)
1555 url, smuggled_data = unsmuggle_url(url)
1556 force_videoid = None
1557 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1558 if smuggled_data and 'force_videoid' in smuggled_data:
1559 force_videoid = smuggled_data['force_videoid']
1560 video_id = force_videoid
1562 video_id = self._generic_id(url)
1564 self.to_screen('%s: Requesting header' % video_id)
1566 head_req = HEADRequest(url)
1567 head_response = self._request_webpage(
1569 note=False, errnote='Could not send HEAD request to %s' % url,
1572 if head_response is not False:
1573 # Check for redirect
1574 new_url = head_response.geturl()
1576 self.report_following_redirect(new_url)
1578 new_url = smuggle_url(
1579 new_url, {'force_videoid': force_videoid})
1580 return self.url_result(new_url)
1582 full_response = None
1583 if head_response is False:
1584 request = sanitized_Request(url)
1585 request.add_header('Accept-Encoding', '*')
1586 full_response = self._request_webpage(request, video_id)
1587 head_response = full_response
1591 'title': self._generic_title(url),
1592 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1595 # Check for direct link to a video
1596 content_type = head_response.headers.get('Content-Type', '').lower()
1597 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1599 format_id = m.group('format_id')
1600 if format_id.endswith('mpegurl'):
1601 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1602 elif format_id == 'f4m':
1603 formats = self._extract_f4m_formats(url, video_id)
1606 'format_id': m.group('format_id'),
1608 'vcodec': 'none' if m.group('type') == 'audio' else None
1610 info_dict['direct'] = True
1611 self._sort_formats(formats)
1612 info_dict['formats'] = formats
1615 if not self._downloader.params.get('test', False) and not is_intentional:
1616 force = self._downloader.params.get('force_generic_extractor', False)
1617 self._downloader.report_warning(
1618 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1620 if not full_response:
1621 request = sanitized_Request(url)
1622 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1623 # making it impossible to download only chunk of the file (yet we need only 512kB to
1624 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1625 # that will always result in downloading the whole file that is not desirable.
1626 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1627 # to accept raw bytes and being able to download only a chunk.
1628 # It may probably better to solve this by checking Content-Type for application/octet-stream
1629 # after HEAD request finishes, but not sure if we can rely on this.
1630 request.add_header('Accept-Encoding', '*')
1631 full_response = self._request_webpage(request, video_id)
1633 first_bytes = full_response.read(512)
1635 # Is it an M3U playlist?
1636 if first_bytes.startswith(b'#EXTM3U'):
1637 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1638 self._sort_formats(info_dict['formats'])
1641 # Maybe it's a direct link to a video?
1642 # Be careful not to download the whole thing!
1643 if not is_html(first_bytes):
1644 self._downloader.report_warning(
1645 'URL could be a direct video link, returning it as such.')
1652 webpage = self._webpage_read_content(
1653 full_response, url, video_id, prefix=first_bytes)
1655 self.report_extraction(video_id)
1657 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1659 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1660 if doc.tag == 'rss':
1661 return self._extract_rss(url, video_id, doc)
1662 elif doc.tag == 'SmoothStreamingMedia':
1663 info_dict['formats'] = self._parse_ism_formats(doc, url)
1664 self._sort_formats(info_dict['formats'])
1666 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1667 smil = self._parse_smil(doc, url, video_id)
1668 self._sort_formats(smil['formats'])
1670 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1671 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1672 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1673 info_dict['formats'] = self._parse_mpd_formats(
1675 mpd_base_url=full_response.geturl().rpartition('/')[0],
1677 self._sort_formats(info_dict['formats'])
1679 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1680 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1681 self._sort_formats(info_dict['formats'])
1683 except compat_xml_parse_error:
1686 # Is it a Camtasia project?
1687 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1688 if camtasia_res is not None:
1691 # Sometimes embedded video player is hidden behind percent encoding
1692 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1693 # Unescaping the whole page allows to handle those cases in a generic way
1694 webpage = compat_urllib_parse_unquote(webpage)
1696 # it's tempting to parse this further, but you would
1697 # have to take into account all the variations like
1698 # Video Title - Site Name
1699 # Site Name | Video Title
1700 # Video Title - Tagline | Site Name
1701 # and so on and so forth; it's just not practical
1702 video_title = self._og_search_title(
1703 webpage, default=None) or self._html_search_regex(
1704 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1707 # Try to detect age limit automatically
1708 age_limit = self._rta_search(webpage)
1709 # And then there are the jokers who advertise that they use RTA,
1710 # but actually don't.
1711 AGE_LIMIT_MARKERS = [
1712 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1714 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1717 # video uploader is domain name
1718 video_uploader = self._search_regex(
1719 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1721 video_description = self._og_search_description(webpage, default=None)
1722 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1725 def _playlist_from_matches(matches, getter=None, ie=None):
1727 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1729 return self.playlist_result(
1730 urlrs, playlist_id=video_id, playlist_title=video_title)
1732 # Look for Brightcove Legacy Studio embeds
1733 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1735 self.to_screen('Brightcove video detected.')
1738 'url': smuggle_url(bc_url, {'Referer': url}),
1739 'ie_key': 'BrightcoveLegacy'
1740 } for bc_url in bc_urls]
1743 '_type': 'playlist',
1744 'title': video_title,
1749 # Look for Brightcove New Studio embeds
1750 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1752 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1754 # Look for ThePlatform embeds
1755 tp_urls = ThePlatformIE._extract_urls(webpage)
1757 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1759 # Look for Vessel embeds
1760 vessel_urls = VesselIE._extract_urls(webpage)
1762 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1764 # Look for embedded rtl.nl player
1765 matches = re.findall(
1766 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1769 return _playlist_from_matches(matches, ie='RtlNl')
1771 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1773 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1775 vid_me_embed_url = self._search_regex(
1776 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1777 webpage, 'vid.me embed', default=None)
1778 if vid_me_embed_url is not None:
1779 return self.url_result(vid_me_embed_url, 'Vidme')
1781 # Look for embedded YouTube player
1782 matches = re.findall(r'''(?x)
1791 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1795 return _playlist_from_matches(
1796 matches, lambda m: unescapeHTML(m[1]))
1798 # Look for lazyYT YouTube embed
1799 matches = re.findall(
1800 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1802 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1804 # Look for Wordpress "YouTube Video Importer" plugin
1805 matches = re.findall(r'''(?x)<div[^>]+
1806 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1807 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1809 return _playlist_from_matches(matches, lambda m: m[-1])
1811 matches = DailymotionIE._extract_urls(webpage)
1813 return _playlist_from_matches(matches)
1815 # Look for embedded Dailymotion playlist player (#3822)
1817 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1819 playlists = re.findall(
1820 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1822 return _playlist_from_matches(
1823 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1825 # Look for embedded Wistia player
1827 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1829 embed_url = self._proto_relative_url(
1830 unescapeHTML(match.group('url')))
1832 '_type': 'url_transparent',
1835 'uploader': video_uploader,
1838 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1841 '_type': 'url_transparent',
1842 'url': 'wistia:%s' % match.group('id'),
1844 'uploader': video_uploader,
1849 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1850 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1853 return self.url_result(self._proto_relative_url(
1854 'wistia:%s' % match.group('id')), 'Wistia')
1856 # Look for SVT player
1857 svt_url = SVTIE._extract_url(webpage)
1859 return self.url_result(svt_url, 'SVT')
1861 # Look for embedded condenast player
1862 matches = re.findall(
1863 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1867 '_type': 'playlist',
1870 'ie_key': 'CondeNast',
1872 } for ma in matches],
1873 'title': video_title,
1877 # Look for Bandcamp pages with custom domain
1878 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1879 if mobj is not None:
1880 burl = unescapeHTML(mobj.group(1))
1881 # Don't set the extractor because it can be a track url or an album
1882 return self.url_result(burl)
1884 # Look for embedded Vevo player
1886 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1887 if mobj is not None:
1888 return self.url_result(mobj.group('url'))
1890 # Look for embedded Viddler player
1892 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1894 if mobj is not None:
1895 return self.url_result(mobj.group('url'))
1897 # Look for NYTimes player
1899 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1901 if mobj is not None:
1902 return self.url_result(mobj.group('url'))
1904 # Look for Libsyn player
1906 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1907 if mobj is not None:
1908 return self.url_result(mobj.group('url'))
1910 # Look for Ooyala videos
1911 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1912 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1913 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1914 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1915 if mobj is not None:
1916 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1918 # Look for multiple Ooyala embeds on SBN network websites
1919 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1920 if mobj is not None:
1921 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1923 return _playlist_from_matches(
1924 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1926 # Look for Aparat videos
1927 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1928 if mobj is not None:
1929 return self.url_result(mobj.group(1), 'Aparat')
1931 # Look for MPORA videos
1932 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1933 if mobj is not None:
1934 return self.url_result(mobj.group(1), 'Mpora')
1936 # Look for embedded NovaMov-based player
1938 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1939 (?P<url>http://(?:(?:embed|www)\.)?
1941 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1942 videoweed\.(?:es|com)|
1943 movshare\.(?:net|sx|ag)|
1944 divxstage\.(?:eu|net|ch|co|at|ag))
1945 /embed\.php.+?)\1''', webpage)
1946 if mobj is not None:
1947 return self.url_result(mobj.group('url'))
1949 # Look for embedded Facebook player
1950 facebook_url = FacebookIE._extract_url(webpage)
1951 if facebook_url is not None:
1952 return self.url_result(facebook_url, 'Facebook')
1954 # Look for embedded VK player
1955 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1956 if mobj is not None:
1957 return self.url_result(mobj.group('url'), 'VK')
1959 # Look for embedded Odnoklassniki player
1960 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1961 if mobj is not None:
1962 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1964 # Look for embedded ivi player
1965 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1966 if mobj is not None:
1967 return self.url_result(mobj.group('url'), 'Ivi')
1969 # Look for embedded Huffington Post player
1971 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1972 if mobj is not None:
1973 return self.url_result(mobj.group('url'), 'HuffPost')
1976 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1977 if mobj is not None:
1978 return self.url_result(mobj.group('url'))
1979 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1980 if mobj is not None:
1981 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1983 # Look for funnyordie embed
1984 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1986 return _playlist_from_matches(
1987 matches, getter=unescapeHTML, ie='FunnyOrDie')
1989 # Look for BBC iPlayer embed
1990 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1992 return _playlist_from_matches(matches, ie='BBCCoUk')
1994 # Look for embedded RUTV player
1995 rutv_url = RUTVIE._extract_url(webpage)
1997 return self.url_result(rutv_url, 'RUTV')
1999 # Look for embedded TVC player
2000 tvc_url = TVCIE._extract_url(webpage)
2002 return self.url_result(tvc_url, 'TVC')
2004 # Look for embedded SportBox player
2005 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2007 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2009 # Look for embedded XHamster player
2010 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2012 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2014 # Look for embedded TNAFlixNetwork player
2015 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2017 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2019 # Look for embedded PornHub player
2020 pornhub_urls = PornHubIE._extract_urls(webpage)
2022 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2024 # Look for embedded DrTuber player
2025 drtuber_urls = DrTuberIE._extract_urls(webpage)
2027 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2029 # Look for embedded RedTube player
2030 redtube_urls = RedTubeIE._extract_urls(webpage)
2032 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2034 # Look for embedded Tvigle player
2036 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2037 if mobj is not None:
2038 return self.url_result(mobj.group('url'), 'Tvigle')
2040 # Look for embedded TED player
2042 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2043 if mobj is not None:
2044 return self.url_result(mobj.group('url'), 'TED')
2046 # Look for embedded Ustream videos
2048 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2049 if mobj is not None:
2050 return self.url_result(mobj.group('url'), 'Ustream')
2052 # Look for embedded arte.tv player
2054 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2056 if mobj is not None:
2057 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2059 # Look for embedded francetv player
2061 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2063 if mobj is not None:
2064 return self.url_result(mobj.group('url'))
2066 # Look for embedded smotri.com player
2067 smotri_url = SmotriIE._extract_url(webpage)
2069 return self.url_result(smotri_url, 'Smotri')
2071 # Look for embedded Myvi.ru player
2072 myvi_url = MyviIE._extract_url(webpage)
2074 return self.url_result(myvi_url)
2076 # Look for embedded soundcloud player
2077 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2079 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2081 # Look for embedded mtvservices player
2082 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2084 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2086 # Look for embedded yahoo player
2088 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2090 if mobj is not None:
2091 return self.url_result(mobj.group('url'), 'Yahoo')
2093 # Look for embedded sbs.com.au player
2097 <meta\s+property="og:video"\s+content=|
2100 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2102 if mobj is not None:
2103 return self.url_result(mobj.group('url'), 'SBS')
2105 # Look for embedded Cinchcast player
2107 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2109 if mobj is not None:
2110 return self.url_result(mobj.group('url'), 'Cinchcast')
2113 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2117 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2119 if mobj is not None:
2120 return self.url_result(mobj.group('url'), 'MLB')
2123 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2125 if mobj is not None:
2126 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2129 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2131 if mobj is not None:
2132 return self.url_result(mobj.group('url'), 'Livestream')
2134 # Look for Zapiks embed
2136 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2137 if mobj is not None:
2138 return self.url_result(mobj.group('url'), 'Zapiks')
2140 # Look for Kaltura embeds
2141 kaltura_url = KalturaIE._extract_url(webpage)
2143 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2145 # Look for Eagle.Platform embeds
2146 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2147 if eagleplatform_url:
2148 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2150 # Look for ClipYou (uses Eagle.Platform) embeds
2152 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2153 if mobj is not None:
2154 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2156 # Look for Pladform embeds
2157 pladform_url = PladformIE._extract_url(webpage)
2159 return self.url_result(pladform_url)
2161 # Look for Videomore embeds
2162 videomore_url = VideomoreIE._extract_url(webpage)
2164 return self.url_result(videomore_url)
2166 # Look for Webcaster embeds
2167 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2169 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2171 # Look for Playwire embeds
2173 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2174 if mobj is not None:
2175 return self.url_result(mobj.group('url'))
2177 # Look for 5min embeds
2179 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2180 if mobj is not None:
2181 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2183 # Look for Crooks and Liars embeds
2185 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2186 if mobj is not None:
2187 return self.url_result(mobj.group('url'))
2189 # Look for NBC Sports VPlayer embeds
2190 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2192 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2194 # Look for NBC News embeds
2195 nbc_news_embed_url = re.search(
2196 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2197 if nbc_news_embed_url:
2198 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2200 # Look for Google Drive embeds
2201 google_drive_url = GoogleDriveIE._extract_url(webpage)
2202 if google_drive_url:
2203 return self.url_result(google_drive_url, 'GoogleDrive')
2205 # Look for UDN embeds
2207 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2208 if mobj is not None:
2209 return self.url_result(
2210 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2212 # Look for Senate ISVP iframe
2213 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2215 return self.url_result(senate_isvp_url, 'SenateISVP')
2217 # Look for Dailymotion Cloud videos
2218 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2220 return self.url_result(dmcloud_url, 'DailymotionCloud')
2222 # Look for OnionStudios embeds
2223 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2224 if onionstudios_url:
2225 return self.url_result(onionstudios_url)
2227 # Look for ViewLift embeds
2228 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2230 return self.url_result(viewlift_url)
2232 # Look for JWPlatform embeds
2233 jwplatform_url = JWPlatformIE._extract_url(webpage)
2235 return self.url_result(jwplatform_url, 'JWPlatform')
2237 # Look for Digiteka embeds
2238 digiteka_url = DigitekaIE._extract_url(webpage)
2240 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2242 # Look for Arkena embeds
2243 arkena_url = ArkenaIE._extract_url(webpage)
2245 return self.url_result(arkena_url, ArkenaIE.ie_key())
2247 # Look for Piksel embeds
2248 piksel_url = PikselIE._extract_url(webpage)
2250 return self.url_result(piksel_url, PikselIE.ie_key())
2252 # Look for Limelight embeds
2253 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2257 'Channel': 'channel',
2258 'ChannelList': 'channel_list',
2260 return self.url_result('limelight:%s:%s' % (
2261 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2265 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2267 name=(["\'])flashVars\2[^>]+
2268 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2271 return self.url_result('limelight:media:%s' % mobj.group('id'))
2273 # Look for AdobeTVVideo embeds
2275 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2277 if mobj is not None:
2278 return self.url_result(
2279 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2282 # Look for Vine embeds
2284 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2286 if mobj is not None:
2287 return self.url_result(
2288 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2290 # Look for VODPlatform embeds
2292 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2294 if mobj is not None:
2295 return self.url_result(
2296 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2298 # Look for Mangomolo embeds
2300 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2302 video\?.*?\bid=(?P<video_id>\d+)|
2303 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2304 ).+?)\1''', webpage)
2305 if mobj is not None:
2307 '_type': 'url_transparent',
2308 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2309 'title': video_title,
2310 'description': video_description,
2311 'thumbnail': video_thumbnail,
2312 'uploader': video_uploader,
2314 video_id = mobj.group('video_id')
2317 'ie_key': 'MangomoloVideo',
2322 'ie_key': 'MangomoloLive',
2323 'id': mobj.group('channel_id'),
2327 # Look for Instagram embeds
2328 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2329 if instagram_embed_url is not None:
2330 return self.url_result(
2331 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2333 # Look for LiveLeak embeds
2334 liveleak_url = LiveLeakIE._extract_url(webpage)
2336 return self.url_result(liveleak_url, 'LiveLeak')
2338 # Look for 3Q SDN embeds
2339 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2342 '_type': 'url_transparent',
2343 'ie_key': ThreeQSDNIE.ie_key(),
2344 'url': self._proto_relative_url(threeqsdn_url),
2345 'title': video_title,
2346 'description': video_description,
2347 'thumbnail': video_thumbnail,
2348 'uploader': video_uploader,
2351 # Look for VBOX7 embeds
2352 vbox7_url = Vbox7IE._extract_url(webpage)
2354 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2356 # Look for DBTV embeds
2357 dbtv_urls = DBTVIE._extract_urls(webpage)
2359 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2361 # Looking for http://schema.org/VideoObject
2362 json_ld = self._search_json_ld(
2363 webpage, video_id, default={}, expected_type='VideoObject')
2364 if json_ld.get('url'):
2366 'title': video_title or info_dict['title'],
2367 'description': video_description,
2368 'thumbnail': video_thumbnail,
2369 'age_limit': age_limit
2371 info_dict.update(json_ld)
2374 # Look for HTML5 media
2375 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2377 for entry in entries:
2380 'title': video_title,
2382 self._sort_formats(entry['formats'])
2383 return self.playlist_result(entries)
2385 def check_video(vurl):
2386 if YoutubeIE.suitable(vurl):
2388 vpath = compat_urlparse.urlparse(vurl).path
2389 vext = determine_ext(vpath)
2390 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2392 def filter_video(urls):
2393 return list(filter(check_video, urls))
2395 # Start with something easy: JW Player in SWFObject
2396 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2398 # Look for gorilla-vid style embedding
2399 found = filter_video(re.findall(r'''(?sx)
2403 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2406 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2408 # Broaden the search a little bit
2409 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2411 # Broaden the findall a little bit: JWPlayer JS loader
2412 found = filter_video(re.findall(
2413 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2416 found = filter_video(re.findall(r'''(?xs)
2417 flowplayer\("[^"]+",\s*
2419 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2420 ["']?url["']?\s*:\s*["']([^"']+)["']
2425 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2427 # Try to find twitter cards info
2428 # twitter:player:stream should be checked before twitter:player since
2429 # it is expected to contain a raw stream (see
2430 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2431 found = filter_video(re.findall(
2432 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2434 # We look for Open Graph info:
2435 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2436 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2437 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2438 if m_video_type is not None:
2439 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2441 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2443 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2444 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2447 # Look also in Refresh HTTP header
2448 refresh_header = head_response.headers.get('Refresh')
2450 # In python 2 response HTTP headers are bytestrings
2451 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2452 refresh_header = refresh_header.decode('iso-8859-1')
2453 found = re.search(REDIRECT_REGEX, refresh_header)
2455 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2456 self.report_following_redirect(new_url)
2463 # twitter:player is a https URL to iframe player that may or may not
2464 # be supported by youtube-dl thus this is checked the very last (see
2465 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2466 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2468 return self.url_result(embed_url)
2471 raise UnsupportedError(url)
2474 for video_url in orderedSet(found):
2475 video_url = unescapeHTML(video_url)
2476 video_url = video_url.replace('\\/', '/')
2477 video_url = compat_urlparse.urljoin(url, video_url)
2478 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2480 # Sometimes, jwplayer extraction will result in a YouTube URL
2481 if YoutubeIE.suitable(video_url):
2482 entries.append(self.url_result(video_url, 'Youtube'))
2485 # here's a fun little line of code for you:
2486 video_id = os.path.splitext(video_id)[0]
2490 'uploader': video_uploader,
2491 'title': video_title,
2492 'age_limit': age_limit,
2495 ext = determine_ext(video_url)
2497 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2499 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2501 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2503 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2505 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2506 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2507 # Just matching .ism/manifest is not enough to be reliably sure
2508 # whether it's actually an ISM manifest or some other streaming
2509 # manifest since there are various streaming URL formats
2510 # possible (see [1]) as well as some other shenanigans like
2511 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2513 # Thus the most reasonable way to solve this is to delegate
2514 # to generic extractor in order to look into the contents of
2515 # the manifest itself.
2516 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2517 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2518 entry_info_dict = self.url_result(
2519 smuggle_url(video_url, {'to_generic': True}),
2522 entry_info_dict['url'] = video_url
2524 if entry_info_dict.get('formats'):
2525 self._sort_formats(entry_info_dict['formats'])
2527 entries.append(entry_info_dict)
2529 if len(entries) == 1:
2532 for num, e in enumerate(entries, start=1):
2533 # 'url' results don't have a title
2534 if e.get('title') is not None:
2535 e['title'] = '%s (%d)' % (e['title'], num)
2537 '_type': 'playlist',