3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
43 from .nbc import NBCSportsVPlayerIE
44 from .ooyala import OoyalaIE
45 from .rutv import RUTVIE
46 from .tvc import TVCIE
47 from .sportbox import SportBoxEmbedIE
48 from .smotri import SmotriIE
49 from .myvi import MyviIE
50 from .condenast import CondeNastIE
51 from .udn import UDNEmbedIE
52 from .senateisvp import SenateISVPIE
53 from .svt import SVTIE
54 from .pornhub import PornHubIE
55 from .xhamster import XHamsterEmbedIE
56 from .tnaflix import TNAFlixNetworkEmbedIE
57 from .drtuber import DrTuberIE
58 from .redtube import RedTubeIE
59 from .vimeo import VimeoIE
60 from .dailymotion import (
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
103 class GenericIE(InfoExtractor):
104 IE_DESC = 'Generic downloader that works on some sites'
108 # Direct link to a video
110 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
111 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
116 'upload_date': '20100513',
119 # Direct link to media delivered compressed (until Accept-Encoding is *)
121 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
122 'md5': '128c42e68b13950268b648275386fc74',
124 'id': 'FictionJunction-Parallel_Hearts',
126 'title': 'FictionJunction-Parallel_Hearts',
127 'upload_date': '20140522',
129 'expected_warnings': [
130 'URL could be a direct video link, returning it as such.'
132 'skip': 'URL invalid',
134 # Direct download with broken HEAD
136 'url': 'http://ai-radio.org:8000/radio.opus',
143 'skip_download': True, # infinite live stream
145 'expected_warnings': [
146 r'501.*Not Implemented',
150 # Direct link with incorrect MIME type
152 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
153 'md5': '4ccbebe5f36706d85221f204d7eb5913',
155 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
156 'id': '5_Lennart_Poettering_-_Systemd',
158 'title': '5_Lennart_Poettering_-_Systemd',
159 'upload_date': '20141120',
161 'expected_warnings': [
162 'URL could be a direct video link, returning it as such.'
167 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
169 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
170 'title': 'Zero Punctuation',
171 'description': 're:.*groundbreaking video review series.*'
173 'playlist_mincount': 11,
175 # RSS feed with enclosure
177 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
179 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
181 'upload_date': '20150228',
182 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
185 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
187 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
191 'title': 'Automatics, robotics and biocybernetics',
192 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
193 'upload_date': '20130627',
194 'formats': 'mincount:16',
195 'subtitles': 'mincount:1',
198 'force_generic_extractor': True,
199 'skip_download': True,
202 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
204 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
209 'formats': 'mincount:1',
212 'skip_download': True,
215 # SMIL from https://www.restudy.dk/video/play/id/1637
217 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
221 'title': 'video_1637',
222 'formats': 'mincount:3',
225 'skip_download': True,
228 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
230 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
232 'id': 'smil-service',
234 'title': 'smil-service',
235 'formats': 'mincount:1',
238 'skip_download': True,
241 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
243 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
247 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
248 'formats': 'mincount:3',
251 'skip_download': True,
254 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
256 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
258 'id': 'mZlp2ctYIUEB',
260 'title': 'Tikibad ontruimd wegens brand',
261 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
262 'thumbnail': r're:^https?://.*\.jpg$',
266 'skip_download': True,
269 # MPD from http://dash-mse-test.appspot.com/media.html
271 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
272 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
274 'id': 'car-20120827-manifest',
276 'title': 'car-20120827-manifest',
277 'formats': 'mincount:9',
278 'upload_date': '20130904',
281 'format': 'bestvideo',
284 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
286 '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',
291 'formats': 'mincount:8',
295 'skip_download': True,
297 'skip': 'video gone',
299 # m3u8 served with Content-Type: text/plain
301 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
306 'upload_date': '20140720',
307 'formats': 'mincount:11',
311 'skip_download': True,
313 'skip': 'video gone',
317 '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',
321 'upload_date': '20130224',
322 'uploader_id': 'TheVerge',
323 'description': r're:^Chris Ziegler takes a look at the\.*',
324 'uploader': 'The Verge',
325 'title': 'First Firefox OS phones side-by-side',
328 'skip_download': False,
332 # redirect in Refresh HTTP header
333 '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',
337 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
338 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
339 'upload_date': '20150917',
340 'uploader_id': 'brtvofficial',
341 'uploader': 'Boiler Room',
344 'skip_download': False,
348 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
349 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
351 'id': '13601338388002',
353 'uploader': 'www.hodiho.fr',
354 'title': 'R\u00e9gis plante sa Jeep',
357 # bandcamp page with custom domain
359 'add_ie': ['Bandcamp'],
360 'url': 'http://bronyrock.com/track/the-pony-mash',
364 'title': 'The Pony Mash',
365 'uploader': 'M_Pallante',
367 'skip': 'There is a limit of 200 free downloads / month for the test song',
370 # embedded brightcove video
371 # it also tests brightcove videos that need to set the 'Referer'
372 # in the http requests
373 'add_ie': ['BrightcoveLegacy'],
374 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
376 'id': '2765128793001',
378 'title': 'Le cours de bourse : l’analyse technique',
379 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
380 'uploader': 'BFM BUSINESS',
383 'skip_download': True,
387 # embedded with itemprop embedURL and video id spelled as `idVideo`
388 'add_id': ['BrightcoveLegacy'],
389 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
391 'id': '5255628253001',
393 'title': 'md5:37c519b1128915607601e75a87995fc0',
394 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
395 'uploader': 'BFM BUSINESS',
396 'uploader_id': '876450612001',
397 'timestamp': 1482255315,
398 'upload_date': '20161220',
401 'skip_download': True,
405 # https://github.com/rg3/youtube-dl/issues/2253
406 'url': 'http://bcove.me/i6nfkrc3',
407 'md5': '0ba9446db037002366bab3b3eb30c88c',
409 'id': '3101154703001',
411 'title': 'Still no power',
412 'uploader': 'thestar.com',
413 '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.',
415 'add_ie': ['BrightcoveLegacy'],
416 'skip': 'video gone',
419 'url': 'http://www.championat.com/video/football/v/87/87499.html',
420 'md5': 'fb973ecf6e4a78a67453647444222983',
422 'id': '3414141473001',
424 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
425 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
426 'uploader': 'Championat',
430 # https://github.com/rg3/youtube-dl/issues/3541
431 'add_ie': ['BrightcoveLegacy'],
432 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
434 'id': '3866516442001',
436 'title': 'Leer mij vrouwen kennen: Aflevering 1',
437 'description': 'Leer mij vrouwen kennen: Aflevering 1',
438 'uploader': 'SBS Broadcasting',
440 'skip': 'Restricted to Netherlands',
442 'skip_download': True, # m3u8 download
446 # Brightcove video in <iframe>
447 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
448 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
450 'id': '5360463607001',
452 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
453 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
454 'uploader': 'United Nations',
455 'uploader_id': '1362235914001',
456 'timestamp': 1489593889,
457 'upload_date': '20170315',
459 'add_ie': ['BrightcoveLegacy'],
462 # Brightcove with alternative playerID key
463 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
465 'id': 'nmeth.2062_SV1',
466 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
470 'id': '2228375078001',
472 'title': 'nmeth.2062-sv1',
473 'description': 'nmeth.2062-sv1',
474 'timestamp': 1363357591,
475 'upload_date': '20130315',
476 'uploader': 'Nature Publishing Group',
477 'uploader_id': '1964492299001',
482 # Brightcove with UUID in videoPlayer
483 'url': 'http://www8.hp.com/cn/zh/home.html',
485 'id': '5255815316001',
487 'title': 'Sprocket Video - China',
488 'description': 'Sprocket Video - China',
489 'uploader': 'HP-Video Gallery',
490 'timestamp': 1482263210,
491 'upload_date': '20161220',
492 'uploader_id': '1107601872001',
495 'skip_download': True, # m3u8 download
497 'skip': 'video rotates...weekly?',
500 # Brightcove:new type [2].
501 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
502 'md5': '2b35148fcf48da41c9fb4591650784f3',
504 'id': '5348741021001',
506 'upload_date': '20170306',
507 'uploader_id': '4191638492001',
508 'timestamp': 1488769918,
509 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
514 # Alternative brightcove <video> attributes
515 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
517 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
518 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
521 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
523 'id': '5311302538001',
525 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
526 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
527 'timestamp': 1486321708,
528 'upload_date': '20170205',
529 'uploader_id': '800000640001',
531 'only_matching': True,
535 # Brightcove with UUID in videoPlayer
536 'url': 'http://www8.hp.com/cn/zh/home.html',
538 'id': '5255815316001',
540 'title': 'Sprocket Video - China',
541 'description': 'Sprocket Video - China',
542 'uploader': 'HP-Video Gallery',
543 'timestamp': 1482263210,
544 'upload_date': '20161220',
545 'uploader_id': '1107601872001',
548 'skip_download': True, # m3u8 download
553 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
554 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
556 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
558 'title': '2cc213299525360.mov', # that's what we get
561 'add_ie': ['Ooyala'],
564 # ooyala video embedded with http://player.ooyala.com/iframe.js
565 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
567 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
569 'title': '"Steve Jobs: Man in the Machine" trailer',
570 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
574 'skip_download': True,
576 'skip': 'movie expired',
580 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
584 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
585 'upload_date': '20140225',
586 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
587 'uploader': 'Tested',
588 'uploader_id': 'testedcom',
590 # No need to test YoutubeIE here
592 'skip_download': True,
597 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
601 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
602 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
604 # HEAD requests lead to endless 301, while GET is OK
605 'expected_warnings': ['301'],
609 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
613 'title': 'Охотское море стало целиком российским',
614 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
618 'skip_download': True,
623 '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/',
627 'title': 'Дошкольное воспитание',
632 'url': 'http://www.vestifinance.ru/articles/25753',
635 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
640 'title': 'Госзаказ. День 3',
646 'title': 'Госзаказ. День 2',
652 'title': 'Госзаказ. День 1',
658 'skip_download': True,
663 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
665 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
667 'title': 'Ужастики, русский трейлер (2015)',
668 'thumbnail': r're:^https?://.*\.jpg$',
674 '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',
677 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
679 'playlist_mincount': 7,
680 # This forum does not allow <iframe> syntaxes anymore
681 # Now HTML tags are displayed as-is
682 'skip': 'No videos on this page',
686 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
687 'md5': '65fdff94098e4a607385a60c5177c638',
691 'title': 'Hidden miracles of the natural world',
692 'uploader': 'Louie Schwartzberg',
693 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
696 # nowvideo embed hidden behind percent encoding
698 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
699 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
701 'id': '06e53103ca9aa',
703 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
704 'description': 'No description',
709 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
710 'md5': '7653032cbb25bf6c80d80f217055fa43',
712 'id': '048195-004_PLUS7-F',
715 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
716 'upload_date': '20140320',
719 'skip_download': 'Requires rtmpdump'
721 'skip': 'video gone',
725 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
729 'title': 'Alcaline, le concert avec Calogero',
730 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
731 'upload_date': '20150226',
732 'timestamp': 1424989860,
737 'skip_download': True,
739 'expected_warnings': [
745 'url': 'http://www.wired.com/2014/04/honda-asimo/',
746 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
748 'id': '53501be369702d3275860000',
750 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
755 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
756 'md5': '441aeeb82eb72c422c7f14ec533999cd',
758 'id': 'k2mm4bCdJ6CQ2i7c8o2',
760 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
761 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
763 'uploader_id': 'xgditw',
764 'upload_date': '20140425',
765 'timestamp': 1398441542,
767 'add_ie': ['Dailymotion'],
771 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
775 'title': 'Care worker punches elderly dementia patient in head 11 times',
776 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
778 'add_ie': ['DailyMail'],
780 'skip_download': True,
785 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
789 'title': 'The NBL Auction 2014',
790 'uploader': 'BADMINTON England',
791 'uploader_id': 'BADMINTONEvents',
792 'upload_date': '20140603',
793 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
795 'add_ie': ['Youtube'],
797 'skip_download': True,
802 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
803 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
805 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
807 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
808 'description': 'Two valets share their love for movie star Liam Neesons.',
809 'timestamp': 1349922600,
810 'upload_date': '20121011',
813 # YouTube embed via <data-embed-url="">
815 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
819 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
820 'uploader': 'Gameloft',
821 'uploader_id': 'gameloft',
822 'upload_date': '20140828',
823 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
826 'skip_download': True,
829 # YouTube <object> embed
831 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
832 'md5': '516718101ec834f74318df76259fb3cc',
836 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
837 'upload_date': '20080526',
838 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
839 'uploader': 'Christopher Sykes',
840 'uploader_id': 'ChristopherJSykes',
842 'add_ie': ['Youtube'],
846 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
848 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
850 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
851 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
856 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
858 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
859 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
865 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
870 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
871 'md5': '9d65602bf31c6e20014319c7d07fba27',
873 'id': '5123ea6d5e5a7',
876 'uploader': 'www.handjobhub.com',
877 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
880 # Multiple brightcove videos
881 # https://github.com/rg3/youtube-dl/issues/2283
883 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
885 'id': 'always-never',
886 'title': 'Always / Never - The New Yorker',
890 'extract_flat': False,
891 'skip_download': True,
896 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
897 'md5': '96f09a37e44da40dd083e12d9a683327',
901 'title': 'Ump changes call to ball',
902 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
904 'timestamp': 1401537900,
905 'upload_date': '20140531',
906 'thumbnail': r're:^https?://.*\.jpg$',
911 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
912 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
916 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
917 'description': 'a Paywall Videos video from Remilon',
919 'uploader': 'study.com',
920 'timestamp': 1459678540,
921 'upload_date': '20160403',
922 'filesize': 24687186,
926 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
927 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
931 'title': 'Conversation about Hexagonal Rails Part 1',
932 'description': 'a Martin Fowler video from ThoughtWorks',
934 'uploader': 'thoughtworks.wistia.com',
935 'timestamp': 1401832161,
936 'upload_date': '20140603',
939 # Wistia standard embed (async)
941 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
945 'title': 'Drip Brennan Dunn Workshop',
946 'description': 'a JV Webinars video from getdrip-1',
948 'timestamp': 1463607249,
949 'upload_date': '20160518',
952 'skip_download': True,
957 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
961 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
962 'uploader': 'Sophos Security',
963 'title': 'Chet Chat 171 - Oct 29, 2014',
964 'upload_date': '20141029',
967 # Soundcloud multiple embeds
969 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
972 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
974 'playlist_mincount': 7,
976 # TuneIn station embed
978 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
983 'location': 'Paris, France',
988 'skip_download': True,
993 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
997 'upload_date': '20141112',
998 'title': 'Rosetta #CometLanding webcast HL 10',
1001 # Another Livestream embed, without 'new.' in URL
1003 'url': 'https://www.freespeech.org/',
1007 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1011 'skip_download': True,
1016 'url': 'https://skiplagged.com/',
1019 'title': 'Skiplagged: The smart way to find cheap flights',
1021 'playlist_mincount': 1,
1022 'add_ie': ['Youtube'],
1026 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1030 'upload_date': '20141126',
1031 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1036 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1038 'id': '730m_DandD_1901_512k',
1040 'uploader': 'www.abc.net.au',
1041 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1044 # embedded viddler video
1046 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1050 'uploader': 'deadspin',
1051 'title': 'WALL-TO-GORTAT',
1052 'timestamp': 1422285291,
1053 'upload_date': '20150126',
1055 'add_ie': ['Viddler'],
1059 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1063 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1064 'description': 'md5:601cb790edd05908957dae8aaa866465',
1065 'upload_date': '20150220',
1067 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1071 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1073 'id': 'Mrj4DVp2zeA',
1075 'upload_date': '20150212',
1076 'uploader': 'The National Archives UK',
1077 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1078 'uploader_id': 'NationalArchives08',
1079 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1084 'url': 'http://www.suffolk.edu/sjc/',
1088 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1089 'uploader': 'www.suffolk.edu',
1092 'skip_download': True,
1097 'url': 'http://www.indiedb.com/games/king-machine/videos',
1101 'title': 'king machine trailer 1',
1102 'thumbnail': r're:^https?://.*\.jpg$',
1106 # JWPlayer config passed as variable
1107 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1111 'title': 'ARIELE | Tube Cup',
1112 'uploader': 'www.txxx.com',
1116 'skip_download': True,
1121 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1122 'playlist_mincount': 5,
1124 'id': 'aanslagen-kopenhagen',
1125 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1130 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1134 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1137 # Kaltura embed (different embed code)
1139 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1143 'upload_date': '20150127',
1144 'uploader_id': 'PremierMedia',
1146 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1149 # Kaltura embed with single quotes
1151 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1156 'timestamp': 1355743100,
1157 'upload_date': '20121217',
1158 'uploader_id': 'batchUser',
1160 'add_ie': ['Kaltura'],
1163 # Kaltura embedded via quoted entry_id
1164 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1168 'title': '06_matthew_brender_raj_dutt',
1169 'timestamp': 1466638791,
1170 'upload_date': '20160622',
1172 'add_ie': ['Kaltura'],
1173 'expected_warnings': [
1174 'Could not send HEAD request'
1177 'skip_download': True,
1181 # Kaltura embedded, some fileExt broken (#11480)
1182 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1186 'title': 'Our "Standard Models" of particle physics and cosmology',
1187 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1188 'timestamp': 1321158993,
1189 'upload_date': '20111113',
1190 'uploader_id': 'kps1',
1192 'add_ie': ['Kaltura'],
1195 # Kaltura iframe embed
1196 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1197 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1201 'title': 'I. M. Pei: A Centennial Celebration',
1202 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1203 'upload_date': '20170403',
1204 'uploader_id': 'batchUser',
1205 'timestamp': 1491232186,
1207 'add_ie': ['Kaltura'],
1209 # EaglePlatform embed (generic URL)
1211 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1212 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1216 'title': 'Навальный вышел на свободу',
1217 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1218 'thumbnail': r're:^https?://.*\.jpg$',
1224 'skip_download': True,
1227 # referrer protected EaglePlatform embed
1229 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1233 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1234 'thumbnail': r're:^https?://.*\.jpg$',
1239 'skip_download': True,
1242 # ClipYou (EaglePlatform) embed (custom URL)
1244 'url': 'http://muz-tv.ru/play/7129/',
1245 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1249 'title': "'O Sole Mio",
1250 'thumbnail': r're:^https?://.*\.jpg$',
1255 'skip_download': True,
1260 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1264 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1265 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1266 'thumbnail': r're:^https?://.*\.jpg$',
1273 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1277 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1278 'thumbnail': r're:^https?://.*\.png$',
1284 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1285 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1289 'title': 'Facebook Creates "On This Day" | Crunch Report',
1294 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1298 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1303 # Crooks and Liars embed
1305 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1309 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1310 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1311 'timestamp': 1428207000,
1312 'upload_date': '20150405',
1313 'uploader': 'Heather',
1316 # Crooks and Liars external embed
1318 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1320 'id': 'MTE3MjUtMzQ2MzA',
1322 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1323 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1324 'timestamp': 1265032391,
1325 'upload_date': '20100201',
1326 'uploader': 'Heather',
1329 # NBC Sports vplayer embed
1331 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1333 'id': 'ln7x1qSThw4k',
1335 'title': "PFT Live: New leader in the 'new-look' defense",
1336 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1337 'uploader': 'NBCU-SPORTS',
1338 'upload_date': '20140107',
1339 'timestamp': 1389118457,
1344 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1345 'md5': '1aa589c675898ae6d37a17913cf68d66',
1347 'id': '701714499682',
1349 'title': 'PREVIEW: On Assignment: David Letterman',
1350 '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.',
1355 'url': 'https://video.udn.com/news/300346',
1356 'md5': 'fd2060e988c326991037b9aff9df21a6',
1360 'title': '中一中男師變性 全校師生力挺',
1361 'thumbnail': r're:^https?://.*\.jpg$',
1365 'skip_download': True,
1370 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1372 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1374 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1375 'title': 'This is what separates the Excel masters from the wannabes',
1376 'duration': 191.933,
1380 'skip_download': True,
1383 # Brightcove URL in single quotes
1385 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1386 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1388 'id': '4255764656001',
1390 'title': 'SN Presents: Russell Martin, World Citizen',
1391 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1392 'uploader': 'Rogers Sportsnet',
1393 'uploader_id': '1704050871',
1394 'upload_date': '20150525',
1395 'timestamp': 1432570283,
1398 # Dailymotion Cloud video
1400 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1401 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1405 'title': 'Sauvons les abeilles ! - Le débat',
1406 'description': 'md5:d9082128b1c5277987825d684939ca26',
1407 'thumbnail': r're:^https?://.*\.jpe?g$',
1408 'timestamp': 1434970506,
1409 'upload_date': '20150622',
1410 'uploader': 'Public Sénat',
1411 'uploader_id': 'xa9gza',
1414 # OnionStudios embed
1416 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1420 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1421 'thumbnail': r're:^https?://.*\.jpe?g$',
1422 'uploader': 'ClickHole',
1423 'uploader_id': 'clickhole',
1428 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1430 'id': '74849a00-85a9-11e1-9660-123139220831',
1432 'title': '#whilewewatch',
1435 # AdobeTVVideo embed
1437 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1438 'md5': '43662b577c018ad707a63766462b1e87',
1442 'title': 'New experience with Acrobat DC',
1443 'description': 'New experience with Acrobat DC',
1444 'duration': 248.667,
1447 # BrightcoveInPageEmbed embed
1449 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1451 'id': '4238694884001',
1453 'title': 'Tabletop: Dread, Last Thoughts',
1454 'description': 'Tabletop: Dread, Last Thoughts',
1458 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1459 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1461 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1463 'id': '4785848093001',
1465 'title': 'The Cardinal Pell Interview',
1466 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1467 'uploader': 'GlobeCast Australia - GlobeStream',
1468 'uploader_id': '2733773828001',
1469 'upload_date': '20160304',
1470 'timestamp': 1457083087,
1474 'skip_download': True,
1478 # Brightcove embed with whitespace around attribute names
1479 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1481 'id': '3167554373001',
1483 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1484 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1485 'uploader_id': '1079349493',
1486 'upload_date': '20140207',
1487 'timestamp': 1391810548,
1490 'skip_download': True,
1493 # Another form of arte.tv embed
1495 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1496 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1498 'id': '030273-562_PLUS7-F',
1500 'title': 'ARTE Reportage - Nulle part, en France',
1501 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1502 'upload_date': '20160409',
1507 'url': 'http://www.wykop.pl/link/3088787/',
1508 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1510 'id': '874_1459135191',
1512 'title': 'Man shows poor quality of new apartment building',
1513 'description': 'The wall is like a sand pile.',
1514 'uploader': 'Lake8737',
1517 # Duplicated embedded video URLs
1519 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1521 'id': '149298443_480_16c25b74_2',
1523 'title': 'vs. Blue Orange Spring Game',
1524 'uploader': 'www.hudl.com',
1527 # twitter:player:stream embed
1529 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1533 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1534 'uploader': 'www.rtl.be',
1538 'skip_download': True,
1541 # twitter:player embed
1543 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1544 'md5': 'a3e0df96369831de324f0778e126653c',
1546 'id': '4909620399001',
1548 'title': 'What Do Black Holes Sound Like?',
1549 'description': 'what do black holes sound like',
1550 'upload_date': '20160524',
1551 'uploader_id': '29913724001',
1552 'timestamp': 1464107587,
1553 'uploader': 'TheAtlantic',
1555 'add_ie': ['BrightcoveLegacy'],
1559 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1563 'title': "Yesterday's Jam (OV)",
1564 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1565 'timestamp': 1492594816,
1566 'upload_date': '20170419',
1569 'format': 'bestvideo',
1570 'skip_download': True,
1573 # Facebook <iframe> embed
1575 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1576 'md5': 'fbcde74f534176ecb015849146dd3aee',
1578 'id': '599637780109885',
1580 'title': 'Facebook video #599637780109885',
1583 # Facebook <iframe> embed, plugin video
1585 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1587 'id': '1754168231264132',
1589 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1590 'uploader': 'Tariq Ramadan (official)',
1591 'timestamp': 1496758379,
1592 'upload_date': '20170606',
1595 'skip_download': True,
1598 # Facebook API embed
1600 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1601 'md5': 'a47372ee61b39a7b90287094d447d94e',
1603 'id': '10153467542406923',
1605 'title': 'Facebook video #10153467542406923',
1608 # Wordpress "YouTube Video Importer" plugin
1610 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1611 'md5': 'd16797741b560b485194eddda8121b48',
1613 'id': 'HNTXWDXV9Is',
1615 'title': 'Blue Devils Drumline Stanford lot 2016',
1616 'upload_date': '20160627',
1617 'uploader_id': 'GENOCIDE8GENERAL10',
1618 'uploader': 'cylus cyrus',
1622 # video stored on custom kaltura server
1623 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1624 'md5': '537617d06e64dfed891fa1593c4b30cc',
1628 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1629 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1630 'uploader_id': 'videos.expansion@el-mundo.net',
1631 'upload_date': '20150429',
1632 'timestamp': 1430303472,
1634 'add_ie': ['Kaltura'],
1637 # Non-standard Vimeo embed
1638 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1639 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1643 'title': 'Understanding the web - Teaser',
1644 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1645 'upload_date': '20151214',
1646 'uploader': 'OpenClassrooms',
1647 'uploader_id': 'openclassrooms',
1649 'add_ie': ['Vimeo'],
1652 # generic vimeo embed that requires original URL passed as Referer
1653 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1654 'only_matching': True,
1657 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1658 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1660 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1662 'title': 'Big Buck Bunny',
1663 'description': 'Royalty free test video',
1664 'timestamp': 1432816365,
1665 'upload_date': '20150528',
1669 'skip_download': True,
1671 'add_ie': [ArkenaIE.ie_key()],
1674 '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/',
1678 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1681 'skip_download': True,
1683 'add_ie': [Vbox7IE.ie_key()],
1687 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1690 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1692 'playlist_mincount': 3,
1696 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1698 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1699 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1701 'playlist_mincount': 2,
1705 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1709 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1710 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1713 'skip_download': True,
1715 'add_ie': [TwentyMinutenIE.ie_key()],
1719 'url': 'https://en.support.wordpress.com/videopress/',
1723 'title': 'IMG_5786',
1724 'timestamp': 1435711927,
1725 'upload_date': '20150701',
1728 'skip_download': True,
1730 'add_ie': [VideoPressIE.ie_key()],
1734 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1736 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1738 'title': 'Магаззино: Казань 2',
1739 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1740 'uploader': 'Магаззино',
1741 'upload_date': '20170228',
1742 'uploader_id': '996642',
1745 'skip_download': True,
1747 'add_ie': [RutubeIE.ie_key()],
1750 # ThePlatform embedded with whitespaces in URLs
1751 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1752 'only_matching': True,
1755 # Senate ISVP iframe https
1756 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1757 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1759 'id': 'govtaff020316',
1761 'title': 'Integrated Senate Video Player',
1763 'add_ie': [SenateISVPIE.ie_key()],
1766 # Limelight embeds (1 channel embed + 4 media embeds)
1767 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1769 'id': 'FacilitatorTraining2017',
1770 'title': 'Facilitator Training 2017',
1772 'playlist_mincount': 5,
1775 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1777 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1778 'title': 'Standoff with Walnut Creek murder suspect ends',
1779 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1781 'playlist_mincount': 4,
1784 # WashingtonPost embed
1785 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1787 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1789 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1790 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1791 'timestamp': 1455216756,
1792 'uploader': 'The Washington Post',
1793 'upload_date': '20160211',
1795 'add_ie': [WashingtonPostIE.ie_key()],
1799 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1803 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1806 'skip_download': True,
1808 'add_ie': [MediasetIE.ie_key()],
1812 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1814 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1815 'title': 'Slovenskom sa prehnala vlna silných búrok',
1817 'playlist_mincount': 5,
1818 'add_ie': [JojIE.ie_key()],
1821 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1822 'url': 'https://tvrain.ru/amp/418921/',
1823 'md5': 'cc00413936695987e8de148b67d14f1d',
1827 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1831 # # TODO: find another test
1832 # # http://schema.org/VideoObject
1833 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1834 # 'md5': '888dcf08b7ea671381f00fab74692755',
1836 # 'id': 'nyvTSJMKId',
1838 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1839 # 'description': '#love for cats.',
1840 # 'timestamp': 1461244995,
1841 # 'upload_date': '20160421',
1844 # 'force_generic_extractor': True,
1849 def report_following_redirect(self, new_url):
1850 """Report information extraction."""
1851 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1853 def _extract_rss(self, url, video_id, doc):
1854 playlist_title = doc.find('./channel/title').text
1855 playlist_desc_el = doc.find('./channel/description')
1856 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1859 for it in doc.findall('./channel/item'):
1860 next_url = xpath_text(it, 'link', fatal=False)
1862 enclosure_nodes = it.findall('./enclosure')
1863 for e in enclosure_nodes:
1864 next_url = e.attrib.get('url')
1872 '_type': 'url_transparent',
1874 'title': it.find('title').text,
1878 '_type': 'playlist',
1880 'title': playlist_title,
1881 'description': playlist_desc,
1885 def _extract_camtasia(self, url, video_id, webpage):
1886 """ Returns None if no camtasia video can be found. """
1888 camtasia_cfg = self._search_regex(
1889 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1890 webpage, 'camtasia configuration file', default=None)
1891 if camtasia_cfg is None:
1894 title = self._html_search_meta('DC.title', webpage, fatal=True)
1896 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1897 camtasia_cfg = self._download_xml(
1898 camtasia_url, video_id,
1899 note='Downloading camtasia configuration',
1900 errnote='Failed to download camtasia configuration')
1901 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1904 for n in fileset_node.getchildren():
1905 url_n = n.find('./uri')
1910 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1911 'title': '%s - %s' % (title, n.tag),
1912 'url': compat_urlparse.urljoin(url, url_n.text),
1913 'duration': float_or_none(n.find('./duration').text),
1917 '_type': 'playlist',
1922 def _real_extract(self, url):
1923 if url.startswith('//'):
1926 'url': self.http_scheme() + url,
1929 parsed_url = compat_urlparse.urlparse(url)
1930 if not parsed_url.scheme:
1931 default_search = self._downloader.params.get('default_search')
1932 if default_search is None:
1933 default_search = 'fixup_error'
1935 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1937 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1938 return self.url_result('http://' + url)
1939 elif default_search != 'fixup_error':
1940 if default_search == 'auto_warning':
1941 if re.match(r'^(?:url|URL)$', url):
1942 raise ExtractorError(
1943 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1946 self._downloader.report_warning(
1947 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1948 return self.url_result('ytsearch:' + url)
1950 if default_search in ('error', 'fixup_error'):
1951 raise ExtractorError(
1952 '%r is not a valid URL. '
1953 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1954 % (url, url), expected=True)
1956 if ':' not in default_search:
1957 default_search += ':'
1958 return self.url_result(default_search + url)
1960 url, smuggled_data = unsmuggle_url(url)
1961 force_videoid = None
1962 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1963 if smuggled_data and 'force_videoid' in smuggled_data:
1964 force_videoid = smuggled_data['force_videoid']
1965 video_id = force_videoid
1967 video_id = self._generic_id(url)
1969 self.to_screen('%s: Requesting header' % video_id)
1971 head_req = HEADRequest(url)
1972 head_response = self._request_webpage(
1974 note=False, errnote='Could not send HEAD request to %s' % url,
1977 if head_response is not False:
1978 # Check for redirect
1979 new_url = head_response.geturl()
1981 self.report_following_redirect(new_url)
1983 new_url = smuggle_url(
1984 new_url, {'force_videoid': force_videoid})
1985 return self.url_result(new_url)
1987 full_response = None
1988 if head_response is False:
1989 request = sanitized_Request(url)
1990 request.add_header('Accept-Encoding', '*')
1991 full_response = self._request_webpage(request, video_id)
1992 head_response = full_response
1996 'title': self._generic_title(url),
1997 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2000 # Check for direct link to a video
2001 content_type = head_response.headers.get('Content-Type', '').lower()
2002 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2004 format_id = compat_str(m.group('format_id'))
2005 if format_id.endswith('mpegurl'):
2006 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2007 elif format_id == 'f4m':
2008 formats = self._extract_f4m_formats(url, video_id)
2011 'format_id': format_id,
2013 'vcodec': 'none' if m.group('type') == 'audio' else None
2015 info_dict['direct'] = True
2016 self._sort_formats(formats)
2017 info_dict['formats'] = formats
2020 if not self._downloader.params.get('test', False) and not is_intentional:
2021 force = self._downloader.params.get('force_generic_extractor', False)
2022 self._downloader.report_warning(
2023 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2025 if not full_response:
2026 request = sanitized_Request(url)
2027 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2028 # making it impossible to download only chunk of the file (yet we need only 512kB to
2029 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2030 # that will always result in downloading the whole file that is not desirable.
2031 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2032 # to accept raw bytes and being able to download only a chunk.
2033 # It may probably better to solve this by checking Content-Type for application/octet-stream
2034 # after HEAD request finishes, but not sure if we can rely on this.
2035 request.add_header('Accept-Encoding', '*')
2036 full_response = self._request_webpage(request, video_id)
2038 first_bytes = full_response.read(512)
2040 # Is it an M3U playlist?
2041 if first_bytes.startswith(b'#EXTM3U'):
2042 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2043 self._sort_formats(info_dict['formats'])
2046 # Maybe it's a direct link to a video?
2047 # Be careful not to download the whole thing!
2048 if not is_html(first_bytes):
2049 self._downloader.report_warning(
2050 'URL could be a direct video link, returning it as such.')
2057 webpage = self._webpage_read_content(
2058 full_response, url, video_id, prefix=first_bytes)
2060 self.report_extraction(video_id)
2062 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2064 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2065 if doc.tag == 'rss':
2066 return self._extract_rss(url, video_id, doc)
2067 elif doc.tag == 'SmoothStreamingMedia':
2068 info_dict['formats'] = self._parse_ism_formats(doc, url)
2069 self._sort_formats(info_dict['formats'])
2071 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2072 smil = self._parse_smil(doc, url, video_id)
2073 self._sort_formats(smil['formats'])
2075 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2076 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2077 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2078 info_dict['formats'] = self._parse_mpd_formats(
2080 mpd_base_url=full_response.geturl().rpartition('/')[0],
2082 self._sort_formats(info_dict['formats'])
2084 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2085 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2086 self._sort_formats(info_dict['formats'])
2088 except compat_xml_parse_error:
2091 # Is it a Camtasia project?
2092 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2093 if camtasia_res is not None:
2096 # Sometimes embedded video player is hidden behind percent encoding
2097 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2098 # Unescaping the whole page allows to handle those cases in a generic way
2099 webpage = compat_urllib_parse_unquote(webpage)
2101 # it's tempting to parse this further, but you would
2102 # have to take into account all the variations like
2103 # Video Title - Site Name
2104 # Site Name | Video Title
2105 # Video Title - Tagline | Site Name
2106 # and so on and so forth; it's just not practical
2107 video_title = self._og_search_title(
2108 webpage, default=None) or self._html_search_regex(
2109 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2112 # Try to detect age limit automatically
2113 age_limit = self._rta_search(webpage)
2114 # And then there are the jokers who advertise that they use RTA,
2115 # but actually don't.
2116 AGE_LIMIT_MARKERS = [
2117 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2119 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2122 # video uploader is domain name
2123 video_uploader = self._search_regex(
2124 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2126 video_description = self._og_search_description(webpage, default=None)
2127 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2130 'title': video_title,
2131 'description': video_description,
2132 'thumbnail': video_thumbnail,
2133 'age_limit': age_limit,
2136 # Look for Brightcove Legacy Studio embeds
2137 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2141 'url': smuggle_url(bc_url, {'Referer': url}),
2142 'ie_key': 'BrightcoveLegacy'
2143 } for bc_url in bc_urls]
2146 '_type': 'playlist',
2147 'title': video_title,
2152 # Look for Brightcove New Studio embeds
2153 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2155 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2157 # Look for Nexx embeds
2158 nexx_urls = NexxIE._extract_urls(webpage)
2160 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2162 # Look for Nexx iFrame embeds
2163 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2165 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2167 # Look for ThePlatform embeds
2168 tp_urls = ThePlatformIE._extract_urls(webpage)
2170 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2172 # Look for Vessel embeds
2173 vessel_urls = VesselIE._extract_urls(webpage)
2175 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2177 # Look for embedded rtl.nl player
2178 matches = re.findall(
2179 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2182 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2184 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2186 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2188 vid_me_embed_url = self._search_regex(
2189 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2190 webpage, 'vid.me embed', default=None)
2191 if vid_me_embed_url is not None:
2192 return self.url_result(vid_me_embed_url, 'Vidme')
2194 # Look for embedded YouTube player
2195 matches = re.findall(r'''(?x)
2205 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2209 return self.playlist_from_matches(
2210 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2212 # Look for lazyYT YouTube embed
2213 matches = re.findall(
2214 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2216 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2218 # Look for Wordpress "YouTube Video Importer" plugin
2219 matches = re.findall(r'''(?x)<div[^>]+
2220 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2221 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2223 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2225 matches = DailymotionIE._extract_urls(webpage)
2227 return self.playlist_from_matches(matches, video_id, video_title)
2229 # Look for embedded Dailymotion playlist player (#3822)
2231 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2233 playlists = re.findall(
2234 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2236 return self.playlist_from_matches(
2237 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2239 # Look for DailyMail embeds
2240 dailymail_urls = DailyMailIE._extract_urls(webpage)
2242 return self.playlist_from_matches(
2243 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2245 # Look for embedded Wistia player
2246 wistia_url = WistiaIE._extract_url(webpage)
2249 '_type': 'url_transparent',
2250 'url': self._proto_relative_url(wistia_url),
2251 'ie_key': WistiaIE.ie_key(),
2252 'uploader': video_uploader,
2255 # Look for SVT player
2256 svt_url = SVTIE._extract_url(webpage)
2258 return self.url_result(svt_url, 'SVT')
2260 # Look for Bandcamp pages with custom domain
2261 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2262 if mobj is not None:
2263 burl = unescapeHTML(mobj.group(1))
2264 # Don't set the extractor because it can be a track url or an album
2265 return self.url_result(burl)
2267 # Look for embedded Vevo player
2269 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2270 if mobj is not None:
2271 return self.url_result(mobj.group('url'))
2273 # Look for embedded Viddler player
2275 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2277 if mobj is not None:
2278 return self.url_result(mobj.group('url'))
2280 # Look for NYTimes player
2282 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2284 if mobj is not None:
2285 return self.url_result(mobj.group('url'))
2287 # Look for Libsyn player
2289 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2290 if mobj is not None:
2291 return self.url_result(mobj.group('url'))
2293 # Look for Ooyala videos
2294 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2295 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2296 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2297 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2298 if mobj is not None:
2299 embed_token = self._search_regex(
2300 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2301 webpage, 'ooyala embed token', default=None)
2302 return OoyalaIE._build_url_result(smuggle_url(
2305 'embed_token': embed_token,
2308 # Look for multiple Ooyala embeds on SBN network websites
2309 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2310 if mobj is not None:
2311 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2313 return self.playlist_from_matches(
2314 embeds, video_id, video_title,
2315 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2317 # Look for Aparat videos
2318 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2319 if mobj is not None:
2320 return self.url_result(mobj.group(1), 'Aparat')
2322 # Look for MPORA videos
2323 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2324 if mobj is not None:
2325 return self.url_result(mobj.group(1), 'Mpora')
2327 # Look for embedded NovaMov-based player
2329 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2330 (?P<url>http://(?:(?:embed|www)\.)?
2332 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2333 videoweed\.(?:es|com)|
2334 movshare\.(?:net|sx|ag)|
2335 divxstage\.(?:eu|net|ch|co|at|ag))
2336 /embed\.php.+?)\1''', webpage)
2337 if mobj is not None:
2338 return self.url_result(mobj.group('url'))
2340 # Look for embedded Facebook player
2341 facebook_urls = FacebookIE._extract_urls(webpage)
2343 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2345 # Look for embedded VK player
2346 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2347 if mobj is not None:
2348 return self.url_result(mobj.group('url'), 'VK')
2350 # Look for embedded Odnoklassniki player
2351 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2352 if mobj is not None:
2353 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2355 # Look for embedded ivi player
2356 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2357 if mobj is not None:
2358 return self.url_result(mobj.group('url'), 'Ivi')
2360 # Look for embedded Huffington Post player
2362 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2363 if mobj is not None:
2364 return self.url_result(mobj.group('url'), 'HuffPost')
2367 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2368 if mobj is not None:
2369 return self.url_result(mobj.group('url'))
2370 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2371 if mobj is not None:
2372 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2374 # Look for funnyordie embed
2375 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2377 return self.playlist_from_matches(
2378 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2380 # Look for BBC iPlayer embed
2381 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2383 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2385 # Look for embedded RUTV player
2386 rutv_url = RUTVIE._extract_url(webpage)
2388 return self.url_result(rutv_url, 'RUTV')
2390 # Look for embedded TVC player
2391 tvc_url = TVCIE._extract_url(webpage)
2393 return self.url_result(tvc_url, 'TVC')
2395 # Look for embedded SportBox player
2396 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2398 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2400 # Look for embedded XHamster player
2401 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2403 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2405 # Look for embedded TNAFlixNetwork player
2406 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2408 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2410 # Look for embedded PornHub player
2411 pornhub_urls = PornHubIE._extract_urls(webpage)
2413 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2415 # Look for embedded DrTuber player
2416 drtuber_urls = DrTuberIE._extract_urls(webpage)
2418 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2420 # Look for embedded RedTube player
2421 redtube_urls = RedTubeIE._extract_urls(webpage)
2423 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2425 # Look for embedded Tvigle player
2427 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2428 if mobj is not None:
2429 return self.url_result(mobj.group('url'), 'Tvigle')
2431 # Look for embedded TED player
2433 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2434 if mobj is not None:
2435 return self.url_result(mobj.group('url'), 'TED')
2437 # Look for embedded Ustream videos
2438 ustream_url = UstreamIE._extract_url(webpage)
2440 return self.url_result(ustream_url, UstreamIE.ie_key())
2442 # Look for embedded arte.tv player
2444 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2446 if mobj is not None:
2447 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2449 # Look for embedded francetv player
2451 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2453 if mobj is not None:
2454 return self.url_result(mobj.group('url'))
2456 # Look for embedded smotri.com player
2457 smotri_url = SmotriIE._extract_url(webpage)
2459 return self.url_result(smotri_url, 'Smotri')
2461 # Look for embedded Myvi.ru player
2462 myvi_url = MyviIE._extract_url(webpage)
2464 return self.url_result(myvi_url)
2466 # Look for embedded soundcloud player
2467 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2469 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2471 # Look for tunein player
2472 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2474 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2476 # Look for embedded mtvservices player
2477 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2479 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2481 # Look for embedded yahoo player
2483 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2485 if mobj is not None:
2486 return self.url_result(mobj.group('url'), 'Yahoo')
2488 # Look for embedded sbs.com.au player
2492 <meta\s+property="og:video"\s+content=|
2495 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2497 if mobj is not None:
2498 return self.url_result(mobj.group('url'), 'SBS')
2500 # Look for embedded Cinchcast player
2502 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2504 if mobj is not None:
2505 return self.url_result(mobj.group('url'), 'Cinchcast')
2508 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2512 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2514 if mobj is not None:
2515 return self.url_result(mobj.group('url'), 'MLB')
2518 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2520 if mobj is not None:
2521 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2524 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2526 if mobj is not None:
2527 return self.url_result(mobj.group('url'), 'Livestream')
2529 # Look for Zapiks embed
2531 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'), 'Zapiks')
2535 # Look for Kaltura embeds
2536 kaltura_url = KalturaIE._extract_url(webpage)
2538 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2540 # Look for EaglePlatform embeds
2541 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2542 if eagleplatform_url:
2543 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2545 # Look for ClipYou (uses EaglePlatform) embeds
2547 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2548 if mobj is not None:
2549 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2551 # Look for Pladform embeds
2552 pladform_url = PladformIE._extract_url(webpage)
2554 return self.url_result(pladform_url)
2556 # Look for Videomore embeds
2557 videomore_url = VideomoreIE._extract_url(webpage)
2559 return self.url_result(videomore_url)
2561 # Look for Webcaster embeds
2562 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2564 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2566 # Look for Playwire embeds
2568 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2569 if mobj is not None:
2570 return self.url_result(mobj.group('url'))
2572 # Look for 5min embeds
2574 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2575 if mobj is not None:
2576 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2578 # Look for Crooks and Liars embeds
2580 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'))
2584 # Look for NBC Sports VPlayer embeds
2585 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2587 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2589 # Look for NBC News embeds
2590 nbc_news_embed_url = re.search(
2591 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2592 if nbc_news_embed_url:
2593 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2595 # Look for Google Drive embeds
2596 google_drive_url = GoogleDriveIE._extract_url(webpage)
2597 if google_drive_url:
2598 return self.url_result(google_drive_url, 'GoogleDrive')
2600 # Look for UDN embeds
2602 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2603 if mobj is not None:
2604 return self.url_result(
2605 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2607 # Look for Senate ISVP iframe
2608 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2610 return self.url_result(senate_isvp_url, 'SenateISVP')
2612 # Look for Dailymotion Cloud videos
2613 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2615 return self.url_result(dmcloud_url, 'DailymotionCloud')
2617 # Look for OnionStudios embeds
2618 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2619 if onionstudios_url:
2620 return self.url_result(onionstudios_url)
2622 # Look for ViewLift embeds
2623 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2625 return self.url_result(viewlift_url)
2627 # Look for JWPlatform embeds
2628 jwplatform_url = JWPlatformIE._extract_url(webpage)
2630 return self.url_result(jwplatform_url, 'JWPlatform')
2632 # Look for Digiteka embeds
2633 digiteka_url = DigitekaIE._extract_url(webpage)
2635 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2637 # Look for Arkena embeds
2638 arkena_url = ArkenaIE._extract_url(webpage)
2640 return self.url_result(arkena_url, ArkenaIE.ie_key())
2642 # Look for Piksel embeds
2643 piksel_url = PikselIE._extract_url(webpage)
2645 return self.url_result(piksel_url, PikselIE.ie_key())
2647 # Look for Limelight embeds
2648 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2650 return self.playlist_result(
2651 limelight_urls, video_id, video_title, video_description)
2653 # Look for Anvato embeds
2654 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2656 return self.playlist_result(
2657 anvato_urls, video_id, video_title, video_description)
2659 # Look for AdobeTVVideo embeds
2661 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2663 if mobj is not None:
2664 return self.url_result(
2665 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2668 # Look for Vine embeds
2670 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2672 if mobj is not None:
2673 return self.url_result(
2674 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2676 # Look for VODPlatform embeds
2678 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2680 if mobj is not None:
2681 return self.url_result(
2682 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2684 # Look for Mangomolo embeds
2686 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2688 video\?.*?\bid=(?P<video_id>\d+)|
2689 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2690 ).+?)\1''', webpage)
2691 if mobj is not None:
2693 '_type': 'url_transparent',
2694 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2695 'title': video_title,
2696 'description': video_description,
2697 'thumbnail': video_thumbnail,
2698 'uploader': video_uploader,
2700 video_id = mobj.group('video_id')
2703 'ie_key': 'MangomoloVideo',
2708 'ie_key': 'MangomoloLive',
2709 'id': mobj.group('channel_id'),
2713 # Look for Instagram embeds
2714 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2715 if instagram_embed_url is not None:
2716 return self.url_result(
2717 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2719 # Look for LiveLeak embeds
2720 liveleak_url = LiveLeakIE._extract_url(webpage)
2722 return self.url_result(liveleak_url, 'LiveLeak')
2724 # Look for 3Q SDN embeds
2725 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2728 '_type': 'url_transparent',
2729 'ie_key': ThreeQSDNIE.ie_key(),
2730 'url': self._proto_relative_url(threeqsdn_url),
2731 'title': video_title,
2732 'description': video_description,
2733 'thumbnail': video_thumbnail,
2734 'uploader': video_uploader,
2737 # Look for VBOX7 embeds
2738 vbox7_url = Vbox7IE._extract_url(webpage)
2740 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2742 # Look for DBTV embeds
2743 dbtv_urls = DBTVIE._extract_urls(webpage)
2745 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2747 # Look for Videa embeds
2748 videa_urls = VideaIE._extract_urls(webpage)
2750 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2752 # Look for 20 minuten embeds
2753 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2755 return self.playlist_from_matches(
2756 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2758 # Look for Openload embeds
2759 openload_urls = OpenloadIE._extract_urls(webpage)
2761 return self.playlist_from_matches(
2762 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2764 # Look for VideoPress embeds
2765 videopress_urls = VideoPressIE._extract_urls(webpage)
2767 return self.playlist_from_matches(
2768 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2770 # Look for Rutube embeds
2771 rutube_urls = RutubeIE._extract_urls(webpage)
2773 return self.playlist_from_matches(
2774 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2776 # Look for WashingtonPost embeds
2777 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2779 return self.playlist_from_matches(
2780 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2782 # Look for Mediaset embeds
2783 mediaset_urls = MediasetIE._extract_urls(webpage)
2785 return self.playlist_from_matches(
2786 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2788 # Look for JOJ.sk embeds
2789 joj_urls = JojIE._extract_urls(webpage)
2791 return self.playlist_from_matches(
2792 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2794 # Look for megaphone.fm embeds
2795 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2797 return self.playlist_from_matches(
2798 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2801 def merge_dicts(dict1, dict2):
2803 for k, v in dict1.items():
2806 for k, v in dict2.items():
2809 if (k not in merged or
2810 (isinstance(v, compat_str) and v and
2811 isinstance(merged[k], compat_str) and
2816 # Looking for http://schema.org/VideoObject
2817 json_ld = self._search_json_ld(
2818 webpage, video_id, default={}, expected_type='VideoObject')
2819 if json_ld.get('url'):
2820 return merge_dicts(json_ld, info_dict)
2822 # Look for HTML5 media
2823 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2825 for entry in entries:
2828 'title': video_title,
2830 self._sort_formats(entry['formats'])
2831 return self.playlist_result(entries)
2833 jwplayer_data = self._find_jwplayer_data(
2834 webpage, video_id, transform_source=js_to_json)
2836 info = self._parse_jwplayer_data(
2837 jwplayer_data, video_id, require_title=False, base_url=url)
2838 return merge_dicts(info, info_dict)
2840 def check_video(vurl):
2841 if YoutubeIE.suitable(vurl):
2843 if RtmpIE.suitable(vurl):
2845 vpath = compat_urlparse.urlparse(vurl).path
2846 vext = determine_ext(vpath)
2847 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2849 def filter_video(urls):
2850 return list(filter(check_video, urls))
2852 # Start with something easy: JW Player in SWFObject
2853 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2855 # Look for gorilla-vid style embedding
2856 found = filter_video(re.findall(r'''(?sx)
2860 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2863 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2865 # Broaden the search a little bit
2866 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2868 # Broaden the findall a little bit: JWPlayer JS loader
2869 found = filter_video(re.findall(
2870 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2873 found = filter_video(re.findall(r'''(?xs)
2874 flowplayer\("[^"]+",\s*
2876 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2877 ["']?url["']?\s*:\s*["']([^"']+)["']
2882 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2884 # Try to find twitter cards info
2885 # twitter:player:stream should be checked before twitter:player since
2886 # it is expected to contain a raw stream (see
2887 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2888 found = filter_video(re.findall(
2889 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2891 # We look for Open Graph info:
2892 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2893 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2894 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2895 if m_video_type is not None:
2896 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2898 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2900 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2901 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2904 # Look also in Refresh HTTP header
2905 refresh_header = head_response.headers.get('Refresh')
2907 # In python 2 response HTTP headers are bytestrings
2908 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2909 refresh_header = refresh_header.decode('iso-8859-1')
2910 found = re.search(REDIRECT_REGEX, refresh_header)
2912 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2914 self.report_following_redirect(new_url)
2923 # twitter:player is a https URL to iframe player that may or may not
2924 # be supported by youtube-dl thus this is checked the very last (see
2925 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2926 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2928 return self.url_result(embed_url)
2931 raise UnsupportedError(url)
2934 for video_url in orderedSet(found):
2935 video_url = unescapeHTML(video_url)
2936 video_url = video_url.replace('\\/', '/')
2937 video_url = compat_urlparse.urljoin(url, video_url)
2938 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2940 # Sometimes, jwplayer extraction will result in a YouTube URL
2941 if YoutubeIE.suitable(video_url):
2942 entries.append(self.url_result(video_url, 'Youtube'))
2945 # here's a fun little line of code for you:
2946 video_id = os.path.splitext(video_id)[0]
2950 'uploader': video_uploader,
2951 'title': video_title,
2952 'age_limit': age_limit,
2955 if RtmpIE.suitable(video_url):
2956 entry_info_dict.update({
2957 '_type': 'url_transparent',
2958 'ie_key': RtmpIE.ie_key(),
2961 entries.append(entry_info_dict)
2964 ext = determine_ext(video_url)
2966 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2968 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2970 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2972 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2974 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2975 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2976 # Just matching .ism/manifest is not enough to be reliably sure
2977 # whether it's actually an ISM manifest or some other streaming
2978 # manifest since there are various streaming URL formats
2979 # possible (see [1]) as well as some other shenanigans like
2980 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2982 # Thus the most reasonable way to solve this is to delegate
2983 # to generic extractor in order to look into the contents of
2984 # the manifest itself.
2985 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2986 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2987 entry_info_dict = self.url_result(
2988 smuggle_url(video_url, {'to_generic': True}),
2991 entry_info_dict['url'] = video_url
2993 if entry_info_dict.get('formats'):
2994 self._sort_formats(entry_info_dict['formats'])
2996 entries.append(entry_info_dict)
2998 if len(entries) == 1:
3001 for num, e in enumerate(entries, start=1):
3002 # 'url' results don't have a title
3003 if e.get('title') is not None:
3004 e['title'] = '%s (%d)' % (e['title'], num)
3006 '_type': 'playlist',