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,
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxEmbedIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
112 class GenericIE(InfoExtractor):
113 IE_DESC = 'Generic downloader that works on some sites'
117 # Direct link to a video
119 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
120 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
125 'upload_date': '20100513',
128 # Direct link to media delivered compressed (until Accept-Encoding is *)
130 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
131 'md5': '128c42e68b13950268b648275386fc74',
133 'id': 'FictionJunction-Parallel_Hearts',
135 'title': 'FictionJunction-Parallel_Hearts',
136 'upload_date': '20140522',
138 'expected_warnings': [
139 'URL could be a direct video link, returning it as such.'
141 'skip': 'URL invalid',
143 # Direct download with broken HEAD
145 'url': 'http://ai-radio.org:8000/radio.opus',
152 'skip_download': True, # infinite live stream
154 'expected_warnings': [
155 r'501.*Not Implemented',
159 # Direct link with incorrect MIME type
161 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
162 'md5': '4ccbebe5f36706d85221f204d7eb5913',
164 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
165 'id': '5_Lennart_Poettering_-_Systemd',
167 'title': '5_Lennart_Poettering_-_Systemd',
168 'upload_date': '20141120',
170 'expected_warnings': [
171 'URL could be a direct video link, returning it as such.'
176 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
178 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
179 'title': 'Zero Punctuation',
180 'description': 're:.*groundbreaking video review series.*'
182 'playlist_mincount': 11,
184 # RSS feed with enclosure
186 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
188 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
190 'upload_date': '20150228',
191 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
194 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
196 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
200 'title': 'Automatics, robotics and biocybernetics',
201 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
202 'upload_date': '20130627',
203 'formats': 'mincount:16',
204 'subtitles': 'mincount:1',
207 'force_generic_extractor': True,
208 'skip_download': True,
211 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
213 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
218 'formats': 'mincount:1',
221 'skip_download': True,
224 # SMIL from https://www.restudy.dk/video/play/id/1637
226 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
230 'title': 'video_1637',
231 'formats': 'mincount:3',
234 'skip_download': True,
237 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
239 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
241 'id': 'smil-service',
243 'title': 'smil-service',
244 'formats': 'mincount:1',
247 'skip_download': True,
250 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
252 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
256 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
257 'formats': 'mincount:3',
260 'skip_download': True,
263 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
265 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
267 'id': 'mZlp2ctYIUEB',
269 'title': 'Tikibad ontruimd wegens brand',
270 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
271 'thumbnail': r're:^https?://.*\.jpg$',
275 'skip_download': True,
278 # MPD from http://dash-mse-test.appspot.com/media.html
280 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
281 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
283 'id': 'car-20120827-manifest',
285 'title': 'car-20120827-manifest',
286 'formats': 'mincount:9',
287 'upload_date': '20130904',
290 'format': 'bestvideo',
293 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
295 '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',
300 'formats': 'mincount:8',
304 'skip_download': True,
306 'skip': 'video gone',
308 # m3u8 served with Content-Type: text/plain
310 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
315 'upload_date': '20140720',
316 'formats': 'mincount:11',
320 'skip_download': True,
322 'skip': 'video gone',
326 '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',
330 'upload_date': '20130224',
331 'uploader_id': 'TheVerge',
332 'description': r're:^Chris Ziegler takes a look at the\.*',
333 'uploader': 'The Verge',
334 'title': 'First Firefox OS phones side-by-side',
337 'skip_download': False,
341 # redirect in Refresh HTTP header
342 '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',
346 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
347 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
348 'upload_date': '20150917',
349 'uploader_id': 'brtvofficial',
350 'uploader': 'Boiler Room',
353 'skip_download': False,
357 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
358 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
360 'id': '13601338388002',
362 'uploader': 'www.hodiho.fr',
363 'title': 'R\u00e9gis plante sa Jeep',
366 # bandcamp page with custom domain
368 'add_ie': ['Bandcamp'],
369 'url': 'http://bronyrock.com/track/the-pony-mash',
373 'title': 'The Pony Mash',
374 'uploader': 'M_Pallante',
376 'skip': 'There is a limit of 200 free downloads / month for the test song',
379 # embedded brightcove video
380 # it also tests brightcove videos that need to set the 'Referer'
381 # in the http requests
382 'add_ie': ['BrightcoveLegacy'],
383 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
385 'id': '2765128793001',
387 'title': 'Le cours de bourse : l’analyse technique',
388 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
389 'uploader': 'BFM BUSINESS',
392 'skip_download': True,
396 # embedded with itemprop embedURL and video id spelled as `idVideo`
397 'add_id': ['BrightcoveLegacy'],
398 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
400 'id': '5255628253001',
402 'title': 'md5:37c519b1128915607601e75a87995fc0',
403 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
404 'uploader': 'BFM BUSINESS',
405 'uploader_id': '876450612001',
406 'timestamp': 1482255315,
407 'upload_date': '20161220',
410 'skip_download': True,
414 # https://github.com/rg3/youtube-dl/issues/2253
415 'url': 'http://bcove.me/i6nfkrc3',
416 'md5': '0ba9446db037002366bab3b3eb30c88c',
418 'id': '3101154703001',
420 'title': 'Still no power',
421 'uploader': 'thestar.com',
422 '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.',
424 'add_ie': ['BrightcoveLegacy'],
425 'skip': 'video gone',
428 'url': 'http://www.championat.com/video/football/v/87/87499.html',
429 'md5': 'fb973ecf6e4a78a67453647444222983',
431 'id': '3414141473001',
433 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
434 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
435 'uploader': 'Championat',
439 # https://github.com/rg3/youtube-dl/issues/3541
440 'add_ie': ['BrightcoveLegacy'],
441 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
443 'id': '3866516442001',
445 'title': 'Leer mij vrouwen kennen: Aflevering 1',
446 'description': 'Leer mij vrouwen kennen: Aflevering 1',
447 'uploader': 'SBS Broadcasting',
449 'skip': 'Restricted to Netherlands',
451 'skip_download': True, # m3u8 download
455 # Brightcove video in <iframe>
456 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
457 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
459 'id': '5360463607001',
461 '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',
462 '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。',
463 'uploader': 'United Nations',
464 'uploader_id': '1362235914001',
465 'timestamp': 1489593889,
466 'upload_date': '20170315',
468 'add_ie': ['BrightcoveLegacy'],
471 # Brightcove with alternative playerID key
472 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
474 'id': 'nmeth.2062_SV1',
475 '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',
479 'id': '2228375078001',
481 'title': 'nmeth.2062-sv1',
482 'description': 'nmeth.2062-sv1',
483 'timestamp': 1363357591,
484 'upload_date': '20130315',
485 'uploader': 'Nature Publishing Group',
486 'uploader_id': '1964492299001',
491 # Brightcove with UUID in videoPlayer
492 'url': 'http://www8.hp.com/cn/zh/home.html',
494 'id': '5255815316001',
496 'title': 'Sprocket Video - China',
497 'description': 'Sprocket Video - China',
498 'uploader': 'HP-Video Gallery',
499 'timestamp': 1482263210,
500 'upload_date': '20161220',
501 'uploader_id': '1107601872001',
504 'skip_download': True, # m3u8 download
506 'skip': 'video rotates...weekly?',
509 # Brightcove:new type [2].
510 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
511 'md5': '2b35148fcf48da41c9fb4591650784f3',
513 'id': '5348741021001',
515 'upload_date': '20170306',
516 'uploader_id': '4191638492001',
517 'timestamp': 1488769918,
518 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
523 # Alternative brightcove <video> attributes
524 '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/',
526 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
527 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
530 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
532 'id': '5311302538001',
534 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
535 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
536 'timestamp': 1486321708,
537 'upload_date': '20170205',
538 'uploader_id': '800000640001',
540 'only_matching': True,
544 # Brightcove with UUID in videoPlayer
545 'url': 'http://www8.hp.com/cn/zh/home.html',
547 'id': '5255815316001',
549 'title': 'Sprocket Video - China',
550 'description': 'Sprocket Video - China',
551 'uploader': 'HP-Video Gallery',
552 'timestamp': 1482263210,
553 'upload_date': '20161220',
554 'uploader_id': '1107601872001',
557 'skip_download': True, # m3u8 download
562 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
563 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
565 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
567 'title': '2cc213299525360.mov', # that's what we get
570 'add_ie': ['Ooyala'],
573 # ooyala video embedded with http://player.ooyala.com/iframe.js
574 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
576 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
578 'title': '"Steve Jobs: Man in the Machine" trailer',
579 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
583 'skip_download': True,
585 'skip': 'movie expired',
587 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
589 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
591 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
593 'title': 'Steampunk Fest Comes to Honesdale',
597 'skip_download': True,
602 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
606 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
607 'upload_date': '20140225',
608 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
609 'uploader': 'Tested',
610 'uploader_id': 'testedcom',
612 # No need to test YoutubeIE here
614 'skip_download': True,
619 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
623 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
624 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
626 # HEAD requests lead to endless 301, while GET is OK
627 'expected_warnings': ['301'],
631 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
635 'title': 'Охотское море стало целиком российским',
636 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
640 'skip_download': True,
645 '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/',
649 'title': 'Дошкольное воспитание',
654 'url': 'http://www.vestifinance.ru/articles/25753',
657 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
662 'title': 'Госзаказ. День 3',
668 'title': 'Госзаказ. День 2',
674 'title': 'Госзаказ. День 1',
680 'skip_download': True,
685 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
687 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
689 'title': 'Ужастики, русский трейлер (2015)',
690 'thumbnail': r're:^https?://.*\.jpg$',
696 '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',
699 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
701 'playlist_mincount': 7,
702 # This forum does not allow <iframe> syntaxes anymore
703 # Now HTML tags are displayed as-is
704 'skip': 'No videos on this page',
708 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
709 'md5': '65fdff94098e4a607385a60c5177c638',
713 'title': 'Hidden miracles of the natural world',
714 'uploader': 'Louie Schwartzberg',
715 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
718 # nowvideo embed hidden behind percent encoding
720 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
721 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
723 'id': '06e53103ca9aa',
725 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
726 'description': 'No description',
731 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
732 'md5': '7653032cbb25bf6c80d80f217055fa43',
734 'id': '048195-004_PLUS7-F',
737 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
738 'upload_date': '20140320',
741 'skip_download': 'Requires rtmpdump'
743 'skip': 'video gone',
747 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
751 'title': 'Alcaline, le concert avec Calogero',
752 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
753 'upload_date': '20150226',
754 'timestamp': 1424989860,
759 'skip_download': True,
761 'expected_warnings': [
767 'url': 'http://www.wired.com/2014/04/honda-asimo/',
768 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
770 'id': '53501be369702d3275860000',
772 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
777 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
778 'md5': '441aeeb82eb72c422c7f14ec533999cd',
780 'id': 'k2mm4bCdJ6CQ2i7c8o2',
782 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
783 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
785 'uploader_id': 'xgditw',
786 'upload_date': '20140425',
787 'timestamp': 1398441542,
789 'add_ie': ['Dailymotion'],
793 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
797 'title': 'Care worker punches elderly dementia patient in head 11 times',
798 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
800 'add_ie': ['DailyMail'],
802 'skip_download': True,
807 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
811 'title': 'The NBL Auction 2014',
812 'uploader': 'BADMINTON England',
813 'uploader_id': 'BADMINTONEvents',
814 'upload_date': '20140603',
815 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
817 'add_ie': ['Youtube'],
819 'skip_download': True,
824 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
825 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
827 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
829 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
830 'description': 'Two valets share their love for movie star Liam Neesons.',
831 'timestamp': 1349922600,
832 'upload_date': '20121011',
835 # YouTube embed via <data-embed-url="">
837 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
841 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
842 'uploader': 'Gameloft',
843 'uploader_id': 'gameloft',
844 'upload_date': '20140828',
845 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
848 'skip_download': True,
851 # YouTube <object> embed
853 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
854 'md5': '516718101ec834f74318df76259fb3cc',
858 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
859 'upload_date': '20080526',
860 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
861 'uploader': 'Christopher Sykes',
862 'uploader_id': 'ChristopherJSykes',
864 'add_ie': ['Youtube'],
868 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
870 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
872 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
873 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
878 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
880 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
881 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
887 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
892 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
893 'md5': '9d65602bf31c6e20014319c7d07fba27',
895 'id': '5123ea6d5e5a7',
898 'uploader': 'www.handjobhub.com',
899 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
902 # Multiple brightcove videos
903 # https://github.com/rg3/youtube-dl/issues/2283
905 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
907 'id': 'always-never',
908 'title': 'Always / Never - The New Yorker',
912 'extract_flat': False,
913 'skip_download': True,
918 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
919 'md5': '96f09a37e44da40dd083e12d9a683327',
923 'title': 'Ump changes call to ball',
924 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
926 'timestamp': 1401537900,
927 'upload_date': '20140531',
928 'thumbnail': r're:^https?://.*\.jpg$',
933 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
934 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
938 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
939 'description': 'a Paywall Videos video from Remilon',
941 'uploader': 'study.com',
942 'timestamp': 1459678540,
943 'upload_date': '20160403',
944 'filesize': 24687186,
948 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
949 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
953 'title': 'Conversation about Hexagonal Rails Part 1',
954 'description': 'a Martin Fowler video from ThoughtWorks',
956 'uploader': 'thoughtworks.wistia.com',
957 'timestamp': 1401832161,
958 'upload_date': '20140603',
961 # Wistia standard embed (async)
963 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
967 'title': 'Drip Brennan Dunn Workshop',
968 'description': 'a JV Webinars video from getdrip-1',
970 'timestamp': 1463607249,
971 'upload_date': '20160518',
974 'skip_download': True,
979 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
983 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
984 'uploader': 'Sophos Security',
985 'title': 'Chet Chat 171 - Oct 29, 2014',
986 'upload_date': '20141029',
989 # Soundcloud multiple embeds
991 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
994 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
996 'playlist_mincount': 7,
998 # TuneIn station embed
1000 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1005 'location': 'Paris, France',
1010 'skip_download': True,
1015 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1019 'upload_date': '20141112',
1020 'title': 'Rosetta #CometLanding webcast HL 10',
1023 # Another Livestream embed, without 'new.' in URL
1025 'url': 'https://www.freespeech.org/',
1029 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1033 'skip_download': True,
1038 'url': 'https://skiplagged.com/',
1041 'title': 'Skiplagged: The smart way to find cheap flights',
1043 'playlist_mincount': 1,
1044 'add_ie': ['Youtube'],
1048 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1052 'upload_date': '20141126',
1053 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1058 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1060 'id': '730m_DandD_1901_512k',
1062 'uploader': 'www.abc.net.au',
1063 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1066 # embedded viddler video
1068 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1072 'uploader': 'deadspin',
1073 'title': 'WALL-TO-GORTAT',
1074 'timestamp': 1422285291,
1075 'upload_date': '20150126',
1077 'add_ie': ['Viddler'],
1081 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1085 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1086 'description': 'md5:601cb790edd05908957dae8aaa866465',
1087 'upload_date': '20150220',
1089 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1093 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1095 'id': 'Mrj4DVp2zeA',
1097 'upload_date': '20150212',
1098 'uploader': 'The National Archives UK',
1099 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1100 'uploader_id': 'NationalArchives08',
1101 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1106 'url': 'http://www.suffolk.edu/sjc/live.php',
1110 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1111 'uploader': 'www.suffolk.edu',
1114 'skip_download': True,
1116 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1120 'url': 'http://www.indiedb.com/games/king-machine/videos',
1124 'title': 'king machine trailer 1',
1125 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1126 'thumbnail': r're:^https?://.*\.jpg$',
1130 # JWPlayer config passed as variable
1131 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1135 'title': 'ARIELE | Tube Cup',
1136 'uploader': 'www.txxx.com',
1140 'skip_download': True,
1145 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1146 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1150 'upload_date': '20171122',
1151 'timestamp': 1511366290,
1152 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1154 'add_ie': [JWPlatformIE.ie_key()],
1157 # Video.js embed, multiple formats
1158 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1160 'id': 'yygqldloqIk',
1162 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1163 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1164 'upload_date': '20130314',
1165 'uploader': 'PROстое3D',
1166 'uploader_id': 'PROstoe3D',
1169 'skip_download': True,
1173 # Video.js embed, single format
1174 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1178 'title': 'Step 1 - Good Foundation',
1179 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1182 'skip_download': True,
1187 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1188 'playlist_mincount': 5,
1190 'id': 'aanslagen-kopenhagen',
1191 'title': 'Aanslagen Kopenhagen',
1196 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1200 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1203 # Kaltura embed (different embed code)
1205 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1209 'upload_date': '20150127',
1210 'uploader_id': 'PremierMedia',
1212 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1215 # Kaltura embed with single quotes
1217 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1222 'timestamp': 1355743100,
1223 'upload_date': '20121217',
1224 'uploader_id': 'cplapp@learn360.com',
1226 'add_ie': ['Kaltura'],
1229 # Kaltura embedded via quoted entry_id
1230 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1234 'title': '06_matthew_brender_raj_dutt',
1235 'timestamp': 1466638791,
1236 'upload_date': '20160622',
1238 'add_ie': ['Kaltura'],
1239 'expected_warnings': [
1240 'Could not send HEAD request'
1243 'skip_download': True,
1247 # Kaltura embedded, some fileExt broken (#11480)
1248 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1252 'title': 'Our "Standard Models" of particle physics and cosmology',
1253 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1254 'timestamp': 1321158993,
1255 'upload_date': '20111113',
1256 'uploader_id': 'kps1',
1258 'add_ie': ['Kaltura'],
1261 # Kaltura iframe embed
1262 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1263 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1267 'title': 'I. M. Pei: A Centennial Celebration',
1268 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1269 'upload_date': '20170403',
1270 'uploader_id': 'batchUser',
1271 'timestamp': 1491232186,
1273 'add_ie': ['Kaltura'],
1276 # meta twitter:player
1277 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1281 'title': 'Main Twerk (Video)',
1282 'upload_date': '20171208',
1283 'uploader_id': 'sebastian.salinas@thechive.com',
1284 'timestamp': 1512713057,
1287 'skip_download': True,
1289 'add_ie': ['Kaltura'],
1291 # referrer protected EaglePlatform embed
1293 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1297 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1298 'thumbnail': r're:^https?://.*\.jpg$',
1303 'skip_download': True,
1306 # ClipYou (EaglePlatform) embed (custom URL)
1308 'url': 'http://muz-tv.ru/play/7129/',
1309 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1313 'title': "'O Sole Mio",
1314 'thumbnail': r're:^https?://.*\.jpg$',
1319 'skip_download': True,
1321 'skip': 'This video is unavailable.',
1325 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1329 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1330 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1331 'thumbnail': r're:^https?://.*\.jpg$',
1335 'skip': 'HTTP Error 404: Not Found',
1339 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1343 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1344 'thumbnail': r're:^https?://.*\.png$',
1350 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1351 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1355 'title': 'Facebook Creates "On This Day" | Crunch Report',
1356 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1357 'timestamp': 1427237531,
1358 'uploader': 'Crunch Report',
1359 'upload_date': '20150324',
1363 'skip_download': True,
1368 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1372 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1377 # Crooks and Liars embed
1379 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1383 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1384 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1385 'timestamp': 1428207000,
1386 'upload_date': '20150405',
1387 'uploader': 'Heather',
1390 # Crooks and Liars external embed
1392 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1394 'id': 'MTE3MjUtMzQ2MzA',
1396 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1397 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1398 'timestamp': 1265032391,
1399 'upload_date': '20100201',
1400 'uploader': 'Heather',
1403 # NBC Sports vplayer embed
1405 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1407 'id': 'ln7x1qSThw4k',
1409 'title': "PFT Live: New leader in the 'new-look' defense",
1410 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1411 'uploader': 'NBCU-SPORTS',
1412 'upload_date': '20140107',
1413 'timestamp': 1389118457,
1415 'skip': 'Invalid Page URL',
1419 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1420 'md5': '1aa589c675898ae6d37a17913cf68d66',
1422 'id': 'x_dtl_oa_LettermanliftPR_160608',
1424 'title': 'David Letterman: A Preview',
1425 '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.',
1426 'upload_date': '20160609',
1427 'timestamp': 1465431544,
1428 'uploader': 'NBCU-NEWS',
1433 'url': 'https://video.udn.com/news/300346',
1434 'md5': 'fd2060e988c326991037b9aff9df21a6',
1438 'title': '中一中男師變性 全校師生力挺',
1439 'thumbnail': r're:^https?://.*\.jpg$',
1443 'skip_download': True,
1445 'expected_warnings': ['Failed to parse JSON Expecting value'],
1449 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1451 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1453 'description': 'Index/Match versus VLOOKUP.',
1454 'title': 'This is what separates the Excel masters from the wannabes',
1455 'duration': 191.933,
1459 'skip_download': True,
1462 # Brightcove URL in single quotes
1464 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1465 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1467 'id': '4255764656001',
1469 'title': 'SN Presents: Russell Martin, World Citizen',
1470 '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.',
1471 'uploader': 'Rogers Sportsnet',
1472 'uploader_id': '1704050871',
1473 'upload_date': '20150525',
1474 'timestamp': 1432570283,
1477 # OnionStudios embed
1479 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1483 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1484 'thumbnail': r're:^https?://.*\.jpe?g$',
1485 'uploader': 'ClickHole',
1486 'uploader_id': 'clickhole',
1491 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1493 'id': '74849a00-85a9-11e1-9660-123139220831',
1495 'title': '#whilewewatch',
1498 # AdobeTVVideo embed
1500 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1501 'md5': '43662b577c018ad707a63766462b1e87',
1505 'title': 'New experience with Acrobat DC',
1506 'description': 'New experience with Acrobat DC',
1507 'duration': 248.667,
1510 # BrightcoveInPageEmbed embed
1512 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1514 'id': '4238694884001',
1516 'title': 'Tabletop: Dread, Last Thoughts',
1517 'description': 'Tabletop: Dread, Last Thoughts',
1521 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1522 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1524 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1526 'id': '4785848093001',
1528 'title': 'The Cardinal Pell Interview',
1529 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1530 'uploader': 'GlobeCast Australia - GlobeStream',
1531 'uploader_id': '2733773828001',
1532 'upload_date': '20160304',
1533 'timestamp': 1457083087,
1537 'skip_download': True,
1541 # Brightcove embed with whitespace around attribute names
1542 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1544 'id': '3167554373001',
1546 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1547 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1548 'uploader_id': '1079349493',
1549 'upload_date': '20140207',
1550 'timestamp': 1391810548,
1553 'skip_download': True,
1556 # Another form of arte.tv embed
1558 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1559 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1561 'id': '030273-562_PLUS7-F',
1563 'title': 'ARTE Reportage - Nulle part, en France',
1564 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1565 'upload_date': '20160409',
1570 'url': 'http://www.wykop.pl/link/3088787/',
1571 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1573 'id': '874_1459135191',
1575 'title': 'Man shows poor quality of new apartment building',
1576 'description': 'The wall is like a sand pile.',
1577 'uploader': 'Lake8737',
1579 'add_ie': [LiveLeakIE.ie_key()],
1581 # Another LiveLeak embed pattern (#13336)
1583 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1585 'id': '2eb_1496309988',
1587 'title': 'Thief robs place where everyone was armed',
1588 'description': 'md5:694d73ee79e535953cf2488562288eee',
1589 'uploader': 'brazilwtf',
1591 'add_ie': [LiveLeakIE.ie_key()],
1593 # Duplicated embedded video URLs
1595 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1597 'id': '149298443_480_16c25b74_2',
1599 'title': 'vs. Blue Orange Spring Game',
1600 'uploader': 'www.hudl.com',
1603 # twitter:player:stream embed
1605 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1609 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1610 'uploader': 'www.rtl.be',
1614 'skip_download': True,
1617 # twitter:player embed
1619 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1620 'md5': 'a3e0df96369831de324f0778e126653c',
1622 'id': '4909620399001',
1624 'title': 'What Do Black Holes Sound Like?',
1625 'description': 'what do black holes sound like',
1626 'upload_date': '20160524',
1627 'uploader_id': '29913724001',
1628 'timestamp': 1464107587,
1629 'uploader': 'TheAtlantic',
1631 'add_ie': ['BrightcoveLegacy'],
1633 # Facebook <iframe> embed
1635 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1636 'md5': 'fbcde74f534176ecb015849146dd3aee',
1638 'id': '599637780109885',
1640 'title': 'Facebook video #599637780109885',
1643 # Facebook <iframe> embed, plugin video
1645 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1647 'id': '1754168231264132',
1649 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1650 'uploader': 'Tariq Ramadan (official)',
1651 'timestamp': 1496758379,
1652 'upload_date': '20170606',
1655 'skip_download': True,
1658 # Facebook API embed
1660 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1661 'md5': 'a47372ee61b39a7b90287094d447d94e',
1663 'id': '10153467542406923',
1665 'title': 'Facebook video #10153467542406923',
1668 # Wordpress "YouTube Video Importer" plugin
1670 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1671 'md5': 'd16797741b560b485194eddda8121b48',
1673 'id': 'HNTXWDXV9Is',
1675 'title': 'Blue Devils Drumline Stanford lot 2016',
1676 'upload_date': '20160627',
1677 'uploader_id': 'GENOCIDE8GENERAL10',
1678 'uploader': 'cylus cyrus',
1682 # video stored on custom kaltura server
1683 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1684 'md5': '537617d06e64dfed891fa1593c4b30cc',
1688 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1689 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1690 'uploader_id': 'videos.expansion@el-mundo.net',
1691 'upload_date': '20150429',
1692 'timestamp': 1430303472,
1694 'add_ie': ['Kaltura'],
1697 # Non-standard Vimeo embed
1698 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1699 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1703 'title': 'Understanding the web - Teaser',
1704 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1705 'upload_date': '20151214',
1706 'uploader': 'OpenClassrooms',
1707 'uploader_id': 'openclassrooms',
1709 'add_ie': ['Vimeo'],
1712 # generic vimeo embed that requires original URL passed as Referer
1713 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1714 'only_matching': True,
1717 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1718 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1720 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1722 'title': 'Big Buck Bunny',
1723 'description': 'Royalty free test video',
1724 'timestamp': 1432816365,
1725 'upload_date': '20150528',
1729 'skip_download': True,
1731 'add_ie': [ArkenaIE.ie_key()],
1734 '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/',
1738 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1741 'skip_download': True,
1743 'add_ie': [Vbox7IE.ie_key()],
1747 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1750 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1752 'playlist_mincount': 3,
1756 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1758 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1759 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1761 'playlist_mincount': 2,
1765 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1769 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1770 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1773 'skip_download': True,
1775 'add_ie': [TwentyMinutenIE.ie_key()],
1779 'url': 'https://en.support.wordpress.com/videopress/',
1783 'title': 'IMG_5786',
1784 'timestamp': 1435711927,
1785 'upload_date': '20150701',
1788 'skip_download': True,
1790 'add_ie': [VideoPressIE.ie_key()],
1794 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1796 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1798 'title': 'Магаззино: Казань 2',
1799 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1800 'uploader': 'Магаззино',
1801 'upload_date': '20170228',
1802 'uploader_id': '996642',
1805 'skip_download': True,
1807 'add_ie': [RutubeIE.ie_key()],
1810 # ThePlatform embedded with whitespaces in URLs
1811 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1812 'only_matching': True,
1815 # Senate ISVP iframe https
1816 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1817 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1819 'id': 'govtaff020316',
1821 'title': 'Integrated Senate Video Player',
1823 'add_ie': [SenateISVPIE.ie_key()],
1826 # Limelight embeds (1 channel embed + 4 media embeds)
1827 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1829 'id': 'FacilitatorTraining2017',
1830 'title': 'Facilitator Training 2017',
1832 'playlist_mincount': 5,
1835 # Limelight embed (LimelightPlayerUtil.embed)
1836 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1838 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1840 'title': '07448641',
1841 'timestamp': 1499890639,
1842 'upload_date': '20170712',
1845 'skip_download': True,
1847 'add_ie': ['LimelightMedia'],
1850 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1852 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1853 'title': 'Standoff with Walnut Creek murder suspect ends',
1854 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1856 'playlist_mincount': 4,
1859 # WashingtonPost embed
1860 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1862 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1864 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1865 '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.',
1866 'timestamp': 1455216756,
1867 'uploader': 'The Washington Post',
1868 'upload_date': '20160211',
1870 'add_ie': [WashingtonPostIE.ie_key()],
1874 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1878 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1881 'skip_download': True,
1883 'add_ie': [MediasetIE.ie_key()],
1887 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1889 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1890 'title': 'Slovenskom sa prehnala vlna silných búrok',
1892 'playlist_mincount': 5,
1893 'add_ie': [JojIE.ie_key()],
1896 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1897 'url': 'https://tvrain.ru/amp/418921/',
1898 'md5': 'cc00413936695987e8de148b67d14f1d',
1902 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1907 'url': 'http://help.vzaar.com/article/165-embedding-video',
1908 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1912 'title': 'Building A Business Online: Principal Chairs Q & A',
1916 # multiple HTML5 videos on one page
1917 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1919 'id': 'keyscenarios',
1920 'title': 'Rescue Kit 14 Free Edition - Getting started',
1922 'playlist_count': 4,
1926 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1927 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1930 'title': 'vl14062007715967',
1935 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1936 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1938 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1940 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1941 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1942 'timestamp': 1474354800,
1943 'upload_date': '20160920',
1947 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1951 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1952 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1953 'timestamp': 1516100691,
1954 'upload_date': '20180116',
1957 'skip_download': True,
1959 'add_ie': [SpringboardPlatformIE.ie_key()],
1962 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1964 'id': 'uPDB5I9wfp8',
1966 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1967 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1968 'upload_date': '20160219',
1969 'uploader': 'Pocoyo - Português (BR)',
1970 'uploader_id': 'PocoyoBrazil',
1972 'add_ie': [YoutubeIE.ie_key()],
1974 'skip_download': True,
1978 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1980 'id': 'vMDE4NzI1Mjgt690b',
1984 'add_ie': [YapFilesIE.ie_key()],
1986 'skip_download': True,
1990 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
1991 'md5': 'b68d276de422ab07ee1d49388103f457',
1994 'title': 'Lock up and get excited',
1997 'skip': 'TODO: fix nested playlists processing in tests',
2000 # # TODO: find another test
2001 # # http://schema.org/VideoObject
2002 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2003 # 'md5': '888dcf08b7ea671381f00fab74692755',
2005 # 'id': 'nyvTSJMKId',
2007 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2008 # 'description': '#love for cats.',
2009 # 'timestamp': 1461244995,
2010 # 'upload_date': '20160421',
2013 # 'force_generic_extractor': True,
2018 def report_following_redirect(self, new_url):
2019 """Report information extraction."""
2020 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2022 def _extract_rss(self, url, video_id, doc):
2023 playlist_title = doc.find('./channel/title').text
2024 playlist_desc_el = doc.find('./channel/description')
2025 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2028 for it in doc.findall('./channel/item'):
2029 next_url = xpath_text(it, 'link', fatal=False)
2031 enclosure_nodes = it.findall('./enclosure')
2032 for e in enclosure_nodes:
2033 next_url = e.attrib.get('url')
2041 '_type': 'url_transparent',
2043 'title': it.find('title').text,
2047 '_type': 'playlist',
2049 'title': playlist_title,
2050 'description': playlist_desc,
2054 def _extract_camtasia(self, url, video_id, webpage):
2055 """ Returns None if no camtasia video can be found. """
2057 camtasia_cfg = self._search_regex(
2058 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2059 webpage, 'camtasia configuration file', default=None)
2060 if camtasia_cfg is None:
2063 title = self._html_search_meta('DC.title', webpage, fatal=True)
2065 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2066 camtasia_cfg = self._download_xml(
2067 camtasia_url, video_id,
2068 note='Downloading camtasia configuration',
2069 errnote='Failed to download camtasia configuration')
2070 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2073 for n in fileset_node.getchildren():
2074 url_n = n.find('./uri')
2079 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2080 'title': '%s - %s' % (title, n.tag),
2081 'url': compat_urlparse.urljoin(url, url_n.text),
2082 'duration': float_or_none(n.find('./duration').text),
2086 '_type': 'playlist',
2091 def _real_extract(self, url):
2092 if url.startswith('//'):
2095 'url': self.http_scheme() + url,
2098 parsed_url = compat_urlparse.urlparse(url)
2099 if not parsed_url.scheme:
2100 default_search = self._downloader.params.get('default_search')
2101 if default_search is None:
2102 default_search = 'fixup_error'
2104 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2106 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2107 return self.url_result('http://' + url)
2108 elif default_search != 'fixup_error':
2109 if default_search == 'auto_warning':
2110 if re.match(r'^(?:url|URL)$', url):
2111 raise ExtractorError(
2112 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2115 self._downloader.report_warning(
2116 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2117 return self.url_result('ytsearch:' + url)
2119 if default_search in ('error', 'fixup_error'):
2120 raise ExtractorError(
2121 '%r is not a valid URL. '
2122 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2123 % (url, url), expected=True)
2125 if ':' not in default_search:
2126 default_search += ':'
2127 return self.url_result(default_search + url)
2129 url, smuggled_data = unsmuggle_url(url)
2130 force_videoid = None
2131 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2132 if smuggled_data and 'force_videoid' in smuggled_data:
2133 force_videoid = smuggled_data['force_videoid']
2134 video_id = force_videoid
2136 video_id = self._generic_id(url)
2138 self.to_screen('%s: Requesting header' % video_id)
2140 head_req = HEADRequest(url)
2141 head_response = self._request_webpage(
2143 note=False, errnote='Could not send HEAD request to %s' % url,
2146 if head_response is not False:
2147 # Check for redirect
2148 new_url = compat_str(head_response.geturl())
2150 self.report_following_redirect(new_url)
2152 new_url = smuggle_url(
2153 new_url, {'force_videoid': force_videoid})
2154 return self.url_result(new_url)
2156 full_response = None
2157 if head_response is False:
2158 request = sanitized_Request(url)
2159 request.add_header('Accept-Encoding', '*')
2160 full_response = self._request_webpage(request, video_id)
2161 head_response = full_response
2165 'title': self._generic_title(url),
2166 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2169 # Check for direct link to a video
2170 content_type = head_response.headers.get('Content-Type', '').lower()
2171 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2173 format_id = compat_str(m.group('format_id'))
2174 if format_id.endswith('mpegurl'):
2175 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2176 elif format_id == 'f4m':
2177 formats = self._extract_f4m_formats(url, video_id)
2180 'format_id': format_id,
2182 'vcodec': 'none' if m.group('type') == 'audio' else None
2184 info_dict['direct'] = True
2185 self._sort_formats(formats)
2186 info_dict['formats'] = formats
2189 if not self._downloader.params.get('test', False) and not is_intentional:
2190 force = self._downloader.params.get('force_generic_extractor', False)
2191 self._downloader.report_warning(
2192 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2194 if not full_response:
2195 request = sanitized_Request(url)
2196 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2197 # making it impossible to download only chunk of the file (yet we need only 512kB to
2198 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2199 # that will always result in downloading the whole file that is not desirable.
2200 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2201 # to accept raw bytes and being able to download only a chunk.
2202 # It may probably better to solve this by checking Content-Type for application/octet-stream
2203 # after HEAD request finishes, but not sure if we can rely on this.
2204 request.add_header('Accept-Encoding', '*')
2205 full_response = self._request_webpage(request, video_id)
2207 first_bytes = full_response.read(512)
2209 # Is it an M3U playlist?
2210 if first_bytes.startswith(b'#EXTM3U'):
2211 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2212 self._sort_formats(info_dict['formats'])
2215 # Maybe it's a direct link to a video?
2216 # Be careful not to download the whole thing!
2217 if not is_html(first_bytes):
2218 self._downloader.report_warning(
2219 'URL could be a direct video link, returning it as such.')
2226 webpage = self._webpage_read_content(
2227 full_response, url, video_id, prefix=first_bytes)
2229 self.report_extraction(video_id)
2231 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2233 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2234 if doc.tag == 'rss':
2235 return self._extract_rss(url, video_id, doc)
2236 elif doc.tag == 'SmoothStreamingMedia':
2237 info_dict['formats'] = self._parse_ism_formats(doc, url)
2238 self._sort_formats(info_dict['formats'])
2240 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2241 smil = self._parse_smil(doc, url, video_id)
2242 self._sort_formats(smil['formats'])
2244 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2245 return self.playlist_result(
2247 doc, video_id, xspf_url=url,
2248 xspf_base_url=compat_str(full_response.geturl())),
2250 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2251 info_dict['formats'] = self._parse_mpd_formats(
2253 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2255 self._sort_formats(info_dict['formats'])
2257 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2258 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2259 self._sort_formats(info_dict['formats'])
2261 except compat_xml_parse_error:
2264 # Is it a Camtasia project?
2265 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2266 if camtasia_res is not None:
2269 # Sometimes embedded video player is hidden behind percent encoding
2270 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2271 # Unescaping the whole page allows to handle those cases in a generic way
2272 webpage = compat_urllib_parse_unquote(webpage)
2274 # it's tempting to parse this further, but you would
2275 # have to take into account all the variations like
2276 # Video Title - Site Name
2277 # Site Name | Video Title
2278 # Video Title - Tagline | Site Name
2279 # and so on and so forth; it's just not practical
2280 video_title = self._og_search_title(
2281 webpage, default=None) or self._html_search_regex(
2282 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2285 # Try to detect age limit automatically
2286 age_limit = self._rta_search(webpage)
2287 # And then there are the jokers who advertise that they use RTA,
2288 # but actually don't.
2289 AGE_LIMIT_MARKERS = [
2290 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2292 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2295 # video uploader is domain name
2296 video_uploader = self._search_regex(
2297 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2299 video_description = self._og_search_description(webpage, default=None)
2300 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2303 'title': video_title,
2304 'description': video_description,
2305 'thumbnail': video_thumbnail,
2306 'age_limit': age_limit,
2309 # Look for Brightcove Legacy Studio embeds
2310 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2314 'url': smuggle_url(bc_url, {'Referer': url}),
2315 'ie_key': 'BrightcoveLegacy'
2316 } for bc_url in bc_urls]
2319 '_type': 'playlist',
2320 'title': video_title,
2325 # Look for Brightcove New Studio embeds
2326 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2328 return self.playlist_from_matches(
2329 bc_urls, video_id, video_title,
2330 getter=lambda x: smuggle_url(x, {'referrer': url}),
2333 # Look for Nexx embeds
2334 nexx_urls = NexxIE._extract_urls(webpage)
2336 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2338 # Look for Nexx iFrame embeds
2339 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2341 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2343 # Look for ThePlatform embeds
2344 tp_urls = ThePlatformIE._extract_urls(webpage)
2346 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2348 # Look for Vessel embeds
2349 vessel_urls = VesselIE._extract_urls(webpage)
2351 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2353 # Look for embedded rtl.nl player
2354 matches = re.findall(
2355 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2358 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2360 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2362 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2364 vid_me_embed_url = self._search_regex(
2365 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2366 webpage, 'vid.me embed', default=None)
2367 if vid_me_embed_url is not None:
2368 return self.url_result(vid_me_embed_url, 'Vidme')
2370 # Look for YouTube embeds
2371 youtube_urls = YoutubeIE._extract_urls(webpage)
2373 return self.playlist_from_matches(
2374 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2376 matches = DailymotionIE._extract_urls(webpage)
2378 return self.playlist_from_matches(matches, video_id, video_title)
2380 # Look for embedded Dailymotion playlist player (#3822)
2382 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2384 playlists = re.findall(
2385 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2387 return self.playlist_from_matches(
2388 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2390 # Look for DailyMail embeds
2391 dailymail_urls = DailyMailIE._extract_urls(webpage)
2393 return self.playlist_from_matches(
2394 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2396 # Look for embedded Wistia player
2397 wistia_url = WistiaIE._extract_url(webpage)
2400 '_type': 'url_transparent',
2401 'url': self._proto_relative_url(wistia_url),
2402 'ie_key': WistiaIE.ie_key(),
2403 'uploader': video_uploader,
2406 # Look for SVT player
2407 svt_url = SVTIE._extract_url(webpage)
2409 return self.url_result(svt_url, 'SVT')
2411 # Look for Bandcamp pages with custom domain
2412 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2413 if mobj is not None:
2414 burl = unescapeHTML(mobj.group(1))
2415 # Don't set the extractor because it can be a track url or an album
2416 return self.url_result(burl)
2418 # Look for embedded Vevo player
2420 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2421 if mobj is not None:
2422 return self.url_result(mobj.group('url'))
2424 # Look for embedded Viddler player
2426 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2428 if mobj is not None:
2429 return self.url_result(mobj.group('url'))
2431 # Look for NYTimes player
2433 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2435 if mobj is not None:
2436 return self.url_result(mobj.group('url'))
2438 # Look for Libsyn player
2440 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2441 if mobj is not None:
2442 return self.url_result(mobj.group('url'))
2444 # Look for Ooyala videos
2445 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2446 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2447 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2448 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2449 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2450 if mobj is not None:
2451 embed_token = self._search_regex(
2452 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2453 webpage, 'ooyala embed token', default=None)
2454 return OoyalaIE._build_url_result(smuggle_url(
2457 'embed_token': embed_token,
2460 # Look for multiple Ooyala embeds on SBN network websites
2461 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2462 if mobj is not None:
2463 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2465 return self.playlist_from_matches(
2466 embeds, video_id, video_title,
2467 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2469 # Look for Aparat videos
2470 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2471 if mobj is not None:
2472 return self.url_result(mobj.group(1), 'Aparat')
2474 # Look for MPORA videos
2475 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2476 if mobj is not None:
2477 return self.url_result(mobj.group(1), 'Mpora')
2479 # Look for embedded NovaMov-based player
2481 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2482 (?P<url>http://(?:(?:embed|www)\.)?
2484 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2485 videoweed\.(?:es|com)|
2486 movshare\.(?:net|sx|ag)|
2487 divxstage\.(?:eu|net|ch|co|at|ag))
2488 /embed\.php.+?)\1''', webpage)
2489 if mobj is not None:
2490 return self.url_result(mobj.group('url'))
2492 # Look for embedded Facebook player
2493 facebook_urls = FacebookIE._extract_urls(webpage)
2495 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2497 # Look for embedded VK player
2498 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2499 if mobj is not None:
2500 return self.url_result(mobj.group('url'), 'VK')
2502 # Look for embedded Odnoklassniki player
2503 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2504 if mobj is not None:
2505 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2507 # Look for embedded ivi player
2508 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2509 if mobj is not None:
2510 return self.url_result(mobj.group('url'), 'Ivi')
2512 # Look for embedded Huffington Post player
2514 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2515 if mobj is not None:
2516 return self.url_result(mobj.group('url'), 'HuffPost')
2519 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2520 if mobj is not None:
2521 return self.url_result(mobj.group('url'))
2522 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2523 if mobj is not None:
2524 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2526 # Look for funnyordie embed
2527 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2529 return self.playlist_from_matches(
2530 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2532 # Look for BBC iPlayer embed
2533 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2535 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2537 # Look for embedded RUTV player
2538 rutv_url = RUTVIE._extract_url(webpage)
2540 return self.url_result(rutv_url, 'RUTV')
2542 # Look for embedded TVC player
2543 tvc_url = TVCIE._extract_url(webpage)
2545 return self.url_result(tvc_url, 'TVC')
2547 # Look for embedded SportBox player
2548 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2550 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2552 # Look for embedded XHamster player
2553 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2555 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2557 # Look for embedded TNAFlixNetwork player
2558 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2560 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2562 # Look for embedded PornHub player
2563 pornhub_urls = PornHubIE._extract_urls(webpage)
2565 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2567 # Look for embedded DrTuber player
2568 drtuber_urls = DrTuberIE._extract_urls(webpage)
2570 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2572 # Look for embedded RedTube player
2573 redtube_urls = RedTubeIE._extract_urls(webpage)
2575 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2577 # Look for embedded Tube8 player
2578 tube8_urls = Tube8IE._extract_urls(webpage)
2580 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2582 # Look for embedded Tvigle player
2584 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2585 if mobj is not None:
2586 return self.url_result(mobj.group('url'), 'Tvigle')
2588 # Look for embedded TED player
2590 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2591 if mobj is not None:
2592 return self.url_result(mobj.group('url'), 'TED')
2594 # Look for embedded Ustream videos
2595 ustream_url = UstreamIE._extract_url(webpage)
2597 return self.url_result(ustream_url, UstreamIE.ie_key())
2599 # Look for embedded arte.tv player
2601 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2606 # Look for embedded francetv player
2608 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2610 if mobj is not None:
2611 return self.url_result(mobj.group('url'))
2613 # Look for embedded smotri.com player
2614 smotri_url = SmotriIE._extract_url(webpage)
2616 return self.url_result(smotri_url, 'Smotri')
2618 # Look for embedded Myvi.ru player
2619 myvi_url = MyviIE._extract_url(webpage)
2621 return self.url_result(myvi_url)
2623 # Look for embedded soundcloud player
2624 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2626 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2628 # Look for tunein player
2629 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2631 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2633 # Look for embedded mtvservices player
2634 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2636 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2638 # Look for embedded yahoo player
2640 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2642 if mobj is not None:
2643 return self.url_result(mobj.group('url'), 'Yahoo')
2645 # Look for embedded sbs.com.au player
2649 <meta\s+property="og:video"\s+content=|
2652 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2654 if mobj is not None:
2655 return self.url_result(mobj.group('url'), 'SBS')
2657 # Look for embedded Cinchcast player
2659 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2661 if mobj is not None:
2662 return self.url_result(mobj.group('url'), 'Cinchcast')
2665 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2669 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2671 if mobj is not None:
2672 return self.url_result(mobj.group('url'), 'MLB')
2675 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2677 if mobj is not None:
2678 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2681 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2683 if mobj is not None:
2684 return self.url_result(mobj.group('url'), 'Livestream')
2686 # Look for Zapiks embed
2688 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2689 if mobj is not None:
2690 return self.url_result(mobj.group('url'), 'Zapiks')
2692 # Look for Kaltura embeds
2693 kaltura_url = KalturaIE._extract_url(webpage)
2695 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2697 # Look for EaglePlatform embeds
2698 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2699 if eagleplatform_url:
2700 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2702 # Look for ClipYou (uses EaglePlatform) embeds
2704 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2705 if mobj is not None:
2706 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2708 # Look for Pladform embeds
2709 pladform_url = PladformIE._extract_url(webpage)
2711 return self.url_result(pladform_url)
2713 # Look for Videomore embeds
2714 videomore_url = VideomoreIE._extract_url(webpage)
2716 return self.url_result(videomore_url)
2718 # Look for Webcaster embeds
2719 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2721 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2723 # Look for Playwire embeds
2725 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2726 if mobj is not None:
2727 return self.url_result(mobj.group('url'))
2729 # Look for 5min embeds
2731 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2732 if mobj is not None:
2733 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2735 # Look for Crooks and Liars embeds
2737 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2738 if mobj is not None:
2739 return self.url_result(mobj.group('url'))
2741 # Look for NBC Sports VPlayer embeds
2742 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2744 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2746 # Look for NBC News embeds
2747 nbc_news_embed_url = re.search(
2748 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2749 if nbc_news_embed_url:
2750 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2752 # Look for Google Drive embeds
2753 google_drive_url = GoogleDriveIE._extract_url(webpage)
2754 if google_drive_url:
2755 return self.url_result(google_drive_url, 'GoogleDrive')
2757 # Look for UDN embeds
2759 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2760 if mobj is not None:
2761 return self.url_result(
2762 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2764 # Look for Senate ISVP iframe
2765 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2767 return self.url_result(senate_isvp_url, 'SenateISVP')
2769 # Look for OnionStudios embeds
2770 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2771 if onionstudios_url:
2772 return self.url_result(onionstudios_url)
2774 # Look for ViewLift embeds
2775 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2777 return self.url_result(viewlift_url)
2779 # Look for JWPlatform embeds
2780 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2782 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2784 # Look for Digiteka embeds
2785 digiteka_url = DigitekaIE._extract_url(webpage)
2787 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2789 # Look for Arkena embeds
2790 arkena_url = ArkenaIE._extract_url(webpage)
2792 return self.url_result(arkena_url, ArkenaIE.ie_key())
2794 # Look for Piksel embeds
2795 piksel_url = PikselIE._extract_url(webpage)
2797 return self.url_result(piksel_url, PikselIE.ie_key())
2799 # Look for Limelight embeds
2800 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2802 return self.playlist_result(
2803 limelight_urls, video_id, video_title, video_description)
2805 # Look for Anvato embeds
2806 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2808 return self.playlist_result(
2809 anvato_urls, video_id, video_title, video_description)
2811 # Look for AdobeTVVideo embeds
2813 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2815 if mobj is not None:
2816 return self.url_result(
2817 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2820 # Look for Vine embeds
2822 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2824 if mobj is not None:
2825 return self.url_result(
2826 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2828 # Look for VODPlatform embeds
2830 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2832 if mobj is not None:
2833 return self.url_result(
2834 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2836 # Look for Mangomolo embeds
2838 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2840 video\?.*?\bid=(?P<video_id>\d+)|
2841 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2842 ).+?)\1''', webpage)
2843 if mobj is not None:
2845 '_type': 'url_transparent',
2846 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2847 'title': video_title,
2848 'description': video_description,
2849 'thumbnail': video_thumbnail,
2850 'uploader': video_uploader,
2852 video_id = mobj.group('video_id')
2855 'ie_key': 'MangomoloVideo',
2860 'ie_key': 'MangomoloLive',
2861 'id': mobj.group('channel_id'),
2865 # Look for Instagram embeds
2866 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2867 if instagram_embed_url is not None:
2868 return self.url_result(
2869 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2871 # Look for LiveLeak embeds
2872 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2874 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2876 # Look for 3Q SDN embeds
2877 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2880 '_type': 'url_transparent',
2881 'ie_key': ThreeQSDNIE.ie_key(),
2882 'url': self._proto_relative_url(threeqsdn_url),
2883 'title': video_title,
2884 'description': video_description,
2885 'thumbnail': video_thumbnail,
2886 'uploader': video_uploader,
2889 # Look for VBOX7 embeds
2890 vbox7_url = Vbox7IE._extract_url(webpage)
2892 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2894 # Look for DBTV embeds
2895 dbtv_urls = DBTVIE._extract_urls(webpage)
2897 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2899 # Look for Videa embeds
2900 videa_urls = VideaIE._extract_urls(webpage)
2902 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2904 # Look for 20 minuten embeds
2905 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2907 return self.playlist_from_matches(
2908 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2910 # Look for Openload embeds
2911 openload_urls = OpenloadIE._extract_urls(webpage)
2913 return self.playlist_from_matches(
2914 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2916 # Look for VideoPress embeds
2917 videopress_urls = VideoPressIE._extract_urls(webpage)
2919 return self.playlist_from_matches(
2920 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2922 # Look for Rutube embeds
2923 rutube_urls = RutubeIE._extract_urls(webpage)
2925 return self.playlist_from_matches(
2926 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2928 # Look for WashingtonPost embeds
2929 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2931 return self.playlist_from_matches(
2932 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2934 # Look for Mediaset embeds
2935 mediaset_urls = MediasetIE._extract_urls(webpage)
2937 return self.playlist_from_matches(
2938 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2940 # Look for JOJ.sk embeds
2941 joj_urls = JojIE._extract_urls(webpage)
2943 return self.playlist_from_matches(
2944 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2946 # Look for megaphone.fm embeds
2947 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2949 return self.playlist_from_matches(
2950 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2952 # Look for vzaar embeds
2953 vzaar_urls = VzaarIE._extract_urls(webpage)
2955 return self.playlist_from_matches(
2956 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2958 channel9_urls = Channel9IE._extract_urls(webpage)
2960 return self.playlist_from_matches(
2961 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2963 vshare_urls = VShareIE._extract_urls(webpage)
2965 return self.playlist_from_matches(
2966 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2968 # Look for Mediasite embeds
2969 mediasite_urls = MediasiteIE._extract_urls(webpage)
2972 self.url_result(smuggle_url(
2973 compat_urlparse.urljoin(url, mediasite_url),
2974 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2975 for mediasite_url in mediasite_urls]
2976 return self.playlist_result(entries, video_id, video_title)
2978 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2979 if springboardplatform_urls:
2980 return self.playlist_from_matches(
2981 springboardplatform_urls, video_id, video_title,
2982 ie=SpringboardPlatformIE.ie_key())
2984 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2986 return self.playlist_from_matches(
2987 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2989 vice_urls = ViceIE._extract_urls(webpage)
2991 return self.playlist_from_matches(
2992 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2994 xfileshare_urls = XFileShareIE._extract_urls(webpage)
2996 return self.playlist_from_matches(
2997 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
2999 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3000 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3002 if sharevideos_urls:
3003 return self.playlist_from_matches(
3004 sharevideos_urls, video_id, video_title)
3006 # Look for HTML5 media
3007 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3009 if len(entries) == 1:
3012 'title': video_title,
3015 for num, entry in enumerate(entries, start=1):
3017 'id': '%s-%s' % (video_id, num),
3018 'title': '%s (%d)' % (video_title, num),
3020 for entry in entries:
3021 self._sort_formats(entry['formats'])
3022 return self.playlist_result(entries, video_id, video_title)
3024 jwplayer_data = self._find_jwplayer_data(
3025 webpage, video_id, transform_source=js_to_json)
3027 info = self._parse_jwplayer_data(
3028 jwplayer_data, video_id, require_title=False, base_url=url)
3029 return merge_dicts(info, info_dict)
3033 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3035 if mobj is not None:
3036 sources = self._parse_json(
3037 mobj.group(1), video_id, transform_source=js_to_json,
3039 if not isinstance(sources, list):
3042 for source in sources:
3043 src = source.get('src')
3044 if not src or not isinstance(src, compat_str):
3046 src = compat_urlparse.urljoin(url, src)
3047 src_type = source.get('type')
3048 if isinstance(src_type, compat_str):
3049 src_type = src_type.lower()
3050 ext = determine_ext(src).lower()
3051 if src_type == 'video/youtube':
3052 return self.url_result(src, YoutubeIE.ie_key())
3053 if src_type == 'application/dash+xml' or ext == 'mpd':
3054 formats.extend(self._extract_mpd_formats(
3055 src, video_id, mpd_id='dash', fatal=False))
3056 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3057 formats.extend(self._extract_m3u8_formats(
3058 src, video_id, 'mp4', entry_protocol='m3u8_native',
3059 m3u8_id='hls', fatal=False))
3063 'ext': (mimetype2ext(src_type) or
3064 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3067 self._sort_formats(formats)
3068 info_dict['formats'] = formats
3071 # Looking for http://schema.org/VideoObject
3072 json_ld = self._search_json_ld(
3073 webpage, video_id, default={}, expected_type='VideoObject')
3074 if json_ld.get('url'):
3075 return merge_dicts(json_ld, info_dict)
3077 def check_video(vurl):
3078 if YoutubeIE.suitable(vurl):
3080 if RtmpIE.suitable(vurl):
3082 vpath = compat_urlparse.urlparse(vurl).path
3083 vext = determine_ext(vpath)
3084 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3086 def filter_video(urls):
3087 return list(filter(check_video, urls))
3089 # Start with something easy: JW Player in SWFObject
3090 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3092 # Look for gorilla-vid style embedding
3093 found = filter_video(re.findall(r'''(?sx)
3097 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3100 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3102 # Broaden the search a little bit
3103 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3105 # Broaden the findall a little bit: JWPlayer JS loader
3106 found = filter_video(re.findall(
3107 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3110 found = filter_video(re.findall(r'''(?xs)
3111 flowplayer\("[^"]+",\s*
3113 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3114 ["']?url["']?\s*:\s*["']([^"']+)["']
3119 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3121 # Try to find twitter cards info
3122 # twitter:player:stream should be checked before twitter:player since
3123 # it is expected to contain a raw stream (see
3124 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3125 found = filter_video(re.findall(
3126 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3128 # We look for Open Graph info:
3129 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3130 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3131 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3132 if m_video_type is not None:
3133 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3135 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3137 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3138 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3141 # Look also in Refresh HTTP header
3142 refresh_header = head_response.headers.get('Refresh')
3144 # In python 2 response HTTP headers are bytestrings
3145 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3146 refresh_header = refresh_header.decode('iso-8859-1')
3147 found = re.search(REDIRECT_REGEX, refresh_header)
3149 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3151 self.report_following_redirect(new_url)
3160 # twitter:player is a https URL to iframe player that may or may not
3161 # be supported by youtube-dl thus this is checked the very last (see
3162 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3163 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3164 if embed_url and embed_url != url:
3165 return self.url_result(embed_url)
3168 raise UnsupportedError(url)
3171 for video_url in orderedSet(found):
3172 video_url = unescapeHTML(video_url)
3173 video_url = video_url.replace('\\/', '/')
3174 video_url = compat_urlparse.urljoin(url, video_url)
3175 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3177 # Sometimes, jwplayer extraction will result in a YouTube URL
3178 if YoutubeIE.suitable(video_url):
3179 entries.append(self.url_result(video_url, 'Youtube'))
3182 # here's a fun little line of code for you:
3183 video_id = os.path.splitext(video_id)[0]
3187 'uploader': video_uploader,
3188 'title': video_title,
3189 'age_limit': age_limit,
3192 if RtmpIE.suitable(video_url):
3193 entry_info_dict.update({
3194 '_type': 'url_transparent',
3195 'ie_key': RtmpIE.ie_key(),
3198 entries.append(entry_info_dict)
3201 ext = determine_ext(video_url)
3203 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3205 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3207 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3209 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3211 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3212 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3213 # Just matching .ism/manifest is not enough to be reliably sure
3214 # whether it's actually an ISM manifest or some other streaming
3215 # manifest since there are various streaming URL formats
3216 # possible (see [1]) as well as some other shenanigans like
3217 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3219 # Thus the most reasonable way to solve this is to delegate
3220 # to generic extractor in order to look into the contents of
3221 # the manifest itself.
3222 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3223 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3224 entry_info_dict = self.url_result(
3225 smuggle_url(video_url, {'to_generic': True}),
3228 entry_info_dict['url'] = video_url
3230 if entry_info_dict.get('formats'):
3231 self._sort_formats(entry_info_dict['formats'])
3233 entries.append(entry_info_dict)
3235 if len(entries) == 1:
3238 for num, e in enumerate(entries, start=1):
3239 # 'url' results don't have a title
3240 if e.get('title') is not None:
3241 e['title'] = '%s (%d)' % (e['title'], num)
3243 '_type': 'playlist',