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
110 from .cloudflarestream import CloudflareStreamIE
111 from .peertube import PeerTubeIE
112 from .indavideo import IndavideoEmbedIE
115 class GenericIE(InfoExtractor):
116 IE_DESC = 'Generic downloader that works on some sites'
120 # Direct link to a video
122 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
123 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
128 'upload_date': '20100513',
131 # Direct link to media delivered compressed (until Accept-Encoding is *)
133 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
134 'md5': '128c42e68b13950268b648275386fc74',
136 'id': 'FictionJunction-Parallel_Hearts',
138 'title': 'FictionJunction-Parallel_Hearts',
139 'upload_date': '20140522',
141 'expected_warnings': [
142 'URL could be a direct video link, returning it as such.'
144 'skip': 'URL invalid',
146 # Direct download with broken HEAD
148 'url': 'http://ai-radio.org:8000/radio.opus',
155 'skip_download': True, # infinite live stream
157 'expected_warnings': [
158 r'501.*Not Implemented',
162 # Direct link with incorrect MIME type
164 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
165 'md5': '4ccbebe5f36706d85221f204d7eb5913',
167 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
168 'id': '5_Lennart_Poettering_-_Systemd',
170 'title': '5_Lennart_Poettering_-_Systemd',
171 'upload_date': '20141120',
173 'expected_warnings': [
174 'URL could be a direct video link, returning it as such.'
179 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
181 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
182 'title': 'Zero Punctuation',
183 'description': 're:.*groundbreaking video review series.*'
185 'playlist_mincount': 11,
187 # RSS feed with enclosure
189 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
191 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
193 'upload_date': '20150228',
194 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
197 # RSS feed with enclosures and unsupported link URLs
199 'url': 'http://www.hellointernet.fm/podcast?format=rss',
201 'id': 'http://www.hellointernet.fm/podcast?format=rss',
202 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
203 'title': 'Hello Internet',
205 'playlist_mincount': 100,
207 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
209 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
213 'title': 'Automatics, robotics and biocybernetics',
214 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
215 'upload_date': '20130627',
216 'formats': 'mincount:16',
217 'subtitles': 'mincount:1',
220 'force_generic_extractor': True,
221 'skip_download': True,
224 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
226 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
231 'formats': 'mincount:1',
234 'skip_download': True,
237 # SMIL from https://www.restudy.dk/video/play/id/1637
239 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
243 'title': 'video_1637',
244 'formats': 'mincount:3',
247 'skip_download': True,
250 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
252 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
254 'id': 'smil-service',
256 'title': 'smil-service',
257 'formats': 'mincount:1',
260 'skip_download': True,
263 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
265 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
269 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
270 'formats': 'mincount:3',
273 'skip_download': True,
276 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
278 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
280 'id': 'mZlp2ctYIUEB',
282 'title': 'Tikibad ontruimd wegens brand',
283 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
284 'thumbnail': r're:^https?://.*\.jpg$',
288 'skip_download': True,
291 # MPD from http://dash-mse-test.appspot.com/media.html
293 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
294 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
296 'id': 'car-20120827-manifest',
298 'title': 'car-20120827-manifest',
299 'formats': 'mincount:9',
300 'upload_date': '20130904',
303 'format': 'bestvideo',
306 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
308 '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',
313 'formats': 'mincount:8',
317 'skip_download': True,
319 'skip': 'video gone',
321 # m3u8 served with Content-Type: text/plain
323 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
328 'upload_date': '20140720',
329 'formats': 'mincount:11',
333 'skip_download': True,
335 'skip': 'video gone',
339 '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',
343 'upload_date': '20130224',
344 'uploader_id': 'TheVerge',
345 'description': r're:^Chris Ziegler takes a look at the\.*',
346 'uploader': 'The Verge',
347 'title': 'First Firefox OS phones side-by-side',
350 'skip_download': False,
354 # redirect in Refresh HTTP header
355 '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',
359 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
360 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
361 'upload_date': '20150917',
362 'uploader_id': 'brtvofficial',
363 'uploader': 'Boiler Room',
366 'skip_download': False,
370 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
371 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
373 'id': '13601338388002',
375 'uploader': 'www.hodiho.fr',
376 'title': 'R\u00e9gis plante sa Jeep',
379 # bandcamp page with custom domain
381 'add_ie': ['Bandcamp'],
382 'url': 'http://bronyrock.com/track/the-pony-mash',
386 'title': 'The Pony Mash',
387 'uploader': 'M_Pallante',
389 'skip': 'There is a limit of 200 free downloads / month for the test song',
392 # embedded brightcove video
393 # it also tests brightcove videos that need to set the 'Referer'
394 # in the http requests
395 'add_ie': ['BrightcoveLegacy'],
396 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
398 'id': '2765128793001',
400 'title': 'Le cours de bourse : l’analyse technique',
401 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
402 'uploader': 'BFM BUSINESS',
405 'skip_download': True,
409 # embedded with itemprop embedURL and video id spelled as `idVideo`
410 'add_id': ['BrightcoveLegacy'],
411 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
413 'id': '5255628253001',
415 'title': 'md5:37c519b1128915607601e75a87995fc0',
416 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
417 'uploader': 'BFM BUSINESS',
418 'uploader_id': '876450612001',
419 'timestamp': 1482255315,
420 'upload_date': '20161220',
423 'skip_download': True,
427 # https://github.com/rg3/youtube-dl/issues/2253
428 'url': 'http://bcove.me/i6nfkrc3',
429 'md5': '0ba9446db037002366bab3b3eb30c88c',
431 'id': '3101154703001',
433 'title': 'Still no power',
434 'uploader': 'thestar.com',
435 '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.',
437 'add_ie': ['BrightcoveLegacy'],
438 'skip': 'video gone',
441 'url': 'http://www.championat.com/video/football/v/87/87499.html',
442 'md5': 'fb973ecf6e4a78a67453647444222983',
444 'id': '3414141473001',
446 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
447 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
448 'uploader': 'Championat',
452 # https://github.com/rg3/youtube-dl/issues/3541
453 'add_ie': ['BrightcoveLegacy'],
454 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
456 'id': '3866516442001',
458 'title': 'Leer mij vrouwen kennen: Aflevering 1',
459 'description': 'Leer mij vrouwen kennen: Aflevering 1',
460 'uploader': 'SBS Broadcasting',
462 'skip': 'Restricted to Netherlands',
464 'skip_download': True, # m3u8 download
468 # Brightcove video in <iframe>
469 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
470 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
472 'id': '5360463607001',
474 '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',
475 '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。',
476 'uploader': 'United Nations',
477 'uploader_id': '1362235914001',
478 'timestamp': 1489593889,
479 'upload_date': '20170315',
481 'add_ie': ['BrightcoveLegacy'],
484 # Brightcove with alternative playerID key
485 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
487 'id': 'nmeth.2062_SV1',
488 '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',
492 'id': '2228375078001',
494 'title': 'nmeth.2062-sv1',
495 'description': 'nmeth.2062-sv1',
496 'timestamp': 1363357591,
497 'upload_date': '20130315',
498 'uploader': 'Nature Publishing Group',
499 'uploader_id': '1964492299001',
504 # Brightcove with UUID in videoPlayer
505 'url': 'http://www8.hp.com/cn/zh/home.html',
507 'id': '5255815316001',
509 'title': 'Sprocket Video - China',
510 'description': 'Sprocket Video - China',
511 'uploader': 'HP-Video Gallery',
512 'timestamp': 1482263210,
513 'upload_date': '20161220',
514 'uploader_id': '1107601872001',
517 'skip_download': True, # m3u8 download
519 'skip': 'video rotates...weekly?',
522 # Brightcove:new type [2].
523 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
524 'md5': '2b35148fcf48da41c9fb4591650784f3',
526 'id': '5348741021001',
528 'upload_date': '20170306',
529 'uploader_id': '4191638492001',
530 'timestamp': 1488769918,
531 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
536 # Alternative brightcove <video> attributes
537 '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/',
539 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
540 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
543 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
545 'id': '5311302538001',
547 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
548 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
549 'timestamp': 1486321708,
550 'upload_date': '20170205',
551 'uploader_id': '800000640001',
553 'only_matching': True,
557 # Brightcove with UUID in videoPlayer
558 'url': 'http://www8.hp.com/cn/zh/home.html',
560 'id': '5255815316001',
562 'title': 'Sprocket Video - China',
563 'description': 'Sprocket Video - China',
564 'uploader': 'HP-Video Gallery',
565 'timestamp': 1482263210,
566 'upload_date': '20161220',
567 'uploader_id': '1107601872001',
570 'skip_download': True, # m3u8 download
575 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
576 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
578 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
580 'title': '2cc213299525360.mov', # that's what we get
583 'add_ie': ['Ooyala'],
586 # ooyala video embedded with http://player.ooyala.com/iframe.js
587 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
589 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
591 'title': '"Steve Jobs: Man in the Machine" trailer',
592 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
596 'skip_download': True,
598 'skip': 'movie expired',
600 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
602 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
604 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
606 'title': 'Steampunk Fest Comes to Honesdale',
610 'skip_download': True,
615 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
619 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
620 'upload_date': '20140225',
621 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
622 'uploader': 'Tested',
623 'uploader_id': 'testedcom',
625 # No need to test YoutubeIE here
627 'skip_download': True,
632 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
636 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
637 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
639 # HEAD requests lead to endless 301, while GET is OK
640 'expected_warnings': ['301'],
644 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
648 'title': 'Охотское море стало целиком российским',
649 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
653 'skip_download': True,
658 '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/',
662 'title': 'Дошкольное воспитание',
667 'url': 'http://www.vestifinance.ru/articles/25753',
670 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
675 'title': 'Госзаказ. День 3',
681 'title': 'Госзаказ. День 2',
687 'title': 'Госзаказ. День 1',
693 'skip_download': True,
698 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
700 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
702 'title': 'Ужастики, русский трейлер (2015)',
703 'thumbnail': r're:^https?://.*\.jpg$',
709 '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',
712 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
714 'playlist_mincount': 7,
715 # This forum does not allow <iframe> syntaxes anymore
716 # Now HTML tags are displayed as-is
717 'skip': 'No videos on this page',
721 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
722 'md5': '65fdff94098e4a607385a60c5177c638',
726 'title': 'Hidden miracles of the natural world',
727 'uploader': 'Louie Schwartzberg',
728 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
731 # nowvideo embed hidden behind percent encoding
733 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
734 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
736 'id': '06e53103ca9aa',
738 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
739 'description': 'No description',
744 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
745 'md5': '7653032cbb25bf6c80d80f217055fa43',
747 'id': '048195-004_PLUS7-F',
750 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
751 'upload_date': '20140320',
754 'skip_download': 'Requires rtmpdump'
756 'skip': 'video gone',
760 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
764 'title': 'Alcaline, le concert avec Calogero',
765 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
766 'upload_date': '20150226',
767 'timestamp': 1424989860,
772 'skip_download': True,
774 'expected_warnings': [
780 'url': 'http://www.wired.com/2014/04/honda-asimo/',
781 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
783 'id': '53501be369702d3275860000',
785 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
790 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
791 'md5': '441aeeb82eb72c422c7f14ec533999cd',
793 'id': 'k2mm4bCdJ6CQ2i7c8o2',
795 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
796 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
798 'uploader_id': 'xgditw',
799 'upload_date': '20140425',
800 'timestamp': 1398441542,
802 'add_ie': ['Dailymotion'],
806 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
810 'title': 'Care worker punches elderly dementia patient in head 11 times',
811 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
813 'add_ie': ['DailyMail'],
815 'skip_download': True,
820 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
824 'title': 'The NBL Auction 2014',
825 'uploader': 'BADMINTON England',
826 'uploader_id': 'BADMINTONEvents',
827 'upload_date': '20140603',
828 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
830 'add_ie': ['Youtube'],
832 'skip_download': True,
837 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
838 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
840 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
842 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
843 'description': 'Two valets share their love for movie star Liam Neesons.',
844 'timestamp': 1349922600,
845 'upload_date': '20121011',
848 # YouTube embed via <data-embed-url="">
850 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
854 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
855 'uploader': 'Gameloft',
856 'uploader_id': 'gameloft',
857 'upload_date': '20140828',
858 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
861 'skip_download': True,
864 # YouTube <object> embed
866 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
867 'md5': '516718101ec834f74318df76259fb3cc',
871 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
872 'upload_date': '20080526',
873 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
874 'uploader': 'Christopher Sykes',
875 'uploader_id': 'ChristopherJSykes',
877 'add_ie': ['Youtube'],
881 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
883 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
885 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
886 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
891 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
893 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
894 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
905 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
906 'md5': '9d65602bf31c6e20014319c7d07fba27',
908 'id': '5123ea6d5e5a7',
911 'uploader': 'www.handjobhub.com',
912 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
915 # Multiple brightcove videos
916 # https://github.com/rg3/youtube-dl/issues/2283
918 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
920 'id': 'always-never',
921 'title': 'Always / Never - The New Yorker',
925 'extract_flat': False,
926 'skip_download': True,
931 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
932 'md5': '96f09a37e44da40dd083e12d9a683327',
936 'title': 'Ump changes call to ball',
937 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
939 'timestamp': 1401537900,
940 'upload_date': '20140531',
941 'thumbnail': r're:^https?://.*\.jpg$',
946 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
947 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
951 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
952 'description': 'a Paywall Videos video from Remilon',
954 'uploader': 'study.com',
955 'timestamp': 1459678540,
956 'upload_date': '20160403',
957 'filesize': 24687186,
961 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
962 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
966 'title': 'Conversation about Hexagonal Rails Part 1',
967 'description': 'a Martin Fowler video from ThoughtWorks',
969 'uploader': 'thoughtworks.wistia.com',
970 'timestamp': 1401832161,
971 'upload_date': '20140603',
974 # Wistia standard embed (async)
976 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
980 'title': 'Drip Brennan Dunn Workshop',
981 'description': 'a JV Webinars video from getdrip-1',
983 'timestamp': 1463607249,
984 'upload_date': '20160518',
987 'skip_download': True,
992 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
996 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
997 'uploader': 'Sophos Security',
998 'title': 'Chet Chat 171 - Oct 29, 2014',
999 'upload_date': '20141029',
1002 # Soundcloud multiple embeds
1004 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1007 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1009 'playlist_mincount': 7,
1011 # TuneIn station embed
1013 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1018 'location': 'Paris, France',
1023 'skip_download': True,
1028 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1032 'upload_date': '20141112',
1033 'title': 'Rosetta #CometLanding webcast HL 10',
1036 # Another Livestream embed, without 'new.' in URL
1038 'url': 'https://www.freespeech.org/',
1042 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1046 'skip_download': True,
1051 'url': 'https://skiplagged.com/',
1054 'title': 'Skiplagged: The smart way to find cheap flights',
1056 'playlist_mincount': 1,
1057 'add_ie': ['Youtube'],
1061 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1065 'upload_date': '20141126',
1066 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1071 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1073 'id': '730m_DandD_1901_512k',
1075 'uploader': 'www.abc.net.au',
1076 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1079 # embedded viddler video
1081 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1085 'uploader': 'deadspin',
1086 'title': 'WALL-TO-GORTAT',
1087 'timestamp': 1422285291,
1088 'upload_date': '20150126',
1090 'add_ie': ['Viddler'],
1094 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1098 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1099 'description': 'md5:601cb790edd05908957dae8aaa866465',
1100 'upload_date': '20150220',
1102 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1106 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1108 'id': 'Mrj4DVp2zeA',
1110 'upload_date': '20150212',
1111 'uploader': 'The National Archives UK',
1112 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1113 'uploader_id': 'NationalArchives08',
1114 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1119 'url': 'http://www.suffolk.edu/sjc/live.php',
1123 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1124 'uploader': 'www.suffolk.edu',
1127 'skip_download': True,
1129 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1133 'url': 'http://www.indiedb.com/games/king-machine/videos',
1137 'title': 'king machine trailer 1',
1138 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1139 'thumbnail': r're:^https?://.*\.jpg$',
1143 # JWPlayer config passed as variable
1144 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1148 'title': 'ARIELE | Tube Cup',
1149 'uploader': 'www.txxx.com',
1153 'skip_download': True,
1158 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1159 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1163 'upload_date': '20171122',
1164 'timestamp': 1511366290,
1165 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1167 'add_ie': [JWPlatformIE.ie_key()],
1170 # Video.js embed, multiple formats
1171 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1173 'id': 'yygqldloqIk',
1175 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1176 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1177 'upload_date': '20130314',
1178 'uploader': 'PROстое3D',
1179 'uploader_id': 'PROstoe3D',
1182 'skip_download': True,
1186 # Video.js embed, single format
1187 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1191 'title': 'Step 1 - Good Foundation',
1192 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1195 'skip_download': True,
1200 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1201 'playlist_mincount': 5,
1203 'id': 'aanslagen-kopenhagen',
1204 'title': 'Aanslagen Kopenhagen',
1209 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1213 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1216 # Kaltura embed (different embed code)
1218 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1222 'upload_date': '20150127',
1223 'uploader_id': 'PremierMedia',
1225 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1228 # Kaltura embed with single quotes
1230 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1235 'timestamp': 1355743100,
1236 'upload_date': '20121217',
1237 'uploader_id': 'cplapp@learn360.com',
1239 'add_ie': ['Kaltura'],
1242 # Kaltura embedded via quoted entry_id
1243 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1247 'title': '06_matthew_brender_raj_dutt',
1248 'timestamp': 1466638791,
1249 'upload_date': '20160622',
1251 'add_ie': ['Kaltura'],
1252 'expected_warnings': [
1253 'Could not send HEAD request'
1256 'skip_download': True,
1260 # Kaltura embedded, some fileExt broken (#11480)
1261 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1265 'title': 'Our "Standard Models" of particle physics and cosmology',
1266 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1267 'timestamp': 1321158993,
1268 'upload_date': '20111113',
1269 'uploader_id': 'kps1',
1271 'add_ie': ['Kaltura'],
1274 # Kaltura iframe embed
1275 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1276 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1280 'title': 'I. M. Pei: A Centennial Celebration',
1281 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1282 'upload_date': '20170403',
1283 'uploader_id': 'batchUser',
1284 'timestamp': 1491232186,
1286 'add_ie': ['Kaltura'],
1289 # Kaltura iframe embed, more sophisticated
1290 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1294 'title': 'lecture-05sep2017',
1295 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1296 'upload_date': '20170913',
1297 'uploader_id': 'eps2',
1298 'timestamp': 1505340777,
1301 'skip_download': True,
1303 'add_ie': ['Kaltura'],
1306 # meta twitter:player
1307 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1311 'title': 'Main Twerk (Video)',
1312 'upload_date': '20171208',
1313 'uploader_id': 'sebastian.salinas@thechive.com',
1314 'timestamp': 1512713057,
1317 'skip_download': True,
1319 'add_ie': ['Kaltura'],
1321 # referrer protected EaglePlatform embed
1323 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1327 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1328 'thumbnail': r're:^https?://.*\.jpg$',
1333 'skip_download': True,
1336 # ClipYou (EaglePlatform) embed (custom URL)
1338 'url': 'http://muz-tv.ru/play/7129/',
1339 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1343 'title': "'O Sole Mio",
1344 'thumbnail': r're:^https?://.*\.jpg$',
1349 'skip_download': True,
1351 'skip': 'This video is unavailable.',
1355 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1359 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1360 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1361 'thumbnail': r're:^https?://.*\.jpg$',
1365 'skip': 'HTTP Error 404: Not Found',
1369 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1373 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1374 'thumbnail': r're:^https?://.*\.png$',
1380 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1381 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1385 'title': 'Facebook Creates "On This Day" | Crunch Report',
1386 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1387 'timestamp': 1427237531,
1388 'uploader': 'Crunch Report',
1389 'upload_date': '20150324',
1393 'skip_download': True,
1398 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1402 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1407 # Crooks and Liars embed
1409 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1413 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1414 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1415 'timestamp': 1428207000,
1416 'upload_date': '20150405',
1417 'uploader': 'Heather',
1420 # Crooks and Liars external embed
1422 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1424 'id': 'MTE3MjUtMzQ2MzA',
1426 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1427 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1428 'timestamp': 1265032391,
1429 'upload_date': '20100201',
1430 'uploader': 'Heather',
1433 # NBC Sports vplayer embed
1435 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1437 'id': 'ln7x1qSThw4k',
1439 'title': "PFT Live: New leader in the 'new-look' defense",
1440 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1441 'uploader': 'NBCU-SPORTS',
1442 'upload_date': '20140107',
1443 'timestamp': 1389118457,
1445 'skip': 'Invalid Page URL',
1449 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1450 'md5': '1aa589c675898ae6d37a17913cf68d66',
1452 'id': 'x_dtl_oa_LettermanliftPR_160608',
1454 'title': 'David Letterman: A Preview',
1455 '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.',
1456 'upload_date': '20160609',
1457 'timestamp': 1465431544,
1458 'uploader': 'NBCU-NEWS',
1463 'url': 'https://video.udn.com/news/300346',
1464 'md5': 'fd2060e988c326991037b9aff9df21a6',
1468 'title': '中一中男師變性 全校師生力挺',
1469 'thumbnail': r're:^https?://.*\.jpg$',
1473 'skip_download': True,
1475 'expected_warnings': ['Failed to parse JSON Expecting value'],
1477 # Brightcove URL in single quotes
1479 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1480 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1482 'id': '4255764656001',
1484 'title': 'SN Presents: Russell Martin, World Citizen',
1485 '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.',
1486 'uploader': 'Rogers Sportsnet',
1487 'uploader_id': '1704050871',
1488 'upload_date': '20150525',
1489 'timestamp': 1432570283,
1492 # OnionStudios embed
1494 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1498 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1499 'thumbnail': r're:^https?://.*\.jpe?g$',
1500 'uploader': 'ClickHole',
1501 'uploader_id': 'clickhole',
1506 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1508 'id': '74849a00-85a9-11e1-9660-123139220831',
1510 'title': '#whilewewatch',
1513 # AdobeTVVideo embed
1515 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1516 'md5': '43662b577c018ad707a63766462b1e87',
1520 'title': 'New experience with Acrobat DC',
1521 'description': 'New experience with Acrobat DC',
1522 'duration': 248.667,
1525 # BrightcoveInPageEmbed embed
1527 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1529 'id': '4238694884001',
1531 'title': 'Tabletop: Dread, Last Thoughts',
1532 'description': 'Tabletop: Dread, Last Thoughts',
1536 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1537 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1539 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1541 'id': '4785848093001',
1543 'title': 'The Cardinal Pell Interview',
1544 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1545 'uploader': 'GlobeCast Australia - GlobeStream',
1546 'uploader_id': '2733773828001',
1547 'upload_date': '20160304',
1548 'timestamp': 1457083087,
1552 'skip_download': True,
1556 # Brightcove embed with whitespace around attribute names
1557 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1559 'id': '3167554373001',
1561 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1562 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1563 'uploader_id': '1079349493',
1564 'upload_date': '20140207',
1565 'timestamp': 1391810548,
1568 'skip_download': True,
1571 # Another form of arte.tv embed
1573 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1574 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1576 'id': '030273-562_PLUS7-F',
1578 'title': 'ARTE Reportage - Nulle part, en France',
1579 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1580 'upload_date': '20160409',
1585 'url': 'http://www.wykop.pl/link/3088787/',
1586 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1588 'id': '874_1459135191',
1590 'title': 'Man shows poor quality of new apartment building',
1591 'description': 'The wall is like a sand pile.',
1592 'uploader': 'Lake8737',
1594 'add_ie': [LiveLeakIE.ie_key()],
1596 # Another LiveLeak embed pattern (#13336)
1598 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1600 'id': '2eb_1496309988',
1602 'title': 'Thief robs place where everyone was armed',
1603 'description': 'md5:694d73ee79e535953cf2488562288eee',
1604 'uploader': 'brazilwtf',
1606 'add_ie': [LiveLeakIE.ie_key()],
1608 # Duplicated embedded video URLs
1610 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1612 'id': '149298443_480_16c25b74_2',
1614 'title': 'vs. Blue Orange Spring Game',
1615 'uploader': 'www.hudl.com',
1618 # twitter:player:stream embed
1620 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1624 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1625 'uploader': 'www.rtl.be',
1629 'skip_download': True,
1632 # twitter:player embed
1634 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1635 'md5': 'a3e0df96369831de324f0778e126653c',
1637 'id': '4909620399001',
1639 'title': 'What Do Black Holes Sound Like?',
1640 'description': 'what do black holes sound like',
1641 'upload_date': '20160524',
1642 'uploader_id': '29913724001',
1643 'timestamp': 1464107587,
1644 'uploader': 'TheAtlantic',
1646 'add_ie': ['BrightcoveLegacy'],
1648 # Facebook <iframe> embed
1650 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1651 'md5': 'fbcde74f534176ecb015849146dd3aee',
1653 'id': '599637780109885',
1655 'title': 'Facebook video #599637780109885',
1658 # Facebook <iframe> embed, plugin video
1660 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1662 'id': '1754168231264132',
1664 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1665 'uploader': 'Tariq Ramadan (official)',
1666 'timestamp': 1496758379,
1667 'upload_date': '20170606',
1670 'skip_download': True,
1673 # Facebook API embed
1675 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1676 'md5': 'a47372ee61b39a7b90287094d447d94e',
1678 'id': '10153467542406923',
1680 'title': 'Facebook video #10153467542406923',
1683 # Wordpress "YouTube Video Importer" plugin
1685 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1686 'md5': 'd16797741b560b485194eddda8121b48',
1688 'id': 'HNTXWDXV9Is',
1690 'title': 'Blue Devils Drumline Stanford lot 2016',
1691 'upload_date': '20160627',
1692 'uploader_id': 'GENOCIDE8GENERAL10',
1693 'uploader': 'cylus cyrus',
1697 # video stored on custom kaltura server
1698 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1699 'md5': '537617d06e64dfed891fa1593c4b30cc',
1703 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1704 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1705 'uploader_id': 'videos.expansion@el-mundo.net',
1706 'upload_date': '20150429',
1707 'timestamp': 1430303472,
1709 'add_ie': ['Kaltura'],
1712 # Non-standard Vimeo embed
1713 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1714 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1718 'title': 'Understanding the web - Teaser',
1719 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1720 'upload_date': '20151214',
1721 'uploader': 'OpenClassrooms',
1722 'uploader_id': 'openclassrooms',
1724 'add_ie': ['Vimeo'],
1727 # generic vimeo embed that requires original URL passed as Referer
1728 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1729 'only_matching': True,
1732 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1733 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1735 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1737 'title': 'Big Buck Bunny',
1738 'description': 'Royalty free test video',
1739 'timestamp': 1432816365,
1740 'upload_date': '20150528',
1744 'skip_download': True,
1746 'add_ie': [ArkenaIE.ie_key()],
1749 '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/',
1753 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1756 'skip_download': True,
1758 'add_ie': [Vbox7IE.ie_key()],
1762 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1765 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1767 'playlist_mincount': 3,
1771 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1773 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1774 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1776 'playlist_mincount': 2,
1780 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1784 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1785 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1788 'skip_download': True,
1790 'add_ie': [TwentyMinutenIE.ie_key()],
1794 'url': 'https://en.support.wordpress.com/videopress/',
1798 'title': 'IMG_5786',
1799 'timestamp': 1435711927,
1800 'upload_date': '20150701',
1803 'skip_download': True,
1805 'add_ie': [VideoPressIE.ie_key()],
1809 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1811 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1813 'title': 'Магаззино: Казань 2',
1814 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1815 'uploader': 'Магаззино',
1816 'upload_date': '20170228',
1817 'uploader_id': '996642',
1820 'skip_download': True,
1822 'add_ie': [RutubeIE.ie_key()],
1825 # ThePlatform embedded with whitespaces in URLs
1826 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1827 'only_matching': True,
1830 # Senate ISVP iframe https
1831 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1832 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1834 'id': 'govtaff020316',
1836 'title': 'Integrated Senate Video Player',
1838 'add_ie': [SenateISVPIE.ie_key()],
1841 # Limelight embeds (1 channel embed + 4 media embeds)
1842 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1844 'id': 'FacilitatorTraining2017',
1845 'title': 'Facilitator Training 2017',
1847 'playlist_mincount': 5,
1850 # Limelight embed (LimelightPlayerUtil.embed)
1851 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1853 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1855 'title': '07448641',
1856 'timestamp': 1499890639,
1857 'upload_date': '20170712',
1860 'skip_download': True,
1862 'add_ie': ['LimelightMedia'],
1865 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1867 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1868 'title': 'Standoff with Walnut Creek murder suspect ends',
1869 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1871 'playlist_mincount': 4,
1874 # WashingtonPost embed
1875 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1877 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1879 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1880 '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.',
1881 'timestamp': 1455216756,
1882 'uploader': 'The Washington Post',
1883 'upload_date': '20160211',
1885 'add_ie': [WashingtonPostIE.ie_key()],
1889 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1893 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1896 'skip_download': True,
1898 'add_ie': [MediasetIE.ie_key()],
1902 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1904 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1905 'title': 'Slovenskom sa prehnala vlna silných búrok',
1907 'playlist_mincount': 5,
1908 'add_ie': [JojIE.ie_key()],
1911 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1912 'url': 'https://tvrain.ru/amp/418921/',
1913 'md5': 'cc00413936695987e8de148b67d14f1d',
1917 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1922 'url': 'http://help.vzaar.com/article/165-embedding-video',
1923 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1927 'title': 'Building A Business Online: Principal Chairs Q & A',
1931 # multiple HTML5 videos on one page
1932 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1934 'id': 'keyscenarios',
1935 'title': 'Rescue Kit 14 Free Edition - Getting started',
1937 'playlist_count': 4,
1941 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1942 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1945 'title': 'vl14062007715967',
1950 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1951 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1953 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1955 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1956 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1957 'timestamp': 1474354800,
1958 'upload_date': '20160920',
1962 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1966 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1967 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1968 'timestamp': 1516100691,
1969 'upload_date': '20180116',
1972 'skip_download': True,
1974 'add_ie': [SpringboardPlatformIE.ie_key()],
1977 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1979 'id': 'uPDB5I9wfp8',
1981 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1982 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1983 'upload_date': '20160219',
1984 'uploader': 'Pocoyo - Português (BR)',
1985 'uploader_id': 'PocoyoBrazil',
1987 'add_ie': [YoutubeIE.ie_key()],
1989 'skip_download': True,
1993 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1995 'id': 'vMDE4NzI1Mjgt690b',
1999 'add_ie': [YapFilesIE.ie_key()],
2001 'skip_download': True,
2005 # CloudflareStream embed
2006 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2008 'id': '31c9291ab41fac05471db4e73aa11717',
2010 'title': '31c9291ab41fac05471db4e73aa11717',
2012 'add_ie': [CloudflareStreamIE.ie_key()],
2014 'skip_download': True,
2019 'url': 'https://joinpeertube.org/fr/home/',
2022 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2024 'playlist_count': 2,
2028 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2032 'title': 'Így kell otthon hamburgert sütni',
2033 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2034 'timestamp': 1426330212,
2035 'upload_date': '20150314',
2036 'uploader': 'StreetKitchen',
2037 'uploader_id': '546363',
2039 'add_ie': [IndavideoEmbedIE.ie_key()],
2041 'skip_download': True,
2045 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2046 'md5': 'b68d276de422ab07ee1d49388103f457',
2049 'title': 'Lock up and get excited',
2052 'skip': 'TODO: fix nested playlists processing in tests',
2055 # # TODO: find another test
2056 # # http://schema.org/VideoObject
2057 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2058 # 'md5': '888dcf08b7ea671381f00fab74692755',
2060 # 'id': 'nyvTSJMKId',
2062 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2063 # 'description': '#love for cats.',
2064 # 'timestamp': 1461244995,
2065 # 'upload_date': '20160421',
2068 # 'force_generic_extractor': True,
2073 def report_following_redirect(self, new_url):
2074 """Report information extraction."""
2075 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2077 def _extract_rss(self, url, video_id, doc):
2078 playlist_title = doc.find('./channel/title').text
2079 playlist_desc_el = doc.find('./channel/description')
2080 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2083 for it in doc.findall('./channel/item'):
2085 enclosure_nodes = it.findall('./enclosure')
2086 for e in enclosure_nodes:
2087 next_url = e.attrib.get('url')
2092 next_url = xpath_text(it, 'link', fatal=False)
2098 '_type': 'url_transparent',
2100 'title': it.find('title').text,
2104 '_type': 'playlist',
2106 'title': playlist_title,
2107 'description': playlist_desc,
2111 def _extract_camtasia(self, url, video_id, webpage):
2112 """ Returns None if no camtasia video can be found. """
2114 camtasia_cfg = self._search_regex(
2115 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2116 webpage, 'camtasia configuration file', default=None)
2117 if camtasia_cfg is None:
2120 title = self._html_search_meta('DC.title', webpage, fatal=True)
2122 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2123 camtasia_cfg = self._download_xml(
2124 camtasia_url, video_id,
2125 note='Downloading camtasia configuration',
2126 errnote='Failed to download camtasia configuration')
2127 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2130 for n in fileset_node.getchildren():
2131 url_n = n.find('./uri')
2136 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2137 'title': '%s - %s' % (title, n.tag),
2138 'url': compat_urlparse.urljoin(url, url_n.text),
2139 'duration': float_or_none(n.find('./duration').text),
2143 '_type': 'playlist',
2148 def _real_extract(self, url):
2149 if url.startswith('//'):
2152 'url': self.http_scheme() + url,
2155 parsed_url = compat_urlparse.urlparse(url)
2156 if not parsed_url.scheme:
2157 default_search = self._downloader.params.get('default_search')
2158 if default_search is None:
2159 default_search = 'fixup_error'
2161 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2163 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2164 return self.url_result('http://' + url)
2165 elif default_search != 'fixup_error':
2166 if default_search == 'auto_warning':
2167 if re.match(r'^(?:url|URL)$', url):
2168 raise ExtractorError(
2169 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2172 self._downloader.report_warning(
2173 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2174 return self.url_result('ytsearch:' + url)
2176 if default_search in ('error', 'fixup_error'):
2177 raise ExtractorError(
2178 '%r is not a valid URL. '
2179 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2180 % (url, url), expected=True)
2182 if ':' not in default_search:
2183 default_search += ':'
2184 return self.url_result(default_search + url)
2186 url, smuggled_data = unsmuggle_url(url)
2187 force_videoid = None
2188 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2189 if smuggled_data and 'force_videoid' in smuggled_data:
2190 force_videoid = smuggled_data['force_videoid']
2191 video_id = force_videoid
2193 video_id = self._generic_id(url)
2195 self.to_screen('%s: Requesting header' % video_id)
2197 head_req = HEADRequest(url)
2198 head_response = self._request_webpage(
2200 note=False, errnote='Could not send HEAD request to %s' % url,
2203 if head_response is not False:
2204 # Check for redirect
2205 new_url = compat_str(head_response.geturl())
2207 self.report_following_redirect(new_url)
2209 new_url = smuggle_url(
2210 new_url, {'force_videoid': force_videoid})
2211 return self.url_result(new_url)
2213 full_response = None
2214 if head_response is False:
2215 request = sanitized_Request(url)
2216 request.add_header('Accept-Encoding', '*')
2217 full_response = self._request_webpage(request, video_id)
2218 head_response = full_response
2222 'title': self._generic_title(url),
2223 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2226 # Check for direct link to a video
2227 content_type = head_response.headers.get('Content-Type', '').lower()
2228 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2230 format_id = compat_str(m.group('format_id'))
2231 if format_id.endswith('mpegurl'):
2232 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2233 elif format_id == 'f4m':
2234 formats = self._extract_f4m_formats(url, video_id)
2237 'format_id': format_id,
2239 'vcodec': 'none' if m.group('type') == 'audio' else None
2241 info_dict['direct'] = True
2242 self._sort_formats(formats)
2243 info_dict['formats'] = formats
2246 if not self._downloader.params.get('test', False) and not is_intentional:
2247 force = self._downloader.params.get('force_generic_extractor', False)
2248 self._downloader.report_warning(
2249 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2251 if not full_response:
2252 request = sanitized_Request(url)
2253 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2254 # making it impossible to download only chunk of the file (yet we need only 512kB to
2255 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2256 # that will always result in downloading the whole file that is not desirable.
2257 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2258 # to accept raw bytes and being able to download only a chunk.
2259 # It may probably better to solve this by checking Content-Type for application/octet-stream
2260 # after HEAD request finishes, but not sure if we can rely on this.
2261 request.add_header('Accept-Encoding', '*')
2262 full_response = self._request_webpage(request, video_id)
2264 first_bytes = full_response.read(512)
2266 # Is it an M3U playlist?
2267 if first_bytes.startswith(b'#EXTM3U'):
2268 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2269 self._sort_formats(info_dict['formats'])
2272 # Maybe it's a direct link to a video?
2273 # Be careful not to download the whole thing!
2274 if not is_html(first_bytes):
2275 self._downloader.report_warning(
2276 'URL could be a direct video link, returning it as such.')
2283 webpage = self._webpage_read_content(
2284 full_response, url, video_id, prefix=first_bytes)
2286 self.report_extraction(video_id)
2288 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2290 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2291 if doc.tag == 'rss':
2292 return self._extract_rss(url, video_id, doc)
2293 elif doc.tag == 'SmoothStreamingMedia':
2294 info_dict['formats'] = self._parse_ism_formats(doc, url)
2295 self._sort_formats(info_dict['formats'])
2297 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2298 smil = self._parse_smil(doc, url, video_id)
2299 self._sort_formats(smil['formats'])
2301 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2302 return self.playlist_result(
2304 doc, video_id, xspf_url=url,
2305 xspf_base_url=compat_str(full_response.geturl())),
2307 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2308 info_dict['formats'] = self._parse_mpd_formats(
2310 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2312 self._sort_formats(info_dict['formats'])
2314 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2315 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2316 self._sort_formats(info_dict['formats'])
2318 except compat_xml_parse_error:
2321 # Is it a Camtasia project?
2322 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2323 if camtasia_res is not None:
2326 # Sometimes embedded video player is hidden behind percent encoding
2327 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2328 # Unescaping the whole page allows to handle those cases in a generic way
2329 webpage = compat_urllib_parse_unquote(webpage)
2331 # it's tempting to parse this further, but you would
2332 # have to take into account all the variations like
2333 # Video Title - Site Name
2334 # Site Name | Video Title
2335 # Video Title - Tagline | Site Name
2336 # and so on and so forth; it's just not practical
2337 video_title = self._og_search_title(
2338 webpage, default=None) or self._html_search_regex(
2339 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2342 # Try to detect age limit automatically
2343 age_limit = self._rta_search(webpage)
2344 # And then there are the jokers who advertise that they use RTA,
2345 # but actually don't.
2346 AGE_LIMIT_MARKERS = [
2347 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2349 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2352 # video uploader is domain name
2353 video_uploader = self._search_regex(
2354 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2356 video_description = self._og_search_description(webpage, default=None)
2357 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2360 'title': video_title,
2361 'description': video_description,
2362 'thumbnail': video_thumbnail,
2363 'age_limit': age_limit,
2366 # Look for Brightcove Legacy Studio embeds
2367 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2371 'url': smuggle_url(bc_url, {'Referer': url}),
2372 'ie_key': 'BrightcoveLegacy'
2373 } for bc_url in bc_urls]
2376 '_type': 'playlist',
2377 'title': video_title,
2382 # Look for Brightcove New Studio embeds
2383 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2385 return self.playlist_from_matches(
2386 bc_urls, video_id, video_title,
2387 getter=lambda x: smuggle_url(x, {'referrer': url}),
2390 # Look for Nexx embeds
2391 nexx_urls = NexxIE._extract_urls(webpage)
2393 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2395 # Look for Nexx iFrame embeds
2396 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2398 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2400 # Look for ThePlatform embeds
2401 tp_urls = ThePlatformIE._extract_urls(webpage)
2403 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2405 # Look for Vessel embeds
2406 vessel_urls = VesselIE._extract_urls(webpage)
2408 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2410 # Look for embedded rtl.nl player
2411 matches = re.findall(
2412 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2415 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2417 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2419 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2421 vid_me_embed_url = self._search_regex(
2422 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2423 webpage, 'vid.me embed', default=None)
2424 if vid_me_embed_url is not None:
2425 return self.url_result(vid_me_embed_url, 'Vidme')
2427 # Look for YouTube embeds
2428 youtube_urls = YoutubeIE._extract_urls(webpage)
2430 return self.playlist_from_matches(
2431 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2433 matches = DailymotionIE._extract_urls(webpage)
2435 return self.playlist_from_matches(matches, video_id, video_title)
2437 # Look for embedded Dailymotion playlist player (#3822)
2439 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2441 playlists = re.findall(
2442 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2444 return self.playlist_from_matches(
2445 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2447 # Look for DailyMail embeds
2448 dailymail_urls = DailyMailIE._extract_urls(webpage)
2450 return self.playlist_from_matches(
2451 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2453 # Look for embedded Wistia player
2454 wistia_url = WistiaIE._extract_url(webpage)
2457 '_type': 'url_transparent',
2458 'url': self._proto_relative_url(wistia_url),
2459 'ie_key': WistiaIE.ie_key(),
2460 'uploader': video_uploader,
2463 # Look for SVT player
2464 svt_url = SVTIE._extract_url(webpage)
2466 return self.url_result(svt_url, 'SVT')
2468 # Look for Bandcamp pages with custom domain
2469 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2470 if mobj is not None:
2471 burl = unescapeHTML(mobj.group(1))
2472 # Don't set the extractor because it can be a track url or an album
2473 return self.url_result(burl)
2475 # Look for embedded Vevo player
2477 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2478 if mobj is not None:
2479 return self.url_result(mobj.group('url'))
2481 # Look for embedded Viddler player
2483 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2485 if mobj is not None:
2486 return self.url_result(mobj.group('url'))
2488 # Look for NYTimes player
2490 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2492 if mobj is not None:
2493 return self.url_result(mobj.group('url'))
2495 # Look for Libsyn player
2497 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2498 if mobj is not None:
2499 return self.url_result(mobj.group('url'))
2501 # Look for Ooyala videos
2502 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2503 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2504 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2505 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2506 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2507 if mobj is not None:
2508 embed_token = self._search_regex(
2509 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2510 webpage, 'ooyala embed token', default=None)
2511 return OoyalaIE._build_url_result(smuggle_url(
2514 'embed_token': embed_token,
2517 # Look for multiple Ooyala embeds on SBN network websites
2518 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2519 if mobj is not None:
2520 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2522 return self.playlist_from_matches(
2523 embeds, video_id, video_title,
2524 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2526 # Look for Aparat videos
2527 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2528 if mobj is not None:
2529 return self.url_result(mobj.group(1), 'Aparat')
2531 # Look for MPORA videos
2532 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2533 if mobj is not None:
2534 return self.url_result(mobj.group(1), 'Mpora')
2536 # Look for embedded NovaMov-based player
2538 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2539 (?P<url>http://(?:(?:embed|www)\.)?
2541 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2542 videoweed\.(?:es|com)|
2543 movshare\.(?:net|sx|ag)|
2544 divxstage\.(?:eu|net|ch|co|at|ag))
2545 /embed\.php.+?)\1''', webpage)
2546 if mobj is not None:
2547 return self.url_result(mobj.group('url'))
2549 # Look for embedded Facebook player
2550 facebook_urls = FacebookIE._extract_urls(webpage)
2552 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2554 # Look for embedded VK player
2555 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2556 if mobj is not None:
2557 return self.url_result(mobj.group('url'), 'VK')
2559 # Look for embedded Odnoklassniki player
2560 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2561 if mobj is not None:
2562 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2564 # Look for embedded ivi player
2565 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2566 if mobj is not None:
2567 return self.url_result(mobj.group('url'), 'Ivi')
2569 # Look for embedded Huffington Post player
2571 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'HuffPost')
2576 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2577 if mobj is not None:
2578 return self.url_result(mobj.group('url'))
2579 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2580 if mobj is not None:
2581 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2583 # Look for funnyordie embed
2584 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2586 return self.playlist_from_matches(
2587 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2589 # Look for BBC iPlayer embed
2590 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2592 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2594 # Look for embedded RUTV player
2595 rutv_url = RUTVIE._extract_url(webpage)
2597 return self.url_result(rutv_url, 'RUTV')
2599 # Look for embedded TVC player
2600 tvc_url = TVCIE._extract_url(webpage)
2602 return self.url_result(tvc_url, 'TVC')
2604 # Look for embedded SportBox player
2605 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2607 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2609 # Look for embedded XHamster player
2610 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2612 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2614 # Look for embedded TNAFlixNetwork player
2615 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2617 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2619 # Look for embedded PornHub player
2620 pornhub_urls = PornHubIE._extract_urls(webpage)
2622 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2624 # Look for embedded DrTuber player
2625 drtuber_urls = DrTuberIE._extract_urls(webpage)
2627 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2629 # Look for embedded RedTube player
2630 redtube_urls = RedTubeIE._extract_urls(webpage)
2632 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2634 # Look for embedded Tube8 player
2635 tube8_urls = Tube8IE._extract_urls(webpage)
2637 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2639 # Look for embedded Tvigle player
2641 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2642 if mobj is not None:
2643 return self.url_result(mobj.group('url'), 'Tvigle')
2645 # Look for embedded TED player
2647 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'), 'TED')
2651 # Look for embedded Ustream videos
2652 ustream_url = UstreamIE._extract_url(webpage)
2654 return self.url_result(ustream_url, UstreamIE.ie_key())
2656 # Look for embedded arte.tv player
2658 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2660 if mobj is not None:
2661 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2663 # Look for embedded francetv player
2665 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2667 if mobj is not None:
2668 return self.url_result(mobj.group('url'))
2670 # Look for embedded smotri.com player
2671 smotri_url = SmotriIE._extract_url(webpage)
2673 return self.url_result(smotri_url, 'Smotri')
2675 # Look for embedded Myvi.ru player
2676 myvi_url = MyviIE._extract_url(webpage)
2678 return self.url_result(myvi_url)
2680 # Look for embedded soundcloud player
2681 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2683 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2685 # Look for tunein player
2686 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2688 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2690 # Look for embedded mtvservices player
2691 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2693 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2695 # Look for embedded yahoo player
2697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2699 if mobj is not None:
2700 return self.url_result(mobj.group('url'), 'Yahoo')
2702 # Look for embedded sbs.com.au player
2706 <meta\s+property="og:video"\s+content=|
2709 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2711 if mobj is not None:
2712 return self.url_result(mobj.group('url'), 'SBS')
2714 # Look for embedded Cinchcast player
2716 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2718 if mobj is not None:
2719 return self.url_result(mobj.group('url'), 'Cinchcast')
2722 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2726 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2728 if mobj is not None:
2729 return self.url_result(mobj.group('url'), 'MLB')
2732 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2734 if mobj is not None:
2735 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2738 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2740 if mobj is not None:
2741 return self.url_result(mobj.group('url'), 'Livestream')
2743 # Look for Zapiks embed
2745 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2746 if mobj is not None:
2747 return self.url_result(mobj.group('url'), 'Zapiks')
2749 # Look for Kaltura embeds
2750 kaltura_url = KalturaIE._extract_url(webpage)
2752 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2754 # Look for EaglePlatform embeds
2755 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2756 if eagleplatform_url:
2757 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2759 # Look for ClipYou (uses EaglePlatform) embeds
2761 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2762 if mobj is not None:
2763 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2765 # Look for Pladform embeds
2766 pladform_url = PladformIE._extract_url(webpage)
2768 return self.url_result(pladform_url)
2770 # Look for Videomore embeds
2771 videomore_url = VideomoreIE._extract_url(webpage)
2773 return self.url_result(videomore_url)
2775 # Look for Webcaster embeds
2776 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2778 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2780 # Look for Playwire embeds
2782 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2783 if mobj is not None:
2784 return self.url_result(mobj.group('url'))
2786 # Look for 5min embeds
2788 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2789 if mobj is not None:
2790 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2792 # Look for Crooks and Liars embeds
2794 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2795 if mobj is not None:
2796 return self.url_result(mobj.group('url'))
2798 # Look for NBC Sports VPlayer embeds
2799 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2801 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2803 # Look for NBC News embeds
2804 nbc_news_embed_url = re.search(
2805 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2806 if nbc_news_embed_url:
2807 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2809 # Look for Google Drive embeds
2810 google_drive_url = GoogleDriveIE._extract_url(webpage)
2811 if google_drive_url:
2812 return self.url_result(google_drive_url, 'GoogleDrive')
2814 # Look for UDN embeds
2816 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2817 if mobj is not None:
2818 return self.url_result(
2819 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2821 # Look for Senate ISVP iframe
2822 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2824 return self.url_result(senate_isvp_url, 'SenateISVP')
2826 # Look for OnionStudios embeds
2827 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2828 if onionstudios_url:
2829 return self.url_result(onionstudios_url)
2831 # Look for ViewLift embeds
2832 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2834 return self.url_result(viewlift_url)
2836 # Look for JWPlatform embeds
2837 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2839 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2841 # Look for Digiteka embeds
2842 digiteka_url = DigitekaIE._extract_url(webpage)
2844 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2846 # Look for Arkena embeds
2847 arkena_url = ArkenaIE._extract_url(webpage)
2849 return self.url_result(arkena_url, ArkenaIE.ie_key())
2851 # Look for Piksel embeds
2852 piksel_url = PikselIE._extract_url(webpage)
2854 return self.url_result(piksel_url, PikselIE.ie_key())
2856 # Look for Limelight embeds
2857 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2859 return self.playlist_result(
2860 limelight_urls, video_id, video_title, video_description)
2862 # Look for Anvato embeds
2863 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2865 return self.playlist_result(
2866 anvato_urls, video_id, video_title, video_description)
2868 # Look for AdobeTVVideo embeds
2870 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2872 if mobj is not None:
2873 return self.url_result(
2874 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2877 # Look for Vine embeds
2879 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2881 if mobj is not None:
2882 return self.url_result(
2883 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2885 # Look for VODPlatform embeds
2887 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2889 if mobj is not None:
2890 return self.url_result(
2891 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2893 # Look for Mangomolo embeds
2895 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2897 video\?.*?\bid=(?P<video_id>\d+)|
2898 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2899 ).+?)\1''', webpage)
2900 if mobj is not None:
2902 '_type': 'url_transparent',
2903 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2904 'title': video_title,
2905 'description': video_description,
2906 'thumbnail': video_thumbnail,
2907 'uploader': video_uploader,
2909 video_id = mobj.group('video_id')
2912 'ie_key': 'MangomoloVideo',
2917 'ie_key': 'MangomoloLive',
2918 'id': mobj.group('channel_id'),
2922 # Look for Instagram embeds
2923 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2924 if instagram_embed_url is not None:
2925 return self.url_result(
2926 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2928 # Look for LiveLeak embeds
2929 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2931 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2933 # Look for 3Q SDN embeds
2934 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2937 '_type': 'url_transparent',
2938 'ie_key': ThreeQSDNIE.ie_key(),
2939 'url': self._proto_relative_url(threeqsdn_url),
2940 'title': video_title,
2941 'description': video_description,
2942 'thumbnail': video_thumbnail,
2943 'uploader': video_uploader,
2946 # Look for VBOX7 embeds
2947 vbox7_url = Vbox7IE._extract_url(webpage)
2949 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2951 # Look for DBTV embeds
2952 dbtv_urls = DBTVIE._extract_urls(webpage)
2954 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2956 # Look for Videa embeds
2957 videa_urls = VideaIE._extract_urls(webpage)
2959 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2961 # Look for 20 minuten embeds
2962 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2964 return self.playlist_from_matches(
2965 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2967 # Look for Openload embeds
2968 openload_urls = OpenloadIE._extract_urls(webpage)
2970 return self.playlist_from_matches(
2971 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2973 # Look for VideoPress embeds
2974 videopress_urls = VideoPressIE._extract_urls(webpage)
2976 return self.playlist_from_matches(
2977 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2979 # Look for Rutube embeds
2980 rutube_urls = RutubeIE._extract_urls(webpage)
2982 return self.playlist_from_matches(
2983 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2985 # Look for WashingtonPost embeds
2986 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2988 return self.playlist_from_matches(
2989 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2991 # Look for Mediaset embeds
2992 mediaset_urls = MediasetIE._extract_urls(webpage)
2994 return self.playlist_from_matches(
2995 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2997 # Look for JOJ.sk embeds
2998 joj_urls = JojIE._extract_urls(webpage)
3000 return self.playlist_from_matches(
3001 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3003 # Look for megaphone.fm embeds
3004 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3006 return self.playlist_from_matches(
3007 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3009 # Look for vzaar embeds
3010 vzaar_urls = VzaarIE._extract_urls(webpage)
3012 return self.playlist_from_matches(
3013 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3015 channel9_urls = Channel9IE._extract_urls(webpage)
3017 return self.playlist_from_matches(
3018 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3020 vshare_urls = VShareIE._extract_urls(webpage)
3022 return self.playlist_from_matches(
3023 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3025 # Look for Mediasite embeds
3026 mediasite_urls = MediasiteIE._extract_urls(webpage)
3029 self.url_result(smuggle_url(
3030 compat_urlparse.urljoin(url, mediasite_url),
3031 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3032 for mediasite_url in mediasite_urls]
3033 return self.playlist_result(entries, video_id, video_title)
3035 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3036 if springboardplatform_urls:
3037 return self.playlist_from_matches(
3038 springboardplatform_urls, video_id, video_title,
3039 ie=SpringboardPlatformIE.ie_key())
3041 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3043 return self.playlist_from_matches(
3044 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3046 vice_urls = ViceIE._extract_urls(webpage)
3048 return self.playlist_from_matches(
3049 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3051 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3053 return self.playlist_from_matches(
3054 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3056 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3057 if cloudflarestream_urls:
3058 return self.playlist_from_matches(
3059 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3061 peertube_urls = PeerTubeIE._extract_urls(webpage)
3063 return self.playlist_from_matches(
3064 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3066 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3068 return self.playlist_from_matches(
3069 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3071 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3072 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3074 if sharevideos_urls:
3075 return self.playlist_from_matches(
3076 sharevideos_urls, video_id, video_title)
3078 # Look for HTML5 media
3079 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3081 if len(entries) == 1:
3084 'title': video_title,
3087 for num, entry in enumerate(entries, start=1):
3089 'id': '%s-%s' % (video_id, num),
3090 'title': '%s (%d)' % (video_title, num),
3092 for entry in entries:
3093 self._sort_formats(entry['formats'])
3094 return self.playlist_result(entries, video_id, video_title)
3096 jwplayer_data = self._find_jwplayer_data(
3097 webpage, video_id, transform_source=js_to_json)
3099 info = self._parse_jwplayer_data(
3100 jwplayer_data, video_id, require_title=False, base_url=url)
3101 return merge_dicts(info, info_dict)
3105 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3107 if mobj is not None:
3108 sources = self._parse_json(
3109 mobj.group(1), video_id, transform_source=js_to_json,
3111 if not isinstance(sources, list):
3114 for source in sources:
3115 src = source.get('src')
3116 if not src or not isinstance(src, compat_str):
3118 src = compat_urlparse.urljoin(url, src)
3119 src_type = source.get('type')
3120 if isinstance(src_type, compat_str):
3121 src_type = src_type.lower()
3122 ext = determine_ext(src).lower()
3123 if src_type == 'video/youtube':
3124 return self.url_result(src, YoutubeIE.ie_key())
3125 if src_type == 'application/dash+xml' or ext == 'mpd':
3126 formats.extend(self._extract_mpd_formats(
3127 src, video_id, mpd_id='dash', fatal=False))
3128 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3129 formats.extend(self._extract_m3u8_formats(
3130 src, video_id, 'mp4', entry_protocol='m3u8_native',
3131 m3u8_id='hls', fatal=False))
3135 'ext': (mimetype2ext(src_type) or
3136 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3139 self._sort_formats(formats)
3140 info_dict['formats'] = formats
3143 # Looking for http://schema.org/VideoObject
3144 json_ld = self._search_json_ld(
3145 webpage, video_id, default={}, expected_type='VideoObject')
3146 if json_ld.get('url'):
3147 return merge_dicts(json_ld, info_dict)
3149 def check_video(vurl):
3150 if YoutubeIE.suitable(vurl):
3152 if RtmpIE.suitable(vurl):
3154 vpath = compat_urlparse.urlparse(vurl).path
3155 vext = determine_ext(vpath)
3156 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3158 def filter_video(urls):
3159 return list(filter(check_video, urls))
3161 # Start with something easy: JW Player in SWFObject
3162 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3164 # Look for gorilla-vid style embedding
3165 found = filter_video(re.findall(r'''(?sx)
3169 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3172 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3174 # Broaden the search a little bit
3175 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3177 # Broaden the findall a little bit: JWPlayer JS loader
3178 found = filter_video(re.findall(
3179 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3182 found = filter_video(re.findall(r'''(?xs)
3183 flowplayer\("[^"]+",\s*
3185 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3186 ["']?url["']?\s*:\s*["']([^"']+)["']
3191 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3193 # Try to find twitter cards info
3194 # twitter:player:stream should be checked before twitter:player since
3195 # it is expected to contain a raw stream (see
3196 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3197 found = filter_video(re.findall(
3198 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3200 # We look for Open Graph info:
3201 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3202 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3203 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3204 if m_video_type is not None:
3205 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3207 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3209 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3210 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3213 # Look also in Refresh HTTP header
3214 refresh_header = head_response.headers.get('Refresh')
3216 # In python 2 response HTTP headers are bytestrings
3217 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3218 refresh_header = refresh_header.decode('iso-8859-1')
3219 found = re.search(REDIRECT_REGEX, refresh_header)
3221 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3223 self.report_following_redirect(new_url)
3232 # twitter:player is a https URL to iframe player that may or may not
3233 # be supported by youtube-dl thus this is checked the very last (see
3234 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3235 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3236 if embed_url and embed_url != url:
3237 return self.url_result(embed_url)
3240 raise UnsupportedError(url)
3243 for video_url in orderedSet(found):
3244 video_url = unescapeHTML(video_url)
3245 video_url = video_url.replace('\\/', '/')
3246 video_url = compat_urlparse.urljoin(url, video_url)
3247 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3249 # Sometimes, jwplayer extraction will result in a YouTube URL
3250 if YoutubeIE.suitable(video_url):
3251 entries.append(self.url_result(video_url, 'Youtube'))
3254 # here's a fun little line of code for you:
3255 video_id = os.path.splitext(video_id)[0]
3259 'uploader': video_uploader,
3260 'title': video_title,
3261 'age_limit': age_limit,
3264 if RtmpIE.suitable(video_url):
3265 entry_info_dict.update({
3266 '_type': 'url_transparent',
3267 'ie_key': RtmpIE.ie_key(),
3270 entries.append(entry_info_dict)
3273 ext = determine_ext(video_url)
3275 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3277 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3279 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3281 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3283 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3284 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3285 # Just matching .ism/manifest is not enough to be reliably sure
3286 # whether it's actually an ISM manifest or some other streaming
3287 # manifest since there are various streaming URL formats
3288 # possible (see [1]) as well as some other shenanigans like
3289 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3291 # Thus the most reasonable way to solve this is to delegate
3292 # to generic extractor in order to look into the contents of
3293 # the manifest itself.
3294 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3295 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3296 entry_info_dict = self.url_result(
3297 smuggle_url(video_url, {'to_generic': True}),
3300 entry_info_dict['url'] = video_url
3302 if entry_info_dict.get('formats'):
3303 self._sort_formats(entry_info_dict['formats'])
3305 entries.append(entry_info_dict)
3307 if len(entries) == 1:
3310 for num, e in enumerate(entries, start=1):
3311 # 'url' results don't have a title
3312 if e.get('title') is not None:
3313 e['title'] = '%s (%d)' % (e['title'], num)
3315 '_type': 'playlist',