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 SportBoxIE
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 .teachable import TeachableIE
113 from .indavideo import IndavideoEmbedIE
114 from .apa import APAIE
115 from .foxnews import FoxNewsIE
116 from .viqeo import ViqeoIE
117 from .expressen import ExpressenIE
118 from .zype import ZypeIE
121 class GenericIE(InfoExtractor):
122 IE_DESC = 'Generic downloader that works on some sites'
126 # Direct link to a video
128 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
129 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
134 'upload_date': '20100513',
137 # Direct link to media delivered compressed (until Accept-Encoding is *)
139 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
140 'md5': '128c42e68b13950268b648275386fc74',
142 'id': 'FictionJunction-Parallel_Hearts',
144 'title': 'FictionJunction-Parallel_Hearts',
145 'upload_date': '20140522',
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
150 'skip': 'URL invalid',
152 # Direct download with broken HEAD
154 'url': 'http://ai-radio.org:8000/radio.opus',
161 'skip_download': True, # infinite live stream
163 'expected_warnings': [
164 r'501.*Not Implemented',
168 # Direct link with incorrect MIME type
170 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
171 'md5': '4ccbebe5f36706d85221f204d7eb5913',
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'id': '5_Lennart_Poettering_-_Systemd',
176 'title': '5_Lennart_Poettering_-_Systemd',
177 'upload_date': '20141120',
179 'expected_warnings': [
180 'URL could be a direct video link, returning it as such.'
185 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
187 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
188 'title': 'Zero Punctuation',
189 'description': 're:.*groundbreaking video review series.*'
191 'playlist_mincount': 11,
193 # RSS feed with enclosure
195 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
197 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
199 'upload_date': '20150228',
200 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
203 # RSS feed with enclosures and unsupported link URLs
205 'url': 'http://www.hellointernet.fm/podcast?format=rss',
207 'id': 'http://www.hellointernet.fm/podcast?format=rss',
208 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
209 'title': 'Hello Internet',
211 'playlist_mincount': 100,
213 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
215 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
219 'title': 'Automatics, robotics and biocybernetics',
220 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
221 'upload_date': '20130627',
222 'formats': 'mincount:16',
223 'subtitles': 'mincount:1',
226 'force_generic_extractor': True,
227 'skip_download': True,
230 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
232 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
237 'formats': 'mincount:1',
240 'skip_download': True,
243 # SMIL from https://www.restudy.dk/video/play/id/1637
245 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
249 'title': 'video_1637',
250 'formats': 'mincount:3',
253 'skip_download': True,
256 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
258 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
260 'id': 'smil-service',
262 'title': 'smil-service',
263 'formats': 'mincount:1',
266 'skip_download': True,
269 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
271 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
275 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
276 'formats': 'mincount:3',
279 'skip_download': True,
282 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
284 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
286 'id': 'mZlp2ctYIUEB',
288 'title': 'Tikibad ontruimd wegens brand',
289 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
290 'thumbnail': r're:^https?://.*\.jpg$',
294 'skip_download': True,
297 # MPD from http://dash-mse-test.appspot.com/media.html
299 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
300 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
302 'id': 'car-20120827-manifest',
304 'title': 'car-20120827-manifest',
305 'formats': 'mincount:9',
306 'upload_date': '20130904',
309 'format': 'bestvideo',
312 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
314 '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',
319 'formats': 'mincount:8',
323 'skip_download': True,
325 'skip': 'video gone',
327 # m3u8 served with Content-Type: text/plain
329 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
334 'upload_date': '20140720',
335 'formats': 'mincount:11',
339 'skip_download': True,
341 'skip': 'video gone',
345 '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',
349 'upload_date': '20130224',
350 'uploader_id': 'TheVerge',
351 'description': r're:^Chris Ziegler takes a look at the\.*',
352 'uploader': 'The Verge',
353 'title': 'First Firefox OS phones side-by-side',
356 'skip_download': False,
360 # redirect in Refresh HTTP header
361 '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',
365 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
366 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
367 'upload_date': '20150917',
368 'uploader_id': 'brtvofficial',
369 'uploader': 'Boiler Room',
372 'skip_download': False,
376 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
377 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
379 'id': '13601338388002',
381 'uploader': 'www.hodiho.fr',
382 'title': 'R\u00e9gis plante sa Jeep',
385 # bandcamp page with custom domain
387 'add_ie': ['Bandcamp'],
388 'url': 'http://bronyrock.com/track/the-pony-mash',
392 'title': 'The Pony Mash',
393 'uploader': 'M_Pallante',
395 'skip': 'There is a limit of 200 free downloads / month for the test song',
398 # embedded brightcove video
399 # it also tests brightcove videos that need to set the 'Referer'
400 # in the http requests
401 'add_ie': ['BrightcoveLegacy'],
402 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
404 'id': '2765128793001',
406 'title': 'Le cours de bourse : l’analyse technique',
407 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
408 'uploader': 'BFM BUSINESS',
411 'skip_download': True,
415 # embedded with itemprop embedURL and video id spelled as `idVideo`
416 'add_id': ['BrightcoveLegacy'],
417 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
419 'id': '5255628253001',
421 'title': 'md5:37c519b1128915607601e75a87995fc0',
422 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
423 'uploader': 'BFM BUSINESS',
424 'uploader_id': '876450612001',
425 'timestamp': 1482255315,
426 'upload_date': '20161220',
429 'skip_download': True,
433 # https://github.com/rg3/youtube-dl/issues/2253
434 'url': 'http://bcove.me/i6nfkrc3',
435 'md5': '0ba9446db037002366bab3b3eb30c88c',
437 'id': '3101154703001',
439 'title': 'Still no power',
440 'uploader': 'thestar.com',
441 '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.',
443 'add_ie': ['BrightcoveLegacy'],
444 'skip': 'video gone',
447 'url': 'http://www.championat.com/video/football/v/87/87499.html',
448 'md5': 'fb973ecf6e4a78a67453647444222983',
450 'id': '3414141473001',
452 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
453 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
454 'uploader': 'Championat',
458 # https://github.com/rg3/youtube-dl/issues/3541
459 'add_ie': ['BrightcoveLegacy'],
460 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
462 'id': '3866516442001',
464 'title': 'Leer mij vrouwen kennen: Aflevering 1',
465 'description': 'Leer mij vrouwen kennen: Aflevering 1',
466 'uploader': 'SBS Broadcasting',
468 'skip': 'Restricted to Netherlands',
470 'skip_download': True, # m3u8 download
474 # Brightcove video in <iframe>
475 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
476 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
478 'id': '5360463607001',
480 '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',
481 '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。',
482 'uploader': 'United Nations',
483 'uploader_id': '1362235914001',
484 'timestamp': 1489593889,
485 'upload_date': '20170315',
487 'add_ie': ['BrightcoveLegacy'],
490 # Brightcove with alternative playerID key
491 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
493 'id': 'nmeth.2062_SV1',
494 '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',
498 'id': '2228375078001',
500 'title': 'nmeth.2062-sv1',
501 'description': 'nmeth.2062-sv1',
502 'timestamp': 1363357591,
503 'upload_date': '20130315',
504 'uploader': 'Nature Publishing Group',
505 'uploader_id': '1964492299001',
510 # Brightcove with UUID in videoPlayer
511 'url': 'http://www8.hp.com/cn/zh/home.html',
513 'id': '5255815316001',
515 'title': 'Sprocket Video - China',
516 'description': 'Sprocket Video - China',
517 'uploader': 'HP-Video Gallery',
518 'timestamp': 1482263210,
519 'upload_date': '20161220',
520 'uploader_id': '1107601872001',
523 'skip_download': True, # m3u8 download
525 'skip': 'video rotates...weekly?',
528 # Brightcove:new type [2].
529 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
530 'md5': '2b35148fcf48da41c9fb4591650784f3',
532 'id': '5348741021001',
534 'upload_date': '20170306',
535 'uploader_id': '4191638492001',
536 'timestamp': 1488769918,
537 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
542 # Alternative brightcove <video> attributes
543 '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/',
545 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
546 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
549 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
551 'id': '5311302538001',
553 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
554 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
555 'timestamp': 1486321708,
556 'upload_date': '20170205',
557 'uploader_id': '800000640001',
559 'only_matching': True,
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
566 'id': '5255815316001',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
576 'skip_download': True, # m3u8 download
581 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
582 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
584 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
586 'title': '2cc213299525360.mov', # that's what we get
589 'add_ie': ['Ooyala'],
592 # ooyala video embedded with http://player.ooyala.com/iframe.js
593 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
595 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
597 'title': '"Steve Jobs: Man in the Machine" trailer',
598 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
602 'skip_download': True,
604 'skip': 'movie expired',
606 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
608 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
610 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
612 'title': 'Steampunk Fest Comes to Honesdale',
616 'skip_download': True,
621 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
625 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
626 'upload_date': '20140225',
627 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
628 'uploader': 'Tested',
629 'uploader_id': 'testedcom',
631 # No need to test YoutubeIE here
633 'skip_download': True,
638 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
642 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
643 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
645 # HEAD requests lead to endless 301, while GET is OK
646 'expected_warnings': ['301'],
650 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
654 'title': 'Охотское море стало целиком российским',
655 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
659 'skip_download': True,
664 '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/',
668 'title': 'Дошкольное воспитание',
673 'url': 'http://www.vestifinance.ru/articles/25753',
676 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
681 'title': 'Госзаказ. День 3',
687 'title': 'Госзаказ. День 2',
693 'title': 'Госзаказ. День 1',
699 'skip_download': True,
704 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
706 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
708 'title': 'Ужастики, русский трейлер (2015)',
709 'thumbnail': r're:^https?://.*\.jpg$',
715 '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',
718 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
720 'playlist_mincount': 7,
721 # This forum does not allow <iframe> syntaxes anymore
722 # Now HTML tags are displayed as-is
723 'skip': 'No videos on this page',
727 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
728 'md5': '65fdff94098e4a607385a60c5177c638',
732 'title': 'Hidden miracles of the natural world',
733 'uploader': 'Louie Schwartzberg',
734 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
737 # nowvideo embed hidden behind percent encoding
739 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
740 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
742 'id': '06e53103ca9aa',
744 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
745 'description': 'No description',
750 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
751 'md5': '7653032cbb25bf6c80d80f217055fa43',
753 'id': '048195-004_PLUS7-F',
756 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
757 'upload_date': '20140320',
760 'skip_download': 'Requires rtmpdump'
762 'skip': 'video gone',
766 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
770 'title': 'Alcaline, le concert avec Calogero',
771 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
772 'upload_date': '20150226',
773 'timestamp': 1424989860,
778 'skip_download': True,
780 'expected_warnings': [
786 'url': 'http://www.wired.com/2014/04/honda-asimo/',
787 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
789 'id': '53501be369702d3275860000',
791 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
796 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
797 'md5': '441aeeb82eb72c422c7f14ec533999cd',
799 'id': 'k2mm4bCdJ6CQ2i7c8o2',
801 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
802 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
804 'uploader_id': 'xgditw',
805 'upload_date': '20140425',
806 'timestamp': 1398441542,
808 'add_ie': ['Dailymotion'],
812 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
816 'title': 'Care worker punches elderly dementia patient in head 11 times',
817 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
819 'add_ie': ['DailyMail'],
821 'skip_download': True,
826 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
830 'title': 'The NBL Auction 2014',
831 'uploader': 'BADMINTON England',
832 'uploader_id': 'BADMINTONEvents',
833 'upload_date': '20140603',
834 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
836 'add_ie': ['Youtube'],
838 'skip_download': True,
843 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
844 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
846 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
848 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
849 'description': 'Two valets share their love for movie star Liam Neesons.',
850 'timestamp': 1349922600,
851 'upload_date': '20121011',
854 # YouTube embed via <data-embed-url="">
856 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
860 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
861 'uploader': 'Gameloft',
862 'uploader_id': 'gameloft',
863 'upload_date': '20140828',
864 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
867 'skip_download': True,
870 # YouTube <object> embed
872 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
873 'md5': '516718101ec834f74318df76259fb3cc',
877 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
878 'upload_date': '20080526',
879 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
880 'uploader': 'Christopher Sykes',
881 'uploader_id': 'ChristopherJSykes',
883 'add_ie': ['Youtube'],
887 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
889 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
897 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
899 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
906 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
911 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
912 'md5': '9d65602bf31c6e20014319c7d07fba27',
914 'id': '5123ea6d5e5a7',
917 'uploader': 'www.handjobhub.com',
918 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
921 # Multiple brightcove videos
922 # https://github.com/rg3/youtube-dl/issues/2283
924 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
926 'id': 'always-never',
927 'title': 'Always / Never - The New Yorker',
931 'extract_flat': False,
932 'skip_download': True,
937 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
938 'md5': '96f09a37e44da40dd083e12d9a683327',
942 'title': 'Ump changes call to ball',
943 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
945 'timestamp': 1401537900,
946 'upload_date': '20140531',
947 'thumbnail': r're:^https?://.*\.jpg$',
952 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
953 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
957 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
958 'description': 'a Paywall Videos video from Remilon',
960 'uploader': 'study.com',
961 'timestamp': 1459678540,
962 'upload_date': '20160403',
963 'filesize': 24687186,
967 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
968 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
972 'title': 'Conversation about Hexagonal Rails Part 1',
973 'description': 'a Martin Fowler video from ThoughtWorks',
975 'uploader': 'thoughtworks.wistia.com',
976 'timestamp': 1401832161,
977 'upload_date': '20140603',
980 # Wistia standard embed (async)
982 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
986 'title': 'Drip Brennan Dunn Workshop',
987 'description': 'a JV Webinars video from getdrip-1',
989 'timestamp': 1463607249,
990 'upload_date': '20160518',
993 'skip_download': True,
998 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1002 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1003 'uploader': 'Sophos Security',
1004 'title': 'Chet Chat 171 - Oct 29, 2014',
1005 'upload_date': '20141029',
1008 # Soundcloud multiple embeds
1010 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1013 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1015 'playlist_mincount': 7,
1017 # TuneIn station embed
1019 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1024 'location': 'Paris, France',
1029 'skip_download': True,
1034 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1038 'upload_date': '20141112',
1039 'title': 'Rosetta #CometLanding webcast HL 10',
1042 # Another Livestream embed, without 'new.' in URL
1044 'url': 'https://www.freespeech.org/',
1048 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1052 'skip_download': True,
1057 'url': 'https://skiplagged.com/',
1060 'title': 'Skiplagged: The smart way to find cheap flights',
1062 'playlist_mincount': 1,
1063 'add_ie': ['Youtube'],
1067 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1071 'upload_date': '20141126',
1072 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1077 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1079 'id': '730m_DandD_1901_512k',
1081 'uploader': 'www.abc.net.au',
1082 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1085 # embedded viddler video
1087 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1091 'uploader': 'deadspin',
1092 'title': 'WALL-TO-GORTAT',
1093 'timestamp': 1422285291,
1094 'upload_date': '20150126',
1096 'add_ie': ['Viddler'],
1100 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1104 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1105 'description': 'md5:601cb790edd05908957dae8aaa866465',
1106 'upload_date': '20150220',
1108 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1112 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1114 'id': 'Mrj4DVp2zeA',
1116 'upload_date': '20150212',
1117 'uploader': 'The National Archives UK',
1118 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1119 'uploader_id': 'NationalArchives08',
1120 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1125 'url': 'http://www.suffolk.edu/sjc/live.php',
1129 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1130 'uploader': 'www.suffolk.edu',
1133 'skip_download': True,
1135 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1139 'url': 'http://www.indiedb.com/games/king-machine/videos',
1143 'title': 'king machine trailer 1',
1144 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1145 'thumbnail': r're:^https?://.*\.jpg$',
1149 # JWPlayer config passed as variable
1150 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1154 'title': 'ARIELE | Tube Cup',
1155 'uploader': 'www.txxx.com',
1159 'skip_download': True,
1164 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1165 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1169 'upload_date': '20171122',
1170 'timestamp': 1511366290,
1171 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1173 'add_ie': [JWPlatformIE.ie_key()],
1176 # Video.js embed, multiple formats
1177 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1179 'id': 'yygqldloqIk',
1181 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1182 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1183 'upload_date': '20130314',
1184 'uploader': 'PROстое3D',
1185 'uploader_id': 'PROstoe3D',
1188 'skip_download': True,
1192 # Video.js embed, single format
1193 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1197 'title': 'Step 1 - Good Foundation',
1198 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1201 'skip_download': True,
1206 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1207 'playlist_mincount': 5,
1209 'id': 'aanslagen-kopenhagen',
1210 'title': 'Aanslagen Kopenhagen',
1215 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1219 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1222 # Kaltura embed (different embed code)
1224 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1228 'upload_date': '20150127',
1229 'uploader_id': 'PremierMedia',
1231 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1234 # Kaltura embed with single quotes
1236 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1241 'timestamp': 1355743100,
1242 'upload_date': '20121217',
1243 'uploader_id': 'cplapp@learn360.com',
1245 'add_ie': ['Kaltura'],
1248 # Kaltura embedded via quoted entry_id
1249 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1253 'title': '06_matthew_brender_raj_dutt',
1254 'timestamp': 1466638791,
1255 'upload_date': '20160622',
1257 'add_ie': ['Kaltura'],
1258 'expected_warnings': [
1259 'Could not send HEAD request'
1262 'skip_download': True,
1266 # Kaltura embedded, some fileExt broken (#11480)
1267 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1271 'title': 'Our "Standard Models" of particle physics and cosmology',
1272 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1273 'timestamp': 1321158993,
1274 'upload_date': '20111113',
1275 'uploader_id': 'kps1',
1277 'add_ie': ['Kaltura'],
1280 # Kaltura iframe embed
1281 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1282 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1286 'title': 'I. M. Pei: A Centennial Celebration',
1287 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1288 'upload_date': '20170403',
1289 'uploader_id': 'batchUser',
1290 'timestamp': 1491232186,
1292 'add_ie': ['Kaltura'],
1295 # Kaltura iframe embed, more sophisticated
1296 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1300 'title': 'lecture-05sep2017',
1301 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1302 'upload_date': '20170913',
1303 'uploader_id': 'eps2',
1304 'timestamp': 1505340777,
1307 'skip_download': True,
1309 'add_ie': ['Kaltura'],
1312 # meta twitter:player
1313 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1317 'title': 'Main Twerk (Video)',
1318 'upload_date': '20171208',
1319 'uploader_id': 'sebastian.salinas@thechive.com',
1320 'timestamp': 1512713057,
1323 'skip_download': True,
1325 'add_ie': ['Kaltura'],
1327 # referrer protected EaglePlatform embed
1329 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1333 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1334 'thumbnail': r're:^https?://.*\.jpg$',
1339 'skip_download': True,
1342 # ClipYou (EaglePlatform) embed (custom URL)
1344 'url': 'http://muz-tv.ru/play/7129/',
1345 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1349 'title': "'O Sole Mio",
1350 'thumbnail': r're:^https?://.*\.jpg$',
1355 'skip_download': True,
1357 'skip': 'This video is unavailable.',
1361 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1365 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1366 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1367 'thumbnail': r're:^https?://.*\.jpg$',
1371 'skip': 'HTTP Error 404: Not Found',
1375 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1379 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1380 'thumbnail': r're:^https?://.*\.png$',
1386 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1387 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1391 'title': 'Facebook Creates "On This Day" | Crunch Report',
1392 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1393 'timestamp': 1427237531,
1394 'uploader': 'Crunch Report',
1395 'upload_date': '20150324',
1399 'skip_download': True,
1402 # Crooks and Liars embed
1404 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1408 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1409 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1410 'timestamp': 1428207000,
1411 'upload_date': '20150405',
1412 'uploader': 'Heather',
1415 # Crooks and Liars external embed
1417 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1419 'id': 'MTE3MjUtMzQ2MzA',
1421 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1422 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1423 'timestamp': 1265032391,
1424 'upload_date': '20100201',
1425 'uploader': 'Heather',
1428 # NBC Sports vplayer embed
1430 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1432 'id': 'ln7x1qSThw4k',
1434 'title': "PFT Live: New leader in the 'new-look' defense",
1435 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1436 'uploader': 'NBCU-SPORTS',
1437 'upload_date': '20140107',
1438 'timestamp': 1389118457,
1440 'skip': 'Invalid Page URL',
1444 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1445 'md5': '1aa589c675898ae6d37a17913cf68d66',
1447 'id': 'x_dtl_oa_LettermanliftPR_160608',
1449 'title': 'David Letterman: A Preview',
1450 '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.',
1451 'upload_date': '20160609',
1452 'timestamp': 1465431544,
1453 'uploader': 'NBCU-NEWS',
1458 'url': 'https://video.udn.com/news/300346',
1459 'md5': 'fd2060e988c326991037b9aff9df21a6',
1463 'title': '中一中男師變性 全校師生力挺',
1464 'thumbnail': r're:^https?://.*\.jpg$',
1468 'skip_download': True,
1470 'expected_warnings': ['Failed to parse JSON Expecting value'],
1472 # Brightcove URL in single quotes
1474 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1475 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1477 'id': '4255764656001',
1479 'title': 'SN Presents: Russell Martin, World Citizen',
1480 '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.',
1481 'uploader': 'Rogers Sportsnet',
1482 'uploader_id': '1704050871',
1483 'upload_date': '20150525',
1484 'timestamp': 1432570283,
1487 # OnionStudios embed
1489 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1494 'thumbnail': r're:^https?://.*\.jpe?g$',
1495 'uploader': 'ClickHole',
1496 'uploader_id': 'clickhole',
1501 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1503 'id': '74849a00-85a9-11e1-9660-123139220831',
1505 'title': '#whilewewatch',
1508 # AdobeTVVideo embed
1510 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1511 'md5': '43662b577c018ad707a63766462b1e87',
1515 'title': 'New experience with Acrobat DC',
1516 'description': 'New experience with Acrobat DC',
1517 'duration': 248.667,
1520 # BrightcoveInPageEmbed embed
1522 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1524 'id': '4238694884001',
1526 'title': 'Tabletop: Dread, Last Thoughts',
1527 'description': 'Tabletop: Dread, Last Thoughts',
1531 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1532 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1534 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1536 'id': '4785848093001',
1538 'title': 'The Cardinal Pell Interview',
1539 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1540 'uploader': 'GlobeCast Australia - GlobeStream',
1541 'uploader_id': '2733773828001',
1542 'upload_date': '20160304',
1543 'timestamp': 1457083087,
1547 'skip_download': True,
1551 # Brightcove embed with whitespace around attribute names
1552 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1554 'id': '3167554373001',
1556 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1557 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1558 'uploader_id': '1079349493',
1559 'upload_date': '20140207',
1560 'timestamp': 1391810548,
1563 'skip_download': True,
1566 # Another form of arte.tv embed
1568 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1569 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1571 'id': '030273-562_PLUS7-F',
1573 'title': 'ARTE Reportage - Nulle part, en France',
1574 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1575 'upload_date': '20160409',
1580 'url': 'http://www.wykop.pl/link/3088787/',
1581 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1583 'id': '874_1459135191',
1585 'title': 'Man shows poor quality of new apartment building',
1586 'description': 'The wall is like a sand pile.',
1587 'uploader': 'Lake8737',
1589 'add_ie': [LiveLeakIE.ie_key()],
1591 # Another LiveLeak embed pattern (#13336)
1593 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1595 'id': '2eb_1496309988',
1597 'title': 'Thief robs place where everyone was armed',
1598 'description': 'md5:694d73ee79e535953cf2488562288eee',
1599 'uploader': 'brazilwtf',
1601 'add_ie': [LiveLeakIE.ie_key()],
1603 # Duplicated embedded video URLs
1605 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1607 'id': '149298443_480_16c25b74_2',
1609 'title': 'vs. Blue Orange Spring Game',
1610 'uploader': 'www.hudl.com',
1613 # twitter:player:stream embed
1615 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1619 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1620 'uploader': 'www.rtl.be',
1624 'skip_download': True,
1627 # twitter:player embed
1629 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1630 'md5': 'a3e0df96369831de324f0778e126653c',
1632 'id': '4909620399001',
1634 'title': 'What Do Black Holes Sound Like?',
1635 'description': 'what do black holes sound like',
1636 'upload_date': '20160524',
1637 'uploader_id': '29913724001',
1638 'timestamp': 1464107587,
1639 'uploader': 'TheAtlantic',
1641 'add_ie': ['BrightcoveLegacy'],
1643 # Facebook <iframe> embed
1645 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1646 'md5': 'fbcde74f534176ecb015849146dd3aee',
1648 'id': '599637780109885',
1650 'title': 'Facebook video #599637780109885',
1653 # Facebook <iframe> embed, plugin video
1655 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1657 'id': '1754168231264132',
1659 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1660 'uploader': 'Tariq Ramadan (official)',
1661 'timestamp': 1496758379,
1662 'upload_date': '20170606',
1665 'skip_download': True,
1668 # Facebook API embed
1670 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1671 'md5': 'a47372ee61b39a7b90287094d447d94e',
1673 'id': '10153467542406923',
1675 'title': 'Facebook video #10153467542406923',
1678 # Wordpress "YouTube Video Importer" plugin
1680 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1681 'md5': 'd16797741b560b485194eddda8121b48',
1683 'id': 'HNTXWDXV9Is',
1685 'title': 'Blue Devils Drumline Stanford lot 2016',
1686 'upload_date': '20160627',
1687 'uploader_id': 'GENOCIDE8GENERAL10',
1688 'uploader': 'cylus cyrus',
1692 # video stored on custom kaltura server
1693 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1694 'md5': '537617d06e64dfed891fa1593c4b30cc',
1698 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1699 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1700 'uploader_id': 'videos.expansion@el-mundo.net',
1701 'upload_date': '20150429',
1702 'timestamp': 1430303472,
1704 'add_ie': ['Kaltura'],
1707 # Non-standard Vimeo embed
1708 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1709 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1713 'title': 'Understanding the web - Teaser',
1714 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1715 'upload_date': '20151214',
1716 'uploader': 'OpenClassrooms',
1717 'uploader_id': 'openclassrooms',
1719 'add_ie': ['Vimeo'],
1722 # generic vimeo embed that requires original URL passed as Referer
1723 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1724 'only_matching': True,
1727 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1728 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1730 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1732 'title': 'Big Buck Bunny',
1733 'description': 'Royalty free test video',
1734 'timestamp': 1432816365,
1735 'upload_date': '20150528',
1739 'skip_download': True,
1741 'add_ie': [ArkenaIE.ie_key()],
1744 '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/',
1748 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1751 'skip_download': True,
1753 'add_ie': [Vbox7IE.ie_key()],
1757 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1760 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1762 'playlist_mincount': 3,
1766 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1768 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1769 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1771 'playlist_mincount': 2,
1775 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1779 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1780 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1783 'skip_download': True,
1785 'add_ie': [TwentyMinutenIE.ie_key()],
1789 'url': 'https://en.support.wordpress.com/videopress/',
1793 'title': 'IMG_5786',
1794 'timestamp': 1435711927,
1795 'upload_date': '20150701',
1798 'skip_download': True,
1800 'add_ie': [VideoPressIE.ie_key()],
1804 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1806 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1808 'title': 'Магаззино: Казань 2',
1809 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1810 'uploader': 'Магаззино',
1811 'upload_date': '20170228',
1812 'uploader_id': '996642',
1815 'skip_download': True,
1817 'add_ie': [RutubeIE.ie_key()],
1820 # ThePlatform embedded with whitespaces in URLs
1821 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1822 'only_matching': True,
1825 # Senate ISVP iframe https
1826 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1827 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1829 'id': 'govtaff020316',
1831 'title': 'Integrated Senate Video Player',
1833 'add_ie': [SenateISVPIE.ie_key()],
1836 # Limelight embeds (1 channel embed + 4 media embeds)
1837 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1839 'id': 'FacilitatorTraining2017',
1840 'title': 'Facilitator Training 2017',
1842 'playlist_mincount': 5,
1845 # Limelight embed (LimelightPlayerUtil.embed)
1846 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1848 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1850 'title': '07448641',
1851 'timestamp': 1499890639,
1852 'upload_date': '20170712',
1855 'skip_download': True,
1857 'add_ie': ['LimelightMedia'],
1860 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1862 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1863 'title': 'Standoff with Walnut Creek murder suspect ends',
1864 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1866 'playlist_mincount': 4,
1869 # WashingtonPost embed
1870 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1872 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1874 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1875 '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.',
1876 'timestamp': 1455216756,
1877 'uploader': 'The Washington Post',
1878 'upload_date': '20160211',
1880 'add_ie': [WashingtonPostIE.ie_key()],
1884 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1888 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1891 'skip_download': True,
1893 'add_ie': [MediasetIE.ie_key()],
1897 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1899 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1900 'title': 'Slovenskom sa prehnala vlna silných búrok',
1902 'playlist_mincount': 5,
1903 'add_ie': [JojIE.ie_key()],
1906 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1907 'url': 'https://tvrain.ru/amp/418921/',
1908 'md5': 'cc00413936695987e8de148b67d14f1d',
1912 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1917 'url': 'http://help.vzaar.com/article/165-embedding-video',
1918 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1922 'title': 'Building A Business Online: Principal Chairs Q & A',
1926 # multiple HTML5 videos on one page
1927 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1929 'id': 'keyscenarios',
1930 'title': 'Rescue Kit 14 Free Edition - Getting started',
1932 'playlist_count': 4,
1936 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1937 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1940 'title': 'vl14062007715967',
1945 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1946 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1948 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1950 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1951 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1952 'timestamp': 1474354800,
1953 'upload_date': '20160920',
1957 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1961 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1962 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1963 'timestamp': 1516100691,
1964 'upload_date': '20180116',
1967 'skip_download': True,
1969 'add_ie': [SpringboardPlatformIE.ie_key()],
1972 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1974 'id': 'uPDB5I9wfp8',
1976 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1977 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1978 'upload_date': '20160219',
1979 'uploader': 'Pocoyo - Português (BR)',
1980 'uploader_id': 'PocoyoBrazil',
1982 'add_ie': [YoutubeIE.ie_key()],
1984 'skip_download': True,
1988 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1990 'id': 'vMDE4NzI1Mjgt690b',
1994 'add_ie': [YapFilesIE.ie_key()],
1996 'skip_download': True,
2000 # CloudflareStream embed
2001 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2003 'id': '31c9291ab41fac05471db4e73aa11717',
2005 'title': '31c9291ab41fac05471db4e73aa11717',
2007 'add_ie': [CloudflareStreamIE.ie_key()],
2009 'skip_download': True,
2014 'url': 'https://joinpeertube.org/fr/home/',
2017 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2019 'playlist_count': 2,
2023 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2027 'title': 'Így kell otthon hamburgert sütni',
2028 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2029 'timestamp': 1426330212,
2030 'upload_date': '20150314',
2031 'uploader': 'StreetKitchen',
2032 'uploader_id': '546363',
2034 'add_ie': [IndavideoEmbedIE.ie_key()],
2036 'skip_download': True,
2040 # APA embed via JWPlatform embed
2041 'url': 'http://www.vol.at/blue-man-group/5593454',
2045 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2046 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2047 'thumbnail': r're:^https?://.*\.jpg$',
2049 'timestamp': 1519211149,
2050 'upload_date': '20180221',
2053 'skip_download': True,
2057 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2058 'md5': 'b68d276de422ab07ee1d49388103f457',
2061 'title': 'Lock up and get excited',
2064 'skip': 'TODO: fix nested playlists processing in tests',
2068 'url': 'https://viqeo.tv/',
2071 'title': 'All-new video platform',
2073 'playlist_count': 6,
2077 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2079 'id': '5b400b834b32992a310622b9',
2081 'title': 'Smoky Barbecue Favorites',
2082 'thumbnail': r're:^https?://.*\.jpe?g',
2084 'add_ie': [ZypeIE.ie_key()],
2086 'skip_download': True,
2091 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2095 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2096 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2097 'thumbnail': r're:^https?://.*\.jpg$',
2100 'skip_download': True,
2102 'expected_warnings': ['Failed to download MPD manifest'],
2105 # # TODO: find another test
2106 # # http://schema.org/VideoObject
2107 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2108 # 'md5': '888dcf08b7ea671381f00fab74692755',
2110 # 'id': 'nyvTSJMKId',
2112 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2113 # 'description': '#love for cats.',
2114 # 'timestamp': 1461244995,
2115 # 'upload_date': '20160421',
2118 # 'force_generic_extractor': True,
2123 def report_following_redirect(self, new_url):
2124 """Report information extraction."""
2125 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2127 def _extract_rss(self, url, video_id, doc):
2128 playlist_title = doc.find('./channel/title').text
2129 playlist_desc_el = doc.find('./channel/description')
2130 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2133 for it in doc.findall('./channel/item'):
2135 enclosure_nodes = it.findall('./enclosure')
2136 for e in enclosure_nodes:
2137 next_url = e.attrib.get('url')
2142 next_url = xpath_text(it, 'link', fatal=False)
2148 '_type': 'url_transparent',
2150 'title': it.find('title').text,
2154 '_type': 'playlist',
2156 'title': playlist_title,
2157 'description': playlist_desc,
2161 def _extract_camtasia(self, url, video_id, webpage):
2162 """ Returns None if no camtasia video can be found. """
2164 camtasia_cfg = self._search_regex(
2165 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2166 webpage, 'camtasia configuration file', default=None)
2167 if camtasia_cfg is None:
2170 title = self._html_search_meta('DC.title', webpage, fatal=True)
2172 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2173 camtasia_cfg = self._download_xml(
2174 camtasia_url, video_id,
2175 note='Downloading camtasia configuration',
2176 errnote='Failed to download camtasia configuration')
2177 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2180 for n in fileset_node.getchildren():
2181 url_n = n.find('./uri')
2186 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2187 'title': '%s - %s' % (title, n.tag),
2188 'url': compat_urlparse.urljoin(url, url_n.text),
2189 'duration': float_or_none(n.find('./duration').text),
2193 '_type': 'playlist',
2198 def _real_extract(self, url):
2199 if url.startswith('//'):
2202 'url': self.http_scheme() + url,
2205 parsed_url = compat_urlparse.urlparse(url)
2206 if not parsed_url.scheme:
2207 default_search = self._downloader.params.get('default_search')
2208 if default_search is None:
2209 default_search = 'fixup_error'
2211 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2213 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2214 return self.url_result('http://' + url)
2215 elif default_search != 'fixup_error':
2216 if default_search == 'auto_warning':
2217 if re.match(r'^(?:url|URL)$', url):
2218 raise ExtractorError(
2219 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2222 self._downloader.report_warning(
2223 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2224 return self.url_result('ytsearch:' + url)
2226 if default_search in ('error', 'fixup_error'):
2227 raise ExtractorError(
2228 '%r is not a valid URL. '
2229 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2230 % (url, url), expected=True)
2232 if ':' not in default_search:
2233 default_search += ':'
2234 return self.url_result(default_search + url)
2236 url, smuggled_data = unsmuggle_url(url)
2237 force_videoid = None
2238 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2239 if smuggled_data and 'force_videoid' in smuggled_data:
2240 force_videoid = smuggled_data['force_videoid']
2241 video_id = force_videoid
2243 video_id = self._generic_id(url)
2245 self.to_screen('%s: Requesting header' % video_id)
2247 head_req = HEADRequest(url)
2248 head_response = self._request_webpage(
2250 note=False, errnote='Could not send HEAD request to %s' % url,
2253 if head_response is not False:
2254 # Check for redirect
2255 new_url = compat_str(head_response.geturl())
2257 self.report_following_redirect(new_url)
2259 new_url = smuggle_url(
2260 new_url, {'force_videoid': force_videoid})
2261 return self.url_result(new_url)
2263 full_response = None
2264 if head_response is False:
2265 request = sanitized_Request(url)
2266 request.add_header('Accept-Encoding', '*')
2267 full_response = self._request_webpage(request, video_id)
2268 head_response = full_response
2272 'title': self._generic_title(url),
2273 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2276 # Check for direct link to a video
2277 content_type = head_response.headers.get('Content-Type', '').lower()
2278 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2280 format_id = compat_str(m.group('format_id'))
2281 if format_id.endswith('mpegurl'):
2282 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2283 elif format_id == 'f4m':
2284 formats = self._extract_f4m_formats(url, video_id)
2287 'format_id': format_id,
2289 'vcodec': 'none' if m.group('type') == 'audio' else None
2291 info_dict['direct'] = True
2292 self._sort_formats(formats)
2293 info_dict['formats'] = formats
2296 if not self._downloader.params.get('test', False) and not is_intentional:
2297 force = self._downloader.params.get('force_generic_extractor', False)
2298 self._downloader.report_warning(
2299 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2301 if not full_response:
2302 request = sanitized_Request(url)
2303 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2304 # making it impossible to download only chunk of the file (yet we need only 512kB to
2305 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2306 # that will always result in downloading the whole file that is not desirable.
2307 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2308 # to accept raw bytes and being able to download only a chunk.
2309 # It may probably better to solve this by checking Content-Type for application/octet-stream
2310 # after HEAD request finishes, but not sure if we can rely on this.
2311 request.add_header('Accept-Encoding', '*')
2312 full_response = self._request_webpage(request, video_id)
2314 first_bytes = full_response.read(512)
2316 # Is it an M3U playlist?
2317 if first_bytes.startswith(b'#EXTM3U'):
2318 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2319 self._sort_formats(info_dict['formats'])
2322 # Maybe it's a direct link to a video?
2323 # Be careful not to download the whole thing!
2324 if not is_html(first_bytes):
2325 self._downloader.report_warning(
2326 'URL could be a direct video link, returning it as such.')
2333 webpage = self._webpage_read_content(
2334 full_response, url, video_id, prefix=first_bytes)
2336 self.report_extraction(video_id)
2338 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2340 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2341 if doc.tag == 'rss':
2342 return self._extract_rss(url, video_id, doc)
2343 elif doc.tag == 'SmoothStreamingMedia':
2344 info_dict['formats'] = self._parse_ism_formats(doc, url)
2345 self._sort_formats(info_dict['formats'])
2347 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2348 smil = self._parse_smil(doc, url, video_id)
2349 self._sort_formats(smil['formats'])
2351 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2352 return self.playlist_result(
2354 doc, video_id, xspf_url=url,
2355 xspf_base_url=compat_str(full_response.geturl())),
2357 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2358 info_dict['formats'] = self._parse_mpd_formats(
2360 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2362 self._sort_formats(info_dict['formats'])
2364 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2365 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2366 self._sort_formats(info_dict['formats'])
2368 except compat_xml_parse_error:
2371 # Is it a Camtasia project?
2372 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2373 if camtasia_res is not None:
2376 # Sometimes embedded video player is hidden behind percent encoding
2377 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2378 # Unescaping the whole page allows to handle those cases in a generic way
2379 webpage = compat_urllib_parse_unquote(webpage)
2381 # it's tempting to parse this further, but you would
2382 # have to take into account all the variations like
2383 # Video Title - Site Name
2384 # Site Name | Video Title
2385 # Video Title - Tagline | Site Name
2386 # and so on and so forth; it's just not practical
2387 video_title = self._og_search_title(
2388 webpage, default=None) or self._html_search_regex(
2389 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2392 # Try to detect age limit automatically
2393 age_limit = self._rta_search(webpage)
2394 # And then there are the jokers who advertise that they use RTA,
2395 # but actually don't.
2396 AGE_LIMIT_MARKERS = [
2397 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2399 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2402 # video uploader is domain name
2403 video_uploader = self._search_regex(
2404 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2406 video_description = self._og_search_description(webpage, default=None)
2407 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2410 'title': video_title,
2411 'description': video_description,
2412 'thumbnail': video_thumbnail,
2413 'age_limit': age_limit,
2416 # Look for Brightcove Legacy Studio embeds
2417 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2421 'url': smuggle_url(bc_url, {'Referer': url}),
2422 'ie_key': 'BrightcoveLegacy'
2423 } for bc_url in bc_urls]
2426 '_type': 'playlist',
2427 'title': video_title,
2432 # Look for Brightcove New Studio embeds
2433 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2435 return self.playlist_from_matches(
2436 bc_urls, video_id, video_title,
2437 getter=lambda x: smuggle_url(x, {'referrer': url}),
2440 # Look for Nexx embeds
2441 nexx_urls = NexxIE._extract_urls(webpage)
2443 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2445 # Look for Nexx iFrame embeds
2446 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2448 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2450 # Look for ThePlatform embeds
2451 tp_urls = ThePlatformIE._extract_urls(webpage)
2453 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2455 # Look for Vessel embeds
2456 vessel_urls = VesselIE._extract_urls(webpage)
2458 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2460 # Look for embedded rtl.nl player
2461 matches = re.findall(
2462 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2465 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2467 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2469 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2471 vid_me_embed_url = self._search_regex(
2472 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2473 webpage, 'vid.me embed', default=None)
2474 if vid_me_embed_url is not None:
2475 return self.url_result(vid_me_embed_url, 'Vidme')
2477 # Look for YouTube embeds
2478 youtube_urls = YoutubeIE._extract_urls(webpage)
2480 return self.playlist_from_matches(
2481 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2483 matches = DailymotionIE._extract_urls(webpage)
2485 return self.playlist_from_matches(matches, video_id, video_title)
2487 # Look for embedded Dailymotion playlist player (#3822)
2489 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2491 playlists = re.findall(
2492 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2494 return self.playlist_from_matches(
2495 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2497 # Look for DailyMail embeds
2498 dailymail_urls = DailyMailIE._extract_urls(webpage)
2500 return self.playlist_from_matches(
2501 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2503 # Look for embedded Wistia player
2504 wistia_url = WistiaIE._extract_url(webpage)
2507 '_type': 'url_transparent',
2508 'url': self._proto_relative_url(wistia_url),
2509 'ie_key': WistiaIE.ie_key(),
2510 'uploader': video_uploader,
2513 # Look for SVT player
2514 svt_url = SVTIE._extract_url(webpage)
2516 return self.url_result(svt_url, 'SVT')
2518 # Look for Bandcamp pages with custom domain
2519 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2520 if mobj is not None:
2521 burl = unescapeHTML(mobj.group(1))
2522 # Don't set the extractor because it can be a track url or an album
2523 return self.url_result(burl)
2525 # Look for embedded Vevo player
2527 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'))
2531 # Look for embedded Viddler player
2533 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2535 if mobj is not None:
2536 return self.url_result(mobj.group('url'))
2538 # Look for NYTimes player
2540 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'))
2545 # Look for Libsyn player
2547 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2548 if mobj is not None:
2549 return self.url_result(mobj.group('url'))
2551 # Look for Ooyala videos
2552 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2553 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2554 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2555 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2556 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2557 if mobj is not None:
2558 embed_token = self._search_regex(
2559 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2560 webpage, 'ooyala embed token', default=None)
2561 return OoyalaIE._build_url_result(smuggle_url(
2564 'embed_token': embed_token,
2567 # Look for multiple Ooyala embeds on SBN network websites
2568 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2569 if mobj is not None:
2570 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2572 return self.playlist_from_matches(
2573 embeds, video_id, video_title,
2574 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2576 # Look for Aparat videos
2577 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2578 if mobj is not None:
2579 return self.url_result(mobj.group(1), 'Aparat')
2581 # Look for MPORA videos
2582 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group(1), 'Mpora')
2586 # Look for embedded NovaMov-based player
2588 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2589 (?P<url>http://(?:(?:embed|www)\.)?
2591 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2592 videoweed\.(?:es|com)|
2593 movshare\.(?:net|sx|ag)|
2594 divxstage\.(?:eu|net|ch|co|at|ag))
2595 /embed\.php.+?)\1''', webpage)
2596 if mobj is not None:
2597 return self.url_result(mobj.group('url'))
2599 # Look for embedded Facebook player
2600 facebook_urls = FacebookIE._extract_urls(webpage)
2602 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2604 # Look for embedded VK player
2605 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2606 if mobj is not None:
2607 return self.url_result(mobj.group('url'), 'VK')
2609 # Look for embedded Odnoklassniki player
2610 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2611 if mobj is not None:
2612 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2614 # Look for embedded ivi player
2615 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2616 if mobj is not None:
2617 return self.url_result(mobj.group('url'), 'Ivi')
2619 # Look for embedded Huffington Post player
2621 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2622 if mobj is not None:
2623 return self.url_result(mobj.group('url'), 'HuffPost')
2626 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2627 if mobj is not None:
2628 return self.url_result(mobj.group('url'))
2629 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2630 if mobj is not None:
2631 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2633 # Look for funnyordie embed
2634 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2636 return self.playlist_from_matches(
2637 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2639 # Look for BBC iPlayer embed
2640 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2642 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2644 # Look for embedded RUTV player
2645 rutv_url = RUTVIE._extract_url(webpage)
2647 return self.url_result(rutv_url, 'RUTV')
2649 # Look for embedded TVC player
2650 tvc_url = TVCIE._extract_url(webpage)
2652 return self.url_result(tvc_url, 'TVC')
2654 # Look for embedded SportBox player
2655 sportbox_urls = SportBoxIE._extract_urls(webpage)
2657 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2659 # Look for embedded XHamster player
2660 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2662 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2664 # Look for embedded TNAFlixNetwork player
2665 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2667 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2669 # Look for embedded PornHub player
2670 pornhub_urls = PornHubIE._extract_urls(webpage)
2672 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2674 # Look for embedded DrTuber player
2675 drtuber_urls = DrTuberIE._extract_urls(webpage)
2677 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2679 # Look for embedded RedTube player
2680 redtube_urls = RedTubeIE._extract_urls(webpage)
2682 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2684 # Look for embedded Tube8 player
2685 tube8_urls = Tube8IE._extract_urls(webpage)
2687 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2689 # Look for embedded Tvigle player
2691 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2692 if mobj is not None:
2693 return self.url_result(mobj.group('url'), 'Tvigle')
2695 # Look for embedded TED player
2697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2698 if mobj is not None:
2699 return self.url_result(mobj.group('url'), 'TED')
2701 # Look for embedded Ustream videos
2702 ustream_url = UstreamIE._extract_url(webpage)
2704 return self.url_result(ustream_url, UstreamIE.ie_key())
2706 # Look for embedded arte.tv player
2708 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2710 if mobj is not None:
2711 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2713 # Look for embedded francetv player
2715 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2717 if mobj is not None:
2718 return self.url_result(mobj.group('url'))
2720 # Look for embedded smotri.com player
2721 smotri_url = SmotriIE._extract_url(webpage)
2723 return self.url_result(smotri_url, 'Smotri')
2725 # Look for embedded Myvi.ru player
2726 myvi_url = MyviIE._extract_url(webpage)
2728 return self.url_result(myvi_url)
2730 # Look for embedded soundcloud player
2731 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2733 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2735 # Look for tunein player
2736 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2738 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2740 # Look for embedded mtvservices player
2741 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2743 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2745 # Look for embedded yahoo player
2747 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2749 if mobj is not None:
2750 return self.url_result(mobj.group('url'), 'Yahoo')
2752 # Look for embedded sbs.com.au player
2756 <meta\s+property="og:video"\s+content=|
2759 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2761 if mobj is not None:
2762 return self.url_result(mobj.group('url'), 'SBS')
2764 # Look for embedded Cinchcast player
2766 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2768 if mobj is not None:
2769 return self.url_result(mobj.group('url'), 'Cinchcast')
2772 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2776 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2778 if mobj is not None:
2779 return self.url_result(mobj.group('url'), 'MLB')
2782 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2784 if mobj is not None:
2785 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2788 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2790 if mobj is not None:
2791 return self.url_result(mobj.group('url'), 'Livestream')
2793 # Look for Zapiks embed
2795 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2796 if mobj is not None:
2797 return self.url_result(mobj.group('url'), 'Zapiks')
2799 # Look for Kaltura embeds
2800 kaltura_url = KalturaIE._extract_url(webpage)
2802 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2804 # Look for EaglePlatform embeds
2805 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2806 if eagleplatform_url:
2807 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2809 # Look for ClipYou (uses EaglePlatform) embeds
2811 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2812 if mobj is not None:
2813 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2815 # Look for Pladform embeds
2816 pladform_url = PladformIE._extract_url(webpage)
2818 return self.url_result(pladform_url)
2820 # Look for Videomore embeds
2821 videomore_url = VideomoreIE._extract_url(webpage)
2823 return self.url_result(videomore_url)
2825 # Look for Webcaster embeds
2826 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2828 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2830 # Look for Playwire embeds
2832 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2833 if mobj is not None:
2834 return self.url_result(mobj.group('url'))
2836 # Look for 5min embeds
2838 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2839 if mobj is not None:
2840 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2842 # Look for Crooks and Liars embeds
2844 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2845 if mobj is not None:
2846 return self.url_result(mobj.group('url'))
2848 # Look for NBC Sports VPlayer embeds
2849 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2851 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2853 # Look for NBC News embeds
2854 nbc_news_embed_url = re.search(
2855 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2856 if nbc_news_embed_url:
2857 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2859 # Look for Google Drive embeds
2860 google_drive_url = GoogleDriveIE._extract_url(webpage)
2861 if google_drive_url:
2862 return self.url_result(google_drive_url, 'GoogleDrive')
2864 # Look for UDN embeds
2866 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2867 if mobj is not None:
2868 return self.url_result(
2869 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2871 # Look for Senate ISVP iframe
2872 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2874 return self.url_result(senate_isvp_url, 'SenateISVP')
2876 # Look for OnionStudios embeds
2877 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2878 if onionstudios_url:
2879 return self.url_result(onionstudios_url)
2881 # Look for ViewLift embeds
2882 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2884 return self.url_result(viewlift_url)
2886 # Look for JWPlatform embeds
2887 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2889 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2891 # Look for Digiteka embeds
2892 digiteka_url = DigitekaIE._extract_url(webpage)
2894 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2896 # Look for Arkena embeds
2897 arkena_url = ArkenaIE._extract_url(webpage)
2899 return self.url_result(arkena_url, ArkenaIE.ie_key())
2901 # Look for Piksel embeds
2902 piksel_url = PikselIE._extract_url(webpage)
2904 return self.url_result(piksel_url, PikselIE.ie_key())
2906 # Look for Limelight embeds
2907 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2909 return self.playlist_result(
2910 limelight_urls, video_id, video_title, video_description)
2912 # Look for Anvato embeds
2913 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2915 return self.playlist_result(
2916 anvato_urls, video_id, video_title, video_description)
2918 # Look for AdobeTVVideo embeds
2920 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2922 if mobj is not None:
2923 return self.url_result(
2924 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2927 # Look for Vine embeds
2929 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2931 if mobj is not None:
2932 return self.url_result(
2933 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2935 # Look for VODPlatform embeds
2937 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2939 if mobj is not None:
2940 return self.url_result(
2941 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2943 # Look for Mangomolo embeds
2945 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2947 video\?.*?\bid=(?P<video_id>\d+)|
2948 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2949 ).+?)\1''', webpage)
2950 if mobj is not None:
2952 '_type': 'url_transparent',
2953 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2954 'title': video_title,
2955 'description': video_description,
2956 'thumbnail': video_thumbnail,
2957 'uploader': video_uploader,
2959 video_id = mobj.group('video_id')
2962 'ie_key': 'MangomoloVideo',
2967 'ie_key': 'MangomoloLive',
2968 'id': mobj.group('channel_id'),
2972 # Look for Instagram embeds
2973 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2974 if instagram_embed_url is not None:
2975 return self.url_result(
2976 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2978 # Look for LiveLeak embeds
2979 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2981 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2983 # Look for 3Q SDN embeds
2984 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2987 '_type': 'url_transparent',
2988 'ie_key': ThreeQSDNIE.ie_key(),
2989 'url': self._proto_relative_url(threeqsdn_url),
2990 'title': video_title,
2991 'description': video_description,
2992 'thumbnail': video_thumbnail,
2993 'uploader': video_uploader,
2996 # Look for VBOX7 embeds
2997 vbox7_url = Vbox7IE._extract_url(webpage)
2999 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3001 # Look for DBTV embeds
3002 dbtv_urls = DBTVIE._extract_urls(webpage)
3004 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3006 # Look for Videa embeds
3007 videa_urls = VideaIE._extract_urls(webpage)
3009 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3011 # Look for 20 minuten embeds
3012 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3014 return self.playlist_from_matches(
3015 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3017 # Look for Openload embeds
3018 openload_urls = OpenloadIE._extract_urls(webpage)
3020 return self.playlist_from_matches(
3021 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3023 # Look for VideoPress embeds
3024 videopress_urls = VideoPressIE._extract_urls(webpage)
3026 return self.playlist_from_matches(
3027 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3029 # Look for Rutube embeds
3030 rutube_urls = RutubeIE._extract_urls(webpage)
3032 return self.playlist_from_matches(
3033 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3035 # Look for WashingtonPost embeds
3036 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3038 return self.playlist_from_matches(
3039 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3041 # Look for Mediaset embeds
3042 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3044 return self.playlist_from_matches(
3045 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3047 # Look for JOJ.sk embeds
3048 joj_urls = JojIE._extract_urls(webpage)
3050 return self.playlist_from_matches(
3051 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3053 # Look for megaphone.fm embeds
3054 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3056 return self.playlist_from_matches(
3057 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3059 # Look for vzaar embeds
3060 vzaar_urls = VzaarIE._extract_urls(webpage)
3062 return self.playlist_from_matches(
3063 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3065 channel9_urls = Channel9IE._extract_urls(webpage)
3067 return self.playlist_from_matches(
3068 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3070 vshare_urls = VShareIE._extract_urls(webpage)
3072 return self.playlist_from_matches(
3073 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3075 # Look for Mediasite embeds
3076 mediasite_urls = MediasiteIE._extract_urls(webpage)
3079 self.url_result(smuggle_url(
3080 compat_urlparse.urljoin(url, mediasite_url),
3081 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3082 for mediasite_url in mediasite_urls]
3083 return self.playlist_result(entries, video_id, video_title)
3085 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3086 if springboardplatform_urls:
3087 return self.playlist_from_matches(
3088 springboardplatform_urls, video_id, video_title,
3089 ie=SpringboardPlatformIE.ie_key())
3091 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3093 return self.playlist_from_matches(
3094 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3096 vice_urls = ViceIE._extract_urls(webpage)
3098 return self.playlist_from_matches(
3099 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3101 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3103 return self.playlist_from_matches(
3104 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3106 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3107 if cloudflarestream_urls:
3108 return self.playlist_from_matches(
3109 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3111 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3113 return self.playlist_from_matches(
3114 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3116 teachable_url = TeachableIE._extract_url(webpage, url)
3118 return self.url_result(teachable_url)
3120 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3122 return self.playlist_from_matches(
3123 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3125 apa_urls = APAIE._extract_urls(webpage)
3127 return self.playlist_from_matches(
3128 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3130 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3132 return self.playlist_from_matches(
3133 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3135 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3136 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3138 if sharevideos_urls:
3139 return self.playlist_from_matches(
3140 sharevideos_urls, video_id, video_title)
3142 viqeo_urls = ViqeoIE._extract_urls(webpage)
3144 return self.playlist_from_matches(
3145 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3147 expressen_urls = ExpressenIE._extract_urls(webpage)
3149 return self.playlist_from_matches(
3150 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3152 zype_urls = ZypeIE._extract_urls(webpage)
3154 return self.playlist_from_matches(
3155 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3157 # Look for HTML5 media
3158 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3160 if len(entries) == 1:
3163 'title': video_title,
3166 for num, entry in enumerate(entries, start=1):
3168 'id': '%s-%s' % (video_id, num),
3169 'title': '%s (%d)' % (video_title, num),
3171 for entry in entries:
3172 self._sort_formats(entry['formats'])
3173 return self.playlist_result(entries, video_id, video_title)
3175 jwplayer_data = self._find_jwplayer_data(
3176 webpage, video_id, transform_source=js_to_json)
3179 info = self._parse_jwplayer_data(
3180 jwplayer_data, video_id, require_title=False, base_url=url)
3181 return merge_dicts(info, info_dict)
3182 except ExtractorError:
3183 # See https://github.com/rg3/youtube-dl/pull/16735
3188 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3190 if mobj is not None:
3191 sources = self._parse_json(
3192 mobj.group(1), video_id, transform_source=js_to_json,
3194 if not isinstance(sources, list):
3197 for source in sources:
3198 src = source.get('src')
3199 if not src or not isinstance(src, compat_str):
3201 src = compat_urlparse.urljoin(url, src)
3202 src_type = source.get('type')
3203 if isinstance(src_type, compat_str):
3204 src_type = src_type.lower()
3205 ext = determine_ext(src).lower()
3206 if src_type == 'video/youtube':
3207 return self.url_result(src, YoutubeIE.ie_key())
3208 if src_type == 'application/dash+xml' or ext == 'mpd':
3209 formats.extend(self._extract_mpd_formats(
3210 src, video_id, mpd_id='dash', fatal=False))
3211 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3212 formats.extend(self._extract_m3u8_formats(
3213 src, video_id, 'mp4', entry_protocol='m3u8_native',
3214 m3u8_id='hls', fatal=False))
3218 'ext': (mimetype2ext(src_type) or
3219 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3222 self._sort_formats(formats)
3223 info_dict['formats'] = formats
3226 # Looking for http://schema.org/VideoObject
3227 json_ld = self._search_json_ld(
3228 webpage, video_id, default={}, expected_type='VideoObject')
3229 if json_ld.get('url'):
3230 return merge_dicts(json_ld, info_dict)
3232 def check_video(vurl):
3233 if YoutubeIE.suitable(vurl):
3235 if RtmpIE.suitable(vurl):
3237 vpath = compat_urlparse.urlparse(vurl).path
3238 vext = determine_ext(vpath)
3239 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3241 def filter_video(urls):
3242 return list(filter(check_video, urls))
3244 # Start with something easy: JW Player in SWFObject
3245 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3247 # Look for gorilla-vid style embedding
3248 found = filter_video(re.findall(r'''(?sx)
3252 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3255 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3257 # Broaden the search a little bit
3258 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3260 # Broaden the findall a little bit: JWPlayer JS loader
3261 found = filter_video(re.findall(
3262 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3265 found = filter_video(re.findall(r'''(?xs)
3266 flowplayer\("[^"]+",\s*
3268 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3269 ["']?url["']?\s*:\s*["']([^"']+)["']
3274 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3276 # Try to find twitter cards info
3277 # twitter:player:stream should be checked before twitter:player since
3278 # it is expected to contain a raw stream (see
3279 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3280 found = filter_video(re.findall(
3281 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3283 # We look for Open Graph info:
3284 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3285 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3286 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3287 if m_video_type is not None:
3288 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3290 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3292 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3293 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3296 # Look also in Refresh HTTP header
3297 refresh_header = head_response.headers.get('Refresh')
3299 # In python 2 response HTTP headers are bytestrings
3300 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3301 refresh_header = refresh_header.decode('iso-8859-1')
3302 found = re.search(REDIRECT_REGEX, refresh_header)
3304 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3306 self.report_following_redirect(new_url)
3315 # twitter:player is a https URL to iframe player that may or may not
3316 # be supported by youtube-dl thus this is checked the very last (see
3317 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3318 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3319 if embed_url and embed_url != url:
3320 return self.url_result(embed_url)
3323 raise UnsupportedError(url)
3326 for video_url in orderedSet(found):
3327 video_url = unescapeHTML(video_url)
3328 video_url = video_url.replace('\\/', '/')
3329 video_url = compat_urlparse.urljoin(url, video_url)
3330 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3332 # Sometimes, jwplayer extraction will result in a YouTube URL
3333 if YoutubeIE.suitable(video_url):
3334 entries.append(self.url_result(video_url, 'Youtube'))
3337 # here's a fun little line of code for you:
3338 video_id = os.path.splitext(video_id)[0]
3342 'uploader': video_uploader,
3343 'title': video_title,
3344 'age_limit': age_limit,
3347 if RtmpIE.suitable(video_url):
3348 entry_info_dict.update({
3349 '_type': 'url_transparent',
3350 'ie_key': RtmpIE.ie_key(),
3353 entries.append(entry_info_dict)
3356 ext = determine_ext(video_url)
3358 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3360 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3362 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3364 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3366 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3367 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3368 # Just matching .ism/manifest is not enough to be reliably sure
3369 # whether it's actually an ISM manifest or some other streaming
3370 # manifest since there are various streaming URL formats
3371 # possible (see [1]) as well as some other shenanigans like
3372 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3374 # Thus the most reasonable way to solve this is to delegate
3375 # to generic extractor in order to look into the contents of
3376 # the manifest itself.
3377 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3378 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3379 entry_info_dict = self.url_result(
3380 smuggle_url(video_url, {'to_generic': True}),
3383 entry_info_dict['url'] = video_url
3385 if entry_info_dict.get('formats'):
3386 self._sort_formats(entry_info_dict['formats'])
3388 entries.append(entry_info_dict)
3390 if len(entries) == 1:
3393 for num, e in enumerate(entries, start=1):
3394 # 'url' results don't have a title
3395 if e.get('title') is not None:
3396 e['title'] = '%s (%d)' % (e['title'], num)
3398 '_type': 'playlist',