3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
39 from .nbc import NBCSportsVPlayerIE
40 from .ooyala import OoyalaIE
41 from .rutv import RUTVIE
42 from .tvc import TVCIE
43 from .sportbox import SportBoxEmbedIE
44 from .smotri import SmotriIE
45 from .myvi import MyviIE
46 from .condenast import CondeNastIE
47 from .udn import UDNEmbedIE
48 from .senateisvp import SenateISVPIE
49 from .svt import SVTIE
50 from .pornhub import PornHubIE
51 from .xhamster import XHamsterEmbedIE
52 from .tnaflix import TNAFlixNetworkEmbedIE
53 from .drtuber import DrTuberIE
54 from .redtube import RedTubeIE
55 from .vimeo import VimeoIE
56 from .dailymotion import (
60 from .onionstudios import OnionStudiosIE
61 from .viewlift import ViewLiftEmbedIE
62 from .mtv import MTVServicesEmbeddedIE
63 from .pladform import PladformIE
64 from .videomore import VideomoreIE
65 from .webcaster import WebcasterFeedIE
66 from .googledrive import GoogleDriveIE
67 from .jwplatform import JWPlatformIE
68 from .digiteka import DigitekaIE
69 from .arkena import ArkenaIE
70 from .instagram import InstagramIE
71 from .liveleak import LiveLeakIE
72 from .threeqsdn import ThreeQSDNIE
73 from .theplatform import ThePlatformIE
74 from .vessel import VesselIE
75 from .kaltura import KalturaIE
76 from .eagleplatform import EaglePlatformIE
77 from .facebook import FacebookIE
78 from .soundcloud import SoundcloudIE
79 from .tunein import TuneInBaseIE
80 from .vbox7 import Vbox7IE
81 from .dbtv import DBTVIE
82 from .piksel import PikselIE
83 from .videa import VideaIE
84 from .twentymin import TwentyMinutenIE
85 from .ustream import UstreamIE
86 from .openload import OpenloadIE
87 from .videopress import VideoPressIE
88 from .rutube import RutubeIE
89 from .limelight import LimelightBaseIE
90 from .anvato import AnvatoIE
91 from .washingtonpost import WashingtonPostIE
92 from .wistia import WistiaIE
93 from .mediaset import MediasetIE
96 class GenericIE(InfoExtractor):
97 IE_DESC = 'Generic downloader that works on some sites'
101 # Direct link to a video
103 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
104 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
109 'upload_date': '20100513',
112 # Direct link to media delivered compressed (until Accept-Encoding is *)
114 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
115 'md5': '128c42e68b13950268b648275386fc74',
117 'id': 'FictionJunction-Parallel_Hearts',
119 'title': 'FictionJunction-Parallel_Hearts',
120 'upload_date': '20140522',
122 'expected_warnings': [
123 'URL could be a direct video link, returning it as such.'
125 'skip': 'URL invalid',
127 # Direct download with broken HEAD
129 'url': 'http://ai-radio.org:8000/radio.opus',
136 'skip_download': True, # infinite live stream
138 'expected_warnings': [
139 r'501.*Not Implemented',
143 # Direct link with incorrect MIME type
145 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
146 'md5': '4ccbebe5f36706d85221f204d7eb5913',
148 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
149 'id': '5_Lennart_Poettering_-_Systemd',
151 'title': '5_Lennart_Poettering_-_Systemd',
152 'upload_date': '20141120',
154 'expected_warnings': [
155 'URL could be a direct video link, returning it as such.'
160 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
162 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
163 'title': 'Zero Punctuation',
164 'description': 're:.*groundbreaking video review series.*'
166 'playlist_mincount': 11,
168 # RSS feed with enclosure
170 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
172 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
174 'upload_date': '20150228',
175 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
178 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
180 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
184 'title': 'Automatics, robotics and biocybernetics',
185 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
186 'upload_date': '20130627',
187 'formats': 'mincount:16',
188 'subtitles': 'mincount:1',
191 'force_generic_extractor': True,
192 'skip_download': True,
195 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
197 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
202 'formats': 'mincount:1',
205 'skip_download': True,
208 # SMIL from https://www.restudy.dk/video/play/id/1637
210 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
214 'title': 'video_1637',
215 'formats': 'mincount:3',
218 'skip_download': True,
221 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
223 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
225 'id': 'smil-service',
227 'title': 'smil-service',
228 'formats': 'mincount:1',
231 'skip_download': True,
234 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
236 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
240 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
241 'formats': 'mincount:3',
244 'skip_download': True,
247 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
249 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
251 'id': 'mZlp2ctYIUEB',
253 'title': 'Tikibad ontruimd wegens brand',
254 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
255 'thumbnail': r're:^https?://.*\.jpg$',
259 'skip_download': True,
262 # MPD from http://dash-mse-test.appspot.com/media.html
264 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
265 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
267 'id': 'car-20120827-manifest',
269 'title': 'car-20120827-manifest',
270 'formats': 'mincount:9',
271 'upload_date': '20130904',
274 'format': 'bestvideo',
277 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
279 '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',
284 'formats': 'mincount:8',
288 'skip_download': True,
290 'skip': 'video gone',
292 # m3u8 served with Content-Type: text/plain
294 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
299 'upload_date': '20140720',
300 'formats': 'mincount:11',
304 'skip_download': True,
306 'skip': 'video gone',
310 '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',
314 'upload_date': '20130224',
315 'uploader_id': 'TheVerge',
316 'description': r're:^Chris Ziegler takes a look at the\.*',
317 'uploader': 'The Verge',
318 'title': 'First Firefox OS phones side-by-side',
321 'skip_download': False,
325 # redirect in Refresh HTTP header
326 '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',
330 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
331 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
332 'upload_date': '20150917',
333 'uploader_id': 'brtvofficial',
334 'uploader': 'Boiler Room',
337 'skip_download': False,
341 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
342 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
344 'id': '13601338388002',
346 'uploader': 'www.hodiho.fr',
347 'title': 'R\u00e9gis plante sa Jeep',
350 # bandcamp page with custom domain
352 'add_ie': ['Bandcamp'],
353 'url': 'http://bronyrock.com/track/the-pony-mash',
357 'title': 'The Pony Mash',
358 'uploader': 'M_Pallante',
360 'skip': 'There is a limit of 200 free downloads / month for the test song',
363 # embedded brightcove video
364 # it also tests brightcove videos that need to set the 'Referer'
365 # in the http requests
366 'add_ie': ['BrightcoveLegacy'],
367 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
369 'id': '2765128793001',
371 'title': 'Le cours de bourse : l’analyse technique',
372 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
373 'uploader': 'BFM BUSINESS',
376 'skip_download': True,
380 # embedded with itemprop embedURL and video id spelled as `idVideo`
381 'add_id': ['BrightcoveLegacy'],
382 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
384 'id': '5255628253001',
386 'title': 'md5:37c519b1128915607601e75a87995fc0',
387 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
388 'uploader': 'BFM BUSINESS',
389 'uploader_id': '876450612001',
390 'timestamp': 1482255315,
391 'upload_date': '20161220',
394 'skip_download': True,
398 # https://github.com/rg3/youtube-dl/issues/2253
399 'url': 'http://bcove.me/i6nfkrc3',
400 'md5': '0ba9446db037002366bab3b3eb30c88c',
402 'id': '3101154703001',
404 'title': 'Still no power',
405 'uploader': 'thestar.com',
406 '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.',
408 'add_ie': ['BrightcoveLegacy'],
409 'skip': 'video gone',
412 'url': 'http://www.championat.com/video/football/v/87/87499.html',
413 'md5': 'fb973ecf6e4a78a67453647444222983',
415 'id': '3414141473001',
417 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
418 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
419 'uploader': 'Championat',
423 # https://github.com/rg3/youtube-dl/issues/3541
424 'add_ie': ['BrightcoveLegacy'],
425 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
427 'id': '3866516442001',
429 'title': 'Leer mij vrouwen kennen: Aflevering 1',
430 'description': 'Leer mij vrouwen kennen: Aflevering 1',
431 'uploader': 'SBS Broadcasting',
433 'skip': 'Restricted to Netherlands',
435 'skip_download': True, # m3u8 download
439 # Brightcove video in <iframe>
440 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
441 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
443 'id': '5360463607001',
445 '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',
446 '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。',
447 'uploader': 'United Nations',
448 'uploader_id': '1362235914001',
449 'timestamp': 1489593889,
450 'upload_date': '20170315',
452 'add_ie': ['BrightcoveLegacy'],
455 # Brightcove with alternative playerID key
456 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
458 'id': 'nmeth.2062_SV1',
459 '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',
463 'id': '2228375078001',
465 'title': 'nmeth.2062-sv1',
466 'description': 'nmeth.2062-sv1',
467 'timestamp': 1363357591,
468 'upload_date': '20130315',
469 'uploader': 'Nature Publishing Group',
470 'uploader_id': '1964492299001',
475 # Brightcove with UUID in videoPlayer
476 'url': 'http://www8.hp.com/cn/zh/home.html',
478 'id': '5255815316001',
480 'title': 'Sprocket Video - China',
481 'description': 'Sprocket Video - China',
482 'uploader': 'HP-Video Gallery',
483 'timestamp': 1482263210,
484 'upload_date': '20161220',
485 'uploader_id': '1107601872001',
488 'skip_download': True, # m3u8 download
490 'skip': 'video rotates...weekly?',
493 # Brightcove:new type [2].
494 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
495 'md5': '2b35148fcf48da41c9fb4591650784f3',
497 'id': '5348741021001',
499 'upload_date': '20170306',
500 'uploader_id': '4191638492001',
501 'timestamp': 1488769918,
502 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
507 # Alternative brightcove <video> attributes
508 '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/',
510 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
511 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
514 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
516 'id': '5311302538001',
518 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
519 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
520 'timestamp': 1486321708,
521 'upload_date': '20170205',
522 'uploader_id': '800000640001',
524 'only_matching': True,
528 # Brightcove with UUID in videoPlayer
529 'url': 'http://www8.hp.com/cn/zh/home.html',
531 'id': '5255815316001',
533 'title': 'Sprocket Video - China',
534 'description': 'Sprocket Video - China',
535 'uploader': 'HP-Video Gallery',
536 'timestamp': 1482263210,
537 'upload_date': '20161220',
538 'uploader_id': '1107601872001',
541 'skip_download': True, # m3u8 download
546 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
547 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
549 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
551 'title': '2cc213299525360.mov', # that's what we get
554 'add_ie': ['Ooyala'],
557 # ooyala video embedded with http://player.ooyala.com/iframe.js
558 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
560 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
562 'title': '"Steve Jobs: Man in the Machine" trailer',
563 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
567 'skip_download': True,
569 'skip': 'movie expired',
573 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
577 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
578 'upload_date': '20140225',
579 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
580 'uploader': 'Tested',
581 'uploader_id': 'testedcom',
583 # No need to test YoutubeIE here
585 'skip_download': True,
590 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
594 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
595 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
597 # HEAD requests lead to endless 301, while GET is OK
598 'expected_warnings': ['301'],
602 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
606 'title': 'Охотское море стало целиком российским',
607 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
611 'skip_download': True,
616 '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/',
620 'title': 'Дошкольное воспитание',
625 'url': 'http://www.vestifinance.ru/articles/25753',
628 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
633 'title': 'Госзаказ. День 3',
639 'title': 'Госзаказ. День 2',
645 'title': 'Госзаказ. День 1',
651 'skip_download': True,
656 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
658 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
660 'title': 'Ужастики, русский трейлер (2015)',
661 'thumbnail': r're:^https?://.*\.jpg$',
667 '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',
670 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
672 'playlist_mincount': 7,
673 # This forum does not allow <iframe> syntaxes anymore
674 # Now HTML tags are displayed as-is
675 'skip': 'No videos on this page',
679 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
680 'md5': '65fdff94098e4a607385a60c5177c638',
684 'title': 'Hidden miracles of the natural world',
685 'uploader': 'Louie Schwartzberg',
686 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
689 # nowvideo embed hidden behind percent encoding
691 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
692 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
694 'id': '06e53103ca9aa',
696 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
697 'description': 'No description',
702 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
703 'md5': '7653032cbb25bf6c80d80f217055fa43',
705 'id': '048195-004_PLUS7-F',
708 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
709 'upload_date': '20140320',
712 'skip_download': 'Requires rtmpdump'
714 'skip': 'video gone',
718 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
722 'title': 'Alcaline, le concert avec Calogero',
723 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
724 'upload_date': '20150226',
725 'timestamp': 1424989860,
730 'skip_download': True,
732 'expected_warnings': [
738 'url': 'http://www.wired.com/2014/04/honda-asimo/',
739 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
741 'id': '53501be369702d3275860000',
743 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
748 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
749 'md5': '441aeeb82eb72c422c7f14ec533999cd',
751 'id': 'k2mm4bCdJ6CQ2i7c8o2',
753 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
754 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
756 'uploader_id': 'xgditw',
757 'upload_date': '20140425',
758 'timestamp': 1398441542,
760 'add_ie': ['Dailymotion'],
764 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
768 'title': 'The NBL Auction 2014',
769 'uploader': 'BADMINTON England',
770 'uploader_id': 'BADMINTONEvents',
771 'upload_date': '20140603',
772 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
774 'add_ie': ['Youtube'],
776 'skip_download': True,
781 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
782 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
784 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
786 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
787 'description': 'Two valets share their love for movie star Liam Neesons.',
788 'timestamp': 1349922600,
789 'upload_date': '20121011',
792 # YouTube embed via <data-embed-url="">
794 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
798 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
799 'uploader': 'Gameloft',
800 'uploader_id': 'gameloft',
801 'upload_date': '20140828',
802 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
805 'skip_download': True,
808 # YouTube <object> embed
810 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
811 'md5': '516718101ec834f74318df76259fb3cc',
815 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
816 'upload_date': '20080526',
817 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
818 'uploader': 'Christopher Sykes',
819 'uploader_id': 'ChristopherJSykes',
821 'add_ie': ['Youtube'],
825 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
827 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
829 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
830 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
835 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
837 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
838 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
844 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
849 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
850 'md5': '9d65602bf31c6e20014319c7d07fba27',
852 'id': '5123ea6d5e5a7',
855 'uploader': 'www.handjobhub.com',
856 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
859 # Multiple brightcove videos
860 # https://github.com/rg3/youtube-dl/issues/2283
862 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
864 'id': 'always-never',
865 'title': 'Always / Never - The New Yorker',
869 'extract_flat': False,
870 'skip_download': True,
875 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
876 'md5': '96f09a37e44da40dd083e12d9a683327',
880 'title': 'Ump changes call to ball',
881 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
883 'timestamp': 1401537900,
884 'upload_date': '20140531',
885 'thumbnail': r're:^https?://.*\.jpg$',
890 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
891 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
895 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
896 'description': 'a Paywall Videos video from Remilon',
898 'uploader': 'study.com',
899 'timestamp': 1459678540,
900 'upload_date': '20160403',
901 'filesize': 24687186,
905 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
906 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
910 'title': 'Conversation about Hexagonal Rails Part 1',
911 'description': 'a Martin Fowler video from ThoughtWorks',
913 'uploader': 'thoughtworks.wistia.com',
914 'timestamp': 1401832161,
915 'upload_date': '20140603',
918 # Wistia standard embed (async)
920 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
924 'title': 'Drip Brennan Dunn Workshop',
925 'description': 'a JV Webinars video from getdrip-1',
927 'timestamp': 1463607249,
928 'upload_date': '20160518',
931 'skip_download': True,
936 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
940 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
941 'uploader': 'Sophos Security',
942 'title': 'Chet Chat 171 - Oct 29, 2014',
943 'upload_date': '20141029',
946 # Soundcloud multiple embeds
948 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
951 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
953 'playlist_mincount': 7,
955 # TuneIn station embed
957 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
962 'location': 'Paris, France',
967 'skip_download': True,
972 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
976 'upload_date': '20141112',
977 'title': 'Rosetta #CometLanding webcast HL 10',
980 # Another Livestream embed, without 'new.' in URL
982 'url': 'https://www.freespeech.org/',
986 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
990 'skip_download': True,
995 'url': 'https://skiplagged.com/',
998 'title': 'Skiplagged: The smart way to find cheap flights',
1000 'playlist_mincount': 1,
1001 'add_ie': ['Youtube'],
1005 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1009 'upload_date': '20141126',
1010 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1015 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1017 'id': '730m_DandD_1901_512k',
1019 'uploader': 'www.abc.net.au',
1020 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1023 # embedded viddler video
1025 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1029 'uploader': 'deadspin',
1030 'title': 'WALL-TO-GORTAT',
1031 'timestamp': 1422285291,
1032 'upload_date': '20150126',
1034 'add_ie': ['Viddler'],
1038 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1042 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1043 'description': 'md5:601cb790edd05908957dae8aaa866465',
1044 'upload_date': '20150220',
1046 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1050 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1052 'id': 'Mrj4DVp2zeA',
1054 'upload_date': '20150212',
1055 'uploader': 'The National Archives UK',
1056 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1057 'uploader_id': 'NationalArchives08',
1058 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1063 'url': 'http://www.suffolk.edu/sjc/',
1067 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1068 'uploader': 'www.suffolk.edu',
1071 'skip_download': True,
1076 'url': 'http://www.indiedb.com/games/king-machine/videos',
1080 'title': 'king machine trailer 1',
1081 'thumbnail': r're:^https?://.*\.jpg$',
1085 # JWPlayer config passed as variable
1086 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1090 'title': 'ARIELE | Tube Cup',
1091 'uploader': 'www.txxx.com',
1095 'skip_download': True,
1100 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1101 'playlist_mincount': 5,
1103 'id': 'aanslagen-kopenhagen',
1104 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1109 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1113 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1116 # Kaltura embed (different embed code)
1118 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1122 'upload_date': '20150127',
1123 'uploader_id': 'PremierMedia',
1125 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1128 # Kaltura embed with single quotes
1130 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1135 'timestamp': 1355743100,
1136 'upload_date': '20121217',
1137 'uploader_id': 'batchUser',
1139 'add_ie': ['Kaltura'],
1142 # Kaltura embedded via quoted entry_id
1143 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1147 'title': '06_matthew_brender_raj_dutt',
1148 'timestamp': 1466638791,
1149 'upload_date': '20160622',
1151 'add_ie': ['Kaltura'],
1152 'expected_warnings': [
1153 'Could not send HEAD request'
1156 'skip_download': True,
1160 # Kaltura embedded, some fileExt broken (#11480)
1161 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1165 'title': 'Our "Standard Models" of particle physics and cosmology',
1166 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1167 'timestamp': 1321158993,
1168 'upload_date': '20111113',
1169 'uploader_id': 'kps1',
1171 'add_ie': ['Kaltura'],
1174 # Kaltura iframe embed
1175 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1176 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1180 'title': 'I. M. Pei: A Centennial Celebration',
1181 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1182 'upload_date': '20170403',
1183 'uploader_id': 'batchUser',
1184 'timestamp': 1491232186,
1186 'add_ie': ['Kaltura'],
1188 # Eagle.Platform embed (generic URL)
1190 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1191 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1195 'title': 'Навальный вышел на свободу',
1196 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1197 'thumbnail': r're:^https?://.*\.jpg$',
1203 # ClipYou (Eagle.Platform) embed (custom URL)
1205 'url': 'http://muz-tv.ru/play/7129/',
1206 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1210 'title': "'O Sole Mio",
1211 'thumbnail': r're:^https?://.*\.jpg$',
1218 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1222 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1223 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1224 'thumbnail': r're:^https?://.*\.jpg$',
1231 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1235 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1236 'thumbnail': r're:^https?://.*\.png$',
1242 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1243 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1247 'title': 'Facebook Creates "On This Day" | Crunch Report',
1252 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1256 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1261 # Crooks and Liars embed
1263 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1267 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1268 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1269 'timestamp': 1428207000,
1270 'upload_date': '20150405',
1271 'uploader': 'Heather',
1274 # Crooks and Liars external embed
1276 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1278 'id': 'MTE3MjUtMzQ2MzA',
1280 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1281 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1282 'timestamp': 1265032391,
1283 'upload_date': '20100201',
1284 'uploader': 'Heather',
1287 # NBC Sports vplayer embed
1289 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1291 'id': 'ln7x1qSThw4k',
1293 'title': "PFT Live: New leader in the 'new-look' defense",
1294 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1295 'uploader': 'NBCU-SPORTS',
1296 'upload_date': '20140107',
1297 'timestamp': 1389118457,
1302 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1303 'md5': '1aa589c675898ae6d37a17913cf68d66',
1305 'id': '701714499682',
1307 'title': 'PREVIEW: On Assignment: David Letterman',
1308 '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.',
1313 'url': 'https://video.udn.com/news/300346',
1314 'md5': 'fd2060e988c326991037b9aff9df21a6',
1318 'title': '中一中男師變性 全校師生力挺',
1319 'thumbnail': r're:^https?://.*\.jpg$',
1323 'skip_download': True,
1328 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1330 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1332 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1333 'title': 'This is what separates the Excel masters from the wannabes',
1334 'duration': 191.933,
1338 'skip_download': True,
1341 # Brightcove URL in single quotes
1343 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1344 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1346 'id': '4255764656001',
1348 'title': 'SN Presents: Russell Martin, World Citizen',
1349 '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.',
1350 'uploader': 'Rogers Sportsnet',
1351 'uploader_id': '1704050871',
1352 'upload_date': '20150525',
1353 'timestamp': 1432570283,
1356 # Dailymotion Cloud video
1358 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1359 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1363 'title': 'Sauvons les abeilles ! - Le débat',
1364 'description': 'md5:d9082128b1c5277987825d684939ca26',
1365 'thumbnail': r're:^https?://.*\.jpe?g$',
1366 'timestamp': 1434970506,
1367 'upload_date': '20150622',
1368 'uploader': 'Public Sénat',
1369 'uploader_id': 'xa9gza',
1372 # OnionStudios embed
1374 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1378 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1379 'thumbnail': r're:^https?://.*\.jpe?g$',
1380 'uploader': 'ClickHole',
1381 'uploader_id': 'clickhole',
1386 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1388 'id': '74849a00-85a9-11e1-9660-123139220831',
1390 'title': '#whilewewatch',
1393 # AdobeTVVideo embed
1395 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1396 'md5': '43662b577c018ad707a63766462b1e87',
1400 'title': 'New experience with Acrobat DC',
1401 'description': 'New experience with Acrobat DC',
1402 'duration': 248.667,
1405 # BrightcoveInPageEmbed embed
1407 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1409 'id': '4238694884001',
1411 'title': 'Tabletop: Dread, Last Thoughts',
1412 'description': 'Tabletop: Dread, Last Thoughts',
1416 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1417 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1419 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1421 'id': '4785848093001',
1423 'title': 'The Cardinal Pell Interview',
1424 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1425 'uploader': 'GlobeCast Australia - GlobeStream',
1426 'uploader_id': '2733773828001',
1427 'upload_date': '20160304',
1428 'timestamp': 1457083087,
1432 'skip_download': True,
1436 # Brightcove embed with whitespace around attribute names
1437 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1439 'id': '3167554373001',
1441 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1442 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1443 'uploader_id': '1079349493',
1444 'upload_date': '20140207',
1445 'timestamp': 1391810548,
1448 'skip_download': True,
1451 # Another form of arte.tv embed
1453 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1454 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1456 'id': '030273-562_PLUS7-F',
1458 'title': 'ARTE Reportage - Nulle part, en France',
1459 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1460 'upload_date': '20160409',
1465 'url': 'http://www.wykop.pl/link/3088787/',
1466 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1468 'id': '874_1459135191',
1470 'title': 'Man shows poor quality of new apartment building',
1471 'description': 'The wall is like a sand pile.',
1472 'uploader': 'Lake8737',
1475 # Duplicated embedded video URLs
1477 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1479 'id': '149298443_480_16c25b74_2',
1481 'title': 'vs. Blue Orange Spring Game',
1482 'uploader': 'www.hudl.com',
1485 # twitter:player:stream embed
1487 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1491 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1492 'uploader': 'www.rtl.be',
1496 'skip_download': True,
1499 # twitter:player embed
1501 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1502 'md5': 'a3e0df96369831de324f0778e126653c',
1504 'id': '4909620399001',
1506 'title': 'What Do Black Holes Sound Like?',
1507 'description': 'what do black holes sound like',
1508 'upload_date': '20160524',
1509 'uploader_id': '29913724001',
1510 'timestamp': 1464107587,
1511 'uploader': 'TheAtlantic',
1513 'add_ie': ['BrightcoveLegacy'],
1515 # Facebook <iframe> embed
1517 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1518 'md5': 'fbcde74f534176ecb015849146dd3aee',
1520 'id': '599637780109885',
1522 'title': 'Facebook video #599637780109885',
1525 # Facebook <iframe> embed, plugin video
1527 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1529 'id': '1754168231264132',
1531 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1532 'uploader': 'Tariq Ramadan (official)',
1533 'timestamp': 1496758379,
1534 'upload_date': '20170606',
1537 'skip_download': True,
1540 # Facebook API embed
1542 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1543 'md5': 'a47372ee61b39a7b90287094d447d94e',
1545 'id': '10153467542406923',
1547 'title': 'Facebook video #10153467542406923',
1550 # Wordpress "YouTube Video Importer" plugin
1552 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1553 'md5': 'd16797741b560b485194eddda8121b48',
1555 'id': 'HNTXWDXV9Is',
1557 'title': 'Blue Devils Drumline Stanford lot 2016',
1558 'upload_date': '20160627',
1559 'uploader_id': 'GENOCIDE8GENERAL10',
1560 'uploader': 'cylus cyrus',
1564 # video stored on custom kaltura server
1565 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1566 'md5': '537617d06e64dfed891fa1593c4b30cc',
1570 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1571 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1572 'uploader_id': 'videos.expansion@el-mundo.net',
1573 'upload_date': '20150429',
1574 'timestamp': 1430303472,
1576 'add_ie': ['Kaltura'],
1579 # Non-standard Vimeo embed
1580 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1581 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1585 'title': 'Understanding the web - Teaser',
1586 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1587 'upload_date': '20151214',
1588 'uploader': 'OpenClassrooms',
1589 'uploader_id': 'openclassrooms',
1591 'add_ie': ['Vimeo'],
1594 # generic vimeo embed that requires original URL passed as Referer
1595 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1596 'only_matching': True,
1599 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1600 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1602 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1604 'title': 'Big Buck Bunny',
1605 'description': 'Royalty free test video',
1606 'timestamp': 1432816365,
1607 'upload_date': '20150528',
1611 'skip_download': True,
1613 'add_ie': [ArkenaIE.ie_key()],
1616 '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/',
1620 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1623 'skip_download': True,
1625 'add_ie': [Vbox7IE.ie_key()],
1629 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1632 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1634 'playlist_mincount': 3,
1638 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1640 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1641 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1643 'playlist_mincount': 2,
1647 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1651 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1652 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1655 'skip_download': True,
1657 'add_ie': [TwentyMinutenIE.ie_key()],
1661 'url': 'https://en.support.wordpress.com/videopress/',
1665 'title': 'IMG_5786',
1666 'timestamp': 1435711927,
1667 'upload_date': '20150701',
1670 'skip_download': True,
1672 'add_ie': [VideoPressIE.ie_key()],
1676 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1678 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1680 'title': 'Магаззино: Казань 2',
1681 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1682 'uploader': 'Магаззино',
1683 'upload_date': '20170228',
1684 'uploader_id': '996642',
1687 'skip_download': True,
1689 'add_ie': [RutubeIE.ie_key()],
1692 # ThePlatform embedded with whitespaces in URLs
1693 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1694 'only_matching': True,
1697 # Senate ISVP iframe https
1698 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1699 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1701 'id': 'govtaff020316',
1703 'title': 'Integrated Senate Video Player',
1705 'add_ie': [SenateISVPIE.ie_key()],
1708 # Limelight embeds (1 channel embed + 4 media embeds)
1709 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1711 'id': 'FacilitatorTraining2017',
1712 'title': 'Facilitator Training 2017',
1714 'playlist_mincount': 5,
1717 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1719 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1720 'title': 'Standoff with Walnut Creek murder suspect ends',
1721 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1723 'playlist_mincount': 4,
1726 # WashingtonPost embed
1727 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1729 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1731 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1732 '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.',
1733 'timestamp': 1455216756,
1734 'uploader': 'The Washington Post',
1735 'upload_date': '20160211',
1737 'add_ie': [WashingtonPostIE.ie_key()],
1741 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1745 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1748 'skip_download': True,
1750 'add_ie': [MediasetIE.ie_key()],
1753 # # TODO: find another test
1754 # # http://schema.org/VideoObject
1755 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1756 # 'md5': '888dcf08b7ea671381f00fab74692755',
1758 # 'id': 'nyvTSJMKId',
1760 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1761 # 'description': '#love for cats.',
1762 # 'timestamp': 1461244995,
1763 # 'upload_date': '20160421',
1766 # 'force_generic_extractor': True,
1771 def report_following_redirect(self, new_url):
1772 """Report information extraction."""
1773 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1775 def _extract_rss(self, url, video_id, doc):
1776 playlist_title = doc.find('./channel/title').text
1777 playlist_desc_el = doc.find('./channel/description')
1778 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1781 for it in doc.findall('./channel/item'):
1782 next_url = xpath_text(it, 'link', fatal=False)
1784 enclosure_nodes = it.findall('./enclosure')
1785 for e in enclosure_nodes:
1786 next_url = e.attrib.get('url')
1794 '_type': 'url_transparent',
1796 'title': it.find('title').text,
1800 '_type': 'playlist',
1802 'title': playlist_title,
1803 'description': playlist_desc,
1807 def _extract_camtasia(self, url, video_id, webpage):
1808 """ Returns None if no camtasia video can be found. """
1810 camtasia_cfg = self._search_regex(
1811 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1812 webpage, 'camtasia configuration file', default=None)
1813 if camtasia_cfg is None:
1816 title = self._html_search_meta('DC.title', webpage, fatal=True)
1818 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1819 camtasia_cfg = self._download_xml(
1820 camtasia_url, video_id,
1821 note='Downloading camtasia configuration',
1822 errnote='Failed to download camtasia configuration')
1823 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1826 for n in fileset_node.getchildren():
1827 url_n = n.find('./uri')
1832 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1833 'title': '%s - %s' % (title, n.tag),
1834 'url': compat_urlparse.urljoin(url, url_n.text),
1835 'duration': float_or_none(n.find('./duration').text),
1839 '_type': 'playlist',
1844 def _real_extract(self, url):
1845 if url.startswith('//'):
1848 'url': self.http_scheme() + url,
1851 parsed_url = compat_urlparse.urlparse(url)
1852 if not parsed_url.scheme:
1853 default_search = self._downloader.params.get('default_search')
1854 if default_search is None:
1855 default_search = 'fixup_error'
1857 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1859 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1860 return self.url_result('http://' + url)
1861 elif default_search != 'fixup_error':
1862 if default_search == 'auto_warning':
1863 if re.match(r'^(?:url|URL)$', url):
1864 raise ExtractorError(
1865 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1868 self._downloader.report_warning(
1869 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1870 return self.url_result('ytsearch:' + url)
1872 if default_search in ('error', 'fixup_error'):
1873 raise ExtractorError(
1874 '%r is not a valid URL. '
1875 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1876 % (url, url), expected=True)
1878 if ':' not in default_search:
1879 default_search += ':'
1880 return self.url_result(default_search + url)
1882 url, smuggled_data = unsmuggle_url(url)
1883 force_videoid = None
1884 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1885 if smuggled_data and 'force_videoid' in smuggled_data:
1886 force_videoid = smuggled_data['force_videoid']
1887 video_id = force_videoid
1889 video_id = self._generic_id(url)
1891 self.to_screen('%s: Requesting header' % video_id)
1893 head_req = HEADRequest(url)
1894 head_response = self._request_webpage(
1896 note=False, errnote='Could not send HEAD request to %s' % url,
1899 if head_response is not False:
1900 # Check for redirect
1901 new_url = head_response.geturl()
1903 self.report_following_redirect(new_url)
1905 new_url = smuggle_url(
1906 new_url, {'force_videoid': force_videoid})
1907 return self.url_result(new_url)
1909 full_response = None
1910 if head_response is False:
1911 request = sanitized_Request(url)
1912 request.add_header('Accept-Encoding', '*')
1913 full_response = self._request_webpage(request, video_id)
1914 head_response = full_response
1918 'title': self._generic_title(url),
1919 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1922 # Check for direct link to a video
1923 content_type = head_response.headers.get('Content-Type', '').lower()
1924 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1926 format_id = compat_str(m.group('format_id'))
1927 if format_id.endswith('mpegurl'):
1928 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1929 elif format_id == 'f4m':
1930 formats = self._extract_f4m_formats(url, video_id)
1933 'format_id': format_id,
1935 'vcodec': 'none' if m.group('type') == 'audio' else None
1937 info_dict['direct'] = True
1938 self._sort_formats(formats)
1939 info_dict['formats'] = formats
1942 if not self._downloader.params.get('test', False) and not is_intentional:
1943 force = self._downloader.params.get('force_generic_extractor', False)
1944 self._downloader.report_warning(
1945 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1947 if not full_response:
1948 request = sanitized_Request(url)
1949 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1950 # making it impossible to download only chunk of the file (yet we need only 512kB to
1951 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1952 # that will always result in downloading the whole file that is not desirable.
1953 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1954 # to accept raw bytes and being able to download only a chunk.
1955 # It may probably better to solve this by checking Content-Type for application/octet-stream
1956 # after HEAD request finishes, but not sure if we can rely on this.
1957 request.add_header('Accept-Encoding', '*')
1958 full_response = self._request_webpage(request, video_id)
1960 first_bytes = full_response.read(512)
1962 # Is it an M3U playlist?
1963 if first_bytes.startswith(b'#EXTM3U'):
1964 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1965 self._sort_formats(info_dict['formats'])
1968 # Maybe it's a direct link to a video?
1969 # Be careful not to download the whole thing!
1970 if not is_html(first_bytes):
1971 self._downloader.report_warning(
1972 'URL could be a direct video link, returning it as such.')
1979 webpage = self._webpage_read_content(
1980 full_response, url, video_id, prefix=first_bytes)
1982 self.report_extraction(video_id)
1984 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1986 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1987 if doc.tag == 'rss':
1988 return self._extract_rss(url, video_id, doc)
1989 elif doc.tag == 'SmoothStreamingMedia':
1990 info_dict['formats'] = self._parse_ism_formats(doc, url)
1991 self._sort_formats(info_dict['formats'])
1993 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1994 smil = self._parse_smil(doc, url, video_id)
1995 self._sort_formats(smil['formats'])
1997 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1998 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1999 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2000 info_dict['formats'] = self._parse_mpd_formats(
2002 mpd_base_url=full_response.geturl().rpartition('/')[0],
2004 self._sort_formats(info_dict['formats'])
2006 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2007 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2008 self._sort_formats(info_dict['formats'])
2010 except compat_xml_parse_error:
2013 # Is it a Camtasia project?
2014 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2015 if camtasia_res is not None:
2018 # Sometimes embedded video player is hidden behind percent encoding
2019 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2020 # Unescaping the whole page allows to handle those cases in a generic way
2021 webpage = compat_urllib_parse_unquote(webpage)
2023 # it's tempting to parse this further, but you would
2024 # have to take into account all the variations like
2025 # Video Title - Site Name
2026 # Site Name | Video Title
2027 # Video Title - Tagline | Site Name
2028 # and so on and so forth; it's just not practical
2029 video_title = self._og_search_title(
2030 webpage, default=None) or self._html_search_regex(
2031 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2034 # Try to detect age limit automatically
2035 age_limit = self._rta_search(webpage)
2036 # And then there are the jokers who advertise that they use RTA,
2037 # but actually don't.
2038 AGE_LIMIT_MARKERS = [
2039 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2041 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2044 # video uploader is domain name
2045 video_uploader = self._search_regex(
2046 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2048 video_description = self._og_search_description(webpage, default=None)
2049 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2052 'title': video_title,
2053 'description': video_description,
2054 'thumbnail': video_thumbnail,
2055 'age_limit': age_limit,
2058 # Look for Brightcove Legacy Studio embeds
2059 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2063 'url': smuggle_url(bc_url, {'Referer': url}),
2064 'ie_key': 'BrightcoveLegacy'
2065 } for bc_url in bc_urls]
2068 '_type': 'playlist',
2069 'title': video_title,
2074 # Look for Brightcove New Studio embeds
2075 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2077 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2079 # Look for ThePlatform embeds
2080 tp_urls = ThePlatformIE._extract_urls(webpage)
2082 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2084 # Look for Vessel embeds
2085 vessel_urls = VesselIE._extract_urls(webpage)
2087 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2089 # Look for embedded rtl.nl player
2090 matches = re.findall(
2091 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2094 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2096 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2098 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2100 vid_me_embed_url = self._search_regex(
2101 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2102 webpage, 'vid.me embed', default=None)
2103 if vid_me_embed_url is not None:
2104 return self.url_result(vid_me_embed_url, 'Vidme')
2106 # Look for embedded YouTube player
2107 matches = re.findall(r'''(?x)
2117 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2121 return self.playlist_from_matches(
2122 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2124 # Look for lazyYT YouTube embed
2125 matches = re.findall(
2126 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2128 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2130 # Look for Wordpress "YouTube Video Importer" plugin
2131 matches = re.findall(r'''(?x)<div[^>]+
2132 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2133 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2135 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2137 matches = DailymotionIE._extract_urls(webpage)
2139 return self.playlist_from_matches(matches, video_id, video_title)
2141 # Look for embedded Dailymotion playlist player (#3822)
2143 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2145 playlists = re.findall(
2146 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2148 return self.playlist_from_matches(
2149 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2151 # Look for embedded Wistia player
2152 wistia_url = WistiaIE._extract_url(webpage)
2155 '_type': 'url_transparent',
2156 'url': self._proto_relative_url(wistia_url),
2157 'ie_key': WistiaIE.ie_key(),
2158 'uploader': video_uploader,
2161 # Look for SVT player
2162 svt_url = SVTIE._extract_url(webpage)
2164 return self.url_result(svt_url, 'SVT')
2166 # Look for Bandcamp pages with custom domain
2167 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2168 if mobj is not None:
2169 burl = unescapeHTML(mobj.group(1))
2170 # Don't set the extractor because it can be a track url or an album
2171 return self.url_result(burl)
2173 # Look for embedded Vevo player
2175 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2176 if mobj is not None:
2177 return self.url_result(mobj.group('url'))
2179 # Look for embedded Viddler player
2181 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2183 if mobj is not None:
2184 return self.url_result(mobj.group('url'))
2186 # Look for NYTimes player
2188 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2190 if mobj is not None:
2191 return self.url_result(mobj.group('url'))
2193 # Look for Libsyn player
2195 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2196 if mobj is not None:
2197 return self.url_result(mobj.group('url'))
2199 # Look for Ooyala videos
2200 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2201 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2202 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2203 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2204 if mobj is not None:
2205 embed_token = self._search_regex(
2206 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2207 webpage, 'ooyala embed token', default=None)
2208 return OoyalaIE._build_url_result(smuggle_url(
2211 'embed_token': embed_token,
2214 # Look for multiple Ooyala embeds on SBN network websites
2215 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2216 if mobj is not None:
2217 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2219 return self.playlist_from_matches(
2220 embeds, video_id, video_title,
2221 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2223 # Look for Aparat videos
2224 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2225 if mobj is not None:
2226 return self.url_result(mobj.group(1), 'Aparat')
2228 # Look for MPORA videos
2229 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2230 if mobj is not None:
2231 return self.url_result(mobj.group(1), 'Mpora')
2233 # Look for embedded NovaMov-based player
2235 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2236 (?P<url>http://(?:(?:embed|www)\.)?
2238 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2239 videoweed\.(?:es|com)|
2240 movshare\.(?:net|sx|ag)|
2241 divxstage\.(?:eu|net|ch|co|at|ag))
2242 /embed\.php.+?)\1''', webpage)
2243 if mobj is not None:
2244 return self.url_result(mobj.group('url'))
2246 # Look for embedded Facebook player
2247 facebook_urls = FacebookIE._extract_urls(webpage)
2249 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2251 # Look for embedded VK player
2252 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2253 if mobj is not None:
2254 return self.url_result(mobj.group('url'), 'VK')
2256 # Look for embedded Odnoklassniki player
2257 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2258 if mobj is not None:
2259 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2261 # Look for embedded ivi player
2262 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2263 if mobj is not None:
2264 return self.url_result(mobj.group('url'), 'Ivi')
2266 # Look for embedded Huffington Post player
2268 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2269 if mobj is not None:
2270 return self.url_result(mobj.group('url'), 'HuffPost')
2273 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2274 if mobj is not None:
2275 return self.url_result(mobj.group('url'))
2276 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2277 if mobj is not None:
2278 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2280 # Look for funnyordie embed
2281 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2283 return self.playlist_from_matches(
2284 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2286 # Look for BBC iPlayer embed
2287 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2289 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2291 # Look for embedded RUTV player
2292 rutv_url = RUTVIE._extract_url(webpage)
2294 return self.url_result(rutv_url, 'RUTV')
2296 # Look for embedded TVC player
2297 tvc_url = TVCIE._extract_url(webpage)
2299 return self.url_result(tvc_url, 'TVC')
2301 # Look for embedded SportBox player
2302 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2304 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2306 # Look for embedded XHamster player
2307 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2309 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2311 # Look for embedded TNAFlixNetwork player
2312 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2314 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2316 # Look for embedded PornHub player
2317 pornhub_urls = PornHubIE._extract_urls(webpage)
2319 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2321 # Look for embedded DrTuber player
2322 drtuber_urls = DrTuberIE._extract_urls(webpage)
2324 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2326 # Look for embedded RedTube player
2327 redtube_urls = RedTubeIE._extract_urls(webpage)
2329 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2331 # Look for embedded Tvigle player
2333 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2334 if mobj is not None:
2335 return self.url_result(mobj.group('url'), 'Tvigle')
2337 # Look for embedded TED player
2339 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2340 if mobj is not None:
2341 return self.url_result(mobj.group('url'), 'TED')
2343 # Look for embedded Ustream videos
2344 ustream_url = UstreamIE._extract_url(webpage)
2346 return self.url_result(ustream_url, UstreamIE.ie_key())
2348 # Look for embedded arte.tv player
2350 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2352 if mobj is not None:
2353 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2355 # Look for embedded francetv player
2357 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2359 if mobj is not None:
2360 return self.url_result(mobj.group('url'))
2362 # Look for embedded smotri.com player
2363 smotri_url = SmotriIE._extract_url(webpage)
2365 return self.url_result(smotri_url, 'Smotri')
2367 # Look for embedded Myvi.ru player
2368 myvi_url = MyviIE._extract_url(webpage)
2370 return self.url_result(myvi_url)
2372 # Look for embedded soundcloud player
2373 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2375 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2377 # Look for tunein player
2378 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2380 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2382 # Look for embedded mtvservices player
2383 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2385 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2387 # Look for embedded yahoo player
2389 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2391 if mobj is not None:
2392 return self.url_result(mobj.group('url'), 'Yahoo')
2394 # Look for embedded sbs.com.au player
2398 <meta\s+property="og:video"\s+content=|
2401 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2403 if mobj is not None:
2404 return self.url_result(mobj.group('url'), 'SBS')
2406 # Look for embedded Cinchcast player
2408 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2410 if mobj is not None:
2411 return self.url_result(mobj.group('url'), 'Cinchcast')
2414 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2418 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2420 if mobj is not None:
2421 return self.url_result(mobj.group('url'), 'MLB')
2424 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2426 if mobj is not None:
2427 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2430 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2432 if mobj is not None:
2433 return self.url_result(mobj.group('url'), 'Livestream')
2435 # Look for Zapiks embed
2437 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2438 if mobj is not None:
2439 return self.url_result(mobj.group('url'), 'Zapiks')
2441 # Look for Kaltura embeds
2442 kaltura_url = KalturaIE._extract_url(webpage)
2444 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2446 # Look for Eagle.Platform embeds
2447 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2448 if eagleplatform_url:
2449 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2451 # Look for ClipYou (uses Eagle.Platform) embeds
2453 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2454 if mobj is not None:
2455 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2457 # Look for Pladform embeds
2458 pladform_url = PladformIE._extract_url(webpage)
2460 return self.url_result(pladform_url)
2462 # Look for Videomore embeds
2463 videomore_url = VideomoreIE._extract_url(webpage)
2465 return self.url_result(videomore_url)
2467 # Look for Webcaster embeds
2468 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2470 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2472 # Look for Playwire embeds
2474 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2475 if mobj is not None:
2476 return self.url_result(mobj.group('url'))
2478 # Look for 5min embeds
2480 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2481 if mobj is not None:
2482 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2484 # Look for Crooks and Liars embeds
2486 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2487 if mobj is not None:
2488 return self.url_result(mobj.group('url'))
2490 # Look for NBC Sports VPlayer embeds
2491 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2493 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2495 # Look for NBC News embeds
2496 nbc_news_embed_url = re.search(
2497 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2498 if nbc_news_embed_url:
2499 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2501 # Look for Google Drive embeds
2502 google_drive_url = GoogleDriveIE._extract_url(webpage)
2503 if google_drive_url:
2504 return self.url_result(google_drive_url, 'GoogleDrive')
2506 # Look for UDN embeds
2508 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2509 if mobj is not None:
2510 return self.url_result(
2511 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2513 # Look for Senate ISVP iframe
2514 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2516 return self.url_result(senate_isvp_url, 'SenateISVP')
2518 # Look for Dailymotion Cloud videos
2519 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2521 return self.url_result(dmcloud_url, 'DailymotionCloud')
2523 # Look for OnionStudios embeds
2524 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2525 if onionstudios_url:
2526 return self.url_result(onionstudios_url)
2528 # Look for ViewLift embeds
2529 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2531 return self.url_result(viewlift_url)
2533 # Look for JWPlatform embeds
2534 jwplatform_url = JWPlatformIE._extract_url(webpage)
2536 return self.url_result(jwplatform_url, 'JWPlatform')
2538 # Look for Digiteka embeds
2539 digiteka_url = DigitekaIE._extract_url(webpage)
2541 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2543 # Look for Arkena embeds
2544 arkena_url = ArkenaIE._extract_url(webpage)
2546 return self.url_result(arkena_url, ArkenaIE.ie_key())
2548 # Look for Piksel embeds
2549 piksel_url = PikselIE._extract_url(webpage)
2551 return self.url_result(piksel_url, PikselIE.ie_key())
2553 # Look for Limelight embeds
2554 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2556 return self.playlist_result(
2557 limelight_urls, video_id, video_title, video_description)
2559 # Look for Anvato embeds
2560 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2562 return self.playlist_result(
2563 anvato_urls, video_id, video_title, video_description)
2565 # Look for AdobeTVVideo embeds
2567 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2569 if mobj is not None:
2570 return self.url_result(
2571 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2574 # Look for Vine embeds
2576 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2578 if mobj is not None:
2579 return self.url_result(
2580 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2582 # Look for VODPlatform embeds
2584 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2586 if mobj is not None:
2587 return self.url_result(
2588 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2590 # Look for Mangomolo embeds
2592 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2594 video\?.*?\bid=(?P<video_id>\d+)|
2595 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2596 ).+?)\1''', webpage)
2597 if mobj is not None:
2599 '_type': 'url_transparent',
2600 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2601 'title': video_title,
2602 'description': video_description,
2603 'thumbnail': video_thumbnail,
2604 'uploader': video_uploader,
2606 video_id = mobj.group('video_id')
2609 'ie_key': 'MangomoloVideo',
2614 'ie_key': 'MangomoloLive',
2615 'id': mobj.group('channel_id'),
2619 # Look for Instagram embeds
2620 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2621 if instagram_embed_url is not None:
2622 return self.url_result(
2623 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2625 # Look for LiveLeak embeds
2626 liveleak_url = LiveLeakIE._extract_url(webpage)
2628 return self.url_result(liveleak_url, 'LiveLeak')
2630 # Look for 3Q SDN embeds
2631 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2634 '_type': 'url_transparent',
2635 'ie_key': ThreeQSDNIE.ie_key(),
2636 'url': self._proto_relative_url(threeqsdn_url),
2637 'title': video_title,
2638 'description': video_description,
2639 'thumbnail': video_thumbnail,
2640 'uploader': video_uploader,
2643 # Look for VBOX7 embeds
2644 vbox7_url = Vbox7IE._extract_url(webpage)
2646 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2648 # Look for DBTV embeds
2649 dbtv_urls = DBTVIE._extract_urls(webpage)
2651 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2653 # Look for Videa embeds
2654 videa_urls = VideaIE._extract_urls(webpage)
2656 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2658 # Look for 20 minuten embeds
2659 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2661 return self.playlist_from_matches(
2662 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2664 # Look for Openload embeds
2665 openload_urls = OpenloadIE._extract_urls(webpage)
2667 return self.playlist_from_matches(
2668 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2670 # Look for VideoPress embeds
2671 videopress_urls = VideoPressIE._extract_urls(webpage)
2673 return self.playlist_from_matches(
2674 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2676 # Look for Rutube embeds
2677 rutube_urls = RutubeIE._extract_urls(webpage)
2679 return self.playlist_from_matches(
2680 rutube_urls, ie=RutubeIE.ie_key())
2682 # Look for WashingtonPost embeds
2683 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2685 return self.playlist_from_matches(
2686 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2688 # Look for Mediaset embeds
2689 mediaset_urls = MediasetIE._extract_urls(webpage)
2691 return self.playlist_from_matches(
2692 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2694 def merge_dicts(dict1, dict2):
2696 for k, v in dict1.items():
2699 for k, v in dict2.items():
2702 if (k not in merged or
2703 (isinstance(v, compat_str) and v and
2704 isinstance(merged[k], compat_str) and
2709 # Looking for http://schema.org/VideoObject
2710 json_ld = self._search_json_ld(
2711 webpage, video_id, default={}, expected_type='VideoObject')
2712 if json_ld.get('url'):
2713 return merge_dicts(json_ld, info_dict)
2715 # Look for HTML5 media
2716 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2718 for entry in entries:
2721 'title': video_title,
2723 self._sort_formats(entry['formats'])
2724 return self.playlist_result(entries)
2726 jwplayer_data = self._find_jwplayer_data(
2727 webpage, video_id, transform_source=js_to_json)
2729 info = self._parse_jwplayer_data(
2730 jwplayer_data, video_id, require_title=False, base_url=url)
2731 return merge_dicts(info, info_dict)
2733 def check_video(vurl):
2734 if YoutubeIE.suitable(vurl):
2736 if RtmpIE.suitable(vurl):
2738 vpath = compat_urlparse.urlparse(vurl).path
2739 vext = determine_ext(vpath)
2740 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2742 def filter_video(urls):
2743 return list(filter(check_video, urls))
2745 # Start with something easy: JW Player in SWFObject
2746 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2748 # Look for gorilla-vid style embedding
2749 found = filter_video(re.findall(r'''(?sx)
2753 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2756 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2758 # Broaden the search a little bit
2759 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2761 # Broaden the findall a little bit: JWPlayer JS loader
2762 found = filter_video(re.findall(
2763 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2766 found = filter_video(re.findall(r'''(?xs)
2767 flowplayer\("[^"]+",\s*
2769 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2770 ["']?url["']?\s*:\s*["']([^"']+)["']
2775 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2777 # Try to find twitter cards info
2778 # twitter:player:stream should be checked before twitter:player since
2779 # it is expected to contain a raw stream (see
2780 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2781 found = filter_video(re.findall(
2782 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2784 # We look for Open Graph info:
2785 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2786 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2787 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2788 if m_video_type is not None:
2789 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2791 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2793 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2794 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2797 # Look also in Refresh HTTP header
2798 refresh_header = head_response.headers.get('Refresh')
2800 # In python 2 response HTTP headers are bytestrings
2801 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2802 refresh_header = refresh_header.decode('iso-8859-1')
2803 found = re.search(REDIRECT_REGEX, refresh_header)
2805 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2807 self.report_following_redirect(new_url)
2816 # twitter:player is a https URL to iframe player that may or may not
2817 # be supported by youtube-dl thus this is checked the very last (see
2818 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2819 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2821 return self.url_result(embed_url)
2824 raise UnsupportedError(url)
2827 for video_url in orderedSet(found):
2828 video_url = unescapeHTML(video_url)
2829 video_url = video_url.replace('\\/', '/')
2830 video_url = compat_urlparse.urljoin(url, video_url)
2831 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2833 # Sometimes, jwplayer extraction will result in a YouTube URL
2834 if YoutubeIE.suitable(video_url):
2835 entries.append(self.url_result(video_url, 'Youtube'))
2838 # here's a fun little line of code for you:
2839 video_id = os.path.splitext(video_id)[0]
2843 'uploader': video_uploader,
2844 'title': video_title,
2845 'age_limit': age_limit,
2848 if RtmpIE.suitable(video_url):
2849 entry_info_dict.update({
2850 '_type': 'url_transparent',
2851 'ie_key': RtmpIE.ie_key(),
2854 entries.append(entry_info_dict)
2857 ext = determine_ext(video_url)
2859 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2861 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2863 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2865 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2867 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2868 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2869 # Just matching .ism/manifest is not enough to be reliably sure
2870 # whether it's actually an ISM manifest or some other streaming
2871 # manifest since there are various streaming URL formats
2872 # possible (see [1]) as well as some other shenanigans like
2873 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2875 # Thus the most reasonable way to solve this is to delegate
2876 # to generic extractor in order to look into the contents of
2877 # the manifest itself.
2878 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2879 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2880 entry_info_dict = self.url_result(
2881 smuggle_url(video_url, {'to_generic': True}),
2884 entry_info_dict['url'] = video_url
2886 if entry_info_dict.get('formats'):
2887 self._sort_formats(entry_info_dict['formats'])
2889 entries.append(entry_info_dict)
2891 if len(entries) == 1:
2894 for num, e in enumerate(entries, start=1):
2895 # 'url' results don't have a title
2896 if e.get('title') is not None:
2897 e['title'] = '%s (%d)' % (e['title'], num)
2899 '_type': 'playlist',