_ Git - youtube-dl/blob - youtube_dl/extractor/generic.py

   1 # encoding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import os
   6 import re
   7 import sys
   8
   9 from .common import InfoExtractor
  10 from .youtube import YoutubeIE
  11 from ..compat import (
  12     compat_etree_fromstring,
  13     compat_urllib_parse_unquote,
  14     compat_urlparse,
  15     compat_xml_parse_error,
  16 )
  17 from ..utils import (
  18     determine_ext,
  19     ExtractorError,
  20     float_or_none,
  21     HEADRequest,
  22     is_html,
  23     orderedSet,
  24     sanitized_Request,
  25     smuggle_url,
  26     unescapeHTML,
  27     unified_strdate,
  28     unsmuggle_url,
  29     UnsupportedError,
  30     url_basename,
  31     xpath_text,
  32 )
  33 from .brightcove import (
  34     BrightcoveLegacyIE,
  35     BrightcoveNewIE,
  36 )
  37 from .nbc import NBCSportsVPlayerIE
  38 from .ooyala import OoyalaIE
  39 from .rutv import RUTVIE
  40 from .tvc import TVCIE
  41 from .sportbox import SportBoxEmbedIE
  42 from .smotri import SmotriIE
  43 from .myvi import MyviIE
  44 from .condenast import CondeNastIE
  45 from .udn import UDNEmbedIE
  46 from .senateisvp import SenateISVPIE
  47 from .svt import SVTIE
  48 from .pornhub import PornHubIE
  49 from .xhamster import XHamsterEmbedIE
  50 from .tnaflix import TNAFlixNetworkEmbedIE
  51 from .vimeo import VimeoIE
  52 from .dailymotion import (
  53     DailymotionIE,
  54     DailymotionCloudIE,
  55 )
  56 from .onionstudios import OnionStudiosIE
  57 from .viewlift import ViewLiftEmbedIE
  58 from .screenwavemedia import ScreenwaveMediaIE
  59 from .mtv import MTVServicesEmbeddedIE
  60 from .pladform import PladformIE
  61 from .videomore import VideomoreIE
  62 from .googledrive import GoogleDriveIE
  63 from .jwplatform import JWPlatformIE
  64 from .digiteka import DigitekaIE
  65 from .arkena import ArkenaIE
  66 from .instagram import InstagramIE
  67 from .liveleak import LiveLeakIE
  68 from .threeqsdn import ThreeQSDNIE
  69 from .theplatform import ThePlatformIE
  70 from .vessel import VesselIE
  71 from .kaltura import KalturaIE
  72 from .eagleplatform import EaglePlatformIE
  73 from .facebook import FacebookIE
  74 from .soundcloud import SoundcloudIE
  75 from .vbox7 import Vbox7IE
  76 from .dbtv import DBTVIE
  77
  78
  79 class GenericIE(InfoExtractor):
  80     IE_DESC = 'Generic downloader that works on some sites'
  81     _VALID_URL = r'.*'
  82     IE_NAME = 'generic'
  83     _TESTS = [
  84         # Direct link to a video
  85         {
  86             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  87             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  88             'info_dict': {
  89                 'id': 'trailer',
  90                 'ext': 'mp4',
  91                 'title': 'trailer',
  92                 'upload_date': '20100513',
  93             }
  94         },
  95         # Direct link to media delivered compressed (until Accept-Encoding is *)
  96         {
  97             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  98             'md5': '128c42e68b13950268b648275386fc74',
  99             'info_dict': {
 100                 'id': 'FictionJunction-Parallel_Hearts',
 101                 'ext': 'flac',
 102                 'title': 'FictionJunction-Parallel_Hearts',
 103                 'upload_date': '20140522',
 104             },
 105             'expected_warnings': [
 106                 'URL could be a direct video link, returning it as such.'
 107             ]
 108         },
 109         # Direct download with broken HEAD
 110         {
 111             'url': 'http://ai-radio.org:8000/radio.opus',
 112             'info_dict': {
 113                 'id': 'radio',
 114                 'ext': 'opus',
 115                 'title': 'radio',
 116             },
 117             'params': {
 118                 'skip_download': True,  # infinite live stream
 119             },
 120             'expected_warnings': [
 121                 r'501.*Not Implemented',
 122                 r'400.*Bad Request',
 123             ],
 124         },
 125         # Direct link with incorrect MIME type
 126         {
 127             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 128             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 129             'info_dict': {
 130                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 131                 'id': '5_Lennart_Poettering_-_Systemd',
 132                 'ext': 'webm',
 133                 'title': '5_Lennart_Poettering_-_Systemd',
 134                 'upload_date': '20141120',
 135             },
 136             'expected_warnings': [
 137                 'URL could be a direct video link, returning it as such.'
 138             ]
 139         },
 140         # RSS feed
 141         {
 142             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 143             'info_dict': {
 144                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 145                 'title': 'Zero Punctuation',
 146                 'description': 're:.*groundbreaking video review series.*'
 147             },
 148             'playlist_mincount': 11,
 149         },
 150         # RSS feed with enclosure
 151         {
 152             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 153             'info_dict': {
 154                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 155                 'ext': 'm4v',
 156                 'upload_date': '20150228',
 157                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 158             }
 159         },
 160         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 161         {
 162             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 163             'info_dict': {
 164                 'id': 'smil',
 165                 'ext': 'mp4',
 166                 'title': 'Automatics, robotics and biocybernetics',
 167                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 168                 'upload_date': '20130627',
 169                 'formats': 'mincount:16',
 170                 'subtitles': 'mincount:1',
 171             },
 172             'params': {
 173                 'force_generic_extractor': True,
 174                 'skip_download': True,
 175             },
 176         },
 177         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 178         {
 179             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 180             'info_dict': {
 181                 'id': 'hds',
 182                 'ext': 'flv',
 183                 'title': 'hds',
 184                 'formats': 'mincount:1',
 185             },
 186             'params': {
 187                 'skip_download': True,
 188             },
 189         },
 190         # SMIL from https://www.restudy.dk/video/play/id/1637
 191         {
 192             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 193             'info_dict': {
 194                 'id': 'video_1637',
 195                 'ext': 'flv',
 196                 'title': 'video_1637',
 197                 'formats': 'mincount:3',
 198             },
 199             'params': {
 200                 'skip_download': True,
 201             },
 202         },
 203         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 204         {
 205             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 206             'info_dict': {
 207                 'id': 'smil-service',
 208                 'ext': 'flv',
 209                 'title': 'smil-service',
 210                 'formats': 'mincount:1',
 211             },
 212             'params': {
 213                 'skip_download': True,
 214             },
 215         },
 216         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 217         {
 218             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 219             'info_dict': {
 220                 'id': '4719370',
 221                 'ext': 'mp4',
 222                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 223                 'formats': 'mincount:3',
 224             },
 225             'params': {
 226                 'skip_download': True,
 227             },
 228         },
 229         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 230         {
 231             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 232             'info_dict': {
 233                 'id': 'mZlp2ctYIUEB',
 234                 'ext': 'mp4',
 235                 'title': 'Tikibad ontruimd wegens brand',
 236                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 237                 'thumbnail': 're:^https?://.*\.jpg$',
 238                 'duration': 33,
 239             },
 240             'params': {
 241                 'skip_download': True,
 242             },
 243         },
 244         # MPD from http://dash-mse-test.appspot.com/media.html
 245         {
 246             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 247             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 248             'info_dict': {
 249                 'id': 'car-20120827-manifest',
 250                 'ext': 'mp4',
 251                 'title': 'car-20120827-manifest',
 252                 'formats': 'mincount:9',
 253                 'upload_date': '20130904',
 254             },
 255             'params': {
 256                 'format': 'bestvideo',
 257             },
 258         },
 259         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 260         {
 261             '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',
 262             'info_dict': {
 263                 'id': 'content',
 264                 'ext': 'mp4',
 265                 'title': 'content',
 266                 'formats': 'mincount:8',
 267             },
 268             'params': {
 269                 # m3u8 downloads
 270                 'skip_download': True,
 271             }
 272         },
 273         # m3u8 served with Content-Type: text/plain
 274         {
 275             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 276             'info_dict': {
 277                 'id': 'index',
 278                 'ext': 'mp4',
 279                 'title': 'index',
 280                 'upload_date': '20140720',
 281                 'formats': 'mincount:11',
 282             },
 283             'params': {
 284                 # m3u8 downloads
 285                 'skip_download': True,
 286             }
 287         },
 288         # google redirect
 289         {
 290             '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',
 291             'info_dict': {
 292                 'id': 'cmQHVoWB5FY',
 293                 'ext': 'mp4',
 294                 'upload_date': '20130224',
 295                 'uploader_id': 'TheVerge',
 296                 'description': 're:^Chris Ziegler takes a look at the\.*',
 297                 'uploader': 'The Verge',
 298                 'title': 'First Firefox OS phones side-by-side',
 299             },
 300             'params': {
 301                 'skip_download': False,
 302             }
 303         },
 304         {
 305             # redirect in Refresh HTTP header
 306             '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',
 307             'info_dict': {
 308                 'id': 'pO8h3EaFRdo',
 309                 'ext': 'mp4',
 310                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 311                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 312                 'upload_date': '20150917',
 313                 'uploader_id': 'brtvofficial',
 314                 'uploader': 'Boiler Room',
 315             },
 316             'params': {
 317                 'skip_download': False,
 318             },
 319         },
 320         {
 321             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 322             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 323             'info_dict': {
 324                 'id': '13601338388002',
 325                 'ext': 'mp4',
 326                 'uploader': 'www.hodiho.fr',
 327                 'title': 'R\u00e9gis plante sa Jeep',
 328             }
 329         },
 330         # bandcamp page with custom domain
 331         {
 332             'add_ie': ['Bandcamp'],
 333             'url': 'http://bronyrock.com/track/the-pony-mash',
 334             'info_dict': {
 335                 'id': '3235767654',
 336                 'ext': 'mp3',
 337                 'title': 'The Pony Mash',
 338                 'uploader': 'M_Pallante',
 339             },
 340             'skip': 'There is a limit of 200 free downloads / month for the test song',
 341         },
 342         # embedded brightcove video
 343         # it also tests brightcove videos that need to set the 'Referer' in the
 344         # http requests
 345         {
 346             'add_ie': ['BrightcoveLegacy'],
 347             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 348             'info_dict': {
 349                 'id': '2765128793001',
 350                 'ext': 'mp4',
 351                 'title': 'Le cours de bourse : l’analyse technique',
 352                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 353                 'uploader': 'BFM BUSINESS',
 354             },
 355             'params': {
 356                 'skip_download': True,
 357             },
 358         },
 359         {
 360             # https://github.com/rg3/youtube-dl/issues/2253
 361             'url': 'http://bcove.me/i6nfkrc3',
 362             'md5': '0ba9446db037002366bab3b3eb30c88c',
 363             'info_dict': {
 364                 'id': '3101154703001',
 365                 'ext': 'mp4',
 366                 'title': 'Still no power',
 367                 'uploader': 'thestar.com',
 368                 '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.',
 369             },
 370             'add_ie': ['BrightcoveLegacy'],
 371         },
 372         {
 373             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 374             'md5': 'fb973ecf6e4a78a67453647444222983',
 375             'info_dict': {
 376                 'id': '3414141473001',
 377                 'ext': 'mp4',
 378                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 379                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 380                 'uploader': 'Championat',
 381             },
 382         },
 383         {
 384             # https://github.com/rg3/youtube-dl/issues/3541
 385             'add_ie': ['BrightcoveLegacy'],
 386             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 387             'info_dict': {
 388                 'id': '3866516442001',
 389                 'ext': 'mp4',
 390                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 391                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 392                 'uploader': 'SBS Broadcasting',
 393             },
 394             'skip': 'Restricted to Netherlands',
 395             'params': {
 396                 'skip_download': True,  # m3u8 download
 397             },
 398         },
 399         # ooyala video
 400         {
 401             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 402             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 403             'info_dict': {
 404                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 405                 'ext': 'mp4',
 406                 'title': '2cc213299525360.mov',  # that's what we get
 407                 'duration': 238.231,
 408             },
 409             'add_ie': ['Ooyala'],
 410         },
 411         {
 412             # ooyala video embedded with http://player.ooyala.com/iframe.js
 413             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 414             'info_dict': {
 415                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 416                 'ext': 'mp4',
 417                 'title': '"Steve Jobs: Man in the Machine" trailer',
 418                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 419                 'duration': 135.427,
 420             },
 421             'params': {
 422                 'skip_download': True,
 423             },
 424         },
 425         # embed.ly video
 426         {
 427             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 428             'info_dict': {
 429                 'id': '9ODmcdjQcHQ',
 430                 'ext': 'mp4',
 431                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 432                 'upload_date': '20140225',
 433                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 434                 'uploader': 'Tested',
 435                 'uploader_id': 'testedcom',
 436             },
 437             # No need to test YoutubeIE here
 438             'params': {
 439                 'skip_download': True,
 440             },
 441         },
 442         # funnyordie embed
 443         {
 444             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 445             'info_dict': {
 446                 'id': '18e820ec3f',
 447                 'ext': 'mp4',
 448                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 449                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 450             },
 451         },
 452         # RUTV embed
 453         {
 454             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 455             'info_dict': {
 456                 'id': '776940',
 457                 'ext': 'mp4',
 458                 'title': 'Охотское море стало целиком российским',
 459                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 460             },
 461             'params': {
 462                 # m3u8 download
 463                 'skip_download': True,
 464             },
 465         },
 466         # TVC embed
 467         {
 468             '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/',
 469             'info_dict': {
 470                 'id': '55304',
 471                 'ext': 'mp4',
 472                 'title': 'Дошкольное воспитание',
 473             },
 474         },
 475         # SportBox embed
 476         {
 477             'url': 'http://www.vestifinance.ru/articles/25753',
 478             'info_dict': {
 479                 'id': '25753',
 480                 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 481             },
 482             'playlist': [{
 483                 'info_dict': {
 484                     'id': '370908',
 485                     'title': 'Госзаказ. День 3',
 486                     'ext': 'mp4',
 487                 }
 488             }, {
 489                 'info_dict': {
 490                     'id': '370905',
 491                     'title': 'Госзаказ. День 2',
 492                     'ext': 'mp4',
 493                 }
 494             }, {
 495                 'info_dict': {
 496                     'id': '370902',
 497                     'title': 'Госзаказ. День 1',
 498                     'ext': 'mp4',
 499                 }
 500             }],
 501             'params': {
 502                 # m3u8 download
 503                 'skip_download': True,
 504             },
 505         },
 506         # Myvi.ru embed
 507         {
 508             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 509             'info_dict': {
 510                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 511                 'ext': 'mp4',
 512                 'title': 'Ужастики, русский трейлер (2015)',
 513                 'thumbnail': 're:^https?://.*\.jpg$',
 514                 'duration': 153,
 515             }
 516         },
 517         # XHamster embed
 518         {
 519             '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',
 520             'info_dict': {
 521                 'id': 'showthread',
 522                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 523             },
 524             'playlist_mincount': 7,
 525         },
 526         # Embedded TED video
 527         {
 528             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 529             'md5': '65fdff94098e4a607385a60c5177c638',
 530             'info_dict': {
 531                 'id': '1969',
 532                 'ext': 'mp4',
 533                 'title': 'Hidden miracles of the natural world',
 534                 'uploader': 'Louie Schwartzberg',
 535                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 536             }
 537         },
 538         # Embedded Ustream video
 539         {
 540             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
 541             'md5': '27b99cdb639c9b12a79bca876a073417',
 542             'info_dict': {
 543                 'id': '45734260',
 544                 'ext': 'flv',
 545                 'uploader': 'AU SPA:  The NSA and Privacy',
 546                 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
 547             }
 548         },
 549         # nowvideo embed hidden behind percent encoding
 550         {
 551             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 552             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 553             'info_dict': {
 554                 'id': '06e53103ca9aa',
 555                 'ext': 'flv',
 556                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 557                 'description': 'No description',
 558             },
 559         },
 560         # arte embed
 561         {
 562             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 563             'md5': '7653032cbb25bf6c80d80f217055fa43',
 564             'info_dict': {
 565                 'id': '048195-004_PLUS7-F',
 566                 'ext': 'flv',
 567                 'title': 'X:enius',
 568                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 569                 'upload_date': '20140320',
 570             },
 571             'params': {
 572                 'skip_download': 'Requires rtmpdump'
 573             }
 574         },
 575         # francetv embed
 576         {
 577             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 578             'info_dict': {
 579                 'id': 'EV_30231',
 580                 'ext': 'mp4',
 581                 'title': 'Alcaline, le concert avec Calogero',
 582                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 583                 'upload_date': '20150226',
 584                 'timestamp': 1424989860,
 585                 'duration': 5400,
 586             },
 587             'params': {
 588                 # m3u8 downloads
 589                 'skip_download': True,
 590             },
 591             'expected_warnings': [
 592                 'Forbidden'
 593             ]
 594         },
 595         # Condé Nast embed
 596         {
 597             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 598             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 599             'info_dict': {
 600                 'id': '53501be369702d3275860000',
 601                 'ext': 'mp4',
 602                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 603             }
 604         },
 605         # Dailymotion embed
 606         {
 607             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 608             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 609             'info_dict': {
 610                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 611                 'ext': 'mp4',
 612                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 613                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 614                 'uploader': 'Spi0n',
 615                 'uploader_id': 'xgditw',
 616                 'upload_date': '20140425',
 617                 'timestamp': 1398441542,
 618             },
 619             'add_ie': ['Dailymotion'],
 620         },
 621         # YouTube embed
 622         {
 623             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 624             'info_dict': {
 625                 'id': 'FXRb4ykk4S0',
 626                 'ext': 'mp4',
 627                 'title': 'The NBL Auction 2014',
 628                 'uploader': 'BADMINTON England',
 629                 'uploader_id': 'BADMINTONEvents',
 630                 'upload_date': '20140603',
 631                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 632             },
 633             'add_ie': ['Youtube'],
 634             'params': {
 635                 'skip_download': True,
 636             }
 637         },
 638         # MTVSercices embed
 639         {
 640             'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
 641             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
 642             'info_dict': {
 643                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
 644                 'ext': 'mp4',
 645                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
 646                 'description': 'Two valets share their love for movie star Liam Neesons.',
 647                 'timestamp': 1349922600,
 648                 'upload_date': '20121011',
 649             },
 650         },
 651         # YouTube embed via <data-embed-url="">
 652         {
 653             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 654             'info_dict': {
 655                 'id': '4vAffPZIT44',
 656                 'ext': 'mp4',
 657                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 658                 'uploader': 'Gameloft',
 659                 'uploader_id': 'gameloft',
 660                 'upload_date': '20140828',
 661                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 662             },
 663             'params': {
 664                 'skip_download': True,
 665             }
 666         },
 667         # Camtasia studio
 668         {
 669             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 670             'playlist': [{
 671                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 672                 'info_dict': {
 673                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 674                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 675                     'ext': 'flv',
 676                     'duration': 2235.90,
 677                 }
 678             }, {
 679                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 680                 'info_dict': {
 681                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 682                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 683                     'ext': 'flv',
 684                     'duration': 2235.93,
 685                 }
 686             }],
 687             'info_dict': {
 688                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 689             }
 690         },
 691         # Flowplayer
 692         {
 693             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 694             'md5': '9d65602bf31c6e20014319c7d07fba27',
 695             'info_dict': {
 696                 'id': '5123ea6d5e5a7',
 697                 'ext': 'mp4',
 698                 'age_limit': 18,
 699                 'uploader': 'www.handjobhub.com',
 700                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 701             }
 702         },
 703         # Multiple brightcove videos
 704         # https://github.com/rg3/youtube-dl/issues/2283
 705         {
 706             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 707             'info_dict': {
 708                 'id': 'always-never',
 709                 'title': 'Always / Never - The New Yorker',
 710             },
 711             'playlist_count': 3,
 712             'params': {
 713                 'extract_flat': False,
 714                 'skip_download': True,
 715             }
 716         },
 717         # MLB embed
 718         {
 719             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 720             'md5': '96f09a37e44da40dd083e12d9a683327',
 721             'info_dict': {
 722                 'id': '33322633',
 723                 'ext': 'mp4',
 724                 'title': 'Ump changes call to ball',
 725                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 726                 'duration': 48,
 727                 'timestamp': 1401537900,
 728                 'upload_date': '20140531',
 729                 'thumbnail': 're:^https?://.*\.jpg$',
 730             },
 731         },
 732         # Wistia embed
 733         {
 734             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 735             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 736             'info_dict': {
 737                 'id': '6e2wtrbdaf',
 738                 'ext': 'mov',
 739                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 740                 'description': 'a Paywall Videos video from Remilon',
 741                 'duration': 644.072,
 742                 'uploader': 'study.com',
 743                 'timestamp': 1459678540,
 744                 'upload_date': '20160403',
 745                 'filesize': 24687186,
 746             },
 747         },
 748         {
 749             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 750             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 751             'info_dict': {
 752                 'id': 'uxjb0lwrcz',
 753                 'ext': 'mp4',
 754                 'title': 'Conversation about Hexagonal Rails Part 1',
 755                 'description': 'a Martin Fowler video from ThoughtWorks',
 756                 'duration': 1715.0,
 757                 'uploader': 'thoughtworks.wistia.com',
 758                 'timestamp': 1401832161,
 759                 'upload_date': '20140603',
 760             },
 761         },
 762         # Wistia standard embed (async)
 763         {
 764             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 765             'info_dict': {
 766                 'id': '807fafadvk',
 767                 'ext': 'mp4',
 768                 'title': 'Drip Brennan Dunn Workshop',
 769                 'description': 'a JV Webinars video from getdrip-1',
 770                 'duration': 4986.95,
 771                 'timestamp': 1463607249,
 772                 'upload_date': '20160518',
 773             },
 774             'params': {
 775                 'skip_download': True,
 776             }
 777         },
 778         # Soundcloud embed
 779         {
 780             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 781             'info_dict': {
 782                 'id': '174391317',
 783                 'ext': 'mp3',
 784                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 785                 'uploader': 'Sophos Security',
 786                 'title': 'Chet Chat 171 - Oct 29, 2014',
 787                 'upload_date': '20141029',
 788             }
 789         },
 790         # Soundcloud multiple embeds
 791         {
 792             'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
 793             'info_dict': {
 794                 'id': '52809',
 795                 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
 796             },
 797             'playlist_mincount': 7,
 798         },
 799         # Livestream embed
 800         {
 801             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 802             'info_dict': {
 803                 'id': '67864563',
 804                 'ext': 'flv',
 805                 'upload_date': '20141112',
 806                 'title': 'Rosetta #CometLanding webcast HL 10',
 807             }
 808         },
 809         # Another Livestream embed, without 'new.' in URL
 810         {
 811             'url': 'https://www.freespeech.org/',
 812             'info_dict': {
 813                 'id': '123537347',
 814                 'ext': 'mp4',
 815                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 816             },
 817             'params': {
 818                 # Live stream
 819                 'skip_download': True,
 820             },
 821         },
 822         # LazyYT
 823         {
 824             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
 825             'info_dict': {
 826                 'id': '1986',
 827                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
 828             },
 829             'playlist_mincount': 2,
 830         },
 831         # Cinchcast embed
 832         {
 833             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
 834             'info_dict': {
 835                 'id': '7141703',
 836                 'ext': 'mp3',
 837                 'upload_date': '20141126',
 838                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
 839             }
 840         },
 841         # Cinerama player
 842         {
 843             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
 844             'info_dict': {
 845                 'id': '730m_DandD_1901_512k',
 846                 'ext': 'mp4',
 847                 'uploader': 'www.abc.net.au',
 848                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
 849             }
 850         },
 851         # embedded viddler video
 852         {
 853             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
 854             'info_dict': {
 855                 'id': '4d03aad9',
 856                 'ext': 'mp4',
 857                 'uploader': 'deadspin',
 858                 'title': 'WALL-TO-GORTAT',
 859                 'timestamp': 1422285291,
 860                 'upload_date': '20150126',
 861             },
 862             'add_ie': ['Viddler'],
 863         },
 864         # Libsyn embed
 865         {
 866             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
 867             'info_dict': {
 868                 'id': '3377616',
 869                 'ext': 'mp3',
 870                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
 871                 'description': 'md5:601cb790edd05908957dae8aaa866465',
 872                 'upload_date': '20150220',
 873             },
 874             'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
 875         },
 876         # jwplayer YouTube
 877         {
 878             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
 879             'info_dict': {
 880                 'id': 'Mrj4DVp2zeA',
 881                 'ext': 'mp4',
 882                 'upload_date': '20150212',
 883                 'uploader': 'The National Archives UK',
 884                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
 885                 'uploader_id': 'NationalArchives08',
 886                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
 887             },
 888         },
 889         # rtl.nl embed
 890         {
 891             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
 892             'playlist_mincount': 5,
 893             'info_dict': {
 894                 'id': 'aanslagen-kopenhagen',
 895                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
 896             }
 897         },
 898         # Zapiks embed
 899         {
 900             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
 901             'info_dict': {
 902                 'id': '118046',
 903                 'ext': 'mp4',
 904                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
 905             }
 906         },
 907         # Kaltura embed (different embed code)
 908         {
 909             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
 910             'info_dict': {
 911                 'id': '1_a52wc67y',
 912                 'ext': 'flv',
 913                 'upload_date': '20150127',
 914                 'uploader_id': 'PremierMedia',
 915                 'timestamp': int,
 916                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
 917             },
 918         },
 919         # Kaltura embed protected with referrer
 920         {
 921             'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
 922             'info_dict': {
 923                 'id': '1_g4fbemnq',
 924                 'ext': 'mp4',
 925                 'title': 'Violetta - Achter De Schermen - Ruggero',
 926                 'description': 'Achter de schermen met Ruggero',
 927                 'timestamp': 1435133761,
 928                 'upload_date': '20150624',
 929                 'uploader_id': 'echojecka',
 930             },
 931         },
 932         # Kaltura embed with single quotes
 933         {
 934             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
 935             'info_dict': {
 936                 'id': '0_izeg5utt',
 937                 'ext': 'mp4',
 938                 'title': '35871',
 939                 'timestamp': 1355743100,
 940                 'upload_date': '20121217',
 941                 'uploader_id': 'batchUser',
 942             },
 943             'add_ie': ['Kaltura'],
 944         },
 945         {
 946             # Kaltura embedded via quoted entry_id
 947             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
 948             'info_dict': {
 949                 'id': '0_utuok90b',
 950                 'ext': 'mp4',
 951                 'title': '06_matthew_brender_raj_dutt',
 952                 'timestamp': 1466638791,
 953                 'upload_date': '20160622',
 954             },
 955             'add_ie': ['Kaltura'],
 956             'expected_warnings': [
 957                 'Could not send HEAD request'
 958             ],
 959             'params': {
 960                 'skip_download': True,
 961             }
 962         },
 963         # Eagle.Platform embed (generic URL)
 964         {
 965             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
 966             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 967             'info_dict': {
 968                 'id': '227304',
 969                 'ext': 'mp4',
 970                 'title': 'Навальный вышел на свободу',
 971                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
 972                 'thumbnail': 're:^https?://.*\.jpg$',
 973                 'duration': 87,
 974                 'view_count': int,
 975                 'age_limit': 0,
 976             },
 977         },
 978         # ClipYou (Eagle.Platform) embed (custom URL)
 979         {
 980             'url': 'http://muz-tv.ru/play/7129/',
 981             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 982             'info_dict': {
 983                 'id': '12820',
 984                 'ext': 'mp4',
 985                 'title': "'O Sole Mio",
 986                 'thumbnail': 're:^https?://.*\.jpg$',
 987                 'duration': 216,
 988                 'view_count': int,
 989             },
 990         },
 991         # Pladform embed
 992         {
 993             'url': 'http://muz-tv.ru/kinozal/view/7400/',
 994             'info_dict': {
 995                 'id': '100183293',
 996                 'ext': 'mp4',
 997                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
 998                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
 999                 'thumbnail': 're:^https?://.*\.jpg$',
1000                 'duration': 694,
1001                 'age_limit': 0,
1002             },
1003         },
1004         # Playwire embed
1005         {
1006             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1007             'info_dict': {
1008                 'id': '3519514',
1009                 'ext': 'mp4',
1010                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1011                 'thumbnail': 're:^https?://.*\.png$',
1012                 'duration': 45.115,
1013             },
1014         },
1015         # 5min embed
1016         {
1017             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1018             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1019             'info_dict': {
1020                 'id': '518726732',
1021                 'ext': 'mp4',
1022                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1023             },
1024         },
1025         # SVT embed
1026         {
1027             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1028             'info_dict': {
1029                 'id': '2900353',
1030                 'ext': 'flv',
1031                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1032                 'duration': 27,
1033                 'age_limit': 0,
1034             },
1035         },
1036         # Crooks and Liars embed
1037         {
1038             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1039             'info_dict': {
1040                 'id': '8RUoRhRi',
1041                 'ext': 'mp4',
1042                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1043                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1044                 'timestamp': 1428207000,
1045                 'upload_date': '20150405',
1046                 'uploader': 'Heather',
1047             },
1048         },
1049         # Crooks and Liars external embed
1050         {
1051             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1052             'info_dict': {
1053                 'id': 'MTE3MjUtMzQ2MzA',
1054                 'ext': 'mp4',
1055                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1056                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1057                 'timestamp': 1265032391,
1058                 'upload_date': '20100201',
1059                 'uploader': 'Heather',
1060             },
1061         },
1062         # NBC Sports vplayer embed
1063         {
1064             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1065             'info_dict': {
1066                 'id': 'ln7x1qSThw4k',
1067                 'ext': 'flv',
1068                 'title': "PFT Live: New leader in the 'new-look' defense",
1069                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1070                 'uploader': 'NBCU-SPORTS',
1071                 'upload_date': '20140107',
1072                 'timestamp': 1389118457,
1073             },
1074         },
1075         # NBC News embed
1076         {
1077             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1078             'md5': '1aa589c675898ae6d37a17913cf68d66',
1079             'info_dict': {
1080                 'id': '701714499682',
1081                 'ext': 'mp4',
1082                 'title': 'PREVIEW: On Assignment: David Letterman',
1083                 '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.',
1084             },
1085         },
1086         # UDN embed
1087         {
1088             'url': 'https://video.udn.com/news/300346',
1089             'md5': 'fd2060e988c326991037b9aff9df21a6',
1090             'info_dict': {
1091                 'id': '300346',
1092                 'ext': 'mp4',
1093                 'title': '中一中男師變性 全校師生力挺',
1094                 'thumbnail': 're:^https?://.*\.jpg$',
1095             },
1096             'params': {
1097                 # m3u8 download
1098                 'skip_download': True,
1099             },
1100         },
1101         # Ooyala embed
1102         {
1103             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1104             'info_dict': {
1105                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1106                 'ext': 'mp4',
1107                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1108                 'title': 'This is what separates the Excel masters from the wannabes',
1109                 'duration': 191.933,
1110             },
1111             'params': {
1112                 # m3u8 downloads
1113                 'skip_download': True,
1114             }
1115         },
1116         # Brightcove URL in single quotes
1117         {
1118             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1119             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1120             'info_dict': {
1121                 'id': '4255764656001',
1122                 'ext': 'mp4',
1123                 'title': 'SN Presents: Russell Martin, World Citizen',
1124                 '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.',
1125                 'uploader': 'Rogers Sportsnet',
1126                 'uploader_id': '1704050871',
1127                 'upload_date': '20150525',
1128                 'timestamp': 1432570283,
1129             },
1130         },
1131         # Dailymotion Cloud video
1132         {
1133             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1134             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1135             'info_dict': {
1136                 'id': 'x2uy8t3',
1137                 'ext': 'mp4',
1138                 'title': 'Sauvons les abeilles ! - Le débat',
1139                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1140                 'thumbnail': 're:^https?://.*\.jpe?g$',
1141                 'timestamp': 1434970506,
1142                 'upload_date': '20150622',
1143                 'uploader': 'Public Sénat',
1144                 'uploader_id': 'xa9gza',
1145             }
1146         },
1147         # OnionStudios embed
1148         {
1149             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1150             'info_dict': {
1151                 'id': '2855',
1152                 'ext': 'mp4',
1153                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1154                 'thumbnail': 're:^https?://.*\.jpe?g$',
1155                 'uploader': 'ClickHole',
1156                 'uploader_id': 'clickhole',
1157             }
1158         },
1159         # SnagFilms embed
1160         {
1161             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1162             'info_dict': {
1163                 'id': '74849a00-85a9-11e1-9660-123139220831',
1164                 'ext': 'mp4',
1165                 'title': '#whilewewatch',
1166             }
1167         },
1168         # AdobeTVVideo embed
1169         {
1170             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1171             'md5': '43662b577c018ad707a63766462b1e87',
1172             'info_dict': {
1173                 'id': '2456',
1174                 'ext': 'mp4',
1175                 'title': 'New experience with Acrobat DC',
1176                 'description': 'New experience with Acrobat DC',
1177                 'duration': 248.667,
1178             },
1179         },
1180         # ScreenwaveMedia embed
1181         {
1182             'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1183             'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1184             'info_dict': {
1185                 'id': 'cinemasnob-55d26273809dd',
1186                 'ext': 'mp4',
1187                 'title': 'cinemasnob',
1188             },
1189         },
1190         # BrightcoveInPageEmbed embed
1191         {
1192             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1193             'info_dict': {
1194                 'id': '4238694884001',
1195                 'ext': 'flv',
1196                 'title': 'Tabletop: Dread, Last Thoughts',
1197                 'description': 'Tabletop: Dread, Last Thoughts',
1198                 'duration': 51690,
1199             },
1200         },
1201         # JWPlayer with M3U8
1202         {
1203             'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1204             'info_dict': {
1205                 'id': 'playlist',
1206                 'ext': 'mp4',
1207                 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1208                 'uploader': 'ren.tv',
1209             },
1210             'params': {
1211                 # m3u8 downloads
1212                 'skip_download': True,
1213             }
1214         },
1215         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1216         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1217         {
1218             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1219             'info_dict': {
1220                 'id': '4785848093001',
1221                 'ext': 'mp4',
1222                 'title': 'The Cardinal Pell Interview',
1223                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1224                 'uploader': 'GlobeCast Australia - GlobeStream',
1225                 'uploader_id': '2733773828001',
1226                 'upload_date': '20160304',
1227                 'timestamp': 1457083087,
1228             },
1229             'params': {
1230                 # m3u8 downloads
1231                 'skip_download': True,
1232             },
1233         },
1234         # Another form of arte.tv embed
1235         {
1236             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1237             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1238             'info_dict': {
1239                 'id': '030273-562_PLUS7-F',
1240                 'ext': 'mp4',
1241                 'title': 'ARTE Reportage - Nulle part, en France',
1242                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1243                 'upload_date': '20160409',
1244             },
1245         },
1246         # LiveLeak embed
1247         {
1248             'url': 'http://www.wykop.pl/link/3088787/',
1249             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1250             'info_dict': {
1251                 'id': '874_1459135191',
1252                 'ext': 'mp4',
1253                 'title': 'Man shows poor quality of new apartment building',
1254                 'description': 'The wall is like a sand pile.',
1255                 'uploader': 'Lake8737',
1256             }
1257         },
1258         # Duplicated embedded video URLs
1259         {
1260             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1261             'info_dict': {
1262                 'id': '149298443_480_16c25b74_2',
1263                 'ext': 'mp4',
1264                 'title': 'vs. Blue Orange Spring Game',
1265                 'uploader': 'www.hudl.com',
1266             },
1267         },
1268         # twitter:player:stream embed
1269         {
1270             'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1271             'info_dict': {
1272                 'id': 'master',
1273                 'ext': 'mp4',
1274                 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1275                 'uploader': 'www.rtl.be',
1276             },
1277             'params': {
1278                 # m3u8 downloads
1279                 'skip_download': True,
1280             },
1281         },
1282         # twitter:player embed
1283         {
1284             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1285             'md5': 'a3e0df96369831de324f0778e126653c',
1286             'info_dict': {
1287                 'id': '4909620399001',
1288                 'ext': 'mp4',
1289                 'title': 'What Do Black Holes Sound Like?',
1290                 'description': 'what do black holes sound like',
1291                 'upload_date': '20160524',
1292                 'uploader_id': '29913724001',
1293                 'timestamp': 1464107587,
1294                 'uploader': 'TheAtlantic',
1295             },
1296             'add_ie': ['BrightcoveLegacy'],
1297         },
1298         # Facebook <iframe> embed
1299         {
1300             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1301             'md5': 'fbcde74f534176ecb015849146dd3aee',
1302             'info_dict': {
1303                 'id': '599637780109885',
1304                 'ext': 'mp4',
1305                 'title': 'Facebook video #599637780109885',
1306             },
1307         },
1308         # Facebook API embed
1309         {
1310             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1311             'md5': 'a47372ee61b39a7b90287094d447d94e',
1312             'info_dict': {
1313                 'id': '10153467542406923',
1314                 'ext': 'mp4',
1315                 'title': 'Facebook video #10153467542406923',
1316             },
1317         },
1318         # Wordpress "YouTube Video Importer" plugin
1319         {
1320             'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1321             'md5': 'd16797741b560b485194eddda8121b48',
1322             'info_dict': {
1323                 'id': 'HNTXWDXV9Is',
1324                 'ext': 'mp4',
1325                 'title': 'Blue Devils Drumline Stanford lot 2016',
1326                 'upload_date': '20160627',
1327                 'uploader_id': 'GENOCIDE8GENERAL10',
1328                 'uploader': 'cylus cyrus',
1329             },
1330         },
1331         {
1332             # video stored on custom kaltura server
1333             'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1334             'md5': '537617d06e64dfed891fa1593c4b30cc',
1335             'info_dict': {
1336                 'id': '0_1iotm5bh',
1337                 'ext': 'mp4',
1338                 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1339                 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1340                 'uploader_id': 'videos.expansion@el-mundo.net',
1341                 'upload_date': '20150429',
1342                 'timestamp': 1430303472,
1343             },
1344             'add_ie': ['Kaltura'],
1345         },
1346         {
1347             # Non-standard Vimeo embed
1348             'url': 'https://openclassrooms.com/courses/understanding-the-web',
1349             'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1350             'info_dict': {
1351                 'id': '148867247',
1352                 'ext': 'mp4',
1353                 'title': 'Understanding the web - Teaser',
1354                 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1355                 'upload_date': '20151214',
1356                 'uploader': 'OpenClassrooms',
1357                 'uploader_id': 'openclassrooms',
1358             },
1359             'add_ie': ['Vimeo'],
1360         },
1361         {
1362             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1363             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1364             'info_dict': {
1365                 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1366                 'ext': 'mp4',
1367                 'title': 'Big Buck Bunny',
1368                 'description': 'Royalty free test video',
1369                 'timestamp': 1432816365,
1370                 'upload_date': '20150528',
1371                 'is_live': False,
1372             },
1373             'params': {
1374                 'skip_download': True,
1375             },
1376             'add_ie': [ArkenaIE.ie_key()],
1377         },
1378         {
1379             '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/',
1380             'info_dict': {
1381                 'id': '1c7141f46c',
1382                 'ext': 'mp4',
1383                 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1384             },
1385             'params': {
1386                 'skip_download': True,
1387             },
1388             'add_ie': [Vbox7IE.ie_key()],
1389         },
1390         {
1391             # DBTV embeds
1392             'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1393             'playlist_mincount': 3,
1394         },
1395         # {
1396         #     # TODO: find another test
1397         #     # http://schema.org/VideoObject
1398         #     'url': 'https://flipagram.com/f/nyvTSJMKId',
1399         #     'md5': '888dcf08b7ea671381f00fab74692755',
1400         #     'info_dict': {
1401         #         'id': 'nyvTSJMKId',
1402         #         'ext': 'mp4',
1403         #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1404         #         'description': '#love for cats.',
1405         #         'timestamp': 1461244995,
1406         #         'upload_date': '20160421',
1407         #     },
1408         #     'params': {
1409         #         'force_generic_extractor': True,
1410         #     },
1411         # }
1412     ]
1413
1414     def report_following_redirect(self, new_url):
1415         """Report information extraction."""
1416         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1417
1418     def _extract_rss(self, url, video_id, doc):
1419         playlist_title = doc.find('./channel/title').text
1420         playlist_desc_el = doc.find('./channel/description')
1421         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1422
1423         entries = []
1424         for it in doc.findall('./channel/item'):
1425             next_url = xpath_text(it, 'link', fatal=False)
1426             if not next_url:
1427                 enclosure_nodes = it.findall('./enclosure')
1428                 for e in enclosure_nodes:
1429                     next_url = e.attrib.get('url')
1430                     if next_url:
1431                         break
1432
1433             if not next_url:
1434                 continue
1435
1436             entries.append({
1437                 '_type': 'url',
1438                 'url': next_url,
1439                 'title': it.find('title').text,
1440             })
1441
1442         return {
1443             '_type': 'playlist',
1444             'id': url,
1445             'title': playlist_title,
1446             'description': playlist_desc,
1447             'entries': entries,
1448         }
1449
1450     def _extract_camtasia(self, url, video_id, webpage):
1451         """ Returns None if no camtasia video can be found. """
1452
1453         camtasia_cfg = self._search_regex(
1454             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1455             webpage, 'camtasia configuration file', default=None)
1456         if camtasia_cfg is None:
1457             return None
1458
1459         title = self._html_search_meta('DC.title', webpage, fatal=True)
1460
1461         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1462         camtasia_cfg = self._download_xml(
1463             camtasia_url, video_id,
1464             note='Downloading camtasia configuration',
1465             errnote='Failed to download camtasia configuration')
1466         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1467
1468         entries = []
1469         for n in fileset_node.getchildren():
1470             url_n = n.find('./uri')
1471             if url_n is None:
1472                 continue
1473
1474             entries.append({
1475                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1476                 'title': '%s - %s' % (title, n.tag),
1477                 'url': compat_urlparse.urljoin(url, url_n.text),
1478                 'duration': float_or_none(n.find('./duration').text),
1479             })
1480
1481         return {
1482             '_type': 'playlist',
1483             'entries': entries,
1484             'title': title,
1485         }
1486
1487     def _real_extract(self, url):
1488         if url.startswith('//'):
1489             return {
1490                 '_type': 'url',
1491                 'url': self.http_scheme() + url,
1492             }
1493
1494         parsed_url = compat_urlparse.urlparse(url)
1495         if not parsed_url.scheme:
1496             default_search = self._downloader.params.get('default_search')
1497             if default_search is None:
1498                 default_search = 'fixup_error'
1499
1500             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1501                 if '/' in url:
1502                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1503                     return self.url_result('http://' + url)
1504                 elif default_search != 'fixup_error':
1505                     if default_search == 'auto_warning':
1506                         if re.match(r'^(?:url|URL)$', url):
1507                             raise ExtractorError(
1508                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1509                                 expected=True)
1510                         else:
1511                             self._downloader.report_warning(
1512                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1513                     return self.url_result('ytsearch:' + url)
1514
1515             if default_search in ('error', 'fixup_error'):
1516                 raise ExtractorError(
1517                     '%r is not a valid URL. '
1518                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1519                     % (url, url), expected=True)
1520             else:
1521                 if ':' not in default_search:
1522                     default_search += ':'
1523                 return self.url_result(default_search + url)
1524
1525         url, smuggled_data = unsmuggle_url(url)
1526         force_videoid = None
1527         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1528         if smuggled_data and 'force_videoid' in smuggled_data:
1529             force_videoid = smuggled_data['force_videoid']
1530             video_id = force_videoid
1531         else:
1532             video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1533
1534         self.to_screen('%s: Requesting header' % video_id)
1535
1536         head_req = HEADRequest(url)
1537         head_response = self._request_webpage(
1538             head_req, video_id,
1539             note=False, errnote='Could not send HEAD request to %s' % url,
1540             fatal=False)
1541
1542         if head_response is not False:
1543             # Check for redirect
1544             new_url = head_response.geturl()
1545             if url != new_url:
1546                 self.report_following_redirect(new_url)
1547                 if force_videoid:
1548                     new_url = smuggle_url(
1549                         new_url, {'force_videoid': force_videoid})
1550                 return self.url_result(new_url)
1551
1552         full_response = None
1553         if head_response is False:
1554             request = sanitized_Request(url)
1555             request.add_header('Accept-Encoding', '*')
1556             full_response = self._request_webpage(request, video_id)
1557             head_response = full_response
1558
1559         info_dict = {
1560             'id': video_id,
1561             'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1562             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1563         }
1564
1565         # Check for direct link to a video
1566         content_type = head_response.headers.get('Content-Type', '').lower()
1567         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1568         if m:
1569             format_id = m.group('format_id')
1570             if format_id.endswith('mpegurl'):
1571                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1572             elif format_id == 'f4m':
1573                 formats = self._extract_f4m_formats(url, video_id)
1574             else:
1575                 formats = [{
1576                     'format_id': m.group('format_id'),
1577                     'url': url,
1578                     'vcodec': 'none' if m.group('type') == 'audio' else None
1579                 }]
1580                 info_dict['direct'] = True
1581             self._sort_formats(formats)
1582             info_dict['formats'] = formats
1583             return info_dict
1584
1585         if not self._downloader.params.get('test', False) and not is_intentional:
1586             force = self._downloader.params.get('force_generic_extractor', False)
1587             self._downloader.report_warning(
1588                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1589
1590         if not full_response:
1591             request = sanitized_Request(url)
1592             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1593             # making it impossible to download only chunk of the file (yet we need only 512kB to
1594             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1595             # that will always result in downloading the whole file that is not desirable.
1596             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1597             # to accept raw bytes and being able to download only a chunk.
1598             # It may probably better to solve this by checking Content-Type for application/octet-stream
1599             # after HEAD request finishes, but not sure if we can rely on this.
1600             request.add_header('Accept-Encoding', '*')
1601             full_response = self._request_webpage(request, video_id)
1602
1603         first_bytes = full_response.read(512)
1604
1605         # Is it an M3U playlist?
1606         if first_bytes.startswith(b'#EXTM3U'):
1607             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1608             self._sort_formats(info_dict['formats'])
1609             return info_dict
1610
1611         # Maybe it's a direct link to a video?
1612         # Be careful not to download the whole thing!
1613         if not is_html(first_bytes):
1614             self._downloader.report_warning(
1615                 'URL could be a direct video link, returning it as such.')
1616             info_dict.update({
1617                 'direct': True,
1618                 'url': url,
1619             })
1620             return info_dict
1621
1622         webpage = self._webpage_read_content(
1623             full_response, url, video_id, prefix=first_bytes)
1624
1625         self.report_extraction(video_id)
1626
1627         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1628         try:
1629             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1630             if doc.tag == 'rss':
1631                 return self._extract_rss(url, video_id, doc)
1632             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1633                 smil = self._parse_smil(doc, url, video_id)
1634                 self._sort_formats(smil['formats'])
1635                 return smil
1636             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1637                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1638             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1639                 info_dict['formats'] = self._parse_mpd_formats(
1640                     doc, video_id, mpd_base_url=url.rpartition('/')[0])
1641                 self._sort_formats(info_dict['formats'])
1642                 return info_dict
1643             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1644                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1645                 self._sort_formats(info_dict['formats'])
1646                 return info_dict
1647         except compat_xml_parse_error:
1648             pass
1649
1650         # Is it a Camtasia project?
1651         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1652         if camtasia_res is not None:
1653             return camtasia_res
1654
1655         # Sometimes embedded video player is hidden behind percent encoding
1656         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1657         # Unescaping the whole page allows to handle those cases in a generic way
1658         webpage = compat_urllib_parse_unquote(webpage)
1659
1660         # it's tempting to parse this further, but you would
1661         # have to take into account all the variations like
1662         #   Video Title - Site Name
1663         #   Site Name | Video Title
1664         #   Video Title - Tagline | Site Name
1665         # and so on and so forth; it's just not practical
1666         video_title = self._og_search_title(
1667             webpage, default=None) or self._html_search_regex(
1668             r'(?s)<title>(.*?)</title>', webpage, 'video title',
1669             default='video')
1670
1671         # Try to detect age limit automatically
1672         age_limit = self._rta_search(webpage)
1673         # And then there are the jokers who advertise that they use RTA,
1674         # but actually don't.
1675         AGE_LIMIT_MARKERS = [
1676             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1677         ]
1678         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1679             age_limit = 18
1680
1681         # video uploader is domain name
1682         video_uploader = self._search_regex(
1683             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1684
1685         video_description = self._og_search_description(webpage, default=None)
1686         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1687
1688         # Helper method
1689         def _playlist_from_matches(matches, getter=None, ie=None):
1690             urlrs = orderedSet(
1691                 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1692                 for m in matches)
1693             return self.playlist_result(
1694                 urlrs, playlist_id=video_id, playlist_title=video_title)
1695
1696         # Look for Brightcove Legacy Studio embeds
1697         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1698         if bc_urls:
1699             self.to_screen('Brightcove video detected.')
1700             entries = [{
1701                 '_type': 'url',
1702                 'url': smuggle_url(bc_url, {'Referer': url}),
1703                 'ie_key': 'BrightcoveLegacy'
1704             } for bc_url in bc_urls]
1705
1706             return {
1707                 '_type': 'playlist',
1708                 'title': video_title,
1709                 'id': video_id,
1710                 'entries': entries,
1711             }
1712
1713         # Look for Brightcove New Studio embeds
1714         bc_urls = BrightcoveNewIE._extract_urls(webpage)
1715         if bc_urls:
1716             return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1717
1718         # Look for ThePlatform embeds
1719         tp_urls = ThePlatformIE._extract_urls(webpage)
1720         if tp_urls:
1721             return _playlist_from_matches(tp_urls, ie='ThePlatform')
1722
1723         # Look for Vessel embeds
1724         vessel_urls = VesselIE._extract_urls(webpage)
1725         if vessel_urls:
1726             return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1727
1728         # Look for embedded rtl.nl player
1729         matches = re.findall(
1730             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1731             webpage)
1732         if matches:
1733             return _playlist_from_matches(matches, ie='RtlNl')
1734
1735         vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1736         if vimeo_url is not None:
1737             return self.url_result(vimeo_url)
1738
1739         vid_me_embed_url = self._search_regex(
1740             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1741             webpage, 'vid.me embed', default=None)
1742         if vid_me_embed_url is not None:
1743             return self.url_result(vid_me_embed_url, 'Vidme')
1744
1745         # Look for embedded YouTube player
1746         matches = re.findall(r'''(?x)
1747             (?:
1748                 <iframe[^>]+?src=|
1749                 data-video-url=|
1750                 <embed[^>]+?src=|
1751                 embedSWF\(?:\s*|
1752                 new\s+SWFObject\(
1753             )
1754             (["\'])
1755                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1756                 (?:embed|v|p)/.+?)
1757             \1''', webpage)
1758         if matches:
1759             return _playlist_from_matches(
1760                 matches, lambda m: unescapeHTML(m[1]))
1761
1762         # Look for lazyYT YouTube embed
1763         matches = re.findall(
1764             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1765         if matches:
1766             return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1767
1768         # Look for Wordpress "YouTube Video Importer" plugin
1769         matches = re.findall(r'''(?x)<div[^>]+
1770             class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1771             data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1772         if matches:
1773             return _playlist_from_matches(matches, lambda m: m[-1])
1774
1775         matches = DailymotionIE._extract_urls(webpage)
1776         if matches:
1777             return _playlist_from_matches(matches)
1778
1779         # Look for embedded Dailymotion playlist player (#3822)
1780         m = re.search(
1781             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1782         if m:
1783             playlists = re.findall(
1784                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1785             if playlists:
1786                 return _playlist_from_matches(
1787                     playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1788
1789         # Look for embedded Wistia player
1790         match = re.search(
1791             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1792         if match:
1793             embed_url = self._proto_relative_url(
1794                 unescapeHTML(match.group('url')))
1795             return {
1796                 '_type': 'url_transparent',
1797                 'url': embed_url,
1798                 'ie_key': 'Wistia',
1799                 'uploader': video_uploader,
1800             }
1801
1802         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1803         if match:
1804             return {
1805                 '_type': 'url_transparent',
1806                 'url': 'wistia:%s' % match.group('id'),
1807                 'ie_key': 'Wistia',
1808                 'uploader': video_uploader,
1809             }
1810
1811         match = re.search(
1812             r'''(?sx)
1813                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1814                 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1815             ''', webpage)
1816         if match:
1817             return self.url_result(self._proto_relative_url(
1818                 'wistia:%s' % match.group('id')), 'Wistia')
1819
1820         # Look for SVT player
1821         svt_url = SVTIE._extract_url(webpage)
1822         if svt_url:
1823             return self.url_result(svt_url, 'SVT')
1824
1825         # Look for embedded condenast player
1826         matches = re.findall(
1827             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1828             webpage)
1829         if matches:
1830             return {
1831                 '_type': 'playlist',
1832                 'entries': [{
1833                     '_type': 'url',
1834                     'ie_key': 'CondeNast',
1835                     'url': ma,
1836                 } for ma in matches],
1837                 'title': video_title,
1838                 'id': video_id,
1839             }
1840
1841         # Look for Bandcamp pages with custom domain
1842         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1843         if mobj is not None:
1844             burl = unescapeHTML(mobj.group(1))
1845             # Don't set the extractor because it can be a track url or an album
1846             return self.url_result(burl)
1847
1848         # Look for embedded Vevo player
1849         mobj = re.search(
1850             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1851         if mobj is not None:
1852             return self.url_result(mobj.group('url'))
1853
1854         # Look for embedded Viddler player
1855         mobj = re.search(
1856             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1857             webpage)
1858         if mobj is not None:
1859             return self.url_result(mobj.group('url'))
1860
1861         # Look for NYTimes player
1862         mobj = re.search(
1863             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1864             webpage)
1865         if mobj is not None:
1866             return self.url_result(mobj.group('url'))
1867
1868         # Look for Libsyn player
1869         mobj = re.search(
1870             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1871         if mobj is not None:
1872             return self.url_result(mobj.group('url'))
1873
1874         # Look for Ooyala videos
1875         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1876                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1877                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1878                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1879         if mobj is not None:
1880             return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1881
1882         # Look for multiple Ooyala embeds on SBN network websites
1883         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1884         if mobj is not None:
1885             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1886             if embeds:
1887                 return _playlist_from_matches(
1888                     embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1889
1890         # Look for Aparat videos
1891         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1892         if mobj is not None:
1893             return self.url_result(mobj.group(1), 'Aparat')
1894
1895         # Look for MPORA videos
1896         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1897         if mobj is not None:
1898             return self.url_result(mobj.group(1), 'Mpora')
1899
1900         # Look for embedded NovaMov-based player
1901         mobj = re.search(
1902             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1903                     (?P<url>http://(?:(?:embed|www)\.)?
1904                         (?:novamov\.com|
1905                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
1906                            videoweed\.(?:es|com)|
1907                            movshare\.(?:net|sx|ag)|
1908                            divxstage\.(?:eu|net|ch|co|at|ag))
1909                         /embed\.php.+?)\1''', webpage)
1910         if mobj is not None:
1911             return self.url_result(mobj.group('url'))
1912
1913         # Look for embedded Facebook player
1914         facebook_url = FacebookIE._extract_url(webpage)
1915         if facebook_url is not None:
1916             return self.url_result(facebook_url, 'Facebook')
1917
1918         # Look for embedded VK player
1919         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1920         if mobj is not None:
1921             return self.url_result(mobj.group('url'), 'VK')
1922
1923         # Look for embedded Odnoklassniki player
1924         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1925         if mobj is not None:
1926             return self.url_result(mobj.group('url'), 'Odnoklassniki')
1927
1928         # Look for embedded ivi player
1929         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1930         if mobj is not None:
1931             return self.url_result(mobj.group('url'), 'Ivi')
1932
1933         # Look for embedded Huffington Post player
1934         mobj = re.search(
1935             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1936         if mobj is not None:
1937             return self.url_result(mobj.group('url'), 'HuffPost')
1938
1939         # Look for embed.ly
1940         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1941         if mobj is not None:
1942             return self.url_result(mobj.group('url'))
1943         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1944         if mobj is not None:
1945             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1946
1947         # Look for funnyordie embed
1948         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1949         if matches:
1950             return _playlist_from_matches(
1951                 matches, getter=unescapeHTML, ie='FunnyOrDie')
1952
1953         # Look for BBC iPlayer embed
1954         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1955         if matches:
1956             return _playlist_from_matches(matches, ie='BBCCoUk')
1957
1958         # Look for embedded RUTV player
1959         rutv_url = RUTVIE._extract_url(webpage)
1960         if rutv_url:
1961             return self.url_result(rutv_url, 'RUTV')
1962
1963         # Look for embedded TVC player
1964         tvc_url = TVCIE._extract_url(webpage)
1965         if tvc_url:
1966             return self.url_result(tvc_url, 'TVC')
1967
1968         # Look for embedded SportBox player
1969         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1970         if sportbox_urls:
1971             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1972
1973         # Look for embedded PornHub player
1974         pornhub_url = PornHubIE._extract_url(webpage)
1975         if pornhub_url:
1976             return self.url_result(pornhub_url, 'PornHub')
1977
1978         # Look for embedded XHamster player
1979         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1980         if xhamster_urls:
1981             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1982
1983         # Look for embedded TNAFlixNetwork player
1984         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1985         if tnaflix_urls:
1986             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1987
1988         # Look for embedded Tvigle player
1989         mobj = re.search(
1990             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1991         if mobj is not None:
1992             return self.url_result(mobj.group('url'), 'Tvigle')
1993
1994         # Look for embedded TED player
1995         mobj = re.search(
1996             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1997         if mobj is not None:
1998             return self.url_result(mobj.group('url'), 'TED')
1999
2000         # Look for embedded Ustream videos
2001         mobj = re.search(
2002             r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2003         if mobj is not None:
2004             return self.url_result(mobj.group('url'), 'Ustream')
2005
2006         # Look for embedded arte.tv player
2007         mobj = re.search(
2008             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2009             webpage)
2010         if mobj is not None:
2011             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2012
2013         # Look for embedded francetv player
2014         mobj = re.search(
2015             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2016             webpage)
2017         if mobj is not None:
2018             return self.url_result(mobj.group('url'))
2019
2020         # Look for embedded smotri.com player
2021         smotri_url = SmotriIE._extract_url(webpage)
2022         if smotri_url:
2023             return self.url_result(smotri_url, 'Smotri')
2024
2025         # Look for embedded Myvi.ru player
2026         myvi_url = MyviIE._extract_url(webpage)
2027         if myvi_url:
2028             return self.url_result(myvi_url)
2029
2030         # Look for embedded soundcloud player
2031         soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2032         if soundcloud_urls:
2033             return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2034
2035         # Look for embedded mtvservices player
2036         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2037         if mtvservices_url:
2038             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2039
2040         # Look for embedded yahoo player
2041         mobj = re.search(
2042             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2043             webpage)
2044         if mobj is not None:
2045             return self.url_result(mobj.group('url'), 'Yahoo')
2046
2047         # Look for embedded sbs.com.au player
2048         mobj = re.search(
2049             r'''(?x)
2050             (?:
2051                 <meta\s+property="og:video"\s+content=|
2052                 <iframe[^>]+?src=
2053             )
2054             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2055             webpage)
2056         if mobj is not None:
2057             return self.url_result(mobj.group('url'), 'SBS')
2058
2059         # Look for embedded Cinchcast player
2060         mobj = re.search(
2061             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2062             webpage)
2063         if mobj is not None:
2064             return self.url_result(mobj.group('url'), 'Cinchcast')
2065
2066         mobj = re.search(
2067             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2068             webpage)
2069         if not mobj:
2070             mobj = re.search(
2071                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2072                 webpage)
2073         if mobj is not None:
2074             return self.url_result(mobj.group('url'), 'MLB')
2075
2076         mobj = re.search(
2077             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2078             webpage)
2079         if mobj is not None:
2080             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2081
2082         mobj = re.search(
2083             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2084             webpage)
2085         if mobj is not None:
2086             return self.url_result(mobj.group('url'), 'Livestream')
2087
2088         # Look for Zapiks embed
2089         mobj = re.search(
2090             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2091         if mobj is not None:
2092             return self.url_result(mobj.group('url'), 'Zapiks')
2093
2094         # Look for Kaltura embeds
2095         kaltura_url = KalturaIE._extract_url(webpage)
2096         if kaltura_url:
2097             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2098
2099         # Look for Eagle.Platform embeds
2100         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2101         if eagleplatform_url:
2102             return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2103
2104         # Look for ClipYou (uses Eagle.Platform) embeds
2105         mobj = re.search(
2106             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2107         if mobj is not None:
2108             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2109
2110         # Look for Pladform embeds
2111         pladform_url = PladformIE._extract_url(webpage)
2112         if pladform_url:
2113             return self.url_result(pladform_url)
2114
2115         # Look for Videomore embeds
2116         videomore_url = VideomoreIE._extract_url(webpage)
2117         if videomore_url:
2118             return self.url_result(videomore_url)
2119
2120         # Look for Playwire embeds
2121         mobj = re.search(
2122             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2123         if mobj is not None:
2124             return self.url_result(mobj.group('url'))
2125
2126         # Look for 5min embeds
2127         mobj = re.search(
2128             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2129         if mobj is not None:
2130             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2131
2132         # Look for Crooks and Liars embeds
2133         mobj = re.search(
2134             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2135         if mobj is not None:
2136             return self.url_result(mobj.group('url'))
2137
2138         # Look for NBC Sports VPlayer embeds
2139         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2140         if nbc_sports_url:
2141             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2142
2143         # Look for NBC News embeds
2144         nbc_news_embed_url = re.search(
2145             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2146         if nbc_news_embed_url:
2147             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2148
2149         # Look for Google Drive embeds
2150         google_drive_url = GoogleDriveIE._extract_url(webpage)
2151         if google_drive_url:
2152             return self.url_result(google_drive_url, 'GoogleDrive')
2153
2154         # Look for UDN embeds
2155         mobj = re.search(
2156             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2157         if mobj is not None:
2158             return self.url_result(
2159                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2160
2161         # Look for Senate ISVP iframe
2162         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2163         if senate_isvp_url:
2164             return self.url_result(senate_isvp_url, 'SenateISVP')
2165
2166         # Look for Dailymotion Cloud videos
2167         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2168         if dmcloud_url:
2169             return self.url_result(dmcloud_url, 'DailymotionCloud')
2170
2171         # Look for OnionStudios embeds
2172         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2173         if onionstudios_url:
2174             return self.url_result(onionstudios_url)
2175
2176         # Look for ViewLift embeds
2177         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2178         if viewlift_url:
2179             return self.url_result(viewlift_url)
2180
2181         # Look for JWPlatform embeds
2182         jwplatform_url = JWPlatformIE._extract_url(webpage)
2183         if jwplatform_url:
2184             return self.url_result(jwplatform_url, 'JWPlatform')
2185
2186         # Look for ScreenwaveMedia embeds
2187         mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2188         if mobj is not None:
2189             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2190
2191         # Look for Digiteka embeds
2192         digiteka_url = DigitekaIE._extract_url(webpage)
2193         if digiteka_url:
2194             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2195
2196         # Look for Arkena embeds
2197         arkena_url = ArkenaIE._extract_url(webpage)
2198         if arkena_url:
2199             return self.url_result(arkena_url, ArkenaIE.ie_key())
2200
2201         # Look for Limelight embeds
2202         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2203         if mobj:
2204             lm = {
2205                 'Media': 'media',
2206                 'Channel': 'channel',
2207                 'ChannelList': 'channel_list',
2208             }
2209             return self.url_result('limelight:%s:%s' % (
2210                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2211
2212         # Look for AdobeTVVideo embeds
2213         mobj = re.search(
2214             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2215             webpage)
2216         if mobj is not None:
2217             return self.url_result(
2218                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2219                 'AdobeTVVideo')
2220
2221         # Look for Vine embeds
2222         mobj = re.search(
2223             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2224             webpage)
2225         if mobj is not None:
2226             return self.url_result(
2227                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2228
2229         # Look for VODPlatform embeds
2230         mobj = re.search(
2231             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
2232             webpage)
2233         if mobj is not None:
2234             return self.url_result(
2235                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
2236
2237         # Look for Instagram embeds
2238         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2239         if instagram_embed_url is not None:
2240             return self.url_result(
2241                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2242
2243         # Look for LiveLeak embeds
2244         liveleak_url = LiveLeakIE._extract_url(webpage)
2245         if liveleak_url:
2246             return self.url_result(liveleak_url, 'LiveLeak')
2247
2248         # Look for 3Q SDN embeds
2249         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2250         if threeqsdn_url:
2251             return {
2252                 '_type': 'url_transparent',
2253                 'ie_key': ThreeQSDNIE.ie_key(),
2254                 'url': self._proto_relative_url(threeqsdn_url),
2255                 'title': video_title,
2256                 'description': video_description,
2257                 'thumbnail': video_thumbnail,
2258                 'uploader': video_uploader,
2259             }
2260
2261         # Look for VBOX7 embeds
2262         vbox7_url = Vbox7IE._extract_url(webpage)
2263         if vbox7_url:
2264             return self.url_result(vbox7_url, Vbox7IE.ie_key())
2265
2266         # Look for DBTV embeds
2267         dbtv_urls = DBTVIE._extract_urls(webpage)
2268         if dbtv_urls:
2269             return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2270
2271         # Looking for http://schema.org/VideoObject
2272         json_ld = self._search_json_ld(
2273             webpage, video_id, default={}, expected_type='VideoObject')
2274         if json_ld.get('url'):
2275             info_dict.update({
2276                 'title': video_title or info_dict['title'],
2277                 'description': video_description,
2278                 'thumbnail': video_thumbnail,
2279                 'age_limit': age_limit
2280             })
2281             info_dict.update(json_ld)
2282             return info_dict
2283
2284         def check_video(vurl):
2285             if YoutubeIE.suitable(vurl):
2286                 return True
2287             vpath = compat_urlparse.urlparse(vurl).path
2288             vext = determine_ext(vpath)
2289             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2290
2291         def filter_video(urls):
2292             return list(filter(check_video, urls))
2293
2294         # Start with something easy: JW Player in SWFObject
2295         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2296         if not found:
2297             # Look for gorilla-vid style embedding
2298             found = filter_video(re.findall(r'''(?sx)
2299                 (?:
2300                     jw_plugins|
2301                     JWPlayerOptions|
2302                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2303                 )
2304                 .*?
2305                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2306         if not found:
2307             # Broaden the search a little bit
2308             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2309         if not found:
2310             # Broaden the findall a little bit: JWPlayer JS loader
2311             found = filter_video(re.findall(
2312                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2313         if not found:
2314             # Flow player
2315             found = filter_video(re.findall(r'''(?xs)
2316                 flowplayer\("[^"]+",\s*
2317                     \{[^}]+?\}\s*,
2318                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2319                         ["']?url["']?\s*:\s*["']([^"']+)["']
2320             ''', webpage))
2321         if not found:
2322             # Cinerama player
2323             found = re.findall(
2324                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2325         if not found:
2326             # Try to find twitter cards info
2327             # twitter:player:stream should be checked before twitter:player since
2328             # it is expected to contain a raw stream (see
2329             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2330             found = filter_video(re.findall(
2331                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2332         if not found:
2333             # We look for Open Graph info:
2334             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2335             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2336             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2337             if m_video_type is not None:
2338                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2339         if not found:
2340             # HTML5 video
2341             found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2342         if not found:
2343             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2344             found = re.search(
2345                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2346                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2347                 webpage)
2348             if not found:
2349                 # Look also in Refresh HTTP header
2350                 refresh_header = head_response.headers.get('Refresh')
2351                 if refresh_header:
2352                     # In python 2 response HTTP headers are bytestrings
2353                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2354                         refresh_header = refresh_header.decode('iso-8859-1')
2355                     found = re.search(REDIRECT_REGEX, refresh_header)
2356             if found:
2357                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2358                 self.report_following_redirect(new_url)
2359                 return {
2360                     '_type': 'url',
2361                     'url': new_url,
2362                 }
2363
2364         if not found:
2365             # twitter:player is a https URL to iframe player that may or may not
2366             # be supported by youtube-dl thus this is checked the very last (see
2367             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2368             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2369             if embed_url:
2370                 return self.url_result(embed_url)
2371
2372         if not found:
2373             raise UnsupportedError(url)
2374
2375         entries = []
2376         for video_url in orderedSet(found):
2377             video_url = unescapeHTML(video_url)
2378             video_url = video_url.replace('\\/', '/')
2379             video_url = compat_urlparse.urljoin(url, video_url)
2380             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2381
2382             # Sometimes, jwplayer extraction will result in a YouTube URL
2383             if YoutubeIE.suitable(video_url):
2384                 entries.append(self.url_result(video_url, 'Youtube'))
2385                 continue
2386
2387             # here's a fun little line of code for you:
2388             video_id = os.path.splitext(video_id)[0]
2389
2390             entry_info_dict = {
2391                 'id': video_id,
2392                 'uploader': video_uploader,
2393                 'title': video_title,
2394                 'age_limit': age_limit,
2395             }
2396
2397             ext = determine_ext(video_url)
2398             if ext == 'smil':
2399                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2400             elif ext == 'xspf':
2401                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2402             elif ext == 'm3u8':
2403                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2404             elif ext == 'mpd':
2405                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2406             elif ext == 'f4m':
2407                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2408             else:
2409                 entry_info_dict['url'] = video_url
2410
2411             if entry_info_dict.get('formats'):
2412                 self._sort_formats(entry_info_dict['formats'])
2413
2414             entries.append(entry_info_dict)
2415
2416         if len(entries) == 1:
2417             return entries[0]
2418         else:
2419             for num, e in enumerate(entries, start=1):
2420                 # 'url' results don't have a title
2421                 if e.get('title') is not None:
2422                     e['title'] = '%s (%d)' % (e['title'], num)
2423             return {
2424                 '_type': 'playlist',
2425                 'entries': entries,
2426             }