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

   1 # coding: 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     xpath_text,
  31 )
  32 from .brightcove import (
  33     BrightcoveLegacyIE,
  34     BrightcoveNewIE,
  35 )
  36 from .nbc import NBCSportsVPlayerIE
  37 from .ooyala import OoyalaIE
  38 from .rutv import RUTVIE
  39 from .tvc import TVCIE
  40 from .sportbox import SportBoxEmbedIE
  41 from .smotri import SmotriIE
  42 from .myvi import MyviIE
  43 from .condenast import CondeNastIE
  44 from .udn import UDNEmbedIE
  45 from .senateisvp import SenateISVPIE
  46 from .svt import SVTIE
  47 from .pornhub import PornHubIE
  48 from .xhamster import XHamsterEmbedIE
  49 from .tnaflix import TNAFlixNetworkEmbedIE
  50 from .drtuber import DrTuberIE
  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             'skip': 'URL invalid',
 109         },
 110         # Direct download with broken HEAD
 111         {
 112             'url': 'http://ai-radio.org:8000/radio.opus',
 113             'info_dict': {
 114                 'id': 'radio',
 115                 'ext': 'opus',
 116                 'title': 'radio',
 117             },
 118             'params': {
 119                 'skip_download': True,  # infinite live stream
 120             },
 121             'expected_warnings': [
 122                 r'501.*Not Implemented',
 123                 r'400.*Bad Request',
 124             ],
 125         },
 126         # Direct link with incorrect MIME type
 127         {
 128             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 129             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 130             'info_dict': {
 131                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 132                 'id': '5_Lennart_Poettering_-_Systemd',
 133                 'ext': 'webm',
 134                 'title': '5_Lennart_Poettering_-_Systemd',
 135                 'upload_date': '20141120',
 136             },
 137             'expected_warnings': [
 138                 'URL could be a direct video link, returning it as such.'
 139             ]
 140         },
 141         # RSS feed
 142         {
 143             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 144             'info_dict': {
 145                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 146                 'title': 'Zero Punctuation',
 147                 'description': 're:.*groundbreaking video review series.*'
 148             },
 149             'playlist_mincount': 11,
 150         },
 151         # RSS feed with enclosure
 152         {
 153             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 154             'info_dict': {
 155                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 156                 'ext': 'm4v',
 157                 'upload_date': '20150228',
 158                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 159             }
 160         },
 161         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 162         {
 163             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 164             'info_dict': {
 165                 'id': 'smil',
 166                 'ext': 'mp4',
 167                 'title': 'Automatics, robotics and biocybernetics',
 168                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 169                 'upload_date': '20130627',
 170                 'formats': 'mincount:16',
 171                 'subtitles': 'mincount:1',
 172             },
 173             'params': {
 174                 'force_generic_extractor': True,
 175                 'skip_download': True,
 176             },
 177         },
 178         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 179         {
 180             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 181             'info_dict': {
 182                 'id': 'hds',
 183                 'ext': 'flv',
 184                 'title': 'hds',
 185                 'formats': 'mincount:1',
 186             },
 187             'params': {
 188                 'skip_download': True,
 189             },
 190         },
 191         # SMIL from https://www.restudy.dk/video/play/id/1637
 192         {
 193             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 194             'info_dict': {
 195                 'id': 'video_1637',
 196                 'ext': 'flv',
 197                 'title': 'video_1637',
 198                 'formats': 'mincount:3',
 199             },
 200             'params': {
 201                 'skip_download': True,
 202             },
 203         },
 204         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 205         {
 206             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 207             'info_dict': {
 208                 'id': 'smil-service',
 209                 'ext': 'flv',
 210                 'title': 'smil-service',
 211                 'formats': 'mincount:1',
 212             },
 213             'params': {
 214                 'skip_download': True,
 215             },
 216         },
 217         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 218         {
 219             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 220             'info_dict': {
 221                 'id': '4719370',
 222                 'ext': 'mp4',
 223                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 224                 'formats': 'mincount:3',
 225             },
 226             'params': {
 227                 'skip_download': True,
 228             },
 229         },
 230         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 231         {
 232             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 233             'info_dict': {
 234                 'id': 'mZlp2ctYIUEB',
 235                 'ext': 'mp4',
 236                 'title': 'Tikibad ontruimd wegens brand',
 237                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 238                 'thumbnail': 're:^https?://.*\.jpg$',
 239                 'duration': 33,
 240             },
 241             'params': {
 242                 'skip_download': True,
 243             },
 244         },
 245         # MPD from http://dash-mse-test.appspot.com/media.html
 246         {
 247             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 248             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 249             'info_dict': {
 250                 'id': 'car-20120827-manifest',
 251                 'ext': 'mp4',
 252                 'title': 'car-20120827-manifest',
 253                 'formats': 'mincount:9',
 254                 'upload_date': '20130904',
 255             },
 256             'params': {
 257                 'format': 'bestvideo',
 258             },
 259         },
 260         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 261         {
 262             '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',
 263             'info_dict': {
 264                 'id': 'content',
 265                 'ext': 'mp4',
 266                 'title': 'content',
 267                 'formats': 'mincount:8',
 268             },
 269             'params': {
 270                 # m3u8 downloads
 271                 'skip_download': True,
 272             },
 273             'skip': 'video gone',
 274         },
 275         # m3u8 served with Content-Type: text/plain
 276         {
 277             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 278             'info_dict': {
 279                 'id': 'index',
 280                 'ext': 'mp4',
 281                 'title': 'index',
 282                 'upload_date': '20140720',
 283                 'formats': 'mincount:11',
 284             },
 285             'params': {
 286                 # m3u8 downloads
 287                 'skip_download': True,
 288             },
 289             'skip': 'video gone',
 290         },
 291         # google redirect
 292         {
 293             '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',
 294             'info_dict': {
 295                 'id': 'cmQHVoWB5FY',
 296                 'ext': 'mp4',
 297                 'upload_date': '20130224',
 298                 'uploader_id': 'TheVerge',
 299                 'description': 're:^Chris Ziegler takes a look at the\.*',
 300                 'uploader': 'The Verge',
 301                 'title': 'First Firefox OS phones side-by-side',
 302             },
 303             'params': {
 304                 'skip_download': False,
 305             }
 306         },
 307         {
 308             # redirect in Refresh HTTP header
 309             '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',
 310             'info_dict': {
 311                 'id': 'pO8h3EaFRdo',
 312                 'ext': 'mp4',
 313                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 314                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 315                 'upload_date': '20150917',
 316                 'uploader_id': 'brtvofficial',
 317                 'uploader': 'Boiler Room',
 318             },
 319             'params': {
 320                 'skip_download': False,
 321             },
 322         },
 323         {
 324             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 325             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 326             'info_dict': {
 327                 'id': '13601338388002',
 328                 'ext': 'mp4',
 329                 'uploader': 'www.hodiho.fr',
 330                 'title': 'R\u00e9gis plante sa Jeep',
 331             }
 332         },
 333         # bandcamp page with custom domain
 334         {
 335             'add_ie': ['Bandcamp'],
 336             'url': 'http://bronyrock.com/track/the-pony-mash',
 337             'info_dict': {
 338                 'id': '3235767654',
 339                 'ext': 'mp3',
 340                 'title': 'The Pony Mash',
 341                 'uploader': 'M_Pallante',
 342             },
 343             'skip': 'There is a limit of 200 free downloads / month for the test song',
 344         },
 345         # embedded brightcove video
 346         # it also tests brightcove videos that need to set the 'Referer' in the
 347         # http requests
 348         {
 349             'add_ie': ['BrightcoveLegacy'],
 350             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 351             'info_dict': {
 352                 'id': '2765128793001',
 353                 'ext': 'mp4',
 354                 'title': 'Le cours de bourse : l’analyse technique',
 355                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 356                 'uploader': 'BFM BUSINESS',
 357             },
 358             'params': {
 359                 'skip_download': True,
 360             },
 361         },
 362         {
 363             # https://github.com/rg3/youtube-dl/issues/2253
 364             'url': 'http://bcove.me/i6nfkrc3',
 365             'md5': '0ba9446db037002366bab3b3eb30c88c',
 366             'info_dict': {
 367                 'id': '3101154703001',
 368                 'ext': 'mp4',
 369                 'title': 'Still no power',
 370                 'uploader': 'thestar.com',
 371                 '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.',
 372             },
 373             'add_ie': ['BrightcoveLegacy'],
 374             'skip': 'video gone',
 375         },
 376         {
 377             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 378             'md5': 'fb973ecf6e4a78a67453647444222983',
 379             'info_dict': {
 380                 'id': '3414141473001',
 381                 'ext': 'mp4',
 382                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 383                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 384                 'uploader': 'Championat',
 385             },
 386         },
 387         {
 388             # https://github.com/rg3/youtube-dl/issues/3541
 389             'add_ie': ['BrightcoveLegacy'],
 390             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 391             'info_dict': {
 392                 'id': '3866516442001',
 393                 'ext': 'mp4',
 394                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 395                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 396                 'uploader': 'SBS Broadcasting',
 397             },
 398             'skip': 'Restricted to Netherlands',
 399             'params': {
 400                 'skip_download': True,  # m3u8 download
 401             },
 402         },
 403         # ooyala video
 404         {
 405             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 406             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 407             'info_dict': {
 408                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 409                 'ext': 'mp4',
 410                 'title': '2cc213299525360.mov',  # that's what we get
 411                 'duration': 238.231,
 412             },
 413             'add_ie': ['Ooyala'],
 414         },
 415         {
 416             # ooyala video embedded with http://player.ooyala.com/iframe.js
 417             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 418             'info_dict': {
 419                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 420                 'ext': 'mp4',
 421                 'title': '"Steve Jobs: Man in the Machine" trailer',
 422                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 423                 'duration': 135.427,
 424             },
 425             'params': {
 426                 'skip_download': True,
 427             },
 428             'skip': 'movie expired',
 429         },
 430         # embed.ly video
 431         {
 432             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 433             'info_dict': {
 434                 'id': '9ODmcdjQcHQ',
 435                 'ext': 'mp4',
 436                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 437                 'upload_date': '20140225',
 438                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 439                 'uploader': 'Tested',
 440                 'uploader_id': 'testedcom',
 441             },
 442             # No need to test YoutubeIE here
 443             'params': {
 444                 'skip_download': True,
 445             },
 446         },
 447         # funnyordie embed
 448         {
 449             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 450             'info_dict': {
 451                 'id': '18e820ec3f',
 452                 'ext': 'mp4',
 453                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 454                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 455             },
 456             # HEAD requests lead to endless 301, while GET is OK
 457             'expected_warnings': ['301'],
 458         },
 459         # RUTV embed
 460         {
 461             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 462             'info_dict': {
 463                 'id': '776940',
 464                 'ext': 'mp4',
 465                 'title': 'Охотское море стало целиком российским',
 466                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 467             },
 468             'params': {
 469                 # m3u8 download
 470                 'skip_download': True,
 471             },
 472         },
 473         # TVC embed
 474         {
 475             '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/',
 476             'info_dict': {
 477                 'id': '55304',
 478                 'ext': 'mp4',
 479                 'title': 'Дошкольное воспитание',
 480             },
 481         },
 482         # SportBox embed
 483         {
 484             'url': 'http://www.vestifinance.ru/articles/25753',
 485             'info_dict': {
 486                 'id': '25753',
 487                 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 488             },
 489             'playlist': [{
 490                 'info_dict': {
 491                     'id': '370908',
 492                     'title': 'Госзаказ. День 3',
 493                     'ext': 'mp4',
 494                 }
 495             }, {
 496                 'info_dict': {
 497                     'id': '370905',
 498                     'title': 'Госзаказ. День 2',
 499                     'ext': 'mp4',
 500                 }
 501             }, {
 502                 'info_dict': {
 503                     'id': '370902',
 504                     'title': 'Госзаказ. День 1',
 505                     'ext': 'mp4',
 506                 }
 507             }],
 508             'params': {
 509                 # m3u8 download
 510                 'skip_download': True,
 511             },
 512         },
 513         # Myvi.ru embed
 514         {
 515             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 516             'info_dict': {
 517                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 518                 'ext': 'mp4',
 519                 'title': 'Ужастики, русский трейлер (2015)',
 520                 'thumbnail': 're:^https?://.*\.jpg$',
 521                 'duration': 153,
 522             }
 523         },
 524         # XHamster embed
 525         {
 526             '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',
 527             'info_dict': {
 528                 'id': 'showthread',
 529                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 530             },
 531             'playlist_mincount': 7,
 532             # This forum does not allow <iframe> syntaxes anymore
 533             # Now HTML tags are displayed as-is
 534             'skip': 'No videos on this page',
 535         },
 536         # Embedded TED video
 537         {
 538             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 539             'md5': '65fdff94098e4a607385a60c5177c638',
 540             'info_dict': {
 541                 'id': '1969',
 542                 'ext': 'mp4',
 543                 'title': 'Hidden miracles of the natural world',
 544                 'uploader': 'Louie Schwartzberg',
 545                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 546             }
 547         },
 548         # Embedded Ustream video
 549         {
 550             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
 551             'md5': '27b99cdb639c9b12a79bca876a073417',
 552             'info_dict': {
 553                 'id': '45734260',
 554                 'ext': 'flv',
 555                 'uploader': 'AU SPA:  The NSA and Privacy',
 556                 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
 557             }
 558         },
 559         # nowvideo embed hidden behind percent encoding
 560         {
 561             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 562             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 563             'info_dict': {
 564                 'id': '06e53103ca9aa',
 565                 'ext': 'flv',
 566                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 567                 'description': 'No description',
 568             },
 569         },
 570         # arte embed
 571         {
 572             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 573             'md5': '7653032cbb25bf6c80d80f217055fa43',
 574             'info_dict': {
 575                 'id': '048195-004_PLUS7-F',
 576                 'ext': 'flv',
 577                 'title': 'X:enius',
 578                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 579                 'upload_date': '20140320',
 580             },
 581             'params': {
 582                 'skip_download': 'Requires rtmpdump'
 583             },
 584             'skip': 'video gone',
 585         },
 586         # francetv embed
 587         {
 588             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 589             'info_dict': {
 590                 'id': 'EV_30231',
 591                 'ext': 'mp4',
 592                 'title': 'Alcaline, le concert avec Calogero',
 593                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 594                 'upload_date': '20150226',
 595                 'timestamp': 1424989860,
 596                 'duration': 5400,
 597             },
 598             'params': {
 599                 # m3u8 downloads
 600                 'skip_download': True,
 601             },
 602             'expected_warnings': [
 603                 'Forbidden'
 604             ]
 605         },
 606         # Condé Nast embed
 607         {
 608             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 609             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 610             'info_dict': {
 611                 'id': '53501be369702d3275860000',
 612                 'ext': 'mp4',
 613                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 614             }
 615         },
 616         # Dailymotion embed
 617         {
 618             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 619             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 620             'info_dict': {
 621                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 622                 'ext': 'mp4',
 623                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 624                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 625                 'uploader': 'Spi0n',
 626                 'uploader_id': 'xgditw',
 627                 'upload_date': '20140425',
 628                 'timestamp': 1398441542,
 629             },
 630             'add_ie': ['Dailymotion'],
 631         },
 632         # YouTube embed
 633         {
 634             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 635             'info_dict': {
 636                 'id': 'FXRb4ykk4S0',
 637                 'ext': 'mp4',
 638                 'title': 'The NBL Auction 2014',
 639                 'uploader': 'BADMINTON England',
 640                 'uploader_id': 'BADMINTONEvents',
 641                 'upload_date': '20140603',
 642                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 643             },
 644             'add_ie': ['Youtube'],
 645             'params': {
 646                 'skip_download': True,
 647             }
 648         },
 649         # MTVSercices embed
 650         {
 651             'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
 652             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
 653             'info_dict': {
 654                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
 655                 'ext': 'mp4',
 656                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
 657                 'description': 'Two valets share their love for movie star Liam Neesons.',
 658                 'timestamp': 1349922600,
 659                 'upload_date': '20121011',
 660             },
 661         },
 662         # YouTube embed via <data-embed-url="">
 663         {
 664             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 665             'info_dict': {
 666                 'id': '4vAffPZIT44',
 667                 'ext': 'mp4',
 668                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 669                 'uploader': 'Gameloft',
 670                 'uploader_id': 'gameloft',
 671                 'upload_date': '20140828',
 672                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 673             },
 674             'params': {
 675                 'skip_download': True,
 676             }
 677         },
 678         # Camtasia studio
 679         {
 680             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 681             'playlist': [{
 682                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 683                 'info_dict': {
 684                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 685                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 686                     'ext': 'flv',
 687                     'duration': 2235.90,
 688                 }
 689             }, {
 690                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 691                 'info_dict': {
 692                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 693                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 694                     'ext': 'flv',
 695                     'duration': 2235.93,
 696                 }
 697             }],
 698             'info_dict': {
 699                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 700             }
 701         },
 702         # Flowplayer
 703         {
 704             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 705             'md5': '9d65602bf31c6e20014319c7d07fba27',
 706             'info_dict': {
 707                 'id': '5123ea6d5e5a7',
 708                 'ext': 'mp4',
 709                 'age_limit': 18,
 710                 'uploader': 'www.handjobhub.com',
 711                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 712             }
 713         },
 714         # Multiple brightcove videos
 715         # https://github.com/rg3/youtube-dl/issues/2283
 716         {
 717             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 718             'info_dict': {
 719                 'id': 'always-never',
 720                 'title': 'Always / Never - The New Yorker',
 721             },
 722             'playlist_count': 3,
 723             'params': {
 724                 'extract_flat': False,
 725                 'skip_download': True,
 726             }
 727         },
 728         # MLB embed
 729         {
 730             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 731             'md5': '96f09a37e44da40dd083e12d9a683327',
 732             'info_dict': {
 733                 'id': '33322633',
 734                 'ext': 'mp4',
 735                 'title': 'Ump changes call to ball',
 736                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 737                 'duration': 48,
 738                 'timestamp': 1401537900,
 739                 'upload_date': '20140531',
 740                 'thumbnail': 're:^https?://.*\.jpg$',
 741             },
 742         },
 743         # Wistia embed
 744         {
 745             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 746             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 747             'info_dict': {
 748                 'id': '6e2wtrbdaf',
 749                 'ext': 'mov',
 750                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 751                 'description': 'a Paywall Videos video from Remilon',
 752                 'duration': 644.072,
 753                 'uploader': 'study.com',
 754                 'timestamp': 1459678540,
 755                 'upload_date': '20160403',
 756                 'filesize': 24687186,
 757             },
 758         },
 759         {
 760             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 761             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 762             'info_dict': {
 763                 'id': 'uxjb0lwrcz',
 764                 'ext': 'mp4',
 765                 'title': 'Conversation about Hexagonal Rails Part 1',
 766                 'description': 'a Martin Fowler video from ThoughtWorks',
 767                 'duration': 1715.0,
 768                 'uploader': 'thoughtworks.wistia.com',
 769                 'timestamp': 1401832161,
 770                 'upload_date': '20140603',
 771             },
 772         },
 773         # Wistia standard embed (async)
 774         {
 775             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 776             'info_dict': {
 777                 'id': '807fafadvk',
 778                 'ext': 'mp4',
 779                 'title': 'Drip Brennan Dunn Workshop',
 780                 'description': 'a JV Webinars video from getdrip-1',
 781                 'duration': 4986.95,
 782                 'timestamp': 1463607249,
 783                 'upload_date': '20160518',
 784             },
 785             'params': {
 786                 'skip_download': True,
 787             }
 788         },
 789         # Soundcloud embed
 790         {
 791             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 792             'info_dict': {
 793                 'id': '174391317',
 794                 'ext': 'mp3',
 795                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 796                 'uploader': 'Sophos Security',
 797                 'title': 'Chet Chat 171 - Oct 29, 2014',
 798                 'upload_date': '20141029',
 799             }
 800         },
 801         # Soundcloud multiple embeds
 802         {
 803             'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
 804             'info_dict': {
 805                 'id': '52809',
 806                 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
 807             },
 808             'playlist_mincount': 7,
 809         },
 810         # Livestream embed
 811         {
 812             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 813             'info_dict': {
 814                 'id': '67864563',
 815                 'ext': 'flv',
 816                 'upload_date': '20141112',
 817                 'title': 'Rosetta #CometLanding webcast HL 10',
 818             }
 819         },
 820         # Another Livestream embed, without 'new.' in URL
 821         {
 822             'url': 'https://www.freespeech.org/',
 823             'info_dict': {
 824                 'id': '123537347',
 825                 'ext': 'mp4',
 826                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 827             },
 828             'params': {
 829                 # Live stream
 830                 'skip_download': True,
 831             },
 832         },
 833         # LazyYT
 834         {
 835             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
 836             'info_dict': {
 837                 'id': '1986',
 838                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
 839             },
 840             'playlist_mincount': 2,
 841         },
 842         # Cinchcast embed
 843         {
 844             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
 845             'info_dict': {
 846                 'id': '7141703',
 847                 'ext': 'mp3',
 848                 'upload_date': '20141126',
 849                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
 850             }
 851         },
 852         # Cinerama player
 853         {
 854             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
 855             'info_dict': {
 856                 'id': '730m_DandD_1901_512k',
 857                 'ext': 'mp4',
 858                 'uploader': 'www.abc.net.au',
 859                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
 860             }
 861         },
 862         # embedded viddler video
 863         {
 864             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
 865             'info_dict': {
 866                 'id': '4d03aad9',
 867                 'ext': 'mp4',
 868                 'uploader': 'deadspin',
 869                 'title': 'WALL-TO-GORTAT',
 870                 'timestamp': 1422285291,
 871                 'upload_date': '20150126',
 872             },
 873             'add_ie': ['Viddler'],
 874         },
 875         # Libsyn embed
 876         {
 877             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
 878             'info_dict': {
 879                 'id': '3377616',
 880                 'ext': 'mp3',
 881                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
 882                 'description': 'md5:601cb790edd05908957dae8aaa866465',
 883                 'upload_date': '20150220',
 884             },
 885             'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
 886         },
 887         # jwplayer YouTube
 888         {
 889             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
 890             'info_dict': {
 891                 'id': 'Mrj4DVp2zeA',
 892                 'ext': 'mp4',
 893                 'upload_date': '20150212',
 894                 'uploader': 'The National Archives UK',
 895                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
 896                 'uploader_id': 'NationalArchives08',
 897                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
 898             },
 899         },
 900         # rtl.nl embed
 901         {
 902             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
 903             'playlist_mincount': 5,
 904             'info_dict': {
 905                 'id': 'aanslagen-kopenhagen',
 906                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
 907             }
 908         },
 909         # Zapiks embed
 910         {
 911             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
 912             'info_dict': {
 913                 'id': '118046',
 914                 'ext': 'mp4',
 915                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
 916             }
 917         },
 918         # Kaltura embed (different embed code)
 919         {
 920             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
 921             'info_dict': {
 922                 'id': '1_a52wc67y',
 923                 'ext': 'flv',
 924                 'upload_date': '20150127',
 925                 'uploader_id': 'PremierMedia',
 926                 'timestamp': int,
 927                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
 928             },
 929         },
 930         # Kaltura embed protected with referrer
 931         {
 932             'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
 933             'info_dict': {
 934                 'id': '1_g4fbemnq',
 935                 'ext': 'mp4',
 936                 'title': 'Violetta - Achter De Schermen - Ruggero',
 937                 'description': 'Achter de schermen met Ruggero',
 938                 'timestamp': 1435133761,
 939                 'upload_date': '20150624',
 940                 'uploader_id': 'echojecka',
 941             },
 942         },
 943         # Kaltura embed with single quotes
 944         {
 945             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
 946             'info_dict': {
 947                 'id': '0_izeg5utt',
 948                 'ext': 'mp4',
 949                 'title': '35871',
 950                 'timestamp': 1355743100,
 951                 'upload_date': '20121217',
 952                 'uploader_id': 'batchUser',
 953             },
 954             'add_ie': ['Kaltura'],
 955         },
 956         {
 957             # Kaltura embedded via quoted entry_id
 958             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
 959             'info_dict': {
 960                 'id': '0_utuok90b',
 961                 'ext': 'mp4',
 962                 'title': '06_matthew_brender_raj_dutt',
 963                 'timestamp': 1466638791,
 964                 'upload_date': '20160622',
 965             },
 966             'add_ie': ['Kaltura'],
 967             'expected_warnings': [
 968                 'Could not send HEAD request'
 969             ],
 970             'params': {
 971                 'skip_download': True,
 972             }
 973         },
 974         # Eagle.Platform embed (generic URL)
 975         {
 976             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
 977             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 978             'info_dict': {
 979                 'id': '227304',
 980                 'ext': 'mp4',
 981                 'title': 'Навальный вышел на свободу',
 982                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
 983                 'thumbnail': 're:^https?://.*\.jpg$',
 984                 'duration': 87,
 985                 'view_count': int,
 986                 'age_limit': 0,
 987             },
 988         },
 989         # ClipYou (Eagle.Platform) embed (custom URL)
 990         {
 991             'url': 'http://muz-tv.ru/play/7129/',
 992             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 993             'info_dict': {
 994                 'id': '12820',
 995                 'ext': 'mp4',
 996                 'title': "'O Sole Mio",
 997                 'thumbnail': 're:^https?://.*\.jpg$',
 998                 'duration': 216,
 999                 'view_count': int,
1000             },
1001         },
1002         # Pladform embed
1003         {
1004             'url': 'http://muz-tv.ru/kinozal/view/7400/',
1005             'info_dict': {
1006                 'id': '100183293',
1007                 'ext': 'mp4',
1008                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1009                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1010                 'thumbnail': 're:^https?://.*\.jpg$',
1011                 'duration': 694,
1012                 'age_limit': 0,
1013             },
1014         },
1015         # Playwire embed
1016         {
1017             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1018             'info_dict': {
1019                 'id': '3519514',
1020                 'ext': 'mp4',
1021                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1022                 'thumbnail': 're:^https?://.*\.png$',
1023                 'duration': 45.115,
1024             },
1025         },
1026         # 5min embed
1027         {
1028             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1029             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1030             'info_dict': {
1031                 'id': '518726732',
1032                 'ext': 'mp4',
1033                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1034             },
1035         },
1036         # SVT embed
1037         {
1038             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1039             'info_dict': {
1040                 'id': '2900353',
1041                 'ext': 'flv',
1042                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1043                 'duration': 27,
1044                 'age_limit': 0,
1045             },
1046         },
1047         # Crooks and Liars embed
1048         {
1049             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1050             'info_dict': {
1051                 'id': '8RUoRhRi',
1052                 'ext': 'mp4',
1053                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1054                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1055                 'timestamp': 1428207000,
1056                 'upload_date': '20150405',
1057                 'uploader': 'Heather',
1058             },
1059         },
1060         # Crooks and Liars external embed
1061         {
1062             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1063             'info_dict': {
1064                 'id': 'MTE3MjUtMzQ2MzA',
1065                 'ext': 'mp4',
1066                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1067                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1068                 'timestamp': 1265032391,
1069                 'upload_date': '20100201',
1070                 'uploader': 'Heather',
1071             },
1072         },
1073         # NBC Sports vplayer embed
1074         {
1075             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1076             'info_dict': {
1077                 'id': 'ln7x1qSThw4k',
1078                 'ext': 'flv',
1079                 'title': "PFT Live: New leader in the 'new-look' defense",
1080                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1081                 'uploader': 'NBCU-SPORTS',
1082                 'upload_date': '20140107',
1083                 'timestamp': 1389118457,
1084             },
1085         },
1086         # NBC News embed
1087         {
1088             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1089             'md5': '1aa589c675898ae6d37a17913cf68d66',
1090             'info_dict': {
1091                 'id': '701714499682',
1092                 'ext': 'mp4',
1093                 'title': 'PREVIEW: On Assignment: David Letterman',
1094                 '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.',
1095             },
1096         },
1097         # UDN embed
1098         {
1099             'url': 'https://video.udn.com/news/300346',
1100             'md5': 'fd2060e988c326991037b9aff9df21a6',
1101             'info_dict': {
1102                 'id': '300346',
1103                 'ext': 'mp4',
1104                 'title': '中一中男師變性 全校師生力挺',
1105                 'thumbnail': 're:^https?://.*\.jpg$',
1106             },
1107             'params': {
1108                 # m3u8 download
1109                 'skip_download': True,
1110             },
1111         },
1112         # Ooyala embed
1113         {
1114             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1115             'info_dict': {
1116                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1117                 'ext': 'mp4',
1118                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1119                 'title': 'This is what separates the Excel masters from the wannabes',
1120                 'duration': 191.933,
1121             },
1122             'params': {
1123                 # m3u8 downloads
1124                 'skip_download': True,
1125             }
1126         },
1127         # Brightcove URL in single quotes
1128         {
1129             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1130             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1131             'info_dict': {
1132                 'id': '4255764656001',
1133                 'ext': 'mp4',
1134                 'title': 'SN Presents: Russell Martin, World Citizen',
1135                 '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.',
1136                 'uploader': 'Rogers Sportsnet',
1137                 'uploader_id': '1704050871',
1138                 'upload_date': '20150525',
1139                 'timestamp': 1432570283,
1140             },
1141         },
1142         # Dailymotion Cloud video
1143         {
1144             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1145             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1146             'info_dict': {
1147                 'id': 'x2uy8t3',
1148                 'ext': 'mp4',
1149                 'title': 'Sauvons les abeilles ! - Le débat',
1150                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1151                 'thumbnail': 're:^https?://.*\.jpe?g$',
1152                 'timestamp': 1434970506,
1153                 'upload_date': '20150622',
1154                 'uploader': 'Public Sénat',
1155                 'uploader_id': 'xa9gza',
1156             }
1157         },
1158         # OnionStudios embed
1159         {
1160             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1161             'info_dict': {
1162                 'id': '2855',
1163                 'ext': 'mp4',
1164                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1165                 'thumbnail': 're:^https?://.*\.jpe?g$',
1166                 'uploader': 'ClickHole',
1167                 'uploader_id': 'clickhole',
1168             }
1169         },
1170         # SnagFilms embed
1171         {
1172             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1173             'info_dict': {
1174                 'id': '74849a00-85a9-11e1-9660-123139220831',
1175                 'ext': 'mp4',
1176                 'title': '#whilewewatch',
1177             }
1178         },
1179         # AdobeTVVideo embed
1180         {
1181             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1182             'md5': '43662b577c018ad707a63766462b1e87',
1183             'info_dict': {
1184                 'id': '2456',
1185                 'ext': 'mp4',
1186                 'title': 'New experience with Acrobat DC',
1187                 'description': 'New experience with Acrobat DC',
1188                 'duration': 248.667,
1189             },
1190         },
1191         # ScreenwaveMedia embed
1192         {
1193             'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1194             'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1195             'info_dict': {
1196                 'id': 'cinemasnob-55d26273809dd',
1197                 'ext': 'mp4',
1198                 'title': 'cinemasnob',
1199             },
1200         },
1201         # BrightcoveInPageEmbed embed
1202         {
1203             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1204             'info_dict': {
1205                 'id': '4238694884001',
1206                 'ext': 'flv',
1207                 'title': 'Tabletop: Dread, Last Thoughts',
1208                 'description': 'Tabletop: Dread, Last Thoughts',
1209                 'duration': 51690,
1210             },
1211         },
1212         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1213         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1214         {
1215             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1216             'info_dict': {
1217                 'id': '4785848093001',
1218                 'ext': 'mp4',
1219                 'title': 'The Cardinal Pell Interview',
1220                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1221                 'uploader': 'GlobeCast Australia - GlobeStream',
1222                 'uploader_id': '2733773828001',
1223                 'upload_date': '20160304',
1224                 'timestamp': 1457083087,
1225             },
1226             'params': {
1227                 # m3u8 downloads
1228                 'skip_download': True,
1229             },
1230         },
1231         # Another form of arte.tv embed
1232         {
1233             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1234             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1235             'info_dict': {
1236                 'id': '030273-562_PLUS7-F',
1237                 'ext': 'mp4',
1238                 'title': 'ARTE Reportage - Nulle part, en France',
1239                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1240                 'upload_date': '20160409',
1241             },
1242         },
1243         # LiveLeak embed
1244         {
1245             'url': 'http://www.wykop.pl/link/3088787/',
1246             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1247             'info_dict': {
1248                 'id': '874_1459135191',
1249                 'ext': 'mp4',
1250                 'title': 'Man shows poor quality of new apartment building',
1251                 'description': 'The wall is like a sand pile.',
1252                 'uploader': 'Lake8737',
1253             }
1254         },
1255         # Duplicated embedded video URLs
1256         {
1257             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1258             'info_dict': {
1259                 'id': '149298443_480_16c25b74_2',
1260                 'ext': 'mp4',
1261                 'title': 'vs. Blue Orange Spring Game',
1262                 'uploader': 'www.hudl.com',
1263             },
1264         },
1265         # twitter:player:stream embed
1266         {
1267             'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1268             'info_dict': {
1269                 'id': 'master',
1270                 'ext': 'mp4',
1271                 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1272                 'uploader': 'www.rtl.be',
1273             },
1274             'params': {
1275                 # m3u8 downloads
1276                 'skip_download': True,
1277             },
1278         },
1279         # twitter:player embed
1280         {
1281             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1282             'md5': 'a3e0df96369831de324f0778e126653c',
1283             'info_dict': {
1284                 'id': '4909620399001',
1285                 'ext': 'mp4',
1286                 'title': 'What Do Black Holes Sound Like?',
1287                 'description': 'what do black holes sound like',
1288                 'upload_date': '20160524',
1289                 'uploader_id': '29913724001',
1290                 'timestamp': 1464107587,
1291                 'uploader': 'TheAtlantic',
1292             },
1293             'add_ie': ['BrightcoveLegacy'],
1294         },
1295         # Facebook <iframe> embed
1296         {
1297             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1298             'md5': 'fbcde74f534176ecb015849146dd3aee',
1299             'info_dict': {
1300                 'id': '599637780109885',
1301                 'ext': 'mp4',
1302                 'title': 'Facebook video #599637780109885',
1303             },
1304         },
1305         # Facebook API embed
1306         {
1307             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1308             'md5': 'a47372ee61b39a7b90287094d447d94e',
1309             'info_dict': {
1310                 'id': '10153467542406923',
1311                 'ext': 'mp4',
1312                 'title': 'Facebook video #10153467542406923',
1313             },
1314         },
1315         # Wordpress "YouTube Video Importer" plugin
1316         {
1317             'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1318             'md5': 'd16797741b560b485194eddda8121b48',
1319             'info_dict': {
1320                 'id': 'HNTXWDXV9Is',
1321                 'ext': 'mp4',
1322                 'title': 'Blue Devils Drumline Stanford lot 2016',
1323                 'upload_date': '20160627',
1324                 'uploader_id': 'GENOCIDE8GENERAL10',
1325                 'uploader': 'cylus cyrus',
1326             },
1327         },
1328         {
1329             # video stored on custom kaltura server
1330             'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1331             'md5': '537617d06e64dfed891fa1593c4b30cc',
1332             'info_dict': {
1333                 'id': '0_1iotm5bh',
1334                 'ext': 'mp4',
1335                 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1336                 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1337                 'uploader_id': 'videos.expansion@el-mundo.net',
1338                 'upload_date': '20150429',
1339                 'timestamp': 1430303472,
1340             },
1341             'add_ie': ['Kaltura'],
1342         },
1343         {
1344             # Non-standard Vimeo embed
1345             'url': 'https://openclassrooms.com/courses/understanding-the-web',
1346             'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1347             'info_dict': {
1348                 'id': '148867247',
1349                 'ext': 'mp4',
1350                 'title': 'Understanding the web - Teaser',
1351                 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1352                 'upload_date': '20151214',
1353                 'uploader': 'OpenClassrooms',
1354                 'uploader_id': 'openclassrooms',
1355             },
1356             'add_ie': ['Vimeo'],
1357         },
1358         {
1359             # generic vimeo embed that requires original URL passed as Referer
1360             'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1361             'only_matching': True,
1362         },
1363         {
1364             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1365             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1366             'info_dict': {
1367                 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1368                 'ext': 'mp4',
1369                 'title': 'Big Buck Bunny',
1370                 'description': 'Royalty free test video',
1371                 'timestamp': 1432816365,
1372                 'upload_date': '20150528',
1373                 'is_live': False,
1374             },
1375             'params': {
1376                 'skip_download': True,
1377             },
1378             'add_ie': [ArkenaIE.ie_key()],
1379         },
1380         {
1381             '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/',
1382             'info_dict': {
1383                 'id': '1c7141f46c',
1384                 'ext': 'mp4',
1385                 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1386             },
1387             'params': {
1388                 'skip_download': True,
1389             },
1390             'add_ie': [Vbox7IE.ie_key()],
1391         },
1392         {
1393             # DBTV embeds
1394             'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1395             'info_dict': {
1396                 'id': '43254897',
1397                 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1398             },
1399             'playlist_mincount': 3,
1400         },
1401         # {
1402         #     # TODO: find another test
1403         #     # http://schema.org/VideoObject
1404         #     'url': 'https://flipagram.com/f/nyvTSJMKId',
1405         #     'md5': '888dcf08b7ea671381f00fab74692755',
1406         #     'info_dict': {
1407         #         'id': 'nyvTSJMKId',
1408         #         'ext': 'mp4',
1409         #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1410         #         'description': '#love for cats.',
1411         #         'timestamp': 1461244995,
1412         #         'upload_date': '20160421',
1413         #     },
1414         #     'params': {
1415         #         'force_generic_extractor': True,
1416         #     },
1417         # }
1418     ]
1419
1420     def report_following_redirect(self, new_url):
1421         """Report information extraction."""
1422         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1423
1424     def _extract_rss(self, url, video_id, doc):
1425         playlist_title = doc.find('./channel/title').text
1426         playlist_desc_el = doc.find('./channel/description')
1427         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1428
1429         entries = []
1430         for it in doc.findall('./channel/item'):
1431             next_url = xpath_text(it, 'link', fatal=False)
1432             if not next_url:
1433                 enclosure_nodes = it.findall('./enclosure')
1434                 for e in enclosure_nodes:
1435                     next_url = e.attrib.get('url')
1436                     if next_url:
1437                         break
1438
1439             if not next_url:
1440                 continue
1441
1442             entries.append({
1443                 '_type': 'url',
1444                 'url': next_url,
1445                 'title': it.find('title').text,
1446             })
1447
1448         return {
1449             '_type': 'playlist',
1450             'id': url,
1451             'title': playlist_title,
1452             'description': playlist_desc,
1453             'entries': entries,
1454         }
1455
1456     def _extract_camtasia(self, url, video_id, webpage):
1457         """ Returns None if no camtasia video can be found. """
1458
1459         camtasia_cfg = self._search_regex(
1460             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1461             webpage, 'camtasia configuration file', default=None)
1462         if camtasia_cfg is None:
1463             return None
1464
1465         title = self._html_search_meta('DC.title', webpage, fatal=True)
1466
1467         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1468         camtasia_cfg = self._download_xml(
1469             camtasia_url, video_id,
1470             note='Downloading camtasia configuration',
1471             errnote='Failed to download camtasia configuration')
1472         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1473
1474         entries = []
1475         for n in fileset_node.getchildren():
1476             url_n = n.find('./uri')
1477             if url_n is None:
1478                 continue
1479
1480             entries.append({
1481                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1482                 'title': '%s - %s' % (title, n.tag),
1483                 'url': compat_urlparse.urljoin(url, url_n.text),
1484                 'duration': float_or_none(n.find('./duration').text),
1485             })
1486
1487         return {
1488             '_type': 'playlist',
1489             'entries': entries,
1490             'title': title,
1491         }
1492
1493     def _real_extract(self, url):
1494         if url.startswith('//'):
1495             return {
1496                 '_type': 'url',
1497                 'url': self.http_scheme() + url,
1498             }
1499
1500         parsed_url = compat_urlparse.urlparse(url)
1501         if not parsed_url.scheme:
1502             default_search = self._downloader.params.get('default_search')
1503             if default_search is None:
1504                 default_search = 'fixup_error'
1505
1506             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1507                 if '/' in url:
1508                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1509                     return self.url_result('http://' + url)
1510                 elif default_search != 'fixup_error':
1511                     if default_search == 'auto_warning':
1512                         if re.match(r'^(?:url|URL)$', url):
1513                             raise ExtractorError(
1514                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1515                                 expected=True)
1516                         else:
1517                             self._downloader.report_warning(
1518                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1519                     return self.url_result('ytsearch:' + url)
1520
1521             if default_search in ('error', 'fixup_error'):
1522                 raise ExtractorError(
1523                     '%r is not a valid URL. '
1524                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1525                     % (url, url), expected=True)
1526             else:
1527                 if ':' not in default_search:
1528                     default_search += ':'
1529                 return self.url_result(default_search + url)
1530
1531         url, smuggled_data = unsmuggle_url(url)
1532         force_videoid = None
1533         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1534         if smuggled_data and 'force_videoid' in smuggled_data:
1535             force_videoid = smuggled_data['force_videoid']
1536             video_id = force_videoid
1537         else:
1538             video_id = self._generic_id(url)
1539
1540         self.to_screen('%s: Requesting header' % video_id)
1541
1542         head_req = HEADRequest(url)
1543         head_response = self._request_webpage(
1544             head_req, video_id,
1545             note=False, errnote='Could not send HEAD request to %s' % url,
1546             fatal=False)
1547
1548         if head_response is not False:
1549             # Check for redirect
1550             new_url = head_response.geturl()
1551             if url != new_url:
1552                 self.report_following_redirect(new_url)
1553                 if force_videoid:
1554                     new_url = smuggle_url(
1555                         new_url, {'force_videoid': force_videoid})
1556                 return self.url_result(new_url)
1557
1558         full_response = None
1559         if head_response is False:
1560             request = sanitized_Request(url)
1561             request.add_header('Accept-Encoding', '*')
1562             full_response = self._request_webpage(request, video_id)
1563             head_response = full_response
1564
1565         info_dict = {
1566             'id': video_id,
1567             'title': self._generic_title(url),
1568             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1569         }
1570
1571         # Check for direct link to a video
1572         content_type = head_response.headers.get('Content-Type', '').lower()
1573         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1574         if m:
1575             format_id = m.group('format_id')
1576             if format_id.endswith('mpegurl'):
1577                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1578             elif format_id == 'f4m':
1579                 formats = self._extract_f4m_formats(url, video_id)
1580             else:
1581                 formats = [{
1582                     'format_id': m.group('format_id'),
1583                     'url': url,
1584                     'vcodec': 'none' if m.group('type') == 'audio' else None
1585                 }]
1586                 info_dict['direct'] = True
1587             self._sort_formats(formats)
1588             info_dict['formats'] = formats
1589             return info_dict
1590
1591         if not self._downloader.params.get('test', False) and not is_intentional:
1592             force = self._downloader.params.get('force_generic_extractor', False)
1593             self._downloader.report_warning(
1594                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1595
1596         if not full_response:
1597             request = sanitized_Request(url)
1598             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1599             # making it impossible to download only chunk of the file (yet we need only 512kB to
1600             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1601             # that will always result in downloading the whole file that is not desirable.
1602             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1603             # to accept raw bytes and being able to download only a chunk.
1604             # It may probably better to solve this by checking Content-Type for application/octet-stream
1605             # after HEAD request finishes, but not sure if we can rely on this.
1606             request.add_header('Accept-Encoding', '*')
1607             full_response = self._request_webpage(request, video_id)
1608
1609         first_bytes = full_response.read(512)
1610
1611         # Is it an M3U playlist?
1612         if first_bytes.startswith(b'#EXTM3U'):
1613             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1614             self._sort_formats(info_dict['formats'])
1615             return info_dict
1616
1617         # Maybe it's a direct link to a video?
1618         # Be careful not to download the whole thing!
1619         if not is_html(first_bytes):
1620             self._downloader.report_warning(
1621                 'URL could be a direct video link, returning it as such.')
1622             info_dict.update({
1623                 'direct': True,
1624                 'url': url,
1625             })
1626             return info_dict
1627
1628         webpage = self._webpage_read_content(
1629             full_response, url, video_id, prefix=first_bytes)
1630
1631         self.report_extraction(video_id)
1632
1633         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1634         try:
1635             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1636             if doc.tag == 'rss':
1637                 return self._extract_rss(url, video_id, doc)
1638             elif doc.tag == 'SmoothStreamingMedia':
1639                 info_dict['formats'] = self._parse_ism_formats(doc, url)
1640                 self._sort_formats(info_dict['formats'])
1641                 return info_dict
1642             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1643                 smil = self._parse_smil(doc, url, video_id)
1644                 self._sort_formats(smil['formats'])
1645                 return smil
1646             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1647                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1648             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1649                 info_dict['formats'] = self._parse_mpd_formats(
1650                     doc, video_id,
1651                     mpd_base_url=full_response.geturl().rpartition('/')[0],
1652                     mpd_url=url)
1653                 self._sort_formats(info_dict['formats'])
1654                 return info_dict
1655             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1656                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1657                 self._sort_formats(info_dict['formats'])
1658                 return info_dict
1659         except compat_xml_parse_error:
1660             pass
1661
1662         # Is it a Camtasia project?
1663         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1664         if camtasia_res is not None:
1665             return camtasia_res
1666
1667         # Sometimes embedded video player is hidden behind percent encoding
1668         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1669         # Unescaping the whole page allows to handle those cases in a generic way
1670         webpage = compat_urllib_parse_unquote(webpage)
1671
1672         # it's tempting to parse this further, but you would
1673         # have to take into account all the variations like
1674         #   Video Title - Site Name
1675         #   Site Name | Video Title
1676         #   Video Title - Tagline | Site Name
1677         # and so on and so forth; it's just not practical
1678         video_title = self._og_search_title(
1679             webpage, default=None) or self._html_search_regex(
1680             r'(?s)<title>(.*?)</title>', webpage, 'video title',
1681             default='video')
1682
1683         # Try to detect age limit automatically
1684         age_limit = self._rta_search(webpage)
1685         # And then there are the jokers who advertise that they use RTA,
1686         # but actually don't.
1687         AGE_LIMIT_MARKERS = [
1688             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1689         ]
1690         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1691             age_limit = 18
1692
1693         # video uploader is domain name
1694         video_uploader = self._search_regex(
1695             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1696
1697         video_description = self._og_search_description(webpage, default=None)
1698         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1699
1700         # Helper method
1701         def _playlist_from_matches(matches, getter=None, ie=None):
1702             urlrs = orderedSet(
1703                 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1704                 for m in matches)
1705             return self.playlist_result(
1706                 urlrs, playlist_id=video_id, playlist_title=video_title)
1707
1708         # Look for Brightcove Legacy Studio embeds
1709         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1710         if bc_urls:
1711             self.to_screen('Brightcove video detected.')
1712             entries = [{
1713                 '_type': 'url',
1714                 'url': smuggle_url(bc_url, {'Referer': url}),
1715                 'ie_key': 'BrightcoveLegacy'
1716             } for bc_url in bc_urls]
1717
1718             return {
1719                 '_type': 'playlist',
1720                 'title': video_title,
1721                 'id': video_id,
1722                 'entries': entries,
1723             }
1724
1725         # Look for Brightcove New Studio embeds
1726         bc_urls = BrightcoveNewIE._extract_urls(webpage)
1727         if bc_urls:
1728             return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1729
1730         # Look for ThePlatform embeds
1731         tp_urls = ThePlatformIE._extract_urls(webpage)
1732         if tp_urls:
1733             return _playlist_from_matches(tp_urls, ie='ThePlatform')
1734
1735         # Look for Vessel embeds
1736         vessel_urls = VesselIE._extract_urls(webpage)
1737         if vessel_urls:
1738             return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1739
1740         # Look for embedded rtl.nl player
1741         matches = re.findall(
1742             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1743             webpage)
1744         if matches:
1745             return _playlist_from_matches(matches, ie='RtlNl')
1746
1747         vimeo_urls = VimeoIE._extract_urls(url, webpage)
1748         if vimeo_urls:
1749             return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1750
1751         vid_me_embed_url = self._search_regex(
1752             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1753             webpage, 'vid.me embed', default=None)
1754         if vid_me_embed_url is not None:
1755             return self.url_result(vid_me_embed_url, 'Vidme')
1756
1757         # Look for embedded YouTube player
1758         matches = re.findall(r'''(?x)
1759             (?:
1760                 <iframe[^>]+?src=|
1761                 data-video-url=|
1762                 <embed[^>]+?src=|
1763                 embedSWF\(?:\s*|
1764                 new\s+SWFObject\(
1765             )
1766             (["\'])
1767                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1768                 (?:embed|v|p)/.+?)
1769             \1''', webpage)
1770         if matches:
1771             return _playlist_from_matches(
1772                 matches, lambda m: unescapeHTML(m[1]))
1773
1774         # Look for lazyYT YouTube embed
1775         matches = re.findall(
1776             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1777         if matches:
1778             return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1779
1780         # Look for Wordpress "YouTube Video Importer" plugin
1781         matches = re.findall(r'''(?x)<div[^>]+
1782             class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1783             data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1784         if matches:
1785             return _playlist_from_matches(matches, lambda m: m[-1])
1786
1787         matches = DailymotionIE._extract_urls(webpage)
1788         if matches:
1789             return _playlist_from_matches(matches)
1790
1791         # Look for embedded Dailymotion playlist player (#3822)
1792         m = re.search(
1793             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1794         if m:
1795             playlists = re.findall(
1796                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1797             if playlists:
1798                 return _playlist_from_matches(
1799                     playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1800
1801         # Look for embedded Wistia player
1802         match = re.search(
1803             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1804         if match:
1805             embed_url = self._proto_relative_url(
1806                 unescapeHTML(match.group('url')))
1807             return {
1808                 '_type': 'url_transparent',
1809                 'url': embed_url,
1810                 'ie_key': 'Wistia',
1811                 'uploader': video_uploader,
1812             }
1813
1814         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1815         if match:
1816             return {
1817                 '_type': 'url_transparent',
1818                 'url': 'wistia:%s' % match.group('id'),
1819                 'ie_key': 'Wistia',
1820                 'uploader': video_uploader,
1821             }
1822
1823         match = re.search(
1824             r'''(?sx)
1825                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1826                 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1827             ''', webpage)
1828         if match:
1829             return self.url_result(self._proto_relative_url(
1830                 'wistia:%s' % match.group('id')), 'Wistia')
1831
1832         # Look for SVT player
1833         svt_url = SVTIE._extract_url(webpage)
1834         if svt_url:
1835             return self.url_result(svt_url, 'SVT')
1836
1837         # Look for embedded condenast player
1838         matches = re.findall(
1839             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1840             webpage)
1841         if matches:
1842             return {
1843                 '_type': 'playlist',
1844                 'entries': [{
1845                     '_type': 'url',
1846                     'ie_key': 'CondeNast',
1847                     'url': ma,
1848                 } for ma in matches],
1849                 'title': video_title,
1850                 'id': video_id,
1851             }
1852
1853         # Look for Bandcamp pages with custom domain
1854         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1855         if mobj is not None:
1856             burl = unescapeHTML(mobj.group(1))
1857             # Don't set the extractor because it can be a track url or an album
1858             return self.url_result(burl)
1859
1860         # Look for embedded Vevo player
1861         mobj = re.search(
1862             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1863         if mobj is not None:
1864             return self.url_result(mobj.group('url'))
1865
1866         # Look for embedded Viddler player
1867         mobj = re.search(
1868             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1869             webpage)
1870         if mobj is not None:
1871             return self.url_result(mobj.group('url'))
1872
1873         # Look for NYTimes player
1874         mobj = re.search(
1875             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1876             webpage)
1877         if mobj is not None:
1878             return self.url_result(mobj.group('url'))
1879
1880         # Look for Libsyn player
1881         mobj = re.search(
1882             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1883         if mobj is not None:
1884             return self.url_result(mobj.group('url'))
1885
1886         # Look for Ooyala videos
1887         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1888                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1889                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1890                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1891         if mobj is not None:
1892             return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1893
1894         # Look for multiple Ooyala embeds on SBN network websites
1895         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1896         if mobj is not None:
1897             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1898             if embeds:
1899                 return _playlist_from_matches(
1900                     embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1901
1902         # Look for Aparat videos
1903         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1904         if mobj is not None:
1905             return self.url_result(mobj.group(1), 'Aparat')
1906
1907         # Look for MPORA videos
1908         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1909         if mobj is not None:
1910             return self.url_result(mobj.group(1), 'Mpora')
1911
1912         # Look for embedded NovaMov-based player
1913         mobj = re.search(
1914             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1915                     (?P<url>http://(?:(?:embed|www)\.)?
1916                         (?:novamov\.com|
1917                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
1918                            videoweed\.(?:es|com)|
1919                            movshare\.(?:net|sx|ag)|
1920                            divxstage\.(?:eu|net|ch|co|at|ag))
1921                         /embed\.php.+?)\1''', webpage)
1922         if mobj is not None:
1923             return self.url_result(mobj.group('url'))
1924
1925         # Look for embedded Facebook player
1926         facebook_url = FacebookIE._extract_url(webpage)
1927         if facebook_url is not None:
1928             return self.url_result(facebook_url, 'Facebook')
1929
1930         # Look for embedded VK player
1931         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1932         if mobj is not None:
1933             return self.url_result(mobj.group('url'), 'VK')
1934
1935         # Look for embedded Odnoklassniki player
1936         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1937         if mobj is not None:
1938             return self.url_result(mobj.group('url'), 'Odnoklassniki')
1939
1940         # Look for embedded ivi player
1941         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1942         if mobj is not None:
1943             return self.url_result(mobj.group('url'), 'Ivi')
1944
1945         # Look for embedded Huffington Post player
1946         mobj = re.search(
1947             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1948         if mobj is not None:
1949             return self.url_result(mobj.group('url'), 'HuffPost')
1950
1951         # Look for embed.ly
1952         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1953         if mobj is not None:
1954             return self.url_result(mobj.group('url'))
1955         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1956         if mobj is not None:
1957             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1958
1959         # Look for funnyordie embed
1960         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1961         if matches:
1962             return _playlist_from_matches(
1963                 matches, getter=unescapeHTML, ie='FunnyOrDie')
1964
1965         # Look for BBC iPlayer embed
1966         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1967         if matches:
1968             return _playlist_from_matches(matches, ie='BBCCoUk')
1969
1970         # Look for embedded RUTV player
1971         rutv_url = RUTVIE._extract_url(webpage)
1972         if rutv_url:
1973             return self.url_result(rutv_url, 'RUTV')
1974
1975         # Look for embedded TVC player
1976         tvc_url = TVCIE._extract_url(webpage)
1977         if tvc_url:
1978             return self.url_result(tvc_url, 'TVC')
1979
1980         # Look for embedded SportBox player
1981         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1982         if sportbox_urls:
1983             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1984
1985         # Look for embedded PornHub player
1986         pornhub_url = PornHubIE._extract_url(webpage)
1987         if pornhub_url:
1988             return self.url_result(pornhub_url, 'PornHub')
1989
1990         # Look for embedded XHamster player
1991         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1992         if xhamster_urls:
1993             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1994
1995         # Look for embedded TNAFlixNetwork player
1996         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1997         if tnaflix_urls:
1998             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1999
2000         # Look for embedded DrTuber player
2001         drtuber_urls = DrTuberIE._extract_urls(webpage)
2002         if drtuber_urls:
2003             return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2004
2005         # Look for embedded Tvigle player
2006         mobj = re.search(
2007             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2008         if mobj is not None:
2009             return self.url_result(mobj.group('url'), 'Tvigle')
2010
2011         # Look for embedded TED player
2012         mobj = re.search(
2013             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2014         if mobj is not None:
2015             return self.url_result(mobj.group('url'), 'TED')
2016
2017         # Look for embedded Ustream videos
2018         mobj = re.search(
2019             r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2020         if mobj is not None:
2021             return self.url_result(mobj.group('url'), 'Ustream')
2022
2023         # Look for embedded arte.tv player
2024         mobj = re.search(
2025             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2026             webpage)
2027         if mobj is not None:
2028             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2029
2030         # Look for embedded francetv player
2031         mobj = re.search(
2032             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2033             webpage)
2034         if mobj is not None:
2035             return self.url_result(mobj.group('url'))
2036
2037         # Look for embedded smotri.com player
2038         smotri_url = SmotriIE._extract_url(webpage)
2039         if smotri_url:
2040             return self.url_result(smotri_url, 'Smotri')
2041
2042         # Look for embedded Myvi.ru player
2043         myvi_url = MyviIE._extract_url(webpage)
2044         if myvi_url:
2045             return self.url_result(myvi_url)
2046
2047         # Look for embedded soundcloud player
2048         soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2049         if soundcloud_urls:
2050             return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2051
2052         # Look for embedded mtvservices player
2053         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2054         if mtvservices_url:
2055             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2056
2057         # Look for embedded yahoo player
2058         mobj = re.search(
2059             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2060             webpage)
2061         if mobj is not None:
2062             return self.url_result(mobj.group('url'), 'Yahoo')
2063
2064         # Look for embedded sbs.com.au player
2065         mobj = re.search(
2066             r'''(?x)
2067             (?:
2068                 <meta\s+property="og:video"\s+content=|
2069                 <iframe[^>]+?src=
2070             )
2071             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2072             webpage)
2073         if mobj is not None:
2074             return self.url_result(mobj.group('url'), 'SBS')
2075
2076         # Look for embedded Cinchcast player
2077         mobj = re.search(
2078             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2079             webpage)
2080         if mobj is not None:
2081             return self.url_result(mobj.group('url'), 'Cinchcast')
2082
2083         mobj = re.search(
2084             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2085             webpage)
2086         if not mobj:
2087             mobj = re.search(
2088                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2089                 webpage)
2090         if mobj is not None:
2091             return self.url_result(mobj.group('url'), 'MLB')
2092
2093         mobj = re.search(
2094             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2095             webpage)
2096         if mobj is not None:
2097             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2098
2099         mobj = re.search(
2100             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2101             webpage)
2102         if mobj is not None:
2103             return self.url_result(mobj.group('url'), 'Livestream')
2104
2105         # Look for Zapiks embed
2106         mobj = re.search(
2107             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2108         if mobj is not None:
2109             return self.url_result(mobj.group('url'), 'Zapiks')
2110
2111         # Look for Kaltura embeds
2112         kaltura_url = KalturaIE._extract_url(webpage)
2113         if kaltura_url:
2114             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2115
2116         # Look for Eagle.Platform embeds
2117         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2118         if eagleplatform_url:
2119             return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2120
2121         # Look for ClipYou (uses Eagle.Platform) embeds
2122         mobj = re.search(
2123             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2124         if mobj is not None:
2125             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2126
2127         # Look for Pladform embeds
2128         pladform_url = PladformIE._extract_url(webpage)
2129         if pladform_url:
2130             return self.url_result(pladform_url)
2131
2132         # Look for Videomore embeds
2133         videomore_url = VideomoreIE._extract_url(webpage)
2134         if videomore_url:
2135             return self.url_result(videomore_url)
2136
2137         # Look for Playwire embeds
2138         mobj = re.search(
2139             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2140         if mobj is not None:
2141             return self.url_result(mobj.group('url'))
2142
2143         # Look for 5min embeds
2144         mobj = re.search(
2145             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2146         if mobj is not None:
2147             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2148
2149         # Look for Crooks and Liars embeds
2150         mobj = re.search(
2151             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2152         if mobj is not None:
2153             return self.url_result(mobj.group('url'))
2154
2155         # Look for NBC Sports VPlayer embeds
2156         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2157         if nbc_sports_url:
2158             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2159
2160         # Look for NBC News embeds
2161         nbc_news_embed_url = re.search(
2162             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2163         if nbc_news_embed_url:
2164             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2165
2166         # Look for Google Drive embeds
2167         google_drive_url = GoogleDriveIE._extract_url(webpage)
2168         if google_drive_url:
2169             return self.url_result(google_drive_url, 'GoogleDrive')
2170
2171         # Look for UDN embeds
2172         mobj = re.search(
2173             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2174         if mobj is not None:
2175             return self.url_result(
2176                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2177
2178         # Look for Senate ISVP iframe
2179         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2180         if senate_isvp_url:
2181             return self.url_result(senate_isvp_url, 'SenateISVP')
2182
2183         # Look for Dailymotion Cloud videos
2184         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2185         if dmcloud_url:
2186             return self.url_result(dmcloud_url, 'DailymotionCloud')
2187
2188         # Look for OnionStudios embeds
2189         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2190         if onionstudios_url:
2191             return self.url_result(onionstudios_url)
2192
2193         # Look for ViewLift embeds
2194         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2195         if viewlift_url:
2196             return self.url_result(viewlift_url)
2197
2198         # Look for JWPlatform embeds
2199         jwplatform_url = JWPlatformIE._extract_url(webpage)
2200         if jwplatform_url:
2201             return self.url_result(jwplatform_url, 'JWPlatform')
2202
2203         # Look for ScreenwaveMedia embeds
2204         mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2205         if mobj is not None:
2206             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2207
2208         # Look for Digiteka embeds
2209         digiteka_url = DigitekaIE._extract_url(webpage)
2210         if digiteka_url:
2211             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2212
2213         # Look for Arkena embeds
2214         arkena_url = ArkenaIE._extract_url(webpage)
2215         if arkena_url:
2216             return self.url_result(arkena_url, ArkenaIE.ie_key())
2217
2218         # Look for Limelight embeds
2219         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2220         if mobj:
2221             lm = {
2222                 'Media': 'media',
2223                 'Channel': 'channel',
2224                 'ChannelList': 'channel_list',
2225             }
2226             return self.url_result('limelight:%s:%s' % (
2227                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2228
2229         # Look for AdobeTVVideo embeds
2230         mobj = re.search(
2231             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2232             webpage)
2233         if mobj is not None:
2234             return self.url_result(
2235                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2236                 'AdobeTVVideo')
2237
2238         # Look for Vine embeds
2239         mobj = re.search(
2240             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2241             webpage)
2242         if mobj is not None:
2243             return self.url_result(
2244                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2245
2246         # Look for VODPlatform embeds
2247         mobj = re.search(
2248             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2249             webpage)
2250         if mobj is not None:
2251             return self.url_result(
2252                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2253
2254         # Look for Mangomolo embeds
2255         mobj = re.search(
2256             r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2257                 (?:
2258                     video\?.*?\bid=(?P<video_id>\d+)|
2259                     index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2260                 ).+?)\1''', webpage)
2261         if mobj is not None:
2262             info = {
2263                 '_type': 'url_transparent',
2264                 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2265                 'title': video_title,
2266                 'description': video_description,
2267                 'thumbnail': video_thumbnail,
2268                 'uploader': video_uploader,
2269             }
2270             video_id = mobj.group('video_id')
2271             if video_id:
2272                 info.update({
2273                     'ie_key': 'MangomoloVideo',
2274                     'id': video_id,
2275                 })
2276             else:
2277                 info.update({
2278                     'ie_key': 'MangomoloLive',
2279                     'id': mobj.group('channel_id'),
2280                 })
2281             return info
2282
2283         # Look for Instagram embeds
2284         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2285         if instagram_embed_url is not None:
2286             return self.url_result(
2287                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2288
2289         # Look for LiveLeak embeds
2290         liveleak_url = LiveLeakIE._extract_url(webpage)
2291         if liveleak_url:
2292             return self.url_result(liveleak_url, 'LiveLeak')
2293
2294         # Look for 3Q SDN embeds
2295         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2296         if threeqsdn_url:
2297             return {
2298                 '_type': 'url_transparent',
2299                 'ie_key': ThreeQSDNIE.ie_key(),
2300                 'url': self._proto_relative_url(threeqsdn_url),
2301                 'title': video_title,
2302                 'description': video_description,
2303                 'thumbnail': video_thumbnail,
2304                 'uploader': video_uploader,
2305             }
2306
2307         # Look for VBOX7 embeds
2308         vbox7_url = Vbox7IE._extract_url(webpage)
2309         if vbox7_url:
2310             return self.url_result(vbox7_url, Vbox7IE.ie_key())
2311
2312         # Look for DBTV embeds
2313         dbtv_urls = DBTVIE._extract_urls(webpage)
2314         if dbtv_urls:
2315             return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2316
2317         # Looking for http://schema.org/VideoObject
2318         json_ld = self._search_json_ld(
2319             webpage, video_id, default={}, expected_type='VideoObject')
2320         if json_ld.get('url'):
2321             info_dict.update({
2322                 'title': video_title or info_dict['title'],
2323                 'description': video_description,
2324                 'thumbnail': video_thumbnail,
2325                 'age_limit': age_limit
2326             })
2327             info_dict.update(json_ld)
2328             return info_dict
2329
2330         # Look for HTML5 media
2331         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2332         if entries:
2333             for entry in entries:
2334                 entry.update({
2335                     'id': video_id,
2336                     'title': video_title,
2337                 })
2338                 self._sort_formats(entry['formats'])
2339             return self.playlist_result(entries)
2340
2341         def check_video(vurl):
2342             if YoutubeIE.suitable(vurl):
2343                 return True
2344             vpath = compat_urlparse.urlparse(vurl).path
2345             vext = determine_ext(vpath)
2346             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2347
2348         def filter_video(urls):
2349             return list(filter(check_video, urls))
2350
2351         # Start with something easy: JW Player in SWFObject
2352         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2353         if not found:
2354             # Look for gorilla-vid style embedding
2355             found = filter_video(re.findall(r'''(?sx)
2356                 (?:
2357                     jw_plugins|
2358                     JWPlayerOptions|
2359                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2360                 )
2361                 .*?
2362                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2363         if not found:
2364             # Broaden the search a little bit
2365             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2366         if not found:
2367             # Broaden the findall a little bit: JWPlayer JS loader
2368             found = filter_video(re.findall(
2369                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2370         if not found:
2371             # Flow player
2372             found = filter_video(re.findall(r'''(?xs)
2373                 flowplayer\("[^"]+",\s*
2374                     \{[^}]+?\}\s*,
2375                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2376                         ["']?url["']?\s*:\s*["']([^"']+)["']
2377             ''', webpage))
2378         if not found:
2379             # Cinerama player
2380             found = re.findall(
2381                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2382         if not found:
2383             # Try to find twitter cards info
2384             # twitter:player:stream should be checked before twitter:player since
2385             # it is expected to contain a raw stream (see
2386             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2387             found = filter_video(re.findall(
2388                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2389         if not found:
2390             # We look for Open Graph info:
2391             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2392             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2393             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2394             if m_video_type is not None:
2395                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2396         if not found:
2397             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2398             found = re.search(
2399                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2400                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2401                 webpage)
2402             if not found:
2403                 # Look also in Refresh HTTP header
2404                 refresh_header = head_response.headers.get('Refresh')
2405                 if refresh_header:
2406                     # In python 2 response HTTP headers are bytestrings
2407                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2408                         refresh_header = refresh_header.decode('iso-8859-1')
2409                     found = re.search(REDIRECT_REGEX, refresh_header)
2410             if found:
2411                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2412                 self.report_following_redirect(new_url)
2413                 return {
2414                     '_type': 'url',
2415                     'url': new_url,
2416                 }
2417
2418         if not found:
2419             # twitter:player is a https URL to iframe player that may or may not
2420             # be supported by youtube-dl thus this is checked the very last (see
2421             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2422             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2423             if embed_url:
2424                 return self.url_result(embed_url)
2425
2426         if not found:
2427             raise UnsupportedError(url)
2428
2429         entries = []
2430         for video_url in orderedSet(found):
2431             video_url = unescapeHTML(video_url)
2432             video_url = video_url.replace('\\/', '/')
2433             video_url = compat_urlparse.urljoin(url, video_url)
2434             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2435
2436             # Sometimes, jwplayer extraction will result in a YouTube URL
2437             if YoutubeIE.suitable(video_url):
2438                 entries.append(self.url_result(video_url, 'Youtube'))
2439                 continue
2440
2441             # here's a fun little line of code for you:
2442             video_id = os.path.splitext(video_id)[0]
2443
2444             entry_info_dict = {
2445                 'id': video_id,
2446                 'uploader': video_uploader,
2447                 'title': video_title,
2448                 'age_limit': age_limit,
2449             }
2450
2451             ext = determine_ext(video_url)
2452             if ext == 'smil':
2453                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2454             elif ext == 'xspf':
2455                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2456             elif ext == 'm3u8':
2457                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2458             elif ext == 'mpd':
2459                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2460             elif ext == 'f4m':
2461                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2462             elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2463                 # Just matching .ism/manifest is not enough to be reliably sure
2464                 # whether it's actually an ISM manifest or some other streaming
2465                 # manifest since there are various streaming URL formats
2466                 # possible (see [1]) as well as some other shenanigans like
2467                 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2468                 # so on.
2469                 # Thus the most reasonable way to solve this is to delegate
2470                 # to generic extractor in order to look into the contents of
2471                 # the manifest itself.
2472                 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2473                 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2474                 entry_info_dict = self.url_result(
2475                     smuggle_url(video_url, {'to_generic': True}),
2476                     GenericIE.ie_key())
2477             else:
2478                 entry_info_dict['url'] = video_url
2479
2480             if entry_info_dict.get('formats'):
2481                 self._sort_formats(entry_info_dict['formats'])
2482
2483             entries.append(entry_info_dict)
2484
2485         if len(entries) == 1:
2486             return entries[0]
2487         else:
2488             for num, e in enumerate(entries, start=1):
2489                 # 'url' results don't have a title
2490                 if e.get('title') is not None:
2491                     e['title'] = '%s (%d)' % (e['title'], num)
2492             return {
2493                 '_type': 'playlist',
2494                 'entries': entries,
2495             }