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

   1 # encoding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import os
   6 import re
   7 import sys
   8
   9 from .common import InfoExtractor
  10 from .youtube import YoutubeIE
  11 from ..compat import (
  12     compat_etree_fromstring,
  13     compat_urllib_parse_unquote,
  14     compat_urlparse,
  15     compat_xml_parse_error,
  16 )
  17 from ..utils import (
  18     determine_ext,
  19     ExtractorError,
  20     float_or_none,
  21     HEADRequest,
  22     is_html,
  23     orderedSet,
  24     sanitized_Request,
  25     smuggle_url,
  26     unescapeHTML,
  27     unified_strdate,
  28     unsmuggle_url,
  29     UnsupportedError,
  30     url_basename,
  31     xpath_text,
  32 )
  33 from .brightcove import (
  34     BrightcoveLegacyIE,
  35     BrightcoveNewIE,
  36 )
  37 from .nbc import NBCSportsVPlayerIE
  38 from .ooyala import OoyalaIE
  39 from .rutv import RUTVIE
  40 from .tvc import TVCIE
  41 from .sportbox import SportBoxEmbedIE
  42 from .smotri import SmotriIE
  43 from .myvi import MyviIE
  44 from .condenast import CondeNastIE
  45 from .udn import UDNEmbedIE
  46 from .senateisvp import SenateISVPIE
  47 from .svt import SVTIE
  48 from .pornhub import PornHubIE
  49 from .xhamster import XHamsterEmbedIE
  50 from .tnaflix import TNAFlixNetworkEmbedIE
  51 from .vimeo import VimeoIE
  52 from .dailymotion import DailymotionCloudIE
  53 from .onionstudios import OnionStudiosIE
  54 from .snagfilms import SnagFilmsEmbedIE
  55 from .screenwavemedia import ScreenwaveMediaIE
  56 from .mtv import MTVServicesEmbeddedIE
  57 from .pladform import PladformIE
  58 from .videomore import VideomoreIE
  59 from .googledrive import GoogleDriveIE
  60 from .jwplatform import JWPlatformIE
  61 from .digiteka import DigitekaIE
  62 from .instagram import InstagramIE
  63
  64
  65 class GenericIE(InfoExtractor):
  66     IE_DESC = 'Generic downloader that works on some sites'
  67     _VALID_URL = r'.*'
  68     IE_NAME = 'generic'
  69     _TESTS = [
  70         # Direct link to a video
  71         {
  72             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  73             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  74             'info_dict': {
  75                 'id': 'trailer',
  76                 'ext': 'mp4',
  77                 'title': 'trailer',
  78                 'upload_date': '20100513',
  79             }
  80         },
  81         # Direct link to media delivered compressed (until Accept-Encoding is *)
  82         {
  83             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  84             'md5': '128c42e68b13950268b648275386fc74',
  85             'info_dict': {
  86                 'id': 'FictionJunction-Parallel_Hearts',
  87                 'ext': 'flac',
  88                 'title': 'FictionJunction-Parallel_Hearts',
  89                 'upload_date': '20140522',
  90             },
  91             'expected_warnings': [
  92                 'URL could be a direct video link, returning it as such.'
  93             ]
  94         },
  95         # Direct download with broken HEAD
  96         {
  97             'url': 'http://ai-radio.org:8000/radio.opus',
  98             'info_dict': {
  99                 'id': 'radio',
 100                 'ext': 'opus',
 101                 'title': 'radio',
 102             },
 103             'params': {
 104                 'skip_download': True,  # infinite live stream
 105             },
 106             'expected_warnings': [
 107                 r'501.*Not Implemented'
 108             ],
 109         },
 110         # Direct link with incorrect MIME type
 111         {
 112             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 113             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 114             'info_dict': {
 115                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 116                 'id': '5_Lennart_Poettering_-_Systemd',
 117                 'ext': 'webm',
 118                 'title': '5_Lennart_Poettering_-_Systemd',
 119                 'upload_date': '20141120',
 120             },
 121             'expected_warnings': [
 122                 'URL could be a direct video link, returning it as such.'
 123             ]
 124         },
 125         # RSS feed
 126         {
 127             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 128             'info_dict': {
 129                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 130                 'title': 'Zero Punctuation',
 131                 'description': 're:.*groundbreaking video review series.*'
 132             },
 133             'playlist_mincount': 11,
 134         },
 135         # RSS feed with enclosure
 136         {
 137             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 138             'info_dict': {
 139                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 140                 'ext': 'm4v',
 141                 'upload_date': '20150228',
 142                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 143             }
 144         },
 145         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 146         {
 147             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 148             'info_dict': {
 149                 'id': 'smil',
 150                 'ext': 'mp4',
 151                 'title': 'Automatics, robotics and biocybernetics',
 152                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 153                 'upload_date': '20130627',
 154                 'formats': 'mincount:16',
 155                 'subtitles': 'mincount:1',
 156             },
 157             'params': {
 158                 'force_generic_extractor': True,
 159                 'skip_download': True,
 160             },
 161         },
 162         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 163         {
 164             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 165             'info_dict': {
 166                 'id': 'hds',
 167                 'ext': 'flv',
 168                 'title': 'hds',
 169                 'formats': 'mincount:1',
 170             },
 171             'params': {
 172                 'skip_download': True,
 173             },
 174         },
 175         # SMIL from https://www.restudy.dk/video/play/id/1637
 176         {
 177             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 178             'info_dict': {
 179                 'id': 'video_1637',
 180                 'ext': 'flv',
 181                 'title': 'video_1637',
 182                 'formats': 'mincount:3',
 183             },
 184             'params': {
 185                 'skip_download': True,
 186             },
 187         },
 188         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 189         {
 190             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 191             'info_dict': {
 192                 'id': 'smil-service',
 193                 'ext': 'flv',
 194                 'title': 'smil-service',
 195                 'formats': 'mincount:1',
 196             },
 197             'params': {
 198                 'skip_download': True,
 199             },
 200         },
 201         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 202         {
 203             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 204             'info_dict': {
 205                 'id': '4719370',
 206                 'ext': 'mp4',
 207                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 208                 'formats': 'mincount:3',
 209             },
 210             'params': {
 211                 'skip_download': True,
 212             },
 213         },
 214         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 215         {
 216             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 217             'info_dict': {
 218                 'id': 'mZlp2ctYIUEB',
 219                 'ext': 'mp4',
 220                 'title': 'Tikibad ontruimd wegens brand',
 221                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 222                 'thumbnail': 're:^https?://.*\.jpg$',
 223                 'duration': 33,
 224             },
 225             'params': {
 226                 'skip_download': True,
 227             },
 228         },
 229         # MPD from http://dash-mse-test.appspot.com/media.html
 230         {
 231             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 232             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 233             'info_dict': {
 234                 'id': 'car-20120827-manifest',
 235                 'ext': 'mp4',
 236                 'title': 'car-20120827-manifest',
 237                 'formats': 'mincount:9',
 238             },
 239             'params': {
 240                 'format': 'bestvideo',
 241             },
 242         },
 243         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 244         {
 245             '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',
 246             'info_dict': {
 247                 'id': 'content',
 248                 'ext': 'mp4',
 249                 'title': 'content',
 250                 'formats': 'mincount:8',
 251             },
 252             'params': {
 253                 # m3u8 downloads
 254                 'skip_download': True,
 255             }
 256         },
 257         # m3u8 served with Content-Type: text/plain
 258         {
 259             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 260             'info_dict': {
 261                 'id': 'index',
 262                 'ext': 'mp4',
 263                 'title': 'index',
 264                 'upload_date': '20140720',
 265                 'formats': 'mincount:11',
 266             },
 267             'params': {
 268                 # m3u8 downloads
 269                 'skip_download': True,
 270             }
 271         },
 272         # google redirect
 273         {
 274             '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',
 275             'info_dict': {
 276                 'id': 'cmQHVoWB5FY',
 277                 'ext': 'mp4',
 278                 'upload_date': '20130224',
 279                 'uploader_id': 'TheVerge',
 280                 'description': 're:^Chris Ziegler takes a look at the\.*',
 281                 'uploader': 'The Verge',
 282                 'title': 'First Firefox OS phones side-by-side',
 283             },
 284             'params': {
 285                 'skip_download': False,
 286             }
 287         },
 288         {
 289             # redirect in Refresh HTTP header
 290             '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',
 291             'info_dict': {
 292                 'id': 'pO8h3EaFRdo',
 293                 'ext': 'mp4',
 294                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 295                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 296                 'upload_date': '20150917',
 297                 'uploader_id': 'brtvofficial',
 298                 'uploader': 'Boiler Room',
 299             },
 300             'params': {
 301                 'skip_download': False,
 302             },
 303         },
 304         {
 305             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 306             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 307             'info_dict': {
 308                 'id': '13601338388002',
 309                 'ext': 'mp4',
 310                 'uploader': 'www.hodiho.fr',
 311                 'title': 'R\u00e9gis plante sa Jeep',
 312             }
 313         },
 314         # bandcamp page with custom domain
 315         {
 316             'add_ie': ['Bandcamp'],
 317             'url': 'http://bronyrock.com/track/the-pony-mash',
 318             'info_dict': {
 319                 'id': '3235767654',
 320                 'ext': 'mp3',
 321                 'title': 'The Pony Mash',
 322                 'uploader': 'M_Pallante',
 323             },
 324             'skip': 'There is a limit of 200 free downloads / month for the test song',
 325         },
 326         # embedded brightcove video
 327         # it also tests brightcove videos that need to set the 'Referer' in the
 328         # http requests
 329         {
 330             'add_ie': ['BrightcoveLegacy'],
 331             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 332             'info_dict': {
 333                 'id': '2765128793001',
 334                 'ext': 'mp4',
 335                 'title': 'Le cours de bourse : l’analyse technique',
 336                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 337                 'uploader': 'BFM BUSINESS',
 338             },
 339             'params': {
 340                 'skip_download': True,
 341             },
 342         },
 343         {
 344             # https://github.com/rg3/youtube-dl/issues/2253
 345             'url': 'http://bcove.me/i6nfkrc3',
 346             'md5': '0ba9446db037002366bab3b3eb30c88c',
 347             'info_dict': {
 348                 'id': '3101154703001',
 349                 'ext': 'mp4',
 350                 'title': 'Still no power',
 351                 'uploader': 'thestar.com',
 352                 '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.',
 353             },
 354             'add_ie': ['BrightcoveLegacy'],
 355         },
 356         {
 357             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 358             'md5': 'fb973ecf6e4a78a67453647444222983',
 359             'info_dict': {
 360                 'id': '3414141473001',
 361                 'ext': 'mp4',
 362                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 363                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 364                 'uploader': 'Championat',
 365             },
 366         },
 367         {
 368             # https://github.com/rg3/youtube-dl/issues/3541
 369             'add_ie': ['BrightcoveLegacy'],
 370             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 371             'info_dict': {
 372                 'id': '3866516442001',
 373                 'ext': 'mp4',
 374                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 375                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 376                 'uploader': 'SBS Broadcasting',
 377             },
 378             'skip': 'Restricted to Netherlands',
 379             'params': {
 380                 'skip_download': True,  # m3u8 download
 381             },
 382         },
 383         # ooyala video
 384         {
 385             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 386             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 387             'info_dict': {
 388                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 389                 'ext': 'mp4',
 390                 'title': '2cc213299525360.mov',  # that's what we get
 391                 'duration': 238.231,
 392             },
 393             'add_ie': ['Ooyala'],
 394         },
 395         {
 396             # ooyala video embedded with http://player.ooyala.com/iframe.js
 397             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 398             'info_dict': {
 399                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 400                 'ext': 'mp4',
 401                 'title': '"Steve Jobs: Man in the Machine" trailer',
 402                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 403                 'duration': 135.427,
 404             },
 405             'params': {
 406                 'skip_download': True,
 407             },
 408         },
 409         # multiple ooyala embeds on SBN network websites
 410         {
 411             'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
 412             'info_dict': {
 413                 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
 414                 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
 415             },
 416             'playlist_mincount': 3,
 417             'params': {
 418                 'skip_download': True,
 419             },
 420             'add_ie': ['Ooyala'],
 421         },
 422         # embed.ly video
 423         {
 424             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 425             'info_dict': {
 426                 'id': '9ODmcdjQcHQ',
 427                 'ext': 'mp4',
 428                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 429                 'upload_date': '20140225',
 430                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 431                 'uploader': 'Tested',
 432                 'uploader_id': 'testedcom',
 433             },
 434             # No need to test YoutubeIE here
 435             'params': {
 436                 'skip_download': True,
 437             },
 438         },
 439         # funnyordie embed
 440         {
 441             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 442             'info_dict': {
 443                 'id': '18e820ec3f',
 444                 'ext': 'mp4',
 445                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 446                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 447             },
 448         },
 449         # RUTV embed
 450         {
 451             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 452             'info_dict': {
 453                 'id': '776940',
 454                 'ext': 'mp4',
 455                 'title': 'Охотское море стало целиком российским',
 456                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 457             },
 458             'params': {
 459                 # m3u8 download
 460                 'skip_download': True,
 461             },
 462         },
 463         # TVC embed
 464         {
 465             '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/',
 466             'info_dict': {
 467                 'id': '55304',
 468                 'ext': 'mp4',
 469                 'title': 'Дошкольное воспитание',
 470             },
 471         },
 472         # SportBox embed
 473         {
 474             'url': 'http://www.vestifinance.ru/articles/25753',
 475             'info_dict': {
 476                 'id': '25753',
 477                 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 478             },
 479             'playlist': [{
 480                 'info_dict': {
 481                     'id': '370908',
 482                     'title': 'Госзаказ. День 3',
 483                     'ext': 'mp4',
 484                 }
 485             }, {
 486                 'info_dict': {
 487                     'id': '370905',
 488                     'title': 'Госзаказ. День 2',
 489                     'ext': 'mp4',
 490                 }
 491             }, {
 492                 'info_dict': {
 493                     'id': '370902',
 494                     'title': 'Госзаказ. День 1',
 495                     'ext': 'mp4',
 496                 }
 497             }],
 498             'params': {
 499                 # m3u8 download
 500                 'skip_download': True,
 501             },
 502         },
 503         # Myvi.ru embed
 504         {
 505             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 506             'info_dict': {
 507                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 508                 'ext': 'mp4',
 509                 'title': 'Ужастики, русский трейлер (2015)',
 510                 'thumbnail': 're:^https?://.*\.jpg$',
 511                 'duration': 153,
 512             }
 513         },
 514         # XHamster embed
 515         {
 516             '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',
 517             'info_dict': {
 518                 'id': 'showthread',
 519                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 520             },
 521             'playlist_mincount': 7,
 522         },
 523         # Embedded TED video
 524         {
 525             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 526             'md5': '65fdff94098e4a607385a60c5177c638',
 527             'info_dict': {
 528                 'id': '1969',
 529                 'ext': 'mp4',
 530                 'title': 'Hidden miracles of the natural world',
 531                 'uploader': 'Louie Schwartzberg',
 532                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 533             }
 534         },
 535         # Embedded Ustream video
 536         {
 537             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
 538             'md5': '27b99cdb639c9b12a79bca876a073417',
 539             'info_dict': {
 540                 'id': '45734260',
 541                 'ext': 'flv',
 542                 'uploader': 'AU SPA:  The NSA and Privacy',
 543                 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
 544             }
 545         },
 546         # nowvideo embed hidden behind percent encoding
 547         {
 548             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 549             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 550             'info_dict': {
 551                 'id': '06e53103ca9aa',
 552                 'ext': 'flv',
 553                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 554                 'description': 'No description',
 555             },
 556         },
 557         # arte embed
 558         {
 559             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 560             'md5': '7653032cbb25bf6c80d80f217055fa43',
 561             'info_dict': {
 562                 'id': '048195-004_PLUS7-F',
 563                 'ext': 'flv',
 564                 'title': 'X:enius',
 565                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 566                 'upload_date': '20140320',
 567             },
 568             'params': {
 569                 'skip_download': 'Requires rtmpdump'
 570             }
 571         },
 572         # francetv embed
 573         {
 574             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 575             'info_dict': {
 576                 'id': 'EV_30231',
 577                 'ext': 'mp4',
 578                 'title': 'Alcaline, le concert avec Calogero',
 579                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 580                 'upload_date': '20150226',
 581                 'timestamp': 1424989860,
 582                 'duration': 5400,
 583             },
 584             'params': {
 585                 # m3u8 downloads
 586                 'skip_download': True,
 587             },
 588             'expected_warnings': [
 589                 'Forbidden'
 590             ]
 591         },
 592         # Condé Nast embed
 593         {
 594             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 595             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 596             'info_dict': {
 597                 'id': '53501be369702d3275860000',
 598                 'ext': 'mp4',
 599                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 600             }
 601         },
 602         # Dailymotion embed
 603         {
 604             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 605             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 606             'info_dict': {
 607                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 608                 'ext': 'mp4',
 609                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 610                 'uploader': 'Spi0n',
 611             },
 612             'add_ie': ['Dailymotion'],
 613         },
 614         # YouTube embed
 615         {
 616             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 617             'info_dict': {
 618                 'id': 'FXRb4ykk4S0',
 619                 'ext': 'mp4',
 620                 'title': 'The NBL Auction 2014',
 621                 'uploader': 'BADMINTON England',
 622                 'uploader_id': 'BADMINTONEvents',
 623                 'upload_date': '20140603',
 624                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 625             },
 626             'add_ie': ['Youtube'],
 627             'params': {
 628                 'skip_download': True,
 629             }
 630         },
 631         # MTVSercices embed
 632         {
 633             'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
 634             'md5': '35727f82f58c76d996fc188f9755b0d5',
 635             'info_dict': {
 636                 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
 637                 'ext': 'mp4',
 638                 'title': 'Review',
 639                 'description': 'Mario\'s life in the fast lane has never looked so good.',
 640             },
 641         },
 642         # YouTube embed via <data-embed-url="">
 643         {
 644             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 645             'info_dict': {
 646                 'id': '4vAffPZIT44',
 647                 'ext': 'mp4',
 648                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 649                 'uploader': 'Gameloft',
 650                 'uploader_id': 'gameloft',
 651                 'upload_date': '20140828',
 652                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 653             },
 654             'params': {
 655                 'skip_download': True,
 656             }
 657         },
 658         # Camtasia studio
 659         {
 660             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 661             'playlist': [{
 662                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 663                 'info_dict': {
 664                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 665                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 666                     'ext': 'flv',
 667                     'duration': 2235.90,
 668                 }
 669             }, {
 670                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 671                 'info_dict': {
 672                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 673                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 674                     'ext': 'flv',
 675                     'duration': 2235.93,
 676                 }
 677             }],
 678             'info_dict': {
 679                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 680             }
 681         },
 682         # Flowplayer
 683         {
 684             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 685             'md5': '9d65602bf31c6e20014319c7d07fba27',
 686             'info_dict': {
 687                 'id': '5123ea6d5e5a7',
 688                 'ext': 'mp4',
 689                 'age_limit': 18,
 690                 'uploader': 'www.handjobhub.com',
 691                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 692             }
 693         },
 694         # Multiple brightcove videos
 695         # https://github.com/rg3/youtube-dl/issues/2283
 696         {
 697             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 698             'info_dict': {
 699                 'id': 'always-never',
 700                 'title': 'Always / Never - The New Yorker',
 701             },
 702             'playlist_count': 3,
 703             'params': {
 704                 'extract_flat': False,
 705                 'skip_download': True,
 706             }
 707         },
 708         # MLB embed
 709         {
 710             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 711             'md5': '96f09a37e44da40dd083e12d9a683327',
 712             'info_dict': {
 713                 'id': '33322633',
 714                 'ext': 'mp4',
 715                 'title': 'Ump changes call to ball',
 716                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 717                 'duration': 48,
 718                 'timestamp': 1401537900,
 719                 'upload_date': '20140531',
 720                 'thumbnail': 're:^https?://.*\.jpg$',
 721             },
 722         },
 723         # Wistia embed
 724         {
 725             'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 726             'md5': '8788b683c777a5cf25621eaf286d0c23',
 727             'info_dict': {
 728                 'id': '1cfaf6b7ea',
 729                 'ext': 'mov',
 730                 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
 731                 'duration': 643.0,
 732                 'filesize': 182808282,
 733                 'uploader': 'education-portal.com',
 734             },
 735         },
 736         {
 737             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 738             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 739             'info_dict': {
 740                 'id': 'uxjb0lwrcz',
 741                 'ext': 'mp4',
 742                 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
 743                 'duration': 1715.0,
 744                 'uploader': 'thoughtworks.wistia.com',
 745             },
 746         },
 747         # Soundcloud embed
 748         {
 749             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 750             'info_dict': {
 751                 'id': '174391317',
 752                 'ext': 'mp3',
 753                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 754                 'uploader': 'Sophos Security',
 755                 'title': 'Chet Chat 171 - Oct 29, 2014',
 756                 'upload_date': '20141029',
 757             }
 758         },
 759         # Livestream embed
 760         {
 761             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 762             'info_dict': {
 763                 'id': '67864563',
 764                 'ext': 'flv',
 765                 'upload_date': '20141112',
 766                 'title': 'Rosetta #CometLanding webcast HL 10',
 767             }
 768         },
 769         # LazyYT
 770         {
 771             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
 772             'info_dict': {
 773                 'id': '1986',
 774                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
 775             },
 776             'playlist_mincount': 2,
 777         },
 778         # Cinchcast embed
 779         {
 780             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
 781             'info_dict': {
 782                 'id': '7141703',
 783                 'ext': 'mp3',
 784                 'upload_date': '20141126',
 785                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
 786             }
 787         },
 788         # Cinerama player
 789         {
 790             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
 791             'info_dict': {
 792                 'id': '730m_DandD_1901_512k',
 793                 'ext': 'mp4',
 794                 'uploader': 'www.abc.net.au',
 795                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
 796             }
 797         },
 798         # embedded viddler video
 799         {
 800             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
 801             'info_dict': {
 802                 'id': '4d03aad9',
 803                 'ext': 'mp4',
 804                 'uploader': 'deadspin',
 805                 'title': 'WALL-TO-GORTAT',
 806                 'timestamp': 1422285291,
 807                 'upload_date': '20150126',
 808             },
 809             'add_ie': ['Viddler'],
 810         },
 811         # Libsyn embed
 812         {
 813             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
 814             'info_dict': {
 815                 'id': '3377616',
 816                 'ext': 'mp3',
 817                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
 818                 'description': 'md5:601cb790edd05908957dae8aaa866465',
 819                 'upload_date': '20150220',
 820             },
 821         },
 822         # jwplayer YouTube
 823         {
 824             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
 825             'info_dict': {
 826                 'id': 'Mrj4DVp2zeA',
 827                 'ext': 'mp4',
 828                 'upload_date': '20150212',
 829                 'uploader': 'The National Archives UK',
 830                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
 831                 'uploader_id': 'NationalArchives08',
 832                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
 833             },
 834         },
 835         # rtl.nl embed
 836         {
 837             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
 838             'playlist_mincount': 5,
 839             'info_dict': {
 840                 'id': 'aanslagen-kopenhagen',
 841                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
 842             }
 843         },
 844         # Zapiks embed
 845         {
 846             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
 847             'info_dict': {
 848                 'id': '118046',
 849                 'ext': 'mp4',
 850                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
 851             }
 852         },
 853         # Kaltura embed
 854         {
 855             'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
 856             'info_dict': {
 857                 'id': '1_eergr3h1',
 858                 'ext': 'mp4',
 859                 'upload_date': '20150226',
 860                 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
 861                 'timestamp': int,
 862                 'title': 'John Carlson Postgame 2/25/15',
 863             },
 864         },
 865         # Kaltura embed (different embed code)
 866         {
 867             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
 868             'info_dict': {
 869                 'id': '1_a52wc67y',
 870                 'ext': 'flv',
 871                 'upload_date': '20150127',
 872                 'uploader_id': 'PremierMedia',
 873                 'timestamp': int,
 874                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
 875             },
 876         },
 877         # Kaltura embed protected with referrer
 878         {
 879             'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
 880             'info_dict': {
 881                 'id': '1_g4fbemnq',
 882                 'ext': 'mp4',
 883                 'title': 'Violetta - Achter De Schermen - Ruggero',
 884                 'description': 'Achter de schermen met Ruggero',
 885                 'timestamp': 1435133761,
 886                 'upload_date': '20150624',
 887                 'uploader_id': 'echojecka',
 888             },
 889         },
 890         # Eagle.Platform embed (generic URL)
 891         {
 892             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
 893             'info_dict': {
 894                 'id': '227304',
 895                 'ext': 'mp4',
 896                 'title': 'Навальный вышел на свободу',
 897                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
 898                 'thumbnail': 're:^https?://.*\.jpg$',
 899                 'duration': 87,
 900                 'view_count': int,
 901                 'age_limit': 0,
 902             },
 903         },
 904         # ClipYou (Eagle.Platform) embed (custom URL)
 905         {
 906             'url': 'http://muz-tv.ru/play/7129/',
 907             'info_dict': {
 908                 'id': '12820',
 909                 'ext': 'mp4',
 910                 'title': "'O Sole Mio",
 911                 'thumbnail': 're:^https?://.*\.jpg$',
 912                 'duration': 216,
 913                 'view_count': int,
 914             },
 915         },
 916         # Pladform embed
 917         {
 918             'url': 'http://muz-tv.ru/kinozal/view/7400/',
 919             'info_dict': {
 920                 'id': '100183293',
 921                 'ext': 'mp4',
 922                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
 923                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
 924                 'thumbnail': 're:^https?://.*\.jpg$',
 925                 'duration': 694,
 926                 'age_limit': 0,
 927             },
 928         },
 929         # Playwire embed
 930         {
 931             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
 932             'info_dict': {
 933                 'id': '3519514',
 934                 'ext': 'mp4',
 935                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
 936                 'thumbnail': 're:^https?://.*\.png$',
 937                 'duration': 45.115,
 938             },
 939         },
 940         # 5min embed
 941         {
 942             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
 943             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
 944             'info_dict': {
 945                 'id': '518726732',
 946                 'ext': 'mp4',
 947                 'title': 'Facebook Creates "On This Day" | Crunch Report',
 948             },
 949         },
 950         # SVT embed
 951         {
 952             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
 953             'info_dict': {
 954                 'id': '2900353',
 955                 'ext': 'flv',
 956                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
 957                 'duration': 27,
 958                 'age_limit': 0,
 959             },
 960         },
 961         # Crooks and Liars embed
 962         {
 963             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
 964             'info_dict': {
 965                 'id': '8RUoRhRi',
 966                 'ext': 'mp4',
 967                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
 968                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
 969                 'timestamp': 1428207000,
 970                 'upload_date': '20150405',
 971                 'uploader': 'Heather',
 972             },
 973         },
 974         # Crooks and Liars external embed
 975         {
 976             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
 977             'info_dict': {
 978                 'id': 'MTE3MjUtMzQ2MzA',
 979                 'ext': 'mp4',
 980                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
 981                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
 982                 'timestamp': 1265032391,
 983                 'upload_date': '20100201',
 984                 'uploader': 'Heather',
 985             },
 986         },
 987         # NBC Sports vplayer embed
 988         {
 989             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
 990             'info_dict': {
 991                 'id': 'ln7x1qSThw4k',
 992                 'ext': 'flv',
 993                 'title': "PFT Live: New leader in the 'new-look' defense",
 994                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
 995             },
 996         },
 997         # UDN embed
 998         {
 999             'url': 'http://www.udn.com/news/story/7314/822787',
1000             'md5': 'fd2060e988c326991037b9aff9df21a6',
1001             'info_dict': {
1002                 'id': '300346',
1003                 'ext': 'mp4',
1004                 'title': '中一中男師變性 全校師生力挺',
1005                 'thumbnail': 're:^https?://.*\.jpg$',
1006             }
1007         },
1008         # Ooyala embed
1009         {
1010             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1011             'info_dict': {
1012                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1013                 'ext': 'mp4',
1014                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1015                 'title': 'This is what separates the Excel masters from the wannabes',
1016                 'duration': 191.933,
1017             },
1018             'params': {
1019                 # m3u8 downloads
1020                 'skip_download': True,
1021             }
1022         },
1023         # Contains a SMIL manifest
1024         {
1025             'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
1026             'info_dict': {
1027                 'id': 'file',
1028                 'ext': 'flv',
1029                 'title': '+ Football: Lottery Champions League Europe',
1030                 'uploader': 'www.telewebion.com',
1031             },
1032             'params': {
1033                 # rtmpe downloads
1034                 'skip_download': True,
1035             }
1036         },
1037         # Brightcove URL in single quotes
1038         {
1039             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1040             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1041             'info_dict': {
1042                 'id': '4255764656001',
1043                 'ext': 'mp4',
1044                 'title': 'SN Presents: Russell Martin, World Citizen',
1045                 '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.',
1046                 'uploader': 'Rogers Sportsnet',
1047             },
1048         },
1049         # Dailymotion Cloud video
1050         {
1051             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1052             'md5': '49444254273501a64675a7e68c502681',
1053             'info_dict': {
1054                 'id': '5585de919473990de4bee11b',
1055                 'ext': 'mp4',
1056                 'title': 'Le débat',
1057                 'thumbnail': 're:^https?://.*\.jpe?g$',
1058             }
1059         },
1060         # OnionStudios embed
1061         {
1062             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1063             'info_dict': {
1064                 'id': '2855',
1065                 'ext': 'mp4',
1066                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1067                 'thumbnail': 're:^https?://.*\.jpe?g$',
1068                 'uploader': 'ClickHole',
1069                 'uploader_id': 'clickhole',
1070             }
1071         },
1072         # SnagFilms embed
1073         {
1074             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1075             'info_dict': {
1076                 'id': '74849a00-85a9-11e1-9660-123139220831',
1077                 'ext': 'mp4',
1078                 'title': '#whilewewatch',
1079             }
1080         },
1081         # AdobeTVVideo embed
1082         {
1083             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1084             'md5': '43662b577c018ad707a63766462b1e87',
1085             'info_dict': {
1086                 'id': '2456',
1087                 'ext': 'mp4',
1088                 'title': 'New experience with Acrobat DC',
1089                 'description': 'New experience with Acrobat DC',
1090                 'duration': 248.667,
1091             },
1092         },
1093         # ScreenwaveMedia embed
1094         {
1095             'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1096             'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1097             'info_dict': {
1098                 'id': 'cinemasnob-55d26273809dd',
1099                 'ext': 'mp4',
1100                 'title': 'cinemasnob',
1101             },
1102         },
1103         # BrightcoveInPageEmbed embed
1104         {
1105             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1106             'info_dict': {
1107                 'id': '4238694884001',
1108                 'ext': 'flv',
1109                 'title': 'Tabletop: Dread, Last Thoughts',
1110                 'description': 'Tabletop: Dread, Last Thoughts',
1111                 'duration': 51690,
1112             },
1113         },
1114         # JWPlayer with M3U8
1115         {
1116             'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1117             'info_dict': {
1118                 'id': 'playlist',
1119                 'ext': 'mp4',
1120                 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1121                 'uploader': 'ren.tv',
1122             },
1123             'params': {
1124                 # m3u8 downloads
1125                 'skip_download': True,
1126             }
1127         },
1128         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1129         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1130         {
1131             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1132             'info_dict': {
1133                 'id': '4785848093001',
1134                 'ext': 'mp4',
1135                 'title': 'The Cardinal Pell Interview',
1136                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1137                 'uploader': 'GlobeCast Australia - GlobeStream',
1138             },
1139             'params': {
1140                 # m3u8 downloads
1141                 'skip_download': True,
1142             },
1143         },
1144     ]
1145
1146     def report_following_redirect(self, new_url):
1147         """Report information extraction."""
1148         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1149
1150     def _extract_rss(self, url, video_id, doc):
1151         playlist_title = doc.find('./channel/title').text
1152         playlist_desc_el = doc.find('./channel/description')
1153         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1154
1155         entries = []
1156         for it in doc.findall('./channel/item'):
1157             next_url = xpath_text(it, 'link', fatal=False)
1158             if not next_url:
1159                 enclosure_nodes = it.findall('./enclosure')
1160                 for e in enclosure_nodes:
1161                     next_url = e.attrib.get('url')
1162                     if next_url:
1163                         break
1164
1165             if not next_url:
1166                 continue
1167
1168             entries.append({
1169                 '_type': 'url',
1170                 'url': next_url,
1171                 'title': it.find('title').text,
1172             })
1173
1174         return {
1175             '_type': 'playlist',
1176             'id': url,
1177             'title': playlist_title,
1178             'description': playlist_desc,
1179             'entries': entries,
1180         }
1181
1182     def _extract_camtasia(self, url, video_id, webpage):
1183         """ Returns None if no camtasia video can be found. """
1184
1185         camtasia_cfg = self._search_regex(
1186             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1187             webpage, 'camtasia configuration file', default=None)
1188         if camtasia_cfg is None:
1189             return None
1190
1191         title = self._html_search_meta('DC.title', webpage, fatal=True)
1192
1193         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1194         camtasia_cfg = self._download_xml(
1195             camtasia_url, video_id,
1196             note='Downloading camtasia configuration',
1197             errnote='Failed to download camtasia configuration')
1198         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1199
1200         entries = []
1201         for n in fileset_node.getchildren():
1202             url_n = n.find('./uri')
1203             if url_n is None:
1204                 continue
1205
1206             entries.append({
1207                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1208                 'title': '%s - %s' % (title, n.tag),
1209                 'url': compat_urlparse.urljoin(url, url_n.text),
1210                 'duration': float_or_none(n.find('./duration').text),
1211             })
1212
1213         return {
1214             '_type': 'playlist',
1215             'entries': entries,
1216             'title': title,
1217         }
1218
1219     def _real_extract(self, url):
1220         if url.startswith('//'):
1221             return {
1222                 '_type': 'url',
1223                 'url': self.http_scheme() + url,
1224             }
1225
1226         parsed_url = compat_urlparse.urlparse(url)
1227         if not parsed_url.scheme:
1228             default_search = self._downloader.params.get('default_search')
1229             if default_search is None:
1230                 default_search = 'fixup_error'
1231
1232             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1233                 if '/' in url:
1234                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1235                     return self.url_result('http://' + url)
1236                 elif default_search != 'fixup_error':
1237                     if default_search == 'auto_warning':
1238                         if re.match(r'^(?:url|URL)$', url):
1239                             raise ExtractorError(
1240                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1241                                 expected=True)
1242                         else:
1243                             self._downloader.report_warning(
1244                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1245                     return self.url_result('ytsearch:' + url)
1246
1247             if default_search in ('error', 'fixup_error'):
1248                 raise ExtractorError(
1249                     '%r is not a valid URL. '
1250                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1251                     % (url, url), expected=True)
1252             else:
1253                 if ':' not in default_search:
1254                     default_search += ':'
1255                 return self.url_result(default_search + url)
1256
1257         url, smuggled_data = unsmuggle_url(url)
1258         force_videoid = None
1259         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1260         if smuggled_data and 'force_videoid' in smuggled_data:
1261             force_videoid = smuggled_data['force_videoid']
1262             video_id = force_videoid
1263         else:
1264             video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1265
1266         self.to_screen('%s: Requesting header' % video_id)
1267
1268         head_req = HEADRequest(url)
1269         head_response = self._request_webpage(
1270             head_req, video_id,
1271             note=False, errnote='Could not send HEAD request to %s' % url,
1272             fatal=False)
1273
1274         if head_response is not False:
1275             # Check for redirect
1276             new_url = head_response.geturl()
1277             if url != new_url:
1278                 self.report_following_redirect(new_url)
1279                 if force_videoid:
1280                     new_url = smuggle_url(
1281                         new_url, {'force_videoid': force_videoid})
1282                 return self.url_result(new_url)
1283
1284         full_response = None
1285         if head_response is False:
1286             request = sanitized_Request(url)
1287             request.add_header('Accept-Encoding', '*')
1288             full_response = self._request_webpage(request, video_id)
1289             head_response = full_response
1290
1291         info_dict = {
1292             'id': video_id,
1293             'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1294             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1295         }
1296
1297         # Check for direct link to a video
1298         content_type = head_response.headers.get('Content-Type', '').lower()
1299         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1300         if m:
1301             format_id = m.group('format_id')
1302             if format_id.endswith('mpegurl'):
1303                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1304             elif format_id == 'f4m':
1305                 formats = self._extract_f4m_formats(url, video_id)
1306             else:
1307                 formats = [{
1308                     'format_id': m.group('format_id'),
1309                     'url': url,
1310                     'vcodec': 'none' if m.group('type') == 'audio' else None
1311                 }]
1312                 info_dict['direct'] = True
1313             self._sort_formats(formats)
1314             info_dict['formats'] = formats
1315             return info_dict
1316
1317         if not self._downloader.params.get('test', False) and not is_intentional:
1318             force = self._downloader.params.get('force_generic_extractor', False)
1319             self._downloader.report_warning(
1320                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1321
1322         if not full_response:
1323             request = sanitized_Request(url)
1324             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1325             # making it impossible to download only chunk of the file (yet we need only 512kB to
1326             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1327             # that will always result in downloading the whole file that is not desirable.
1328             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1329             # to accept raw bytes and being able to download only a chunk.
1330             # It may probably better to solve this by checking Content-Type for application/octet-stream
1331             # after HEAD request finishes, but not sure if we can rely on this.
1332             request.add_header('Accept-Encoding', '*')
1333             full_response = self._request_webpage(request, video_id)
1334
1335         first_bytes = full_response.read(512)
1336
1337         # Is it an M3U playlist?
1338         if first_bytes.startswith(b'#EXTM3U'):
1339             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1340             self._sort_formats(info_dict['formats'])
1341             return info_dict
1342
1343         # Maybe it's a direct link to a video?
1344         # Be careful not to download the whole thing!
1345         if not is_html(first_bytes):
1346             self._downloader.report_warning(
1347                 'URL could be a direct video link, returning it as such.')
1348             info_dict.update({
1349                 'direct': True,
1350                 'url': url,
1351             })
1352             return info_dict
1353
1354         webpage = self._webpage_read_content(
1355             full_response, url, video_id, prefix=first_bytes)
1356
1357         self.report_extraction(video_id)
1358
1359         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1360         try:
1361             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1362             if doc.tag == 'rss':
1363                 return self._extract_rss(url, video_id, doc)
1364             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1365                 smil = self._parse_smil(doc, url, video_id)
1366                 self._sort_formats(smil['formats'])
1367                 return smil
1368             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1369                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1370             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1371                 info_dict['formats'] = self._parse_mpd_formats(
1372                     doc, video_id, mpd_base_url=url.rpartition('/')[0])
1373                 self._sort_formats(info_dict['formats'])
1374                 return info_dict
1375             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1376                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1377                 self._sort_formats(info_dict['formats'])
1378                 return info_dict
1379         except compat_xml_parse_error:
1380             pass
1381
1382         # Is it a Camtasia project?
1383         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1384         if camtasia_res is not None:
1385             return camtasia_res
1386
1387         # Sometimes embedded video player is hidden behind percent encoding
1388         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1389         # Unescaping the whole page allows to handle those cases in a generic way
1390         webpage = compat_urllib_parse_unquote(webpage)
1391
1392         # it's tempting to parse this further, but you would
1393         # have to take into account all the variations like
1394         #   Video Title - Site Name
1395         #   Site Name | Video Title
1396         #   Video Title - Tagline | Site Name
1397         # and so on and so forth; it's just not practical
1398         video_title = self._html_search_regex(
1399             r'(?s)<title>(.*?)</title>', webpage, 'video title',
1400             default='video')
1401
1402         # Try to detect age limit automatically
1403         age_limit = self._rta_search(webpage)
1404         # And then there are the jokers who advertise that they use RTA,
1405         # but actually don't.
1406         AGE_LIMIT_MARKERS = [
1407             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1408         ]
1409         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1410             age_limit = 18
1411
1412         # video uploader is domain name
1413         video_uploader = self._search_regex(
1414             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1415
1416         # Helper method
1417         def _playlist_from_matches(matches, getter=None, ie=None):
1418             urlrs = orderedSet(
1419                 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1420                 for m in matches)
1421             return self.playlist_result(
1422                 urlrs, playlist_id=video_id, playlist_title=video_title)
1423
1424         # Look for Brightcove Legacy Studio embeds
1425         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1426         if bc_urls:
1427             self.to_screen('Brightcove video detected.')
1428             entries = [{
1429                 '_type': 'url',
1430                 'url': smuggle_url(bc_url, {'Referer': url}),
1431                 'ie_key': 'BrightcoveLegacy'
1432             } for bc_url in bc_urls]
1433
1434             return {
1435                 '_type': 'playlist',
1436                 'title': video_title,
1437                 'id': video_id,
1438                 'entries': entries,
1439             }
1440
1441         # Look for Brightcove New Studio embeds
1442         bc_urls = BrightcoveNewIE._extract_urls(webpage)
1443         if bc_urls:
1444             return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1445
1446         # Look for embedded rtl.nl player
1447         matches = re.findall(
1448             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1449             webpage)
1450         if matches:
1451             return _playlist_from_matches(matches, ie='RtlNl')
1452
1453         vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1454         if vimeo_url is not None:
1455             return self.url_result(vimeo_url)
1456
1457         vid_me_embed_url = self._search_regex(
1458             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1459             webpage, 'vid.me embed', default=None)
1460         if vid_me_embed_url is not None:
1461             return self.url_result(vid_me_embed_url, 'Vidme')
1462
1463         # Look for embedded YouTube player
1464         matches = re.findall(r'''(?x)
1465             (?:
1466                 <iframe[^>]+?src=|
1467                 data-video-url=|
1468                 <embed[^>]+?src=|
1469                 embedSWF\(?:\s*|
1470                 new\s+SWFObject\(
1471             )
1472             (["\'])
1473                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1474                 (?:embed|v|p)/.+?)
1475             \1''', webpage)
1476         if matches:
1477             return _playlist_from_matches(
1478                 matches, lambda m: unescapeHTML(m[1]))
1479
1480         # Look for lazyYT YouTube embed
1481         matches = re.findall(
1482             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1483         if matches:
1484             return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1485
1486         # Look for embedded Dailymotion player
1487         matches = re.findall(
1488             r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1489         if matches:
1490             return _playlist_from_matches(
1491                 matches, lambda m: unescapeHTML(m[1]))
1492
1493         # Look for embedded Dailymotion playlist player (#3822)
1494         m = re.search(
1495             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1496         if m:
1497             playlists = re.findall(
1498                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1499             if playlists:
1500                 return _playlist_from_matches(
1501                     playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1502
1503         # Look for embedded Wistia player
1504         match = re.search(
1505             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1506         if match:
1507             embed_url = self._proto_relative_url(
1508                 unescapeHTML(match.group('url')))
1509             return {
1510                 '_type': 'url_transparent',
1511                 'url': embed_url,
1512                 'ie_key': 'Wistia',
1513                 'uploader': video_uploader,
1514                 'title': video_title,
1515                 'id': video_id,
1516             }
1517
1518         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1519         if match:
1520             return {
1521                 '_type': 'url_transparent',
1522                 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1523                 'ie_key': 'Wistia',
1524                 'uploader': video_uploader,
1525                 'title': video_title,
1526                 'id': match.group('id')
1527             }
1528
1529         # Look for SVT player
1530         svt_url = SVTIE._extract_url(webpage)
1531         if svt_url:
1532             return self.url_result(svt_url, 'SVT')
1533
1534         # Look for embedded condenast player
1535         matches = re.findall(
1536             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1537             webpage)
1538         if matches:
1539             return {
1540                 '_type': 'playlist',
1541                 'entries': [{
1542                     '_type': 'url',
1543                     'ie_key': 'CondeNast',
1544                     'url': ma,
1545                 } for ma in matches],
1546                 'title': video_title,
1547                 'id': video_id,
1548             }
1549
1550         # Look for Bandcamp pages with custom domain
1551         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1552         if mobj is not None:
1553             burl = unescapeHTML(mobj.group(1))
1554             # Don't set the extractor because it can be a track url or an album
1555             return self.url_result(burl)
1556
1557         # Look for embedded Vevo player
1558         mobj = re.search(
1559             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1560         if mobj is not None:
1561             return self.url_result(mobj.group('url'))
1562
1563         # Look for embedded Viddler player
1564         mobj = re.search(
1565             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1566             webpage)
1567         if mobj is not None:
1568             return self.url_result(mobj.group('url'))
1569
1570         # Look for NYTimes player
1571         mobj = re.search(
1572             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1573             webpage)
1574         if mobj is not None:
1575             return self.url_result(mobj.group('url'))
1576
1577         # Look for Libsyn player
1578         mobj = re.search(
1579             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1580         if mobj is not None:
1581             return self.url_result(mobj.group('url'))
1582
1583         # Look for Ooyala videos
1584         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1585                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1586                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1587                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1588         if mobj is not None:
1589             return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1590
1591         # Look for multiple Ooyala embeds on SBN network websites
1592         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1593         if mobj is not None:
1594             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1595             if embeds:
1596                 return _playlist_from_matches(
1597                     embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1598
1599         # Look for Aparat videos
1600         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1601         if mobj is not None:
1602             return self.url_result(mobj.group(1), 'Aparat')
1603
1604         # Look for MPORA videos
1605         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1606         if mobj is not None:
1607             return self.url_result(mobj.group(1), 'Mpora')
1608
1609         # Look for embedded NovaMov-based player
1610         mobj = re.search(
1611             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1612                     (?P<url>http://(?:(?:embed|www)\.)?
1613                         (?:novamov\.com|
1614                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
1615                            videoweed\.(?:es|com)|
1616                            movshare\.(?:net|sx|ag)|
1617                            divxstage\.(?:eu|net|ch|co|at|ag))
1618                         /embed\.php.+?)\1''', webpage)
1619         if mobj is not None:
1620             return self.url_result(mobj.group('url'))
1621
1622         # Look for embedded Facebook player
1623         mobj = re.search(
1624             r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1625         if mobj is not None:
1626             return self.url_result(mobj.group('url'), 'Facebook')
1627
1628         # Look for embedded VK player
1629         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1630         if mobj is not None:
1631             return self.url_result(mobj.group('url'), 'VK')
1632
1633         # Look for embedded Odnoklassniki player
1634         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1635         if mobj is not None:
1636             return self.url_result(mobj.group('url'), 'Odnoklassniki')
1637
1638         # Look for embedded ivi player
1639         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1640         if mobj is not None:
1641             return self.url_result(mobj.group('url'), 'Ivi')
1642
1643         # Look for embedded Huffington Post player
1644         mobj = re.search(
1645             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1646         if mobj is not None:
1647             return self.url_result(mobj.group('url'), 'HuffPost')
1648
1649         # Look for embed.ly
1650         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1651         if mobj is not None:
1652             return self.url_result(mobj.group('url'))
1653         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1654         if mobj is not None:
1655             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1656
1657         # Look for funnyordie embed
1658         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1659         if matches:
1660             return _playlist_from_matches(
1661                 matches, getter=unescapeHTML, ie='FunnyOrDie')
1662
1663         # Look for BBC iPlayer embed
1664         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1665         if matches:
1666             return _playlist_from_matches(matches, ie='BBCCoUk')
1667
1668         # Look for embedded RUTV player
1669         rutv_url = RUTVIE._extract_url(webpage)
1670         if rutv_url:
1671             return self.url_result(rutv_url, 'RUTV')
1672
1673         # Look for embedded TVC player
1674         tvc_url = TVCIE._extract_url(webpage)
1675         if tvc_url:
1676             return self.url_result(tvc_url, 'TVC')
1677
1678         # Look for embedded SportBox player
1679         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1680         if sportbox_urls:
1681             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1682
1683         # Look for embedded PornHub player
1684         pornhub_url = PornHubIE._extract_url(webpage)
1685         if pornhub_url:
1686             return self.url_result(pornhub_url, 'PornHub')
1687
1688         # Look for embedded XHamster player
1689         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1690         if xhamster_urls:
1691             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1692
1693         # Look for embedded TNAFlixNetwork player
1694         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1695         if tnaflix_urls:
1696             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1697
1698         # Look for embedded Tvigle player
1699         mobj = re.search(
1700             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1701         if mobj is not None:
1702             return self.url_result(mobj.group('url'), 'Tvigle')
1703
1704         # Look for embedded TED player
1705         mobj = re.search(
1706             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1707         if mobj is not None:
1708             return self.url_result(mobj.group('url'), 'TED')
1709
1710         # Look for embedded Ustream videos
1711         mobj = re.search(
1712             r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1713         if mobj is not None:
1714             return self.url_result(mobj.group('url'), 'Ustream')
1715
1716         # Look for embedded arte.tv player
1717         mobj = re.search(
1718             r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1719             webpage)
1720         if mobj is not None:
1721             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1722
1723         # Look for embedded francetv player
1724         mobj = re.search(
1725             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1726             webpage)
1727         if mobj is not None:
1728             return self.url_result(mobj.group('url'))
1729
1730         # Look for embedded smotri.com player
1731         smotri_url = SmotriIE._extract_url(webpage)
1732         if smotri_url:
1733             return self.url_result(smotri_url, 'Smotri')
1734
1735         # Look for embedded Myvi.ru player
1736         myvi_url = MyviIE._extract_url(webpage)
1737         if myvi_url:
1738             return self.url_result(myvi_url)
1739
1740         # Look for embedded soundcloud player
1741         mobj = re.search(
1742             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1743             webpage)
1744         if mobj is not None:
1745             url = unescapeHTML(mobj.group('url'))
1746             return self.url_result(url)
1747
1748         # Look for embedded vulture.com player
1749         mobj = re.search(
1750             r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1751             webpage)
1752         if mobj is not None:
1753             url = unescapeHTML(mobj.group('url'))
1754             return self.url_result(url, ie='Vulture')
1755
1756         # Look for embedded mtvservices player
1757         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1758         if mtvservices_url:
1759             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1760
1761         # Look for embedded yahoo player
1762         mobj = re.search(
1763             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1764             webpage)
1765         if mobj is not None:
1766             return self.url_result(mobj.group('url'), 'Yahoo')
1767
1768         # Look for embedded sbs.com.au player
1769         mobj = re.search(
1770             r'''(?x)
1771             (?:
1772                 <meta\s+property="og:video"\s+content=|
1773                 <iframe[^>]+?src=
1774             )
1775             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1776             webpage)
1777         if mobj is not None:
1778             return self.url_result(mobj.group('url'), 'SBS')
1779
1780         # Look for embedded Cinchcast player
1781         mobj = re.search(
1782             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1783             webpage)
1784         if mobj is not None:
1785             return self.url_result(mobj.group('url'), 'Cinchcast')
1786
1787         mobj = re.search(
1788             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1789             webpage)
1790         if not mobj:
1791             mobj = re.search(
1792                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1793                 webpage)
1794         if mobj is not None:
1795             return self.url_result(mobj.group('url'), 'MLB')
1796
1797         mobj = re.search(
1798             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1799             webpage)
1800         if mobj is not None:
1801             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1802
1803         mobj = re.search(
1804             r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1805             webpage)
1806         if mobj is not None:
1807             return self.url_result(mobj.group('url'), 'Livestream')
1808
1809         # Look for Zapiks embed
1810         mobj = re.search(
1811             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1812         if mobj is not None:
1813             return self.url_result(mobj.group('url'), 'Zapiks')
1814
1815         # Look for Kaltura embeds
1816         mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1817                 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1818         if mobj is not None:
1819             return self.url_result(smuggle_url(
1820                 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1821                 {'source_url': url}), 'Kaltura')
1822
1823         # Look for Eagle.Platform embeds
1824         mobj = re.search(
1825             r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1826         if mobj is not None:
1827             return self.url_result(mobj.group('url'), 'EaglePlatform')
1828
1829         # Look for ClipYou (uses Eagle.Platform) embeds
1830         mobj = re.search(
1831             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1832         if mobj is not None:
1833             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1834
1835         # Look for Pladform embeds
1836         pladform_url = PladformIE._extract_url(webpage)
1837         if pladform_url:
1838             return self.url_result(pladform_url)
1839
1840         # Look for Videomore embeds
1841         videomore_url = VideomoreIE._extract_url(webpage)
1842         if videomore_url:
1843             return self.url_result(videomore_url)
1844
1845         # Look for Playwire embeds
1846         mobj = re.search(
1847             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1848         if mobj is not None:
1849             return self.url_result(mobj.group('url'))
1850
1851         # Look for 5min embeds
1852         mobj = re.search(
1853             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1854         if mobj is not None:
1855             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1856
1857         # Look for Crooks and Liars embeds
1858         mobj = re.search(
1859             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1860         if mobj is not None:
1861             return self.url_result(mobj.group('url'))
1862
1863         # Look for NBC Sports VPlayer embeds
1864         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1865         if nbc_sports_url:
1866             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1867
1868         # Look for Google Drive embeds
1869         google_drive_url = GoogleDriveIE._extract_url(webpage)
1870         if google_drive_url:
1871             return self.url_result(google_drive_url, 'GoogleDrive')
1872
1873         # Look for UDN embeds
1874         mobj = re.search(
1875             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1876         if mobj is not None:
1877             return self.url_result(
1878                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1879
1880         # Look for Senate ISVP iframe
1881         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1882         if senate_isvp_url:
1883             return self.url_result(senate_isvp_url, 'SenateISVP')
1884
1885         # Look for Dailymotion Cloud videos
1886         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1887         if dmcloud_url:
1888             return self.url_result(dmcloud_url, 'DailymotionCloud')
1889
1890         # Look for OnionStudios embeds
1891         onionstudios_url = OnionStudiosIE._extract_url(webpage)
1892         if onionstudios_url:
1893             return self.url_result(onionstudios_url)
1894
1895         # Look for SnagFilms embeds
1896         snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1897         if snagfilms_url:
1898             return self.url_result(snagfilms_url)
1899
1900         # Look for JWPlatform embeds
1901         jwplatform_url = JWPlatformIE._extract_url(webpage)
1902         if jwplatform_url:
1903             return self.url_result(jwplatform_url, 'JWPlatform')
1904
1905         # Look for ScreenwaveMedia embeds
1906         mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1907         if mobj is not None:
1908             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1909
1910         # Look for Digiteka embeds
1911         digiteka_url = DigitekaIE._extract_url(webpage)
1912         if digiteka_url:
1913             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1914
1915         # Look for Limelight embeds
1916         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1917         if mobj:
1918             lm = {
1919                 'Media': 'media',
1920                 'Channel': 'channel',
1921                 'ChannelList': 'channel_list',
1922             }
1923             return self.url_result('limelight:%s:%s' % (
1924                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1925
1926         # Look for AdobeTVVideo embeds
1927         mobj = re.search(
1928             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1929             webpage)
1930         if mobj is not None:
1931             return self.url_result(
1932                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1933                 'AdobeTVVideo')
1934
1935         # Look for Vine embeds
1936         mobj = re.search(
1937             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1938             webpage)
1939         if mobj is not None:
1940             return self.url_result(
1941                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1942
1943         # Look for Instagram embeds
1944         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
1945         if instagram_embed_url is not None:
1946             return self.url_result(instagram_embed_url, InstagramIE.ie_key())
1947
1948         def check_video(vurl):
1949             if YoutubeIE.suitable(vurl):
1950                 return True
1951             vpath = compat_urlparse.urlparse(vurl).path
1952             vext = determine_ext(vpath)
1953             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1954
1955         def filter_video(urls):
1956             return list(filter(check_video, urls))
1957
1958         # Start with something easy: JW Player in SWFObject
1959         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1960         if not found:
1961             # Look for gorilla-vid style embedding
1962             found = filter_video(re.findall(r'''(?sx)
1963                 (?:
1964                     jw_plugins|
1965                     JWPlayerOptions|
1966                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1967                 )
1968                 .*?
1969                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1970         if not found:
1971             # Broaden the search a little bit
1972             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1973         if not found:
1974             # Broaden the findall a little bit: JWPlayer JS loader
1975             found = filter_video(re.findall(
1976                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1977         if not found:
1978             # Flow player
1979             found = filter_video(re.findall(r'''(?xs)
1980                 flowplayer\("[^"]+",\s*
1981                     \{[^}]+?\}\s*,
1982                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1983                         ["']?url["']?\s*:\s*["']([^"']+)["']
1984             ''', webpage))
1985         if not found:
1986             # Cinerama player
1987             found = re.findall(
1988                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1989         if not found:
1990             # Try to find twitter cards info
1991             found = filter_video(re.findall(
1992                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1993         if not found:
1994             # We look for Open Graph info:
1995             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1996             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1997             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1998             if m_video_type is not None:
1999                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2000         if not found:
2001             # HTML5 video
2002             found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2003         if not found:
2004             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2005             found = re.search(
2006                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2007                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2008                 webpage)
2009             if not found:
2010                 # Look also in Refresh HTTP header
2011                 refresh_header = head_response.headers.get('Refresh')
2012                 if refresh_header:
2013                     # In python 2 response HTTP headers are bytestrings
2014                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2015                         refresh_header = refresh_header.decode('iso-8859-1')
2016                     found = re.search(REDIRECT_REGEX, refresh_header)
2017             if found:
2018                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2019                 self.report_following_redirect(new_url)
2020                 return {
2021                     '_type': 'url',
2022                     'url': new_url,
2023                 }
2024         if not found:
2025             raise UnsupportedError(url)
2026
2027         entries = []
2028         for video_url in found:
2029             video_url = video_url.replace('\\/', '/')
2030             video_url = compat_urlparse.urljoin(url, video_url)
2031             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2032
2033             # Sometimes, jwplayer extraction will result in a YouTube URL
2034             if YoutubeIE.suitable(video_url):
2035                 entries.append(self.url_result(video_url, 'Youtube'))
2036                 continue
2037
2038             # here's a fun little line of code for you:
2039             video_id = os.path.splitext(video_id)[0]
2040
2041             entry_info_dict = {
2042                 'id': video_id,
2043                 'uploader': video_uploader,
2044                 'title': video_title,
2045                 'age_limit': age_limit,
2046             }
2047
2048             ext = determine_ext(video_url)
2049             if ext == 'smil':
2050                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2051             elif ext == 'xspf':
2052                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2053             elif ext == 'm3u8':
2054                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2055             elif ext == 'mpd':
2056                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2057             elif ext == 'f4m':
2058                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2059             else:
2060                 entry_info_dict['url'] = video_url
2061
2062             if entry_info_dict.get('formats'):
2063                 self._sort_formats(entry_info_dict['formats'])
2064
2065             entries.append(entry_info_dict)
2066
2067         if len(entries) == 1:
2068             return entries[0]
2069         else:
2070             for num, e in enumerate(entries, start=1):
2071                 # 'url' results don't have a title
2072                 if e.get('title') is not None:
2073                     e['title'] = '%s (%d)' % (e['title'], num)
2074             return {
2075                 '_type': 'playlist',
2076                 'entries': entries,
2077             }