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