_ 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 .viewlift import ViewLiftEmbedIE
  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 from .liveleak import LiveLeakIE
  64 from .threeqsdn import ThreeQSDNIE
  65 from .theplatform import ThePlatformIE
  66 from .vessel import VesselIE
  67 from .kaltura import KalturaIE
  68 from .eagleplatform import EaglePlatformIE
  69 from .facebook import FacebookIE
  70
  71
  72 class GenericIE(InfoExtractor):
  73     IE_DESC = 'Generic downloader that works on some sites'
  74     _VALID_URL = r'.*'
  75     IE_NAME = 'generic'
  76     _TESTS = [
  77         # Direct link to a video
  78         {
  79             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  80             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  81             'info_dict': {
  82                 'id': 'trailer',
  83                 'ext': 'mp4',
  84                 'title': 'trailer',
  85                 'upload_date': '20100513',
  86             }
  87         },
  88         # Direct link to media delivered compressed (until Accept-Encoding is *)
  89         {
  90             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  91             'md5': '128c42e68b13950268b648275386fc74',
  92             'info_dict': {
  93                 'id': 'FictionJunction-Parallel_Hearts',
  94                 'ext': 'flac',
  95                 'title': 'FictionJunction-Parallel_Hearts',
  96                 'upload_date': '20140522',
  97             },
  98             'expected_warnings': [
  99                 'URL could be a direct video link, returning it as such.'
 100             ]
 101         },
 102         # Direct download with broken HEAD
 103         {
 104             'url': 'http://ai-radio.org:8000/radio.opus',
 105             'info_dict': {
 106                 'id': 'radio',
 107                 'ext': 'opus',
 108                 'title': 'radio',
 109             },
 110             'params': {
 111                 'skip_download': True,  # infinite live stream
 112             },
 113             'expected_warnings': [
 114                 r'501.*Not Implemented',
 115                 r'400.*Bad Request',
 116             ],
 117         },
 118         # Direct link with incorrect MIME type
 119         {
 120             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 121             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 122             'info_dict': {
 123                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 124                 'id': '5_Lennart_Poettering_-_Systemd',
 125                 'ext': 'webm',
 126                 'title': '5_Lennart_Poettering_-_Systemd',
 127                 'upload_date': '20141120',
 128             },
 129             'expected_warnings': [
 130                 'URL could be a direct video link, returning it as such.'
 131             ]
 132         },
 133         # RSS feed
 134         {
 135             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 136             'info_dict': {
 137                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 138                 'title': 'Zero Punctuation',
 139                 'description': 're:.*groundbreaking video review series.*'
 140             },
 141             'playlist_mincount': 11,
 142         },
 143         # RSS feed with enclosure
 144         {
 145             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 146             'info_dict': {
 147                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 148                 'ext': 'm4v',
 149                 'upload_date': '20150228',
 150                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 151             }
 152         },
 153         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 154         {
 155             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 156             'info_dict': {
 157                 'id': 'smil',
 158                 'ext': 'mp4',
 159                 'title': 'Automatics, robotics and biocybernetics',
 160                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 161                 'upload_date': '20130627',
 162                 'formats': 'mincount:16',
 163                 'subtitles': 'mincount:1',
 164             },
 165             'params': {
 166                 'force_generic_extractor': True,
 167                 'skip_download': True,
 168             },
 169         },
 170         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 171         {
 172             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 173             'info_dict': {
 174                 'id': 'hds',
 175                 'ext': 'flv',
 176                 'title': 'hds',
 177                 'formats': 'mincount:1',
 178             },
 179             'params': {
 180                 'skip_download': True,
 181             },
 182         },
 183         # SMIL from https://www.restudy.dk/video/play/id/1637
 184         {
 185             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 186             'info_dict': {
 187                 'id': 'video_1637',
 188                 'ext': 'flv',
 189                 'title': 'video_1637',
 190                 'formats': 'mincount:3',
 191             },
 192             'params': {
 193                 'skip_download': True,
 194             },
 195         },
 196         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 197         {
 198             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 199             'info_dict': {
 200                 'id': 'smil-service',
 201                 'ext': 'flv',
 202                 'title': 'smil-service',
 203                 'formats': 'mincount:1',
 204             },
 205             'params': {
 206                 'skip_download': True,
 207             },
 208         },
 209         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 210         {
 211             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 212             'info_dict': {
 213                 'id': '4719370',
 214                 'ext': 'mp4',
 215                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 216                 'formats': 'mincount:3',
 217             },
 218             'params': {
 219                 'skip_download': True,
 220             },
 221         },
 222         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 223         {
 224             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 225             'info_dict': {
 226                 'id': 'mZlp2ctYIUEB',
 227                 'ext': 'mp4',
 228                 'title': 'Tikibad ontruimd wegens brand',
 229                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 230                 'thumbnail': 're:^https?://.*\.jpg$',
 231                 'duration': 33,
 232             },
 233             'params': {
 234                 'skip_download': True,
 235             },
 236         },
 237         # MPD from http://dash-mse-test.appspot.com/media.html
 238         {
 239             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 240             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 241             'info_dict': {
 242                 'id': 'car-20120827-manifest',
 243                 'ext': 'mp4',
 244                 'title': 'car-20120827-manifest',
 245                 'formats': 'mincount:9',
 246                 'upload_date': '20130904',
 247             },
 248             'params': {
 249                 'format': 'bestvideo',
 250             },
 251         },
 252         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 253         {
 254             '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',
 255             'info_dict': {
 256                 'id': 'content',
 257                 'ext': 'mp4',
 258                 'title': 'content',
 259                 'formats': 'mincount:8',
 260             },
 261             'params': {
 262                 # m3u8 downloads
 263                 'skip_download': True,
 264             }
 265         },
 266         # m3u8 served with Content-Type: text/plain
 267         {
 268             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 269             'info_dict': {
 270                 'id': 'index',
 271                 'ext': 'mp4',
 272                 'title': 'index',
 273                 'upload_date': '20140720',
 274                 'formats': 'mincount:11',
 275             },
 276             'params': {
 277                 # m3u8 downloads
 278                 'skip_download': True,
 279             }
 280         },
 281         # google redirect
 282         {
 283             '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',
 284             'info_dict': {
 285                 'id': 'cmQHVoWB5FY',
 286                 'ext': 'mp4',
 287                 'upload_date': '20130224',
 288                 'uploader_id': 'TheVerge',
 289                 'description': 're:^Chris Ziegler takes a look at the\.*',
 290                 'uploader': 'The Verge',
 291                 'title': 'First Firefox OS phones side-by-side',
 292             },
 293             'params': {
 294                 'skip_download': False,
 295             }
 296         },
 297         {
 298             # redirect in Refresh HTTP header
 299             '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',
 300             'info_dict': {
 301                 'id': 'pO8h3EaFRdo',
 302                 'ext': 'mp4',
 303                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 304                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 305                 'upload_date': '20150917',
 306                 'uploader_id': 'brtvofficial',
 307                 'uploader': 'Boiler Room',
 308             },
 309             'params': {
 310                 'skip_download': False,
 311             },
 312         },
 313         {
 314             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 315             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 316             'info_dict': {
 317                 'id': '13601338388002',
 318                 'ext': 'mp4',
 319                 'uploader': 'www.hodiho.fr',
 320                 'title': 'R\u00e9gis plante sa Jeep',
 321             }
 322         },
 323         # bandcamp page with custom domain
 324         {
 325             'add_ie': ['Bandcamp'],
 326             'url': 'http://bronyrock.com/track/the-pony-mash',
 327             'info_dict': {
 328                 'id': '3235767654',
 329                 'ext': 'mp3',
 330                 'title': 'The Pony Mash',
 331                 'uploader': 'M_Pallante',
 332             },
 333             'skip': 'There is a limit of 200 free downloads / month for the test song',
 334         },
 335         # embedded brightcove video
 336         # it also tests brightcove videos that need to set the 'Referer' in the
 337         # http requests
 338         {
 339             'add_ie': ['BrightcoveLegacy'],
 340             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 341             'info_dict': {
 342                 'id': '2765128793001',
 343                 'ext': 'mp4',
 344                 'title': 'Le cours de bourse : l’analyse technique',
 345                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 346                 'uploader': 'BFM BUSINESS',
 347             },
 348             'params': {
 349                 'skip_download': True,
 350             },
 351         },
 352         {
 353             # https://github.com/rg3/youtube-dl/issues/2253
 354             'url': 'http://bcove.me/i6nfkrc3',
 355             'md5': '0ba9446db037002366bab3b3eb30c88c',
 356             'info_dict': {
 357                 'id': '3101154703001',
 358                 'ext': 'mp4',
 359                 'title': 'Still no power',
 360                 'uploader': 'thestar.com',
 361                 '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.',
 362             },
 363             'add_ie': ['BrightcoveLegacy'],
 364         },
 365         {
 366             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 367             'md5': 'fb973ecf6e4a78a67453647444222983',
 368             'info_dict': {
 369                 'id': '3414141473001',
 370                 'ext': 'mp4',
 371                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 372                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 373                 'uploader': 'Championat',
 374             },
 375         },
 376         {
 377             # https://github.com/rg3/youtube-dl/issues/3541
 378             'add_ie': ['BrightcoveLegacy'],
 379             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 380             'info_dict': {
 381                 'id': '3866516442001',
 382                 'ext': 'mp4',
 383                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 384                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 385                 'uploader': 'SBS Broadcasting',
 386             },
 387             'skip': 'Restricted to Netherlands',
 388             'params': {
 389                 'skip_download': True,  # m3u8 download
 390             },
 391         },
 392         # ooyala video
 393         {
 394             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 395             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 396             'info_dict': {
 397                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 398                 'ext': 'mp4',
 399                 'title': '2cc213299525360.mov',  # that's what we get
 400                 'duration': 238.231,
 401             },
 402             'add_ie': ['Ooyala'],
 403         },
 404         {
 405             # ooyala video embedded with http://player.ooyala.com/iframe.js
 406             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 407             'info_dict': {
 408                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 409                 'ext': 'mp4',
 410                 'title': '"Steve Jobs: Man in the Machine" trailer',
 411                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 412                 'duration': 135.427,
 413             },
 414             'params': {
 415                 'skip_download': True,
 416             },
 417         },
 418         # embed.ly video
 419         {
 420             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 421             'info_dict': {
 422                 'id': '9ODmcdjQcHQ',
 423                 'ext': 'mp4',
 424                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 425                 'upload_date': '20140225',
 426                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 427                 'uploader': 'Tested',
 428                 'uploader_id': 'testedcom',
 429             },
 430             # No need to test YoutubeIE here
 431             'params': {
 432                 'skip_download': True,
 433             },
 434         },
 435         # funnyordie embed
 436         {
 437             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 438             'info_dict': {
 439                 'id': '18e820ec3f',
 440                 'ext': 'mp4',
 441                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 442                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 443             },
 444         },
 445         # RUTV embed
 446         {
 447             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 448             'info_dict': {
 449                 'id': '776940',
 450                 'ext': 'mp4',
 451                 'title': 'Охотское море стало целиком российским',
 452                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 453             },
 454             'params': {
 455                 # m3u8 download
 456                 'skip_download': True,
 457             },
 458         },
 459         # TVC embed
 460         {
 461             '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/',
 462             'info_dict': {
 463                 'id': '55304',
 464                 'ext': 'mp4',
 465                 'title': 'Дошкольное воспитание',
 466             },
 467         },
 468         # SportBox embed
 469         {
 470             'url': 'http://www.vestifinance.ru/articles/25753',
 471             'info_dict': {
 472                 'id': '25753',
 473                 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 474             },
 475             'playlist': [{
 476                 'info_dict': {
 477                     'id': '370908',
 478                     'title': 'Госзаказ. День 3',
 479                     'ext': 'mp4',
 480                 }
 481             }, {
 482                 'info_dict': {
 483                     'id': '370905',
 484                     'title': 'Госзаказ. День 2',
 485                     'ext': 'mp4',
 486                 }
 487             }, {
 488                 'info_dict': {
 489                     'id': '370902',
 490                     'title': 'Госзаказ. День 1',
 491                     'ext': 'mp4',
 492                 }
 493             }],
 494             'params': {
 495                 # m3u8 download
 496                 'skip_download': True,
 497             },
 498         },
 499         # Myvi.ru embed
 500         {
 501             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 502             'info_dict': {
 503                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 504                 'ext': 'mp4',
 505                 'title': 'Ужастики, русский трейлер (2015)',
 506                 'thumbnail': 're:^https?://.*\.jpg$',
 507                 'duration': 153,
 508             }
 509         },
 510         # XHamster embed
 511         {
 512             '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',
 513             'info_dict': {
 514                 'id': 'showthread',
 515                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 516             },
 517             'playlist_mincount': 7,
 518         },
 519         # Embedded TED video
 520         {
 521             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 522             'md5': '65fdff94098e4a607385a60c5177c638',
 523             'info_dict': {
 524                 'id': '1969',
 525                 'ext': 'mp4',
 526                 'title': 'Hidden miracles of the natural world',
 527                 'uploader': 'Louie Schwartzberg',
 528                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 529             }
 530         },
 531         # Embedded Ustream video
 532         {
 533             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
 534             'md5': '27b99cdb639c9b12a79bca876a073417',
 535             'info_dict': {
 536                 'id': '45734260',
 537                 'ext': 'flv',
 538                 'uploader': 'AU SPA:  The NSA and Privacy',
 539                 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
 540             }
 541         },
 542         # nowvideo embed hidden behind percent encoding
 543         {
 544             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 545             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 546             'info_dict': {
 547                 'id': '06e53103ca9aa',
 548                 'ext': 'flv',
 549                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 550                 'description': 'No description',
 551             },
 552         },
 553         # arte embed
 554         {
 555             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 556             'md5': '7653032cbb25bf6c80d80f217055fa43',
 557             'info_dict': {
 558                 'id': '048195-004_PLUS7-F',
 559                 'ext': 'flv',
 560                 'title': 'X:enius',
 561                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 562                 'upload_date': '20140320',
 563             },
 564             'params': {
 565                 'skip_download': 'Requires rtmpdump'
 566             }
 567         },
 568         # francetv embed
 569         {
 570             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 571             'info_dict': {
 572                 'id': 'EV_30231',
 573                 'ext': 'mp4',
 574                 'title': 'Alcaline, le concert avec Calogero',
 575                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 576                 'upload_date': '20150226',
 577                 'timestamp': 1424989860,
 578                 'duration': 5400,
 579             },
 580             'params': {
 581                 # m3u8 downloads
 582                 'skip_download': True,
 583             },
 584             'expected_warnings': [
 585                 'Forbidden'
 586             ]
 587         },
 588         # Condé Nast embed
 589         {
 590             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 591             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 592             'info_dict': {
 593                 'id': '53501be369702d3275860000',
 594                 'ext': 'mp4',
 595                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 596             }
 597         },
 598         # Dailymotion embed
 599         {
 600             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 601             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 602             'info_dict': {
 603                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 604                 'ext': 'mp4',
 605                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 606                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 607                 'uploader': 'Spi0n',
 608                 'uploader_id': 'xgditw',
 609                 'upload_date': '20140425',
 610                 'timestamp': 1398441542,
 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.vulture.com/2016/06/new-key-peele-sketches-released.html',
 634             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
 635             'info_dict': {
 636                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
 637                 'ext': 'mp4',
 638                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
 639                 'description': 'Two valets share their love for movie star Liam Neesons.',
 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://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 726             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 727             'info_dict': {
 728                 'id': '6e2wtrbdaf',
 729                 'ext': 'mov',
 730                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 731                 'description': 'a Paywall Videos video from Remilon',
 732                 'duration': 644.072,
 733                 'uploader': 'study.com',
 734                 'timestamp': 1459678540,
 735                 'upload_date': '20160403',
 736                 'filesize': 24687186,
 737             },
 738         },
 739         {
 740             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 741             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 742             'info_dict': {
 743                 'id': 'uxjb0lwrcz',
 744                 'ext': 'mp4',
 745                 'title': 'Conversation about Hexagonal Rails Part 1',
 746                 'description': 'a Martin Fowler video from ThoughtWorks',
 747                 'duration': 1715.0,
 748                 'uploader': 'thoughtworks.wistia.com',
 749                 'timestamp': 1401832161,
 750                 'upload_date': '20140603',
 751             },
 752         },
 753         # Wistia standard embed (async)
 754         {
 755             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 756             'info_dict': {
 757                 'id': '807fafadvk',
 758                 'ext': 'mp4',
 759                 'title': 'Drip Brennan Dunn Workshop',
 760                 'description': 'a JV Webinars video from getdrip-1',
 761                 'duration': 4986.95,
 762                 'timestamp': 1463607249,
 763                 'upload_date': '20160518',
 764             },
 765             'params': {
 766                 'skip_download': True,
 767             }
 768         },
 769         # Soundcloud embed
 770         {
 771             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 772             'info_dict': {
 773                 'id': '174391317',
 774                 'ext': 'mp3',
 775                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 776                 'uploader': 'Sophos Security',
 777                 'title': 'Chet Chat 171 - Oct 29, 2014',
 778                 'upload_date': '20141029',
 779             }
 780         },
 781         # Livestream embed
 782         {
 783             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 784             'info_dict': {
 785                 'id': '67864563',
 786                 'ext': 'flv',
 787                 'upload_date': '20141112',
 788                 'title': 'Rosetta #CometLanding webcast HL 10',
 789             }
 790         },
 791         # Another Livestream embed, without 'new.' in URL
 792         {
 793             'url': 'https://www.freespeech.org/',
 794             'info_dict': {
 795                 'id': '123537347',
 796                 'ext': 'mp4',
 797                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 798             },
 799             'params': {
 800                 # Live stream
 801                 'skip_download': True,
 802             },
 803         },
 804         # LazyYT
 805         {
 806             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
 807             'info_dict': {
 808                 'id': '1986',
 809                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
 810             },
 811             'playlist_mincount': 2,
 812         },
 813         # Cinchcast embed
 814         {
 815             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
 816             'info_dict': {
 817                 'id': '7141703',
 818                 'ext': 'mp3',
 819                 'upload_date': '20141126',
 820                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
 821             }
 822         },
 823         # Cinerama player
 824         {
 825             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
 826             'info_dict': {
 827                 'id': '730m_DandD_1901_512k',
 828                 'ext': 'mp4',
 829                 'uploader': 'www.abc.net.au',
 830                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
 831             }
 832         },
 833         # embedded viddler video
 834         {
 835             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
 836             'info_dict': {
 837                 'id': '4d03aad9',
 838                 'ext': 'mp4',
 839                 'uploader': 'deadspin',
 840                 'title': 'WALL-TO-GORTAT',
 841                 'timestamp': 1422285291,
 842                 'upload_date': '20150126',
 843             },
 844             'add_ie': ['Viddler'],
 845         },
 846         # Libsyn embed
 847         {
 848             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
 849             'info_dict': {
 850                 'id': '3377616',
 851                 'ext': 'mp3',
 852                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
 853                 'description': 'md5:601cb790edd05908957dae8aaa866465',
 854                 'upload_date': '20150220',
 855             },
 856         },
 857         # jwplayer YouTube
 858         {
 859             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
 860             'info_dict': {
 861                 'id': 'Mrj4DVp2zeA',
 862                 'ext': 'mp4',
 863                 'upload_date': '20150212',
 864                 'uploader': 'The National Archives UK',
 865                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
 866                 'uploader_id': 'NationalArchives08',
 867                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
 868             },
 869         },
 870         # rtl.nl embed
 871         {
 872             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
 873             'playlist_mincount': 5,
 874             'info_dict': {
 875                 'id': 'aanslagen-kopenhagen',
 876                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
 877             }
 878         },
 879         # Zapiks embed
 880         {
 881             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
 882             'info_dict': {
 883                 'id': '118046',
 884                 'ext': 'mp4',
 885                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
 886             }
 887         },
 888         # Kaltura embed (different embed code)
 889         {
 890             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
 891             'info_dict': {
 892                 'id': '1_a52wc67y',
 893                 'ext': 'flv',
 894                 'upload_date': '20150127',
 895                 'uploader_id': 'PremierMedia',
 896                 'timestamp': int,
 897                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
 898             },
 899         },
 900         # Kaltura embed protected with referrer
 901         {
 902             'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
 903             'info_dict': {
 904                 'id': '1_g4fbemnq',
 905                 'ext': 'mp4',
 906                 'title': 'Violetta - Achter De Schermen - Ruggero',
 907                 'description': 'Achter de schermen met Ruggero',
 908                 'timestamp': 1435133761,
 909                 'upload_date': '20150624',
 910                 'uploader_id': 'echojecka',
 911             },
 912         },
 913         # Kaltura embed with single quotes
 914         {
 915             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
 916             'info_dict': {
 917                 'id': '0_izeg5utt',
 918                 'ext': 'mp4',
 919                 'title': '35871',
 920                 'timestamp': 1355743100,
 921                 'upload_date': '20121217',
 922                 'uploader_id': 'batchUser',
 923             },
 924             'add_ie': ['Kaltura'],
 925         },
 926         {
 927             # Kaltura embedded via quoted entry_id
 928             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
 929             'info_dict': {
 930                 'id': '0_utuok90b',
 931                 'ext': 'mp4',
 932                 'title': '06_matthew_brender_raj_dutt',
 933                 'timestamp': 1466638791,
 934                 'upload_date': '20160622',
 935             },
 936             'add_ie': ['Kaltura'],
 937             'expected_warnings': [
 938                 'Could not send HEAD request'
 939             ],
 940             'params': {
 941                 'skip_download': True,
 942             }
 943         },
 944         # Eagle.Platform embed (generic URL)
 945         {
 946             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
 947             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 948             'info_dict': {
 949                 'id': '227304',
 950                 'ext': 'mp4',
 951                 'title': 'Навальный вышел на свободу',
 952                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
 953                 'thumbnail': 're:^https?://.*\.jpg$',
 954                 'duration': 87,
 955                 'view_count': int,
 956                 'age_limit': 0,
 957             },
 958         },
 959         # ClipYou (Eagle.Platform) embed (custom URL)
 960         {
 961             'url': 'http://muz-tv.ru/play/7129/',
 962             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 963             'info_dict': {
 964                 'id': '12820',
 965                 'ext': 'mp4',
 966                 'title': "'O Sole Mio",
 967                 'thumbnail': 're:^https?://.*\.jpg$',
 968                 'duration': 216,
 969                 'view_count': int,
 970             },
 971         },
 972         # Pladform embed
 973         {
 974             'url': 'http://muz-tv.ru/kinozal/view/7400/',
 975             'info_dict': {
 976                 'id': '100183293',
 977                 'ext': 'mp4',
 978                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
 979                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
 980                 'thumbnail': 're:^https?://.*\.jpg$',
 981                 'duration': 694,
 982                 'age_limit': 0,
 983             },
 984         },
 985         # Playwire embed
 986         {
 987             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
 988             'info_dict': {
 989                 'id': '3519514',
 990                 'ext': 'mp4',
 991                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
 992                 'thumbnail': 're:^https?://.*\.png$',
 993                 'duration': 45.115,
 994             },
 995         },
 996         # 5min embed
 997         {
 998             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
 999             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1000             'info_dict': {
1001                 'id': '518726732',
1002                 'ext': 'mp4',
1003                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1004             },
1005         },
1006         # SVT embed
1007         {
1008             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1009             'info_dict': {
1010                 'id': '2900353',
1011                 'ext': 'flv',
1012                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1013                 'duration': 27,
1014                 'age_limit': 0,
1015             },
1016         },
1017         # Crooks and Liars embed
1018         {
1019             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1020             'info_dict': {
1021                 'id': '8RUoRhRi',
1022                 'ext': 'mp4',
1023                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1024                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1025                 'timestamp': 1428207000,
1026                 'upload_date': '20150405',
1027                 'uploader': 'Heather',
1028             },
1029         },
1030         # Crooks and Liars external embed
1031         {
1032             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1033             'info_dict': {
1034                 'id': 'MTE3MjUtMzQ2MzA',
1035                 'ext': 'mp4',
1036                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1037                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1038                 'timestamp': 1265032391,
1039                 'upload_date': '20100201',
1040                 'uploader': 'Heather',
1041             },
1042         },
1043         # NBC Sports vplayer embed
1044         {
1045             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1046             'info_dict': {
1047                 'id': 'ln7x1qSThw4k',
1048                 'ext': 'flv',
1049                 'title': "PFT Live: New leader in the 'new-look' defense",
1050                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1051                 'uploader': 'NBCU-SPORTS',
1052                 'upload_date': '20140107',
1053                 'timestamp': 1389118457,
1054             },
1055         },
1056         # NBC News embed
1057         {
1058             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1059             'md5': '1aa589c675898ae6d37a17913cf68d66',
1060             'info_dict': {
1061                 'id': '701714499682',
1062                 'ext': 'mp4',
1063                 'title': 'PREVIEW: On Assignment: David Letterman',
1064                 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1065             },
1066         },
1067         # UDN embed
1068         {
1069             'url': 'https://video.udn.com/news/300346',
1070             'md5': 'fd2060e988c326991037b9aff9df21a6',
1071             'info_dict': {
1072                 'id': '300346',
1073                 'ext': 'mp4',
1074                 'title': '中一中男師變性 全校師生力挺',
1075                 'thumbnail': 're:^https?://.*\.jpg$',
1076             },
1077             'params': {
1078                 # m3u8 download
1079                 'skip_download': True,
1080             },
1081         },
1082         # Ooyala embed
1083         {
1084             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1085             'info_dict': {
1086                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1087                 'ext': 'mp4',
1088                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1089                 'title': 'This is what separates the Excel masters from the wannabes',
1090                 'duration': 191.933,
1091             },
1092             'params': {
1093                 # m3u8 downloads
1094                 'skip_download': True,
1095             }
1096         },
1097         # Brightcove URL in single quotes
1098         {
1099             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1100             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1101             'info_dict': {
1102                 'id': '4255764656001',
1103                 'ext': 'mp4',
1104                 'title': 'SN Presents: Russell Martin, World Citizen',
1105                 '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.',
1106                 'uploader': 'Rogers Sportsnet',
1107                 'uploader_id': '1704050871',
1108                 'upload_date': '20150525',
1109                 'timestamp': 1432570283,
1110             },
1111         },
1112         # Dailymotion Cloud video
1113         {
1114             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1115             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1116             'info_dict': {
1117                 'id': 'x2uy8t3',
1118                 'ext': 'mp4',
1119                 'title': 'Sauvons les abeilles ! - Le débat',
1120                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1121                 'thumbnail': 're:^https?://.*\.jpe?g$',
1122                 'timestamp': 1434970506,
1123                 'upload_date': '20150622',
1124                 'uploader': 'Public Sénat',
1125                 'uploader_id': 'xa9gza',
1126             }
1127         },
1128         # OnionStudios embed
1129         {
1130             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1131             'info_dict': {
1132                 'id': '2855',
1133                 'ext': 'mp4',
1134                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1135                 'thumbnail': 're:^https?://.*\.jpe?g$',
1136                 'uploader': 'ClickHole',
1137                 'uploader_id': 'clickhole',
1138             }
1139         },
1140         # SnagFilms embed
1141         {
1142             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1143             'info_dict': {
1144                 'id': '74849a00-85a9-11e1-9660-123139220831',
1145                 'ext': 'mp4',
1146                 'title': '#whilewewatch',
1147             }
1148         },
1149         # AdobeTVVideo embed
1150         {
1151             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1152             'md5': '43662b577c018ad707a63766462b1e87',
1153             'info_dict': {
1154                 'id': '2456',
1155                 'ext': 'mp4',
1156                 'title': 'New experience with Acrobat DC',
1157                 'description': 'New experience with Acrobat DC',
1158                 'duration': 248.667,
1159             },
1160         },
1161         # ScreenwaveMedia embed
1162         {
1163             'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1164             'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1165             'info_dict': {
1166                 'id': 'cinemasnob-55d26273809dd',
1167                 'ext': 'mp4',
1168                 'title': 'cinemasnob',
1169             },
1170         },
1171         # BrightcoveInPageEmbed embed
1172         {
1173             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1174             'info_dict': {
1175                 'id': '4238694884001',
1176                 'ext': 'flv',
1177                 'title': 'Tabletop: Dread, Last Thoughts',
1178                 'description': 'Tabletop: Dread, Last Thoughts',
1179                 'duration': 51690,
1180             },
1181         },
1182         # JWPlayer with M3U8
1183         {
1184             'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1185             'info_dict': {
1186                 'id': 'playlist',
1187                 'ext': 'mp4',
1188                 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1189                 'uploader': 'ren.tv',
1190             },
1191             'params': {
1192                 # m3u8 downloads
1193                 'skip_download': True,
1194             }
1195         },
1196         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1197         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1198         {
1199             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1200             'info_dict': {
1201                 'id': '4785848093001',
1202                 'ext': 'mp4',
1203                 'title': 'The Cardinal Pell Interview',
1204                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1205                 'uploader': 'GlobeCast Australia - GlobeStream',
1206                 'uploader_id': '2733773828001',
1207                 'upload_date': '20160304',
1208                 'timestamp': 1457083087,
1209             },
1210             'params': {
1211                 # m3u8 downloads
1212                 'skip_download': True,
1213             },
1214         },
1215         # Another form of arte.tv embed
1216         {
1217             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1218             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1219             'info_dict': {
1220                 'id': '030273-562_PLUS7-F',
1221                 'ext': 'mp4',
1222                 'title': 'ARTE Reportage - Nulle part, en France',
1223                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1224                 'upload_date': '20160409',
1225             },
1226         },
1227         # LiveLeak embed
1228         {
1229             'url': 'http://www.wykop.pl/link/3088787/',
1230             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1231             'info_dict': {
1232                 'id': '874_1459135191',
1233                 'ext': 'mp4',
1234                 'title': 'Man shows poor quality of new apartment building',
1235                 'description': 'The wall is like a sand pile.',
1236                 'uploader': 'Lake8737',
1237             }
1238         },
1239         # Duplicated embedded video URLs
1240         {
1241             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1242             'info_dict': {
1243                 'id': '149298443_480_16c25b74_2',
1244                 'ext': 'mp4',
1245                 'title': 'vs. Blue Orange Spring Game',
1246                 'uploader': 'www.hudl.com',
1247             },
1248         },
1249         # twitter:player embed
1250         {
1251             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1252             'md5': 'a3e0df96369831de324f0778e126653c',
1253             'info_dict': {
1254                 'id': '4909620399001',
1255                 'ext': 'mp4',
1256                 'title': 'What Do Black Holes Sound Like?',
1257                 'description': 'what do black holes sound like',
1258                 'upload_date': '20160524',
1259                 'uploader_id': '29913724001',
1260                 'timestamp': 1464107587,
1261                 'uploader': 'TheAtlantic',
1262             },
1263             'add_ie': ['BrightcoveLegacy'],
1264         },
1265         # Facebook <iframe> embed
1266         {
1267             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1268             'info_dict': {
1269                 'id': '599637780109885',
1270                 'ext': 'mp4',
1271                 'title': 'Facebook video #599637780109885',
1272             },
1273         },
1274         # Facebook API embed
1275         {
1276             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1277             'info_dict': {
1278                 'id': '10153467542406923',
1279                 'ext': 'mp4',
1280                 'title': 'Facebook video #10153467542406923',
1281             },
1282         }
1283     ]
1284
1285     def report_following_redirect(self, new_url):
1286         """Report information extraction."""
1287         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1288
1289     def _extract_rss(self, url, video_id, doc):
1290         playlist_title = doc.find('./channel/title').text
1291         playlist_desc_el = doc.find('./channel/description')
1292         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1293
1294         entries = []
1295         for it in doc.findall('./channel/item'):
1296             next_url = xpath_text(it, 'link', fatal=False)
1297             if not next_url:
1298                 enclosure_nodes = it.findall('./enclosure')
1299                 for e in enclosure_nodes:
1300                     next_url = e.attrib.get('url')
1301                     if next_url:
1302                         break
1303
1304             if not next_url:
1305                 continue
1306
1307             entries.append({
1308                 '_type': 'url',
1309                 'url': next_url,
1310                 'title': it.find('title').text,
1311             })
1312
1313         return {
1314             '_type': 'playlist',
1315             'id': url,
1316             'title': playlist_title,
1317             'description': playlist_desc,
1318             'entries': entries,
1319         }
1320
1321     def _extract_camtasia(self, url, video_id, webpage):
1322         """ Returns None if no camtasia video can be found. """
1323
1324         camtasia_cfg = self._search_regex(
1325             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1326             webpage, 'camtasia configuration file', default=None)
1327         if camtasia_cfg is None:
1328             return None
1329
1330         title = self._html_search_meta('DC.title', webpage, fatal=True)
1331
1332         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1333         camtasia_cfg = self._download_xml(
1334             camtasia_url, video_id,
1335             note='Downloading camtasia configuration',
1336             errnote='Failed to download camtasia configuration')
1337         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1338
1339         entries = []
1340         for n in fileset_node.getchildren():
1341             url_n = n.find('./uri')
1342             if url_n is None:
1343                 continue
1344
1345             entries.append({
1346                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1347                 'title': '%s - %s' % (title, n.tag),
1348                 'url': compat_urlparse.urljoin(url, url_n.text),
1349                 'duration': float_or_none(n.find('./duration').text),
1350             })
1351
1352         return {
1353             '_type': 'playlist',
1354             'entries': entries,
1355             'title': title,
1356         }
1357
1358     def _real_extract(self, url):
1359         if url.startswith('//'):
1360             return {
1361                 '_type': 'url',
1362                 'url': self.http_scheme() + url,
1363             }
1364
1365         parsed_url = compat_urlparse.urlparse(url)
1366         if not parsed_url.scheme:
1367             default_search = self._downloader.params.get('default_search')
1368             if default_search is None:
1369                 default_search = 'fixup_error'
1370
1371             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1372                 if '/' in url:
1373                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1374                     return self.url_result('http://' + url)
1375                 elif default_search != 'fixup_error':
1376                     if default_search == 'auto_warning':
1377                         if re.match(r'^(?:url|URL)$', url):
1378                             raise ExtractorError(
1379                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1380                                 expected=True)
1381                         else:
1382                             self._downloader.report_warning(
1383                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1384                     return self.url_result('ytsearch:' + url)
1385
1386             if default_search in ('error', 'fixup_error'):
1387                 raise ExtractorError(
1388                     '%r is not a valid URL. '
1389                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1390                     % (url, url), expected=True)
1391             else:
1392                 if ':' not in default_search:
1393                     default_search += ':'
1394                 return self.url_result(default_search + url)
1395
1396         url, smuggled_data = unsmuggle_url(url)
1397         force_videoid = None
1398         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1399         if smuggled_data and 'force_videoid' in smuggled_data:
1400             force_videoid = smuggled_data['force_videoid']
1401             video_id = force_videoid
1402         else:
1403             video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1404
1405         self.to_screen('%s: Requesting header' % video_id)
1406
1407         head_req = HEADRequest(url)
1408         head_response = self._request_webpage(
1409             head_req, video_id,
1410             note=False, errnote='Could not send HEAD request to %s' % url,
1411             fatal=False)
1412
1413         if head_response is not False:
1414             # Check for redirect
1415             new_url = head_response.geturl()
1416             if url != new_url:
1417                 self.report_following_redirect(new_url)
1418                 if force_videoid:
1419                     new_url = smuggle_url(
1420                         new_url, {'force_videoid': force_videoid})
1421                 return self.url_result(new_url)
1422
1423         full_response = None
1424         if head_response is False:
1425             request = sanitized_Request(url)
1426             request.add_header('Accept-Encoding', '*')
1427             full_response = self._request_webpage(request, video_id)
1428             head_response = full_response
1429
1430         info_dict = {
1431             'id': video_id,
1432             'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1433             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1434         }
1435
1436         # Check for direct link to a video
1437         content_type = head_response.headers.get('Content-Type', '').lower()
1438         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1439         if m:
1440             format_id = m.group('format_id')
1441             if format_id.endswith('mpegurl'):
1442                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1443             elif format_id == 'f4m':
1444                 formats = self._extract_f4m_formats(url, video_id)
1445             else:
1446                 formats = [{
1447                     'format_id': m.group('format_id'),
1448                     'url': url,
1449                     'vcodec': 'none' if m.group('type') == 'audio' else None
1450                 }]
1451                 info_dict['direct'] = True
1452             self._sort_formats(formats)
1453             info_dict['formats'] = formats
1454             return info_dict
1455
1456         if not self._downloader.params.get('test', False) and not is_intentional:
1457             force = self._downloader.params.get('force_generic_extractor', False)
1458             self._downloader.report_warning(
1459                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1460
1461         if not full_response:
1462             request = sanitized_Request(url)
1463             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1464             # making it impossible to download only chunk of the file (yet we need only 512kB to
1465             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1466             # that will always result in downloading the whole file that is not desirable.
1467             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1468             # to accept raw bytes and being able to download only a chunk.
1469             # It may probably better to solve this by checking Content-Type for application/octet-stream
1470             # after HEAD request finishes, but not sure if we can rely on this.
1471             request.add_header('Accept-Encoding', '*')
1472             full_response = self._request_webpage(request, video_id)
1473
1474         first_bytes = full_response.read(512)
1475
1476         # Is it an M3U playlist?
1477         if first_bytes.startswith(b'#EXTM3U'):
1478             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1479             self._sort_formats(info_dict['formats'])
1480             return info_dict
1481
1482         # Maybe it's a direct link to a video?
1483         # Be careful not to download the whole thing!
1484         if not is_html(first_bytes):
1485             self._downloader.report_warning(
1486                 'URL could be a direct video link, returning it as such.')
1487             info_dict.update({
1488                 'direct': True,
1489                 'url': url,
1490             })
1491             return info_dict
1492
1493         webpage = self._webpage_read_content(
1494             full_response, url, video_id, prefix=first_bytes)
1495
1496         self.report_extraction(video_id)
1497
1498         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1499         try:
1500             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1501             if doc.tag == 'rss':
1502                 return self._extract_rss(url, video_id, doc)
1503             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1504                 smil = self._parse_smil(doc, url, video_id)
1505                 self._sort_formats(smil['formats'])
1506                 return smil
1507             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1508                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1509             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1510                 info_dict['formats'] = self._parse_mpd_formats(
1511                     doc, video_id, mpd_base_url=url.rpartition('/')[0])
1512                 self._sort_formats(info_dict['formats'])
1513                 return info_dict
1514             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1515                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1516                 self._sort_formats(info_dict['formats'])
1517                 return info_dict
1518         except compat_xml_parse_error:
1519             pass
1520
1521         # Is it a Camtasia project?
1522         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1523         if camtasia_res is not None:
1524             return camtasia_res
1525
1526         # Sometimes embedded video player is hidden behind percent encoding
1527         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1528         # Unescaping the whole page allows to handle those cases in a generic way
1529         webpage = compat_urllib_parse_unquote(webpage)
1530
1531         # it's tempting to parse this further, but you would
1532         # have to take into account all the variations like
1533         #   Video Title - Site Name
1534         #   Site Name | Video Title
1535         #   Video Title - Tagline | Site Name
1536         # and so on and so forth; it's just not practical
1537         video_title = self._og_search_title(
1538             webpage, default=None) or self._html_search_regex(
1539             r'(?s)<title>(.*?)</title>', webpage, 'video title',
1540             default='video')
1541
1542         # Try to detect age limit automatically
1543         age_limit = self._rta_search(webpage)
1544         # And then there are the jokers who advertise that they use RTA,
1545         # but actually don't.
1546         AGE_LIMIT_MARKERS = [
1547             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1548         ]
1549         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1550             age_limit = 18
1551
1552         # video uploader is domain name
1553         video_uploader = self._search_regex(
1554             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1555
1556         video_description = self._og_search_description(webpage, default=None)
1557         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1558
1559         # Helper method
1560         def _playlist_from_matches(matches, getter=None, ie=None):
1561             urlrs = orderedSet(
1562                 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1563                 for m in matches)
1564             return self.playlist_result(
1565                 urlrs, playlist_id=video_id, playlist_title=video_title)
1566
1567         # Look for Brightcove Legacy Studio embeds
1568         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1569         if bc_urls:
1570             self.to_screen('Brightcove video detected.')
1571             entries = [{
1572                 '_type': 'url',
1573                 'url': smuggle_url(bc_url, {'Referer': url}),
1574                 'ie_key': 'BrightcoveLegacy'
1575             } for bc_url in bc_urls]
1576
1577             return {
1578                 '_type': 'playlist',
1579                 'title': video_title,
1580                 'id': video_id,
1581                 'entries': entries,
1582             }
1583
1584         # Look for Brightcove New Studio embeds
1585         bc_urls = BrightcoveNewIE._extract_urls(webpage)
1586         if bc_urls:
1587             return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1588
1589         # Look for ThePlatform embeds
1590         tp_urls = ThePlatformIE._extract_urls(webpage)
1591         if tp_urls:
1592             return _playlist_from_matches(tp_urls, ie='ThePlatform')
1593
1594         # Look for Vessel embeds
1595         vessel_urls = VesselIE._extract_urls(webpage)
1596         if vessel_urls:
1597             return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1598
1599         # Look for embedded rtl.nl player
1600         matches = re.findall(
1601             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1602             webpage)
1603         if matches:
1604             return _playlist_from_matches(matches, ie='RtlNl')
1605
1606         vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1607         if vimeo_url is not None:
1608             return self.url_result(vimeo_url)
1609
1610         vid_me_embed_url = self._search_regex(
1611             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1612             webpage, 'vid.me embed', default=None)
1613         if vid_me_embed_url is not None:
1614             return self.url_result(vid_me_embed_url, 'Vidme')
1615
1616         # Look for embedded YouTube player
1617         matches = re.findall(r'''(?x)
1618             (?:
1619                 <iframe[^>]+?src=|
1620                 data-video-url=|
1621                 <embed[^>]+?src=|
1622                 embedSWF\(?:\s*|
1623                 new\s+SWFObject\(
1624             )
1625             (["\'])
1626                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1627                 (?:embed|v|p)/.+?)
1628             \1''', webpage)
1629         if matches:
1630             return _playlist_from_matches(
1631                 matches, lambda m: unescapeHTML(m[1]))
1632
1633         # Look for lazyYT YouTube embed
1634         matches = re.findall(
1635             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1636         if matches:
1637             return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1638
1639         # Look for embedded Dailymotion player
1640         matches = re.findall(
1641             r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1642         if matches:
1643             return _playlist_from_matches(
1644                 matches, lambda m: unescapeHTML(m[1]))
1645
1646         # Look for embedded Dailymotion playlist player (#3822)
1647         m = re.search(
1648             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1649         if m:
1650             playlists = re.findall(
1651                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1652             if playlists:
1653                 return _playlist_from_matches(
1654                     playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1655
1656         # Look for embedded Wistia player
1657         match = re.search(
1658             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1659         if match:
1660             embed_url = self._proto_relative_url(
1661                 unescapeHTML(match.group('url')))
1662             return {
1663                 '_type': 'url_transparent',
1664                 'url': embed_url,
1665                 'ie_key': 'Wistia',
1666                 'uploader': video_uploader,
1667             }
1668
1669         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1670         if match:
1671             return {
1672                 '_type': 'url_transparent',
1673                 'url': 'wistia:%s' % match.group('id'),
1674                 'ie_key': 'Wistia',
1675                 'uploader': video_uploader,
1676             }
1677
1678         match = re.search(
1679             r'''(?sx)
1680                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1681                 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1682             ''', webpage)
1683         if match:
1684             return self.url_result(self._proto_relative_url(
1685                 'wistia:%s' % match.group('id')), 'Wistia')
1686
1687         # Look for SVT player
1688         svt_url = SVTIE._extract_url(webpage)
1689         if svt_url:
1690             return self.url_result(svt_url, 'SVT')
1691
1692         # Look for embedded condenast player
1693         matches = re.findall(
1694             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1695             webpage)
1696         if matches:
1697             return {
1698                 '_type': 'playlist',
1699                 'entries': [{
1700                     '_type': 'url',
1701                     'ie_key': 'CondeNast',
1702                     'url': ma,
1703                 } for ma in matches],
1704                 'title': video_title,
1705                 'id': video_id,
1706             }
1707
1708         # Look for Bandcamp pages with custom domain
1709         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1710         if mobj is not None:
1711             burl = unescapeHTML(mobj.group(1))
1712             # Don't set the extractor because it can be a track url or an album
1713             return self.url_result(burl)
1714
1715         # Look for embedded Vevo player
1716         mobj = re.search(
1717             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1718         if mobj is not None:
1719             return self.url_result(mobj.group('url'))
1720
1721         # Look for embedded Viddler player
1722         mobj = re.search(
1723             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1724             webpage)
1725         if mobj is not None:
1726             return self.url_result(mobj.group('url'))
1727
1728         # Look for NYTimes player
1729         mobj = re.search(
1730             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1731             webpage)
1732         if mobj is not None:
1733             return self.url_result(mobj.group('url'))
1734
1735         # Look for Libsyn player
1736         mobj = re.search(
1737             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1738         if mobj is not None:
1739             return self.url_result(mobj.group('url'))
1740
1741         # Look for Ooyala videos
1742         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1743                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1744                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1745                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1746         if mobj is not None:
1747             return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1748
1749         # Look for multiple Ooyala embeds on SBN network websites
1750         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1751         if mobj is not None:
1752             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1753             if embeds:
1754                 return _playlist_from_matches(
1755                     embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1756
1757         # Look for Aparat videos
1758         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1759         if mobj is not None:
1760             return self.url_result(mobj.group(1), 'Aparat')
1761
1762         # Look for MPORA videos
1763         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1764         if mobj is not None:
1765             return self.url_result(mobj.group(1), 'Mpora')
1766
1767         # Look for embedded NovaMov-based player
1768         mobj = re.search(
1769             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1770                     (?P<url>http://(?:(?:embed|www)\.)?
1771                         (?:novamov\.com|
1772                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
1773                            videoweed\.(?:es|com)|
1774                            movshare\.(?:net|sx|ag)|
1775                            divxstage\.(?:eu|net|ch|co|at|ag))
1776                         /embed\.php.+?)\1''', webpage)
1777         if mobj is not None:
1778             return self.url_result(mobj.group('url'))
1779
1780         # Look for embedded Facebook player
1781         facebook_url = FacebookIE._extract_url(webpage)
1782         if facebook_url is not None:
1783             return self.url_result(facebook_url, 'Facebook')
1784
1785         # Look for embedded VK player
1786         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1787         if mobj is not None:
1788             return self.url_result(mobj.group('url'), 'VK')
1789
1790         # Look for embedded Odnoklassniki player
1791         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1792         if mobj is not None:
1793             return self.url_result(mobj.group('url'), 'Odnoklassniki')
1794
1795         # Look for embedded ivi player
1796         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1797         if mobj is not None:
1798             return self.url_result(mobj.group('url'), 'Ivi')
1799
1800         # Look for embedded Huffington Post player
1801         mobj = re.search(
1802             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1803         if mobj is not None:
1804             return self.url_result(mobj.group('url'), 'HuffPost')
1805
1806         # Look for embed.ly
1807         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1808         if mobj is not None:
1809             return self.url_result(mobj.group('url'))
1810         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1811         if mobj is not None:
1812             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1813
1814         # Look for funnyordie embed
1815         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1816         if matches:
1817             return _playlist_from_matches(
1818                 matches, getter=unescapeHTML, ie='FunnyOrDie')
1819
1820         # Look for BBC iPlayer embed
1821         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1822         if matches:
1823             return _playlist_from_matches(matches, ie='BBCCoUk')
1824
1825         # Look for embedded RUTV player
1826         rutv_url = RUTVIE._extract_url(webpage)
1827         if rutv_url:
1828             return self.url_result(rutv_url, 'RUTV')
1829
1830         # Look for embedded TVC player
1831         tvc_url = TVCIE._extract_url(webpage)
1832         if tvc_url:
1833             return self.url_result(tvc_url, 'TVC')
1834
1835         # Look for embedded SportBox player
1836         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1837         if sportbox_urls:
1838             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1839
1840         # Look for embedded PornHub player
1841         pornhub_url = PornHubIE._extract_url(webpage)
1842         if pornhub_url:
1843             return self.url_result(pornhub_url, 'PornHub')
1844
1845         # Look for embedded XHamster player
1846         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1847         if xhamster_urls:
1848             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1849
1850         # Look for embedded TNAFlixNetwork player
1851         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1852         if tnaflix_urls:
1853             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1854
1855         # Look for embedded Tvigle player
1856         mobj = re.search(
1857             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1858         if mobj is not None:
1859             return self.url_result(mobj.group('url'), 'Tvigle')
1860
1861         # Look for embedded TED player
1862         mobj = re.search(
1863             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1864         if mobj is not None:
1865             return self.url_result(mobj.group('url'), 'TED')
1866
1867         # Look for embedded Ustream videos
1868         mobj = re.search(
1869             r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1870         if mobj is not None:
1871             return self.url_result(mobj.group('url'), 'Ustream')
1872
1873         # Look for embedded arte.tv player
1874         mobj = re.search(
1875             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1876             webpage)
1877         if mobj is not None:
1878             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1879
1880         # Look for embedded francetv player
1881         mobj = re.search(
1882             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1883             webpage)
1884         if mobj is not None:
1885             return self.url_result(mobj.group('url'))
1886
1887         # Look for embedded smotri.com player
1888         smotri_url = SmotriIE._extract_url(webpage)
1889         if smotri_url:
1890             return self.url_result(smotri_url, 'Smotri')
1891
1892         # Look for embedded Myvi.ru player
1893         myvi_url = MyviIE._extract_url(webpage)
1894         if myvi_url:
1895             return self.url_result(myvi_url)
1896
1897         # Look for embedded soundcloud player
1898         mobj = re.search(
1899             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1900             webpage)
1901         if mobj is not None:
1902             url = unescapeHTML(mobj.group('url'))
1903             return self.url_result(url)
1904
1905         # Look for embedded mtvservices player
1906         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1907         if mtvservices_url:
1908             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1909
1910         # Look for embedded yahoo player
1911         mobj = re.search(
1912             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1913             webpage)
1914         if mobj is not None:
1915             return self.url_result(mobj.group('url'), 'Yahoo')
1916
1917         # Look for embedded sbs.com.au player
1918         mobj = re.search(
1919             r'''(?x)
1920             (?:
1921                 <meta\s+property="og:video"\s+content=|
1922                 <iframe[^>]+?src=
1923             )
1924             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1925             webpage)
1926         if mobj is not None:
1927             return self.url_result(mobj.group('url'), 'SBS')
1928
1929         # Look for embedded Cinchcast player
1930         mobj = re.search(
1931             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1932             webpage)
1933         if mobj is not None:
1934             return self.url_result(mobj.group('url'), 'Cinchcast')
1935
1936         mobj = re.search(
1937             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1938             webpage)
1939         if not mobj:
1940             mobj = re.search(
1941                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1942                 webpage)
1943         if mobj is not None:
1944             return self.url_result(mobj.group('url'), 'MLB')
1945
1946         mobj = re.search(
1947             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1948             webpage)
1949         if mobj is not None:
1950             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1951
1952         mobj = re.search(
1953             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1954             webpage)
1955         if mobj is not None:
1956             return self.url_result(mobj.group('url'), 'Livestream')
1957
1958         # Look for Zapiks embed
1959         mobj = re.search(
1960             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1961         if mobj is not None:
1962             return self.url_result(mobj.group('url'), 'Zapiks')
1963
1964         # Look for Kaltura embeds
1965         kaltura_url = KalturaIE._extract_url(webpage)
1966         if kaltura_url:
1967             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
1968
1969         # Look for Eagle.Platform embeds
1970         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
1971         if eagleplatform_url:
1972             return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
1973
1974         # Look for ClipYou (uses Eagle.Platform) embeds
1975         mobj = re.search(
1976             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1977         if mobj is not None:
1978             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1979
1980         # Look for Pladform embeds
1981         pladform_url = PladformIE._extract_url(webpage)
1982         if pladform_url:
1983             return self.url_result(pladform_url)
1984
1985         # Look for Videomore embeds
1986         videomore_url = VideomoreIE._extract_url(webpage)
1987         if videomore_url:
1988             return self.url_result(videomore_url)
1989
1990         # Look for Playwire embeds
1991         mobj = re.search(
1992             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1993         if mobj is not None:
1994             return self.url_result(mobj.group('url'))
1995
1996         # Look for 5min embeds
1997         mobj = re.search(
1998             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1999         if mobj is not None:
2000             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2001
2002         # Look for Crooks and Liars embeds
2003         mobj = re.search(
2004             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2005         if mobj is not None:
2006             return self.url_result(mobj.group('url'))
2007
2008         # Look for NBC Sports VPlayer embeds
2009         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2010         if nbc_sports_url:
2011             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2012
2013         # Look for NBC News embeds
2014         nbc_news_embed_url = re.search(
2015             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2016         if nbc_news_embed_url:
2017             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2018
2019         # Look for Google Drive embeds
2020         google_drive_url = GoogleDriveIE._extract_url(webpage)
2021         if google_drive_url:
2022             return self.url_result(google_drive_url, 'GoogleDrive')
2023
2024         # Look for UDN embeds
2025         mobj = re.search(
2026             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2027         if mobj is not None:
2028             return self.url_result(
2029                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2030
2031         # Look for Senate ISVP iframe
2032         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2033         if senate_isvp_url:
2034             return self.url_result(senate_isvp_url, 'SenateISVP')
2035
2036         # Look for Dailymotion Cloud videos
2037         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2038         if dmcloud_url:
2039             return self.url_result(dmcloud_url, 'DailymotionCloud')
2040
2041         # Look for OnionStudios embeds
2042         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2043         if onionstudios_url:
2044             return self.url_result(onionstudios_url)
2045
2046         # Look for ViewLift embeds
2047         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2048         if viewlift_url:
2049             return self.url_result(viewlift_url)
2050
2051         # Look for JWPlatform embeds
2052         jwplatform_url = JWPlatformIE._extract_url(webpage)
2053         if jwplatform_url:
2054             return self.url_result(jwplatform_url, 'JWPlatform')
2055
2056         # Look for ScreenwaveMedia embeds
2057         mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2058         if mobj is not None:
2059             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2060
2061         # Look for Digiteka embeds
2062         digiteka_url = DigitekaIE._extract_url(webpage)
2063         if digiteka_url:
2064             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2065
2066         # Look for Limelight embeds
2067         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2068         if mobj:
2069             lm = {
2070                 'Media': 'media',
2071                 'Channel': 'channel',
2072                 'ChannelList': 'channel_list',
2073             }
2074             return self.url_result('limelight:%s:%s' % (
2075                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2076
2077         # Look for AdobeTVVideo embeds
2078         mobj = re.search(
2079             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2080             webpage)
2081         if mobj is not None:
2082             return self.url_result(
2083                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2084                 'AdobeTVVideo')
2085
2086         # Look for Vine embeds
2087         mobj = re.search(
2088             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2089             webpage)
2090         if mobj is not None:
2091             return self.url_result(
2092                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2093
2094         # Look for Instagram embeds
2095         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2096         if instagram_embed_url is not None:
2097             return self.url_result(
2098                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2099
2100         # Look for LiveLeak embeds
2101         liveleak_url = LiveLeakIE._extract_url(webpage)
2102         if liveleak_url:
2103             return self.url_result(liveleak_url, 'LiveLeak')
2104
2105         # Look for 3Q SDN embeds
2106         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2107         if threeqsdn_url:
2108             return {
2109                 '_type': 'url_transparent',
2110                 'ie_key': ThreeQSDNIE.ie_key(),
2111                 'url': self._proto_relative_url(threeqsdn_url),
2112                 'title': video_title,
2113                 'description': video_description,
2114                 'thumbnail': video_thumbnail,
2115                 'uploader': video_uploader,
2116             }
2117
2118         # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
2119         embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2120         if embed_url:
2121             return self.url_result(embed_url)
2122
2123         def check_video(vurl):
2124             if YoutubeIE.suitable(vurl):
2125                 return True
2126             vpath = compat_urlparse.urlparse(vurl).path
2127             vext = determine_ext(vpath)
2128             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2129
2130         def filter_video(urls):
2131             return list(filter(check_video, urls))
2132
2133         # Start with something easy: JW Player in SWFObject
2134         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2135         if not found:
2136             # Look for gorilla-vid style embedding
2137             found = filter_video(re.findall(r'''(?sx)
2138                 (?:
2139                     jw_plugins|
2140                     JWPlayerOptions|
2141                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2142                 )
2143                 .*?
2144                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2145         if not found:
2146             # Broaden the search a little bit
2147             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2148         if not found:
2149             # Broaden the findall a little bit: JWPlayer JS loader
2150             found = filter_video(re.findall(
2151                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2152         if not found:
2153             # Flow player
2154             found = filter_video(re.findall(r'''(?xs)
2155                 flowplayer\("[^"]+",\s*
2156                     \{[^}]+?\}\s*,
2157                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2158                         ["']?url["']?\s*:\s*["']([^"']+)["']
2159             ''', webpage))
2160         if not found:
2161             # Cinerama player
2162             found = re.findall(
2163                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2164         if not found:
2165             # Try to find twitter cards info
2166             found = filter_video(re.findall(
2167                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2168         if not found:
2169             # We look for Open Graph info:
2170             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2171             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2172             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2173             if m_video_type is not None:
2174                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2175         if not found:
2176             # HTML5 video
2177             found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2178         if not found:
2179             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2180             found = re.search(
2181                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2182                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2183                 webpage)
2184             if not found:
2185                 # Look also in Refresh HTTP header
2186                 refresh_header = head_response.headers.get('Refresh')
2187                 if refresh_header:
2188                     # In python 2 response HTTP headers are bytestrings
2189                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2190                         refresh_header = refresh_header.decode('iso-8859-1')
2191                     found = re.search(REDIRECT_REGEX, refresh_header)
2192             if found:
2193                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2194                 self.report_following_redirect(new_url)
2195                 return {
2196                     '_type': 'url',
2197                     'url': new_url,
2198                 }
2199         if not found:
2200             raise UnsupportedError(url)
2201
2202         entries = []
2203         for video_url in orderedSet(found):
2204             video_url = unescapeHTML(video_url)
2205             video_url = video_url.replace('\\/', '/')
2206             video_url = compat_urlparse.urljoin(url, video_url)
2207             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2208
2209             # Sometimes, jwplayer extraction will result in a YouTube URL
2210             if YoutubeIE.suitable(video_url):
2211                 entries.append(self.url_result(video_url, 'Youtube'))
2212                 continue
2213
2214             # here's a fun little line of code for you:
2215             video_id = os.path.splitext(video_id)[0]
2216
2217             entry_info_dict = {
2218                 'id': video_id,
2219                 'uploader': video_uploader,
2220                 'title': video_title,
2221                 'age_limit': age_limit,
2222             }
2223
2224             ext = determine_ext(video_url)
2225             if ext == 'smil':
2226                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2227             elif ext == 'xspf':
2228                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2229             elif ext == 'm3u8':
2230                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2231             elif ext == 'mpd':
2232                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2233             elif ext == 'f4m':
2234                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2235             else:
2236                 entry_info_dict['url'] = video_url
2237
2238             if entry_info_dict.get('formats'):
2239                 self._sort_formats(entry_info_dict['formats'])
2240
2241             entries.append(entry_info_dict)
2242
2243         if len(entries) == 1:
2244             return entries[0]
2245         else:
2246             for num, e in enumerate(entries, start=1):
2247                 # 'url' results don't have a title
2248                 if e.get('title') is not None:
2249                     e['title'] = '%s (%d)' % (e['title'], num)
2250             return {
2251                 '_type': 'playlist',
2252                 'entries': entries,
2253             }