_ 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
  67
  68 class GenericIE(InfoExtractor):
  69     IE_DESC = 'Generic downloader that works on some sites'
  70     _VALID_URL = r'.*'
  71     IE_NAME = 'generic'
  72     _TESTS = [
  73         # Direct link to a video
  74         {
  75             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  76             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  77             'info_dict': {
  78                 'id': 'trailer',
  79                 'ext': 'mp4',
  80                 'title': 'trailer',
  81                 'upload_date': '20100513',
  82             }
  83         },
  84         # Direct link to media delivered compressed (until Accept-Encoding is *)
  85         {
  86             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  87             'md5': '128c42e68b13950268b648275386fc74',
  88             'info_dict': {
  89                 'id': 'FictionJunction-Parallel_Hearts',
  90                 'ext': 'flac',
  91                 'title': 'FictionJunction-Parallel_Hearts',
  92                 'upload_date': '20140522',
  93             },
  94             'expected_warnings': [
  95                 'URL could be a direct video link, returning it as such.'
  96             ]
  97         },
  98         # Direct download with broken HEAD
  99         {
 100             'url': 'http://ai-radio.org:8000/radio.opus',
 101             'info_dict': {
 102                 'id': 'radio',
 103                 'ext': 'opus',
 104                 'title': 'radio',
 105             },
 106             'params': {
 107                 'skip_download': True,  # infinite live stream
 108             },
 109             'expected_warnings': [
 110                 r'501.*Not Implemented',
 111                 r'400.*Bad Request',
 112             ],
 113         },
 114         # Direct link with incorrect MIME type
 115         {
 116             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 117             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 118             'info_dict': {
 119                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 120                 'id': '5_Lennart_Poettering_-_Systemd',
 121                 'ext': 'webm',
 122                 'title': '5_Lennart_Poettering_-_Systemd',
 123                 'upload_date': '20141120',
 124             },
 125             'expected_warnings': [
 126                 'URL could be a direct video link, returning it as such.'
 127             ]
 128         },
 129         # RSS feed
 130         {
 131             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 132             'info_dict': {
 133                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 134                 'title': 'Zero Punctuation',
 135                 'description': 're:.*groundbreaking video review series.*'
 136             },
 137             'playlist_mincount': 11,
 138         },
 139         # RSS feed with enclosure
 140         {
 141             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 142             'info_dict': {
 143                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 144                 'ext': 'm4v',
 145                 'upload_date': '20150228',
 146                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 147             }
 148         },
 149         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 150         {
 151             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 152             'info_dict': {
 153                 'id': 'smil',
 154                 'ext': 'mp4',
 155                 'title': 'Automatics, robotics and biocybernetics',
 156                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 157                 'upload_date': '20130627',
 158                 'formats': 'mincount:16',
 159                 'subtitles': 'mincount:1',
 160             },
 161             'params': {
 162                 'force_generic_extractor': True,
 163                 'skip_download': True,
 164             },
 165         },
 166         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 167         {
 168             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 169             'info_dict': {
 170                 'id': 'hds',
 171                 'ext': 'flv',
 172                 'title': 'hds',
 173                 'formats': 'mincount:1',
 174             },
 175             'params': {
 176                 'skip_download': True,
 177             },
 178         },
 179         # SMIL from https://www.restudy.dk/video/play/id/1637
 180         {
 181             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 182             'info_dict': {
 183                 'id': 'video_1637',
 184                 'ext': 'flv',
 185                 'title': 'video_1637',
 186                 'formats': 'mincount:3',
 187             },
 188             'params': {
 189                 'skip_download': True,
 190             },
 191         },
 192         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 193         {
 194             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 195             'info_dict': {
 196                 'id': 'smil-service',
 197                 'ext': 'flv',
 198                 'title': 'smil-service',
 199                 'formats': 'mincount:1',
 200             },
 201             'params': {
 202                 'skip_download': True,
 203             },
 204         },
 205         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 206         {
 207             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 208             'info_dict': {
 209                 'id': '4719370',
 210                 'ext': 'mp4',
 211                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 212                 'formats': 'mincount:3',
 213             },
 214             'params': {
 215                 'skip_download': True,
 216             },
 217         },
 218         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 219         {
 220             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 221             'info_dict': {
 222                 'id': 'mZlp2ctYIUEB',
 223                 'ext': 'mp4',
 224                 'title': 'Tikibad ontruimd wegens brand',
 225                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 226                 'thumbnail': 're:^https?://.*\.jpg$',
 227                 'duration': 33,
 228             },
 229             'params': {
 230                 'skip_download': True,
 231             },
 232         },
 233         # MPD from http://dash-mse-test.appspot.com/media.html
 234         {
 235             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 236             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 237             'info_dict': {
 238                 'id': 'car-20120827-manifest',
 239                 'ext': 'mp4',
 240                 'title': 'car-20120827-manifest',
 241                 'formats': 'mincount:9',
 242                 'upload_date': '20130904',
 243             },
 244             'params': {
 245                 'format': 'bestvideo',
 246             },
 247         },
 248         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 249         {
 250             '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',
 251             'info_dict': {
 252                 'id': 'content',
 253                 'ext': 'mp4',
 254                 'title': 'content',
 255                 'formats': 'mincount:8',
 256             },
 257             'params': {
 258                 # m3u8 downloads
 259                 'skip_download': True,
 260             }
 261         },
 262         # m3u8 served with Content-Type: text/plain
 263         {
 264             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 265             'info_dict': {
 266                 'id': 'index',
 267                 'ext': 'mp4',
 268                 'title': 'index',
 269                 'upload_date': '20140720',
 270                 'formats': 'mincount:11',
 271             },
 272             'params': {
 273                 # m3u8 downloads
 274                 'skip_download': True,
 275             }
 276         },
 277         # google redirect
 278         {
 279             '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',
 280             'info_dict': {
 281                 'id': 'cmQHVoWB5FY',
 282                 'ext': 'mp4',
 283                 'upload_date': '20130224',
 284                 'uploader_id': 'TheVerge',
 285                 'description': 're:^Chris Ziegler takes a look at the\.*',
 286                 'uploader': 'The Verge',
 287                 'title': 'First Firefox OS phones side-by-side',
 288             },
 289             'params': {
 290                 'skip_download': False,
 291             }
 292         },
 293         {
 294             # redirect in Refresh HTTP header
 295             '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',
 296             'info_dict': {
 297                 'id': 'pO8h3EaFRdo',
 298                 'ext': 'mp4',
 299                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 300                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 301                 'upload_date': '20150917',
 302                 'uploader_id': 'brtvofficial',
 303                 'uploader': 'Boiler Room',
 304             },
 305             'params': {
 306                 'skip_download': False,
 307             },
 308         },
 309         {
 310             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 311             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 312             'info_dict': {
 313                 'id': '13601338388002',
 314                 'ext': 'mp4',
 315                 'uploader': 'www.hodiho.fr',
 316                 'title': 'R\u00e9gis plante sa Jeep',
 317             }
 318         },
 319         # bandcamp page with custom domain
 320         {
 321             'add_ie': ['Bandcamp'],
 322             'url': 'http://bronyrock.com/track/the-pony-mash',
 323             'info_dict': {
 324                 'id': '3235767654',
 325                 'ext': 'mp3',
 326                 'title': 'The Pony Mash',
 327                 'uploader': 'M_Pallante',
 328             },
 329             'skip': 'There is a limit of 200 free downloads / month for the test song',
 330         },
 331         # embedded brightcove video
 332         # it also tests brightcove videos that need to set the 'Referer' in the
 333         # http requests
 334         {
 335             'add_ie': ['BrightcoveLegacy'],
 336             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 337             'info_dict': {
 338                 'id': '2765128793001',
 339                 'ext': 'mp4',
 340                 'title': 'Le cours de bourse : l’analyse technique',
 341                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 342                 'uploader': 'BFM BUSINESS',
 343             },
 344             'params': {
 345                 'skip_download': True,
 346             },
 347         },
 348         {
 349             # https://github.com/rg3/youtube-dl/issues/2253
 350             'url': 'http://bcove.me/i6nfkrc3',
 351             'md5': '0ba9446db037002366bab3b3eb30c88c',
 352             'info_dict': {
 353                 'id': '3101154703001',
 354                 'ext': 'mp4',
 355                 'title': 'Still no power',
 356                 'uploader': 'thestar.com',
 357                 '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.',
 358             },
 359             'add_ie': ['BrightcoveLegacy'],
 360         },
 361         {
 362             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 363             'md5': 'fb973ecf6e4a78a67453647444222983',
 364             'info_dict': {
 365                 'id': '3414141473001',
 366                 'ext': 'mp4',
 367                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 368                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 369                 'uploader': 'Championat',
 370             },
 371         },
 372         {
 373             # https://github.com/rg3/youtube-dl/issues/3541
 374             'add_ie': ['BrightcoveLegacy'],
 375             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 376             'info_dict': {
 377                 'id': '3866516442001',
 378                 'ext': 'mp4',
 379                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 380                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 381                 'uploader': 'SBS Broadcasting',
 382             },
 383             'skip': 'Restricted to Netherlands',
 384             'params': {
 385                 'skip_download': True,  # m3u8 download
 386             },
 387         },
 388         # ooyala video
 389         {
 390             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 391             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 392             'info_dict': {
 393                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 394                 'ext': 'mp4',
 395                 'title': '2cc213299525360.mov',  # that's what we get
 396                 'duration': 238.231,
 397             },
 398             'add_ie': ['Ooyala'],
 399         },
 400         {
 401             # ooyala video embedded with http://player.ooyala.com/iframe.js
 402             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 403             'info_dict': {
 404                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 405                 'ext': 'mp4',
 406                 'title': '"Steve Jobs: Man in the Machine" trailer',
 407                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 408                 'duration': 135.427,
 409             },
 410             'params': {
 411                 'skip_download': True,
 412             },
 413         },
 414         # embed.ly video
 415         {
 416             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 417             'info_dict': {
 418                 'id': '9ODmcdjQcHQ',
 419                 'ext': 'mp4',
 420                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 421                 'upload_date': '20140225',
 422                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 423                 'uploader': 'Tested',
 424                 'uploader_id': 'testedcom',
 425             },
 426             # No need to test YoutubeIE here
 427             'params': {
 428                 'skip_download': True,
 429             },
 430         },
 431         # funnyordie embed
 432         {
 433             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 434             'info_dict': {
 435                 'id': '18e820ec3f',
 436                 'ext': 'mp4',
 437                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 438                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 439             },
 440         },
 441         # RUTV embed
 442         {
 443             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 444             'info_dict': {
 445                 'id': '776940',
 446                 'ext': 'mp4',
 447                 'title': 'Охотское море стало целиком российским',
 448                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 449             },
 450             'params': {
 451                 # m3u8 download
 452                 'skip_download': True,
 453             },
 454         },
 455         # TVC embed
 456         {
 457             '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/',
 458             'info_dict': {
 459                 'id': '55304',
 460                 'ext': 'mp4',
 461                 'title': 'Дошкольное воспитание',
 462             },
 463         },
 464         # SportBox embed
 465         {
 466             'url': 'http://www.vestifinance.ru/articles/25753',
 467             'info_dict': {
 468                 'id': '25753',
 469                 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 470             },
 471             'playlist': [{
 472                 'info_dict': {
 473                     'id': '370908',
 474                     'title': 'Госзаказ. День 3',
 475                     'ext': 'mp4',
 476                 }
 477             }, {
 478                 'info_dict': {
 479                     'id': '370905',
 480                     'title': 'Госзаказ. День 2',
 481                     'ext': 'mp4',
 482                 }
 483             }, {
 484                 'info_dict': {
 485                     'id': '370902',
 486                     'title': 'Госзаказ. День 1',
 487                     'ext': 'mp4',
 488                 }
 489             }],
 490             'params': {
 491                 # m3u8 download
 492                 'skip_download': True,
 493             },
 494         },
 495         # Myvi.ru embed
 496         {
 497             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 498             'info_dict': {
 499                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 500                 'ext': 'mp4',
 501                 'title': 'Ужастики, русский трейлер (2015)',
 502                 'thumbnail': 're:^https?://.*\.jpg$',
 503                 'duration': 153,
 504             }
 505         },
 506         # XHamster embed
 507         {
 508             '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',
 509             'info_dict': {
 510                 'id': 'showthread',
 511                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 512             },
 513             'playlist_mincount': 7,
 514         },
 515         # Embedded TED video
 516         {
 517             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 518             'md5': '65fdff94098e4a607385a60c5177c638',
 519             'info_dict': {
 520                 'id': '1969',
 521                 'ext': 'mp4',
 522                 'title': 'Hidden miracles of the natural world',
 523                 'uploader': 'Louie Schwartzberg',
 524                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 525             }
 526         },
 527         # Embedded Ustream video
 528         {
 529             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
 530             'md5': '27b99cdb639c9b12a79bca876a073417',
 531             'info_dict': {
 532                 'id': '45734260',
 533                 'ext': 'flv',
 534                 'uploader': 'AU SPA:  The NSA and Privacy',
 535                 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
 536             }
 537         },
 538         # nowvideo embed hidden behind percent encoding
 539         {
 540             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 541             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 542             'info_dict': {
 543                 'id': '06e53103ca9aa',
 544                 'ext': 'flv',
 545                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 546                 'description': 'No description',
 547             },
 548         },
 549         # arte embed
 550         {
 551             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 552             'md5': '7653032cbb25bf6c80d80f217055fa43',
 553             'info_dict': {
 554                 'id': '048195-004_PLUS7-F',
 555                 'ext': 'flv',
 556                 'title': 'X:enius',
 557                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 558                 'upload_date': '20140320',
 559             },
 560             'params': {
 561                 'skip_download': 'Requires rtmpdump'
 562             }
 563         },
 564         # francetv embed
 565         {
 566             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 567             'info_dict': {
 568                 'id': 'EV_30231',
 569                 'ext': 'mp4',
 570                 'title': 'Alcaline, le concert avec Calogero',
 571                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 572                 'upload_date': '20150226',
 573                 'timestamp': 1424989860,
 574                 'duration': 5400,
 575             },
 576             'params': {
 577                 # m3u8 downloads
 578                 'skip_download': True,
 579             },
 580             'expected_warnings': [
 581                 'Forbidden'
 582             ]
 583         },
 584         # Condé Nast embed
 585         {
 586             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 587             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 588             'info_dict': {
 589                 'id': '53501be369702d3275860000',
 590                 'ext': 'mp4',
 591                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 592             }
 593         },
 594         # Dailymotion embed
 595         {
 596             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 597             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 598             'info_dict': {
 599                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 600                 'ext': 'mp4',
 601                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 602                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 603                 'uploader': 'Spi0n',
 604                 'uploader_id': 'xgditw',
 605                 'upload_date': '20140425',
 606                 'timestamp': 1398441542,
 607             },
 608             'add_ie': ['Dailymotion'],
 609         },
 610         # YouTube embed
 611         {
 612             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 613             'info_dict': {
 614                 'id': 'FXRb4ykk4S0',
 615                 'ext': 'mp4',
 616                 'title': 'The NBL Auction 2014',
 617                 'uploader': 'BADMINTON England',
 618                 'uploader_id': 'BADMINTONEvents',
 619                 'upload_date': '20140603',
 620                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 621             },
 622             'add_ie': ['Youtube'],
 623             'params': {
 624                 'skip_download': True,
 625             }
 626         },
 627         # MTVSercices embed
 628         {
 629             'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
 630             'md5': '35727f82f58c76d996fc188f9755b0d5',
 631             'info_dict': {
 632                 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
 633                 'ext': 'mp4',
 634                 'title': 'Review',
 635                 'description': 'Mario\'s life in the fast lane has never looked so good.',
 636             },
 637         },
 638         # YouTube embed via <data-embed-url="">
 639         {
 640             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 641             'info_dict': {
 642                 'id': '4vAffPZIT44',
 643                 'ext': 'mp4',
 644                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 645                 'uploader': 'Gameloft',
 646                 'uploader_id': 'gameloft',
 647                 'upload_date': '20140828',
 648                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 649             },
 650             'params': {
 651                 'skip_download': True,
 652             }
 653         },
 654         # Camtasia studio
 655         {
 656             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 657             'playlist': [{
 658                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 659                 'info_dict': {
 660                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 661                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 662                     'ext': 'flv',
 663                     'duration': 2235.90,
 664                 }
 665             }, {
 666                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 667                 'info_dict': {
 668                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 669                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 670                     'ext': 'flv',
 671                     'duration': 2235.93,
 672                 }
 673             }],
 674             'info_dict': {
 675                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 676             }
 677         },
 678         # Flowplayer
 679         {
 680             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 681             'md5': '9d65602bf31c6e20014319c7d07fba27',
 682             'info_dict': {
 683                 'id': '5123ea6d5e5a7',
 684                 'ext': 'mp4',
 685                 'age_limit': 18,
 686                 'uploader': 'www.handjobhub.com',
 687                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 688             }
 689         },
 690         # Multiple brightcove videos
 691         # https://github.com/rg3/youtube-dl/issues/2283
 692         {
 693             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 694             'info_dict': {
 695                 'id': 'always-never',
 696                 'title': 'Always / Never - The New Yorker',
 697             },
 698             'playlist_count': 3,
 699             'params': {
 700                 'extract_flat': False,
 701                 'skip_download': True,
 702             }
 703         },
 704         # MLB embed
 705         {
 706             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 707             'md5': '96f09a37e44da40dd083e12d9a683327',
 708             'info_dict': {
 709                 'id': '33322633',
 710                 'ext': 'mp4',
 711                 'title': 'Ump changes call to ball',
 712                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 713                 'duration': 48,
 714                 'timestamp': 1401537900,
 715                 'upload_date': '20140531',
 716                 'thumbnail': 're:^https?://.*\.jpg$',
 717             },
 718         },
 719         # Wistia embed
 720         {
 721             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 722             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 723             'info_dict': {
 724                 'id': '6e2wtrbdaf',
 725                 'ext': 'mov',
 726                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 727                 'description': 'a Paywall Videos video from Remilon',
 728                 'duration': 644.072,
 729                 'uploader': 'study.com',
 730                 'timestamp': 1459678540,
 731                 'upload_date': '20160403',
 732                 'filesize': 24687186,
 733             },
 734         },
 735         {
 736             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 737             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 738             'info_dict': {
 739                 'id': 'uxjb0lwrcz',
 740                 'ext': 'mp4',
 741                 'title': 'Conversation about Hexagonal Rails Part 1',
 742                 'description': 'a Martin Fowler video from ThoughtWorks',
 743                 'duration': 1715.0,
 744                 'uploader': 'thoughtworks.wistia.com',
 745                 'timestamp': 1401832161,
 746                 'upload_date': '20140603',
 747             },
 748         },
 749         # Wistia standard embed (async)
 750         {
 751             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 752             'info_dict': {
 753                 'id': '807fafadvk',
 754                 'ext': 'mp4',
 755                 'title': 'Drip Brennan Dunn Workshop',
 756                 'description': 'a JV Webinars video from getdrip-1',
 757                 'duration': 4986.95,
 758                 'timestamp': 1463607249,
 759                 'upload_date': '20160518',
 760             },
 761             'params': {
 762                 'skip_download': True,
 763             }
 764         },
 765         # Soundcloud embed
 766         {
 767             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 768             'info_dict': {
 769                 'id': '174391317',
 770                 'ext': 'mp3',
 771                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 772                 'uploader': 'Sophos Security',
 773                 'title': 'Chet Chat 171 - Oct 29, 2014',
 774                 'upload_date': '20141029',
 775             }
 776         },
 777         # Livestream embed
 778         {
 779             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 780             'info_dict': {
 781                 'id': '67864563',
 782                 'ext': 'flv',
 783                 'upload_date': '20141112',
 784                 'title': 'Rosetta #CometLanding webcast HL 10',
 785             }
 786         },
 787         # Another Livestream embed, without 'new.' in URL
 788         {
 789             'url': 'https://www.freespeech.org/',
 790             'info_dict': {
 791                 'id': '123537347',
 792                 'ext': 'mp4',
 793                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 794             },
 795             'params': {
 796                 # Live stream
 797                 'skip_download': True,
 798             },
 799         },
 800         # LazyYT
 801         {
 802             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
 803             'info_dict': {
 804                 'id': '1986',
 805                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
 806             },
 807             'playlist_mincount': 2,
 808         },
 809         # Cinchcast embed
 810         {
 811             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
 812             'info_dict': {
 813                 'id': '7141703',
 814                 'ext': 'mp3',
 815                 'upload_date': '20141126',
 816                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
 817             }
 818         },
 819         # Cinerama player
 820         {
 821             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
 822             'info_dict': {
 823                 'id': '730m_DandD_1901_512k',
 824                 'ext': 'mp4',
 825                 'uploader': 'www.abc.net.au',
 826                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
 827             }
 828         },
 829         # embedded viddler video
 830         {
 831             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
 832             'info_dict': {
 833                 'id': '4d03aad9',
 834                 'ext': 'mp4',
 835                 'uploader': 'deadspin',
 836                 'title': 'WALL-TO-GORTAT',
 837                 'timestamp': 1422285291,
 838                 'upload_date': '20150126',
 839             },
 840             'add_ie': ['Viddler'],
 841         },
 842         # Libsyn embed
 843         {
 844             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
 845             'info_dict': {
 846                 'id': '3377616',
 847                 'ext': 'mp3',
 848                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
 849                 'description': 'md5:601cb790edd05908957dae8aaa866465',
 850                 'upload_date': '20150220',
 851             },
 852         },
 853         # jwplayer YouTube
 854         {
 855             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
 856             'info_dict': {
 857                 'id': 'Mrj4DVp2zeA',
 858                 'ext': 'mp4',
 859                 'upload_date': '20150212',
 860                 'uploader': 'The National Archives UK',
 861                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
 862                 'uploader_id': 'NationalArchives08',
 863                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
 864             },
 865         },
 866         # rtl.nl embed
 867         {
 868             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
 869             'playlist_mincount': 5,
 870             'info_dict': {
 871                 'id': 'aanslagen-kopenhagen',
 872                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
 873             }
 874         },
 875         # Zapiks embed
 876         {
 877             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
 878             'info_dict': {
 879                 'id': '118046',
 880                 'ext': 'mp4',
 881                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
 882             }
 883         },
 884         # Kaltura embed
 885         {
 886             'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
 887             'info_dict': {
 888                 'id': '1_eergr3h1',
 889                 'ext': 'mp4',
 890                 'upload_date': '20150226',
 891                 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
 892                 'timestamp': int,
 893                 'title': 'John Carlson Postgame 2/25/15',
 894             },
 895         },
 896         # Kaltura embed (different embed code)
 897         {
 898             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
 899             'info_dict': {
 900                 'id': '1_a52wc67y',
 901                 'ext': 'flv',
 902                 'upload_date': '20150127',
 903                 'uploader_id': 'PremierMedia',
 904                 'timestamp': int,
 905                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
 906             },
 907         },
 908         # Kaltura embed protected with referrer
 909         {
 910             'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
 911             'info_dict': {
 912                 'id': '1_g4fbemnq',
 913                 'ext': 'mp4',
 914                 'title': 'Violetta - Achter De Schermen - Ruggero',
 915                 'description': 'Achter de schermen met Ruggero',
 916                 'timestamp': 1435133761,
 917                 'upload_date': '20150624',
 918                 'uploader_id': 'echojecka',
 919             },
 920         },
 921         # Eagle.Platform embed (generic URL)
 922         {
 923             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
 924             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 925             'info_dict': {
 926                 'id': '227304',
 927                 'ext': 'mp4',
 928                 'title': 'Навальный вышел на свободу',
 929                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
 930                 'thumbnail': 're:^https?://.*\.jpg$',
 931                 'duration': 87,
 932                 'view_count': int,
 933                 'age_limit': 0,
 934             },
 935         },
 936         # ClipYou (Eagle.Platform) embed (custom URL)
 937         {
 938             'url': 'http://muz-tv.ru/play/7129/',
 939             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 940             'info_dict': {
 941                 'id': '12820',
 942                 'ext': 'mp4',
 943                 'title': "'O Sole Mio",
 944                 'thumbnail': 're:^https?://.*\.jpg$',
 945                 'duration': 216,
 946                 'view_count': int,
 947             },
 948         },
 949         # Pladform embed
 950         {
 951             'url': 'http://muz-tv.ru/kinozal/view/7400/',
 952             'info_dict': {
 953                 'id': '100183293',
 954                 'ext': 'mp4',
 955                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
 956                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
 957                 'thumbnail': 're:^https?://.*\.jpg$',
 958                 'duration': 694,
 959                 'age_limit': 0,
 960             },
 961         },
 962         # Playwire embed
 963         {
 964             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
 965             'info_dict': {
 966                 'id': '3519514',
 967                 'ext': 'mp4',
 968                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
 969                 'thumbnail': 're:^https?://.*\.png$',
 970                 'duration': 45.115,
 971             },
 972         },
 973         # 5min embed
 974         {
 975             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
 976             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
 977             'info_dict': {
 978                 'id': '518726732',
 979                 'ext': 'mp4',
 980                 'title': 'Facebook Creates "On This Day" | Crunch Report',
 981             },
 982         },
 983         # SVT embed
 984         {
 985             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
 986             'info_dict': {
 987                 'id': '2900353',
 988                 'ext': 'flv',
 989                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
 990                 'duration': 27,
 991                 'age_limit': 0,
 992             },
 993         },
 994         # Crooks and Liars embed
 995         {
 996             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
 997             'info_dict': {
 998                 'id': '8RUoRhRi',
 999                 'ext': 'mp4',
1000                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1001                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1002                 'timestamp': 1428207000,
1003                 'upload_date': '20150405',
1004                 'uploader': 'Heather',
1005             },
1006         },
1007         # Crooks and Liars external embed
1008         {
1009             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1010             'info_dict': {
1011                 'id': 'MTE3MjUtMzQ2MzA',
1012                 'ext': 'mp4',
1013                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1014                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1015                 'timestamp': 1265032391,
1016                 'upload_date': '20100201',
1017                 'uploader': 'Heather',
1018             },
1019         },
1020         # NBC Sports vplayer embed
1021         {
1022             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1023             'info_dict': {
1024                 'id': 'ln7x1qSThw4k',
1025                 'ext': 'flv',
1026                 'title': "PFT Live: New leader in the 'new-look' defense",
1027                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1028                 'uploader': 'NBCU-SPORTS',
1029                 'upload_date': '20140107',
1030                 'timestamp': 1389118457,
1031             },
1032         },
1033         # UDN embed
1034         {
1035             'url': 'http://www.udn.com/news/story/7314/822787',
1036             'md5': 'fd2060e988c326991037b9aff9df21a6',
1037             'info_dict': {
1038                 'id': '300346',
1039                 'ext': 'mp4',
1040                 'title': '中一中男師變性 全校師生力挺',
1041                 'thumbnail': 're:^https?://.*\.jpg$',
1042             }
1043         },
1044         # Ooyala embed
1045         {
1046             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1047             'info_dict': {
1048                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1049                 'ext': 'mp4',
1050                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1051                 'title': 'This is what separates the Excel masters from the wannabes',
1052                 'duration': 191.933,
1053             },
1054             'params': {
1055                 # m3u8 downloads
1056                 'skip_download': True,
1057             }
1058         },
1059         # Contains a SMIL manifest
1060         {
1061             'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
1062             'info_dict': {
1063                 'id': 'file',
1064                 'ext': 'flv',
1065                 'title': '+ Football: Lottery Champions League Europe',
1066                 'uploader': 'www.telewebion.com',
1067             },
1068             'params': {
1069                 # rtmpe downloads
1070                 'skip_download': True,
1071             }
1072         },
1073         # Brightcove URL in single quotes
1074         {
1075             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1076             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1077             'info_dict': {
1078                 'id': '4255764656001',
1079                 'ext': 'mp4',
1080                 'title': 'SN Presents: Russell Martin, World Citizen',
1081                 '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.',
1082                 'uploader': 'Rogers Sportsnet',
1083                 'uploader_id': '1704050871',
1084                 'upload_date': '20150525',
1085                 'timestamp': 1432570283,
1086             },
1087         },
1088         # Dailymotion Cloud video
1089         {
1090             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1091             'md5': '49444254273501a64675a7e68c502681',
1092             'info_dict': {
1093                 'id': '5585de919473990de4bee11b',
1094                 'ext': 'mp4',
1095                 'title': 'Le débat',
1096                 'thumbnail': 're:^https?://.*\.jpe?g$',
1097             }
1098         },
1099         # OnionStudios embed
1100         {
1101             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1102             'info_dict': {
1103                 'id': '2855',
1104                 'ext': 'mp4',
1105                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1106                 'thumbnail': 're:^https?://.*\.jpe?g$',
1107                 'uploader': 'ClickHole',
1108                 'uploader_id': 'clickhole',
1109             }
1110         },
1111         # SnagFilms embed
1112         {
1113             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1114             'info_dict': {
1115                 'id': '74849a00-85a9-11e1-9660-123139220831',
1116                 'ext': 'mp4',
1117                 'title': '#whilewewatch',
1118             }
1119         },
1120         # AdobeTVVideo embed
1121         {
1122             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1123             'md5': '43662b577c018ad707a63766462b1e87',
1124             'info_dict': {
1125                 'id': '2456',
1126                 'ext': 'mp4',
1127                 'title': 'New experience with Acrobat DC',
1128                 'description': 'New experience with Acrobat DC',
1129                 'duration': 248.667,
1130             },
1131         },
1132         # ScreenwaveMedia embed
1133         {
1134             'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1135             'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1136             'info_dict': {
1137                 'id': 'cinemasnob-55d26273809dd',
1138                 'ext': 'mp4',
1139                 'title': 'cinemasnob',
1140             },
1141         },
1142         # BrightcoveInPageEmbed embed
1143         {
1144             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1145             'info_dict': {
1146                 'id': '4238694884001',
1147                 'ext': 'flv',
1148                 'title': 'Tabletop: Dread, Last Thoughts',
1149                 'description': 'Tabletop: Dread, Last Thoughts',
1150                 'duration': 51690,
1151             },
1152         },
1153         # JWPlayer with M3U8
1154         {
1155             'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1156             'info_dict': {
1157                 'id': 'playlist',
1158                 'ext': 'mp4',
1159                 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1160                 'uploader': 'ren.tv',
1161             },
1162             'params': {
1163                 # m3u8 downloads
1164                 'skip_download': True,
1165             }
1166         },
1167         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1168         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1169         {
1170             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1171             'info_dict': {
1172                 'id': '4785848093001',
1173                 'ext': 'mp4',
1174                 'title': 'The Cardinal Pell Interview',
1175                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1176                 'uploader': 'GlobeCast Australia - GlobeStream',
1177                 'uploader_id': '2733773828001',
1178                 'upload_date': '20160304',
1179                 'timestamp': 1457083087,
1180             },
1181             'params': {
1182                 # m3u8 downloads
1183                 'skip_download': True,
1184             },
1185         },
1186         # Another form of arte.tv embed
1187         {
1188             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1189             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1190             'info_dict': {
1191                 'id': '030273-562_PLUS7-F',
1192                 'ext': 'mp4',
1193                 'title': 'ARTE Reportage - Nulle part, en France',
1194                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1195                 'upload_date': '20160409',
1196             },
1197         },
1198         # LiveLeak embed
1199         {
1200             'url': 'http://www.wykop.pl/link/3088787/',
1201             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1202             'info_dict': {
1203                 'id': '874_1459135191',
1204                 'ext': 'mp4',
1205                 'title': 'Man shows poor quality of new apartment building',
1206                 'description': 'The wall is like a sand pile.',
1207                 'uploader': 'Lake8737',
1208             }
1209         },
1210         # Duplicated embedded video URLs
1211         {
1212             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1213             'info_dict': {
1214                 'id': '149298443_480_16c25b74_2',
1215                 'ext': 'mp4',
1216                 'title': 'vs. Blue Orange Spring Game',
1217                 'uploader': 'www.hudl.com',
1218             },
1219         },
1220     ]
1221
1222     def report_following_redirect(self, new_url):
1223         """Report information extraction."""
1224         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1225
1226     def _extract_rss(self, url, video_id, doc):
1227         playlist_title = doc.find('./channel/title').text
1228         playlist_desc_el = doc.find('./channel/description')
1229         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1230
1231         entries = []
1232         for it in doc.findall('./channel/item'):
1233             next_url = xpath_text(it, 'link', fatal=False)
1234             if not next_url:
1235                 enclosure_nodes = it.findall('./enclosure')
1236                 for e in enclosure_nodes:
1237                     next_url = e.attrib.get('url')
1238                     if next_url:
1239                         break
1240
1241             if not next_url:
1242                 continue
1243
1244             entries.append({
1245                 '_type': 'url',
1246                 'url': next_url,
1247                 'title': it.find('title').text,
1248             })
1249
1250         return {
1251             '_type': 'playlist',
1252             'id': url,
1253             'title': playlist_title,
1254             'description': playlist_desc,
1255             'entries': entries,
1256         }
1257
1258     def _extract_camtasia(self, url, video_id, webpage):
1259         """ Returns None if no camtasia video can be found. """
1260
1261         camtasia_cfg = self._search_regex(
1262             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1263             webpage, 'camtasia configuration file', default=None)
1264         if camtasia_cfg is None:
1265             return None
1266
1267         title = self._html_search_meta('DC.title', webpage, fatal=True)
1268
1269         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1270         camtasia_cfg = self._download_xml(
1271             camtasia_url, video_id,
1272             note='Downloading camtasia configuration',
1273             errnote='Failed to download camtasia configuration')
1274         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1275
1276         entries = []
1277         for n in fileset_node.getchildren():
1278             url_n = n.find('./uri')
1279             if url_n is None:
1280                 continue
1281
1282             entries.append({
1283                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1284                 'title': '%s - %s' % (title, n.tag),
1285                 'url': compat_urlparse.urljoin(url, url_n.text),
1286                 'duration': float_or_none(n.find('./duration').text),
1287             })
1288
1289         return {
1290             '_type': 'playlist',
1291             'entries': entries,
1292             'title': title,
1293         }
1294
1295     def _real_extract(self, url):
1296         if url.startswith('//'):
1297             return {
1298                 '_type': 'url',
1299                 'url': self.http_scheme() + url,
1300             }
1301
1302         parsed_url = compat_urlparse.urlparse(url)
1303         if not parsed_url.scheme:
1304             default_search = self._downloader.params.get('default_search')
1305             if default_search is None:
1306                 default_search = 'fixup_error'
1307
1308             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1309                 if '/' in url:
1310                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1311                     return self.url_result('http://' + url)
1312                 elif default_search != 'fixup_error':
1313                     if default_search == 'auto_warning':
1314                         if re.match(r'^(?:url|URL)$', url):
1315                             raise ExtractorError(
1316                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1317                                 expected=True)
1318                         else:
1319                             self._downloader.report_warning(
1320                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1321                     return self.url_result('ytsearch:' + url)
1322
1323             if default_search in ('error', 'fixup_error'):
1324                 raise ExtractorError(
1325                     '%r is not a valid URL. '
1326                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1327                     % (url, url), expected=True)
1328             else:
1329                 if ':' not in default_search:
1330                     default_search += ':'
1331                 return self.url_result(default_search + url)
1332
1333         url, smuggled_data = unsmuggle_url(url)
1334         force_videoid = None
1335         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1336         if smuggled_data and 'force_videoid' in smuggled_data:
1337             force_videoid = smuggled_data['force_videoid']
1338             video_id = force_videoid
1339         else:
1340             video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1341
1342         self.to_screen('%s: Requesting header' % video_id)
1343
1344         head_req = HEADRequest(url)
1345         head_response = self._request_webpage(
1346             head_req, video_id,
1347             note=False, errnote='Could not send HEAD request to %s' % url,
1348             fatal=False)
1349
1350         if head_response is not False:
1351             # Check for redirect
1352             new_url = head_response.geturl()
1353             if url != new_url:
1354                 self.report_following_redirect(new_url)
1355                 if force_videoid:
1356                     new_url = smuggle_url(
1357                         new_url, {'force_videoid': force_videoid})
1358                 return self.url_result(new_url)
1359
1360         full_response = None
1361         if head_response is False:
1362             request = sanitized_Request(url)
1363             request.add_header('Accept-Encoding', '*')
1364             full_response = self._request_webpage(request, video_id)
1365             head_response = full_response
1366
1367         info_dict = {
1368             'id': video_id,
1369             'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1370             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1371         }
1372
1373         # Check for direct link to a video
1374         content_type = head_response.headers.get('Content-Type', '').lower()
1375         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1376         if m:
1377             format_id = m.group('format_id')
1378             if format_id.endswith('mpegurl'):
1379                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1380             elif format_id == 'f4m':
1381                 formats = self._extract_f4m_formats(url, video_id)
1382             else:
1383                 formats = [{
1384                     'format_id': m.group('format_id'),
1385                     'url': url,
1386                     'vcodec': 'none' if m.group('type') == 'audio' else None
1387                 }]
1388                 info_dict['direct'] = True
1389             self._sort_formats(formats)
1390             info_dict['formats'] = formats
1391             return info_dict
1392
1393         if not self._downloader.params.get('test', False) and not is_intentional:
1394             force = self._downloader.params.get('force_generic_extractor', False)
1395             self._downloader.report_warning(
1396                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1397
1398         if not full_response:
1399             request = sanitized_Request(url)
1400             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1401             # making it impossible to download only chunk of the file (yet we need only 512kB to
1402             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1403             # that will always result in downloading the whole file that is not desirable.
1404             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1405             # to accept raw bytes and being able to download only a chunk.
1406             # It may probably better to solve this by checking Content-Type for application/octet-stream
1407             # after HEAD request finishes, but not sure if we can rely on this.
1408             request.add_header('Accept-Encoding', '*')
1409             full_response = self._request_webpage(request, video_id)
1410
1411         first_bytes = full_response.read(512)
1412
1413         # Is it an M3U playlist?
1414         if first_bytes.startswith(b'#EXTM3U'):
1415             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1416             self._sort_formats(info_dict['formats'])
1417             return info_dict
1418
1419         # Maybe it's a direct link to a video?
1420         # Be careful not to download the whole thing!
1421         if not is_html(first_bytes):
1422             self._downloader.report_warning(
1423                 'URL could be a direct video link, returning it as such.')
1424             info_dict.update({
1425                 'direct': True,
1426                 'url': url,
1427             })
1428             return info_dict
1429
1430         webpage = self._webpage_read_content(
1431             full_response, url, video_id, prefix=first_bytes)
1432
1433         self.report_extraction(video_id)
1434
1435         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1436         try:
1437             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1438             if doc.tag == 'rss':
1439                 return self._extract_rss(url, video_id, doc)
1440             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1441                 smil = self._parse_smil(doc, url, video_id)
1442                 self._sort_formats(smil['formats'])
1443                 return smil
1444             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1445                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1446             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1447                 info_dict['formats'] = self._parse_mpd_formats(
1448                     doc, video_id, mpd_base_url=url.rpartition('/')[0])
1449                 self._sort_formats(info_dict['formats'])
1450                 return info_dict
1451             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1452                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1453                 self._sort_formats(info_dict['formats'])
1454                 return info_dict
1455         except compat_xml_parse_error:
1456             pass
1457
1458         # Is it a Camtasia project?
1459         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1460         if camtasia_res is not None:
1461             return camtasia_res
1462
1463         # Sometimes embedded video player is hidden behind percent encoding
1464         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1465         # Unescaping the whole page allows to handle those cases in a generic way
1466         webpage = compat_urllib_parse_unquote(webpage)
1467
1468         # it's tempting to parse this further, but you would
1469         # have to take into account all the variations like
1470         #   Video Title - Site Name
1471         #   Site Name | Video Title
1472         #   Video Title - Tagline | Site Name
1473         # and so on and so forth; it's just not practical
1474         video_title = self._og_search_title(
1475             webpage, default=None) or self._html_search_regex(
1476             r'(?s)<title>(.*?)</title>', webpage, 'video title',
1477             default='video')
1478
1479         # Try to detect age limit automatically
1480         age_limit = self._rta_search(webpage)
1481         # And then there are the jokers who advertise that they use RTA,
1482         # but actually don't.
1483         AGE_LIMIT_MARKERS = [
1484             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1485         ]
1486         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1487             age_limit = 18
1488
1489         # video uploader is domain name
1490         video_uploader = self._search_regex(
1491             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1492
1493         video_description = self._og_search_description(webpage, default=None)
1494         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1495
1496         # Helper method
1497         def _playlist_from_matches(matches, getter=None, ie=None):
1498             urlrs = orderedSet(
1499                 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1500                 for m in matches)
1501             return self.playlist_result(
1502                 urlrs, playlist_id=video_id, playlist_title=video_title)
1503
1504         # Look for Brightcove Legacy Studio embeds
1505         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1506         if bc_urls:
1507             self.to_screen('Brightcove video detected.')
1508             entries = [{
1509                 '_type': 'url',
1510                 'url': smuggle_url(bc_url, {'Referer': url}),
1511                 'ie_key': 'BrightcoveLegacy'
1512             } for bc_url in bc_urls]
1513
1514             return {
1515                 '_type': 'playlist',
1516                 'title': video_title,
1517                 'id': video_id,
1518                 'entries': entries,
1519             }
1520
1521         # Look for Brightcove New Studio embeds
1522         bc_urls = BrightcoveNewIE._extract_urls(webpage)
1523         if bc_urls:
1524             return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1525
1526         # Look for ThePlatform embeds
1527         tp_urls = ThePlatformIE._extract_urls(webpage)
1528         if tp_urls:
1529             return _playlist_from_matches(tp_urls, ie='ThePlatform')
1530
1531         # Look for embedded rtl.nl player
1532         matches = re.findall(
1533             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1534             webpage)
1535         if matches:
1536             return _playlist_from_matches(matches, ie='RtlNl')
1537
1538         vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1539         if vimeo_url is not None:
1540             return self.url_result(vimeo_url)
1541
1542         vid_me_embed_url = self._search_regex(
1543             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1544             webpage, 'vid.me embed', default=None)
1545         if vid_me_embed_url is not None:
1546             return self.url_result(vid_me_embed_url, 'Vidme')
1547
1548         # Look for embedded YouTube player
1549         matches = re.findall(r'''(?x)
1550             (?:
1551                 <iframe[^>]+?src=|
1552                 data-video-url=|
1553                 <embed[^>]+?src=|
1554                 embedSWF\(?:\s*|
1555                 new\s+SWFObject\(
1556             )
1557             (["\'])
1558                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1559                 (?:embed|v|p)/.+?)
1560             \1''', webpage)
1561         if matches:
1562             return _playlist_from_matches(
1563                 matches, lambda m: unescapeHTML(m[1]))
1564
1565         # Look for lazyYT YouTube embed
1566         matches = re.findall(
1567             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1568         if matches:
1569             return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1570
1571         # Look for embedded Dailymotion player
1572         matches = re.findall(
1573             r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1574         if matches:
1575             return _playlist_from_matches(
1576                 matches, lambda m: unescapeHTML(m[1]))
1577
1578         # Look for embedded Dailymotion playlist player (#3822)
1579         m = re.search(
1580             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1581         if m:
1582             playlists = re.findall(
1583                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1584             if playlists:
1585                 return _playlist_from_matches(
1586                     playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1587
1588         # Look for embedded Wistia player
1589         match = re.search(
1590             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1591         if match:
1592             embed_url = self._proto_relative_url(
1593                 unescapeHTML(match.group('url')))
1594             return {
1595                 '_type': 'url_transparent',
1596                 'url': embed_url,
1597                 'ie_key': 'Wistia',
1598                 'uploader': video_uploader,
1599             }
1600
1601         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1602         if match:
1603             return {
1604                 '_type': 'url_transparent',
1605                 'url': 'wistia:%s' % match.group('id'),
1606                 'ie_key': 'Wistia',
1607                 'uploader': video_uploader,
1608             }
1609
1610         match = re.search(
1611             r'''(?sx)
1612                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1613                 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1614             ''', webpage)
1615         if match:
1616             return self.url_result(self._proto_relative_url(
1617                 'wistia:%s' % match.group('id')), 'Wistia')
1618
1619         # Look for SVT player
1620         svt_url = SVTIE._extract_url(webpage)
1621         if svt_url:
1622             return self.url_result(svt_url, 'SVT')
1623
1624         # Look for embedded condenast player
1625         matches = re.findall(
1626             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1627             webpage)
1628         if matches:
1629             return {
1630                 '_type': 'playlist',
1631                 'entries': [{
1632                     '_type': 'url',
1633                     'ie_key': 'CondeNast',
1634                     'url': ma,
1635                 } for ma in matches],
1636                 'title': video_title,
1637                 'id': video_id,
1638             }
1639
1640         # Look for Bandcamp pages with custom domain
1641         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1642         if mobj is not None:
1643             burl = unescapeHTML(mobj.group(1))
1644             # Don't set the extractor because it can be a track url or an album
1645             return self.url_result(burl)
1646
1647         # Look for embedded Vevo player
1648         mobj = re.search(
1649             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1650         if mobj is not None:
1651             return self.url_result(mobj.group('url'))
1652
1653         # Look for embedded Viddler player
1654         mobj = re.search(
1655             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1656             webpage)
1657         if mobj is not None:
1658             return self.url_result(mobj.group('url'))
1659
1660         # Look for NYTimes player
1661         mobj = re.search(
1662             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1663             webpage)
1664         if mobj is not None:
1665             return self.url_result(mobj.group('url'))
1666
1667         # Look for Libsyn player
1668         mobj = re.search(
1669             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1670         if mobj is not None:
1671             return self.url_result(mobj.group('url'))
1672
1673         # Look for Ooyala videos
1674         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1675                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1676                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1677                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1678         if mobj is not None:
1679             return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1680
1681         # Look for multiple Ooyala embeds on SBN network websites
1682         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1683         if mobj is not None:
1684             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1685             if embeds:
1686                 return _playlist_from_matches(
1687                     embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1688
1689         # Look for Aparat videos
1690         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1691         if mobj is not None:
1692             return self.url_result(mobj.group(1), 'Aparat')
1693
1694         # Look for MPORA videos
1695         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1696         if mobj is not None:
1697             return self.url_result(mobj.group(1), 'Mpora')
1698
1699         # Look for embedded NovaMov-based player
1700         mobj = re.search(
1701             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1702                     (?P<url>http://(?:(?:embed|www)\.)?
1703                         (?:novamov\.com|
1704                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
1705                            videoweed\.(?:es|com)|
1706                            movshare\.(?:net|sx|ag)|
1707                            divxstage\.(?:eu|net|ch|co|at|ag))
1708                         /embed\.php.+?)\1''', webpage)
1709         if mobj is not None:
1710             return self.url_result(mobj.group('url'))
1711
1712         # Look for embedded Facebook player
1713         mobj = re.search(
1714             r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1715         if mobj is not None:
1716             return self.url_result(mobj.group('url'), 'Facebook')
1717
1718         # Look for embedded VK player
1719         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1720         if mobj is not None:
1721             return self.url_result(mobj.group('url'), 'VK')
1722
1723         # Look for embedded Odnoklassniki player
1724         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1725         if mobj is not None:
1726             return self.url_result(mobj.group('url'), 'Odnoklassniki')
1727
1728         # Look for embedded ivi player
1729         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1730         if mobj is not None:
1731             return self.url_result(mobj.group('url'), 'Ivi')
1732
1733         # Look for embedded Huffington Post player
1734         mobj = re.search(
1735             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1736         if mobj is not None:
1737             return self.url_result(mobj.group('url'), 'HuffPost')
1738
1739         # Look for embed.ly
1740         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1741         if mobj is not None:
1742             return self.url_result(mobj.group('url'))
1743         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1744         if mobj is not None:
1745             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1746
1747         # Look for funnyordie embed
1748         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1749         if matches:
1750             return _playlist_from_matches(
1751                 matches, getter=unescapeHTML, ie='FunnyOrDie')
1752
1753         # Look for BBC iPlayer embed
1754         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1755         if matches:
1756             return _playlist_from_matches(matches, ie='BBCCoUk')
1757
1758         # Look for embedded RUTV player
1759         rutv_url = RUTVIE._extract_url(webpage)
1760         if rutv_url:
1761             return self.url_result(rutv_url, 'RUTV')
1762
1763         # Look for embedded TVC player
1764         tvc_url = TVCIE._extract_url(webpage)
1765         if tvc_url:
1766             return self.url_result(tvc_url, 'TVC')
1767
1768         # Look for embedded SportBox player
1769         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1770         if sportbox_urls:
1771             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1772
1773         # Look for embedded PornHub player
1774         pornhub_url = PornHubIE._extract_url(webpage)
1775         if pornhub_url:
1776             return self.url_result(pornhub_url, 'PornHub')
1777
1778         # Look for embedded XHamster player
1779         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1780         if xhamster_urls:
1781             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1782
1783         # Look for embedded TNAFlixNetwork player
1784         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1785         if tnaflix_urls:
1786             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1787
1788         # Look for embedded Tvigle player
1789         mobj = re.search(
1790             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1791         if mobj is not None:
1792             return self.url_result(mobj.group('url'), 'Tvigle')
1793
1794         # Look for embedded TED player
1795         mobj = re.search(
1796             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1797         if mobj is not None:
1798             return self.url_result(mobj.group('url'), 'TED')
1799
1800         # Look for embedded Ustream videos
1801         mobj = re.search(
1802             r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1803         if mobj is not None:
1804             return self.url_result(mobj.group('url'), 'Ustream')
1805
1806         # Look for embedded arte.tv player
1807         mobj = re.search(
1808             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1809             webpage)
1810         if mobj is not None:
1811             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1812
1813         # Look for embedded francetv player
1814         mobj = re.search(
1815             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1816             webpage)
1817         if mobj is not None:
1818             return self.url_result(mobj.group('url'))
1819
1820         # Look for embedded smotri.com player
1821         smotri_url = SmotriIE._extract_url(webpage)
1822         if smotri_url:
1823             return self.url_result(smotri_url, 'Smotri')
1824
1825         # Look for embedded Myvi.ru player
1826         myvi_url = MyviIE._extract_url(webpage)
1827         if myvi_url:
1828             return self.url_result(myvi_url)
1829
1830         # Look for embedded soundcloud player
1831         mobj = re.search(
1832             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1833             webpage)
1834         if mobj is not None:
1835             url = unescapeHTML(mobj.group('url'))
1836             return self.url_result(url)
1837
1838         # Look for embedded vulture.com player
1839         mobj = re.search(
1840             r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1841             webpage)
1842         if mobj is not None:
1843             url = unescapeHTML(mobj.group('url'))
1844             return self.url_result(url, ie='Vulture')
1845
1846         # Look for embedded mtvservices player
1847         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1848         if mtvservices_url:
1849             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1850
1851         # Look for embedded yahoo player
1852         mobj = re.search(
1853             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1854             webpage)
1855         if mobj is not None:
1856             return self.url_result(mobj.group('url'), 'Yahoo')
1857
1858         # Look for embedded sbs.com.au player
1859         mobj = re.search(
1860             r'''(?x)
1861             (?:
1862                 <meta\s+property="og:video"\s+content=|
1863                 <iframe[^>]+?src=
1864             )
1865             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1866             webpage)
1867         if mobj is not None:
1868             return self.url_result(mobj.group('url'), 'SBS')
1869
1870         # Look for embedded Cinchcast player
1871         mobj = re.search(
1872             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1873             webpage)
1874         if mobj is not None:
1875             return self.url_result(mobj.group('url'), 'Cinchcast')
1876
1877         mobj = re.search(
1878             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1879             webpage)
1880         if not mobj:
1881             mobj = re.search(
1882                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1883                 webpage)
1884         if mobj is not None:
1885             return self.url_result(mobj.group('url'), 'MLB')
1886
1887         mobj = re.search(
1888             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1889             webpage)
1890         if mobj is not None:
1891             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1892
1893         mobj = re.search(
1894             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1895             webpage)
1896         if mobj is not None:
1897             return self.url_result(mobj.group('url'), 'Livestream')
1898
1899         # Look for Zapiks embed
1900         mobj = re.search(
1901             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1902         if mobj is not None:
1903             return self.url_result(mobj.group('url'), 'Zapiks')
1904
1905         # Look for Kaltura embeds
1906         mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1907                 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1908         if mobj is not None:
1909             return self.url_result(smuggle_url(
1910                 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1911                 {'source_url': url}), 'Kaltura')
1912
1913         # Look for Eagle.Platform embeds
1914         mobj = re.search(
1915             r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1916         if mobj is not None:
1917             return self.url_result(mobj.group('url'), 'EaglePlatform')
1918
1919         # Look for ClipYou (uses Eagle.Platform) embeds
1920         mobj = re.search(
1921             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1922         if mobj is not None:
1923             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1924
1925         # Look for Pladform embeds
1926         pladform_url = PladformIE._extract_url(webpage)
1927         if pladform_url:
1928             return self.url_result(pladform_url)
1929
1930         # Look for Videomore embeds
1931         videomore_url = VideomoreIE._extract_url(webpage)
1932         if videomore_url:
1933             return self.url_result(videomore_url)
1934
1935         # Look for Playwire embeds
1936         mobj = re.search(
1937             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1938         if mobj is not None:
1939             return self.url_result(mobj.group('url'))
1940
1941         # Look for 5min embeds
1942         mobj = re.search(
1943             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1944         if mobj is not None:
1945             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1946
1947         # Look for Crooks and Liars embeds
1948         mobj = re.search(
1949             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1950         if mobj is not None:
1951             return self.url_result(mobj.group('url'))
1952
1953         # Look for NBC Sports VPlayer embeds
1954         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1955         if nbc_sports_url:
1956             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1957
1958         # Look for Google Drive embeds
1959         google_drive_url = GoogleDriveIE._extract_url(webpage)
1960         if google_drive_url:
1961             return self.url_result(google_drive_url, 'GoogleDrive')
1962
1963         # Look for UDN embeds
1964         mobj = re.search(
1965             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1966         if mobj is not None:
1967             return self.url_result(
1968                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1969
1970         # Look for Senate ISVP iframe
1971         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1972         if senate_isvp_url:
1973             return self.url_result(senate_isvp_url, 'SenateISVP')
1974
1975         # Look for Dailymotion Cloud videos
1976         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1977         if dmcloud_url:
1978             return self.url_result(dmcloud_url, 'DailymotionCloud')
1979
1980         # Look for OnionStudios embeds
1981         onionstudios_url = OnionStudiosIE._extract_url(webpage)
1982         if onionstudios_url:
1983             return self.url_result(onionstudios_url)
1984
1985         # Look for ViewLift embeds
1986         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1987         if viewlift_url:
1988             return self.url_result(viewlift_url)
1989
1990         # Look for JWPlatform embeds
1991         jwplatform_url = JWPlatformIE._extract_url(webpage)
1992         if jwplatform_url:
1993             return self.url_result(jwplatform_url, 'JWPlatform')
1994
1995         # Look for ScreenwaveMedia embeds
1996         mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1997         if mobj is not None:
1998             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1999
2000         # Look for Digiteka embeds
2001         digiteka_url = DigitekaIE._extract_url(webpage)
2002         if digiteka_url:
2003             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2004
2005         # Look for Limelight embeds
2006         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2007         if mobj:
2008             lm = {
2009                 'Media': 'media',
2010                 'Channel': 'channel',
2011                 'ChannelList': 'channel_list',
2012             }
2013             return self.url_result('limelight:%s:%s' % (
2014                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2015
2016         # Look for AdobeTVVideo embeds
2017         mobj = re.search(
2018             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2019             webpage)
2020         if mobj is not None:
2021             return self.url_result(
2022                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2023                 'AdobeTVVideo')
2024
2025         # Look for Vine embeds
2026         mobj = re.search(
2027             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2028             webpage)
2029         if mobj is not None:
2030             return self.url_result(
2031                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2032
2033         # Look for Instagram embeds
2034         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2035         if instagram_embed_url is not None:
2036             return self.url_result(
2037                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2038
2039         # Look for LiveLeak embeds
2040         liveleak_url = LiveLeakIE._extract_url(webpage)
2041         if liveleak_url:
2042             return self.url_result(liveleak_url, 'LiveLeak')
2043
2044         # Look for 3Q SDN embeds
2045         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2046         if threeqsdn_url:
2047             return {
2048                 '_type': 'url_transparent',
2049                 'ie_key': ThreeQSDNIE.ie_key(),
2050                 'url': self._proto_relative_url(threeqsdn_url),
2051                 'title': video_title,
2052                 'description': video_description,
2053                 'thumbnail': video_thumbnail,
2054                 'uploader': video_uploader,
2055             }
2056
2057         def check_video(vurl):
2058             if YoutubeIE.suitable(vurl):
2059                 return True
2060             vpath = compat_urlparse.urlparse(vurl).path
2061             vext = determine_ext(vpath)
2062             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2063
2064         def filter_video(urls):
2065             return list(filter(check_video, urls))
2066
2067         # Start with something easy: JW Player in SWFObject
2068         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2069         if not found:
2070             # Look for gorilla-vid style embedding
2071             found = filter_video(re.findall(r'''(?sx)
2072                 (?:
2073                     jw_plugins|
2074                     JWPlayerOptions|
2075                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2076                 )
2077                 .*?
2078                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2079         if not found:
2080             # Broaden the search a little bit
2081             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2082         if not found:
2083             # Broaden the findall a little bit: JWPlayer JS loader
2084             found = filter_video(re.findall(
2085                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2086         if not found:
2087             # Flow player
2088             found = filter_video(re.findall(r'''(?xs)
2089                 flowplayer\("[^"]+",\s*
2090                     \{[^}]+?\}\s*,
2091                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2092                         ["']?url["']?\s*:\s*["']([^"']+)["']
2093             ''', webpage))
2094         if not found:
2095             # Cinerama player
2096             found = re.findall(
2097                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2098         if not found:
2099             # Try to find twitter cards info
2100             found = filter_video(re.findall(
2101                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2102         if not found:
2103             # We look for Open Graph info:
2104             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2105             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2106             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2107             if m_video_type is not None:
2108                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2109         if not found:
2110             # HTML5 video
2111             found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2112         if not found:
2113             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2114             found = re.search(
2115                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2116                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2117                 webpage)
2118             if not found:
2119                 # Look also in Refresh HTTP header
2120                 refresh_header = head_response.headers.get('Refresh')
2121                 if refresh_header:
2122                     # In python 2 response HTTP headers are bytestrings
2123                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2124                         refresh_header = refresh_header.decode('iso-8859-1')
2125                     found = re.search(REDIRECT_REGEX, refresh_header)
2126             if found:
2127                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2128                 self.report_following_redirect(new_url)
2129                 return {
2130                     '_type': 'url',
2131                     'url': new_url,
2132                 }
2133         if not found:
2134             raise UnsupportedError(url)
2135
2136         entries = []
2137         for video_url in orderedSet(found):
2138             video_url = unescapeHTML(video_url)
2139             video_url = video_url.replace('\\/', '/')
2140             video_url = compat_urlparse.urljoin(url, video_url)
2141             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2142
2143             # Sometimes, jwplayer extraction will result in a YouTube URL
2144             if YoutubeIE.suitable(video_url):
2145                 entries.append(self.url_result(video_url, 'Youtube'))
2146                 continue
2147
2148             # here's a fun little line of code for you:
2149             video_id = os.path.splitext(video_id)[0]
2150
2151             entry_info_dict = {
2152                 'id': video_id,
2153                 'uploader': video_uploader,
2154                 'title': video_title,
2155                 'age_limit': age_limit,
2156             }
2157
2158             ext = determine_ext(video_url)
2159             if ext == 'smil':
2160                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2161             elif ext == 'xspf':
2162                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2163             elif ext == 'm3u8':
2164                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2165             elif ext == 'mpd':
2166                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2167             elif ext == 'f4m':
2168                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2169             else:
2170                 entry_info_dict['url'] = video_url
2171
2172             if entry_info_dict.get('formats'):
2173                 self._sort_formats(entry_info_dict['formats'])
2174
2175             entries.append(entry_info_dict)
2176
2177         if len(entries) == 1:
2178             return entries[0]
2179         else:
2180             for num, e in enumerate(entries, start=1):
2181                 # 'url' results don't have a title
2182                 if e.get('title') is not None:
2183                     e['title'] = '%s (%d)' % (e['title'], num)
2184             return {
2185                 '_type': 'playlist',
2186                 'entries': entries,
2187             }