_ 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         # LazyYT
 788         {
 789             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
 790             'info_dict': {
 791                 'id': '1986',
 792                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
 793             },
 794             'playlist_mincount': 2,
 795         },
 796         # Cinchcast embed
 797         {
 798             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
 799             'info_dict': {
 800                 'id': '7141703',
 801                 'ext': 'mp3',
 802                 'upload_date': '20141126',
 803                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
 804             }
 805         },
 806         # Cinerama player
 807         {
 808             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
 809             'info_dict': {
 810                 'id': '730m_DandD_1901_512k',
 811                 'ext': 'mp4',
 812                 'uploader': 'www.abc.net.au',
 813                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
 814             }
 815         },
 816         # embedded viddler video
 817         {
 818             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
 819             'info_dict': {
 820                 'id': '4d03aad9',
 821                 'ext': 'mp4',
 822                 'uploader': 'deadspin',
 823                 'title': 'WALL-TO-GORTAT',
 824                 'timestamp': 1422285291,
 825                 'upload_date': '20150126',
 826             },
 827             'add_ie': ['Viddler'],
 828         },
 829         # Libsyn embed
 830         {
 831             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
 832             'info_dict': {
 833                 'id': '3377616',
 834                 'ext': 'mp3',
 835                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
 836                 'description': 'md5:601cb790edd05908957dae8aaa866465',
 837                 'upload_date': '20150220',
 838             },
 839         },
 840         # jwplayer YouTube
 841         {
 842             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
 843             'info_dict': {
 844                 'id': 'Mrj4DVp2zeA',
 845                 'ext': 'mp4',
 846                 'upload_date': '20150212',
 847                 'uploader': 'The National Archives UK',
 848                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
 849                 'uploader_id': 'NationalArchives08',
 850                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
 851             },
 852         },
 853         # rtl.nl embed
 854         {
 855             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
 856             'playlist_mincount': 5,
 857             'info_dict': {
 858                 'id': 'aanslagen-kopenhagen',
 859                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
 860             }
 861         },
 862         # Zapiks embed
 863         {
 864             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
 865             'info_dict': {
 866                 'id': '118046',
 867                 'ext': 'mp4',
 868                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
 869             }
 870         },
 871         # Kaltura embed
 872         {
 873             'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
 874             'info_dict': {
 875                 'id': '1_eergr3h1',
 876                 'ext': 'mp4',
 877                 'upload_date': '20150226',
 878                 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
 879                 'timestamp': int,
 880                 'title': 'John Carlson Postgame 2/25/15',
 881             },
 882         },
 883         # Kaltura embed (different embed code)
 884         {
 885             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
 886             'info_dict': {
 887                 'id': '1_a52wc67y',
 888                 'ext': 'flv',
 889                 'upload_date': '20150127',
 890                 'uploader_id': 'PremierMedia',
 891                 'timestamp': int,
 892                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
 893             },
 894         },
 895         # Kaltura embed protected with referrer
 896         {
 897             'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
 898             'info_dict': {
 899                 'id': '1_g4fbemnq',
 900                 'ext': 'mp4',
 901                 'title': 'Violetta - Achter De Schermen - Ruggero',
 902                 'description': 'Achter de schermen met Ruggero',
 903                 'timestamp': 1435133761,
 904                 'upload_date': '20150624',
 905                 'uploader_id': 'echojecka',
 906             },
 907         },
 908         # Eagle.Platform embed (generic URL)
 909         {
 910             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
 911             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 912             'info_dict': {
 913                 'id': '227304',
 914                 'ext': 'mp4',
 915                 'title': 'Навальный вышел на свободу',
 916                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
 917                 'thumbnail': 're:^https?://.*\.jpg$',
 918                 'duration': 87,
 919                 'view_count': int,
 920                 'age_limit': 0,
 921             },
 922         },
 923         # ClipYou (Eagle.Platform) embed (custom URL)
 924         {
 925             'url': 'http://muz-tv.ru/play/7129/',
 926             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
 927             'info_dict': {
 928                 'id': '12820',
 929                 'ext': 'mp4',
 930                 'title': "'O Sole Mio",
 931                 'thumbnail': 're:^https?://.*\.jpg$',
 932                 'duration': 216,
 933                 'view_count': int,
 934             },
 935         },
 936         # Pladform embed
 937         {
 938             'url': 'http://muz-tv.ru/kinozal/view/7400/',
 939             'info_dict': {
 940                 'id': '100183293',
 941                 'ext': 'mp4',
 942                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
 943                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
 944                 'thumbnail': 're:^https?://.*\.jpg$',
 945                 'duration': 694,
 946                 'age_limit': 0,
 947             },
 948         },
 949         # Playwire embed
 950         {
 951             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
 952             'info_dict': {
 953                 'id': '3519514',
 954                 'ext': 'mp4',
 955                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
 956                 'thumbnail': 're:^https?://.*\.png$',
 957                 'duration': 45.115,
 958             },
 959         },
 960         # 5min embed
 961         {
 962             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
 963             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
 964             'info_dict': {
 965                 'id': '518726732',
 966                 'ext': 'mp4',
 967                 'title': 'Facebook Creates "On This Day" | Crunch Report',
 968             },
 969         },
 970         # SVT embed
 971         {
 972             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
 973             'info_dict': {
 974                 'id': '2900353',
 975                 'ext': 'flv',
 976                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
 977                 'duration': 27,
 978                 'age_limit': 0,
 979             },
 980         },
 981         # Crooks and Liars embed
 982         {
 983             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
 984             'info_dict': {
 985                 'id': '8RUoRhRi',
 986                 'ext': 'mp4',
 987                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
 988                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
 989                 'timestamp': 1428207000,
 990                 'upload_date': '20150405',
 991                 'uploader': 'Heather',
 992             },
 993         },
 994         # Crooks and Liars external embed
 995         {
 996             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
 997             'info_dict': {
 998                 'id': 'MTE3MjUtMzQ2MzA',
 999                 'ext': 'mp4',
1000                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1001                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1002                 'timestamp': 1265032391,
1003                 'upload_date': '20100201',
1004                 'uploader': 'Heather',
1005             },
1006         },
1007         # NBC Sports vplayer embed
1008         {
1009             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1010             'info_dict': {
1011                 'id': 'ln7x1qSThw4k',
1012                 'ext': 'flv',
1013                 'title': "PFT Live: New leader in the 'new-look' defense",
1014                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1015                 'uploader': 'NBCU-SPORTS',
1016                 'upload_date': '20140107',
1017                 'timestamp': 1389118457,
1018             },
1019         },
1020         # UDN embed
1021         {
1022             'url': 'http://www.udn.com/news/story/7314/822787',
1023             'md5': 'fd2060e988c326991037b9aff9df21a6',
1024             'info_dict': {
1025                 'id': '300346',
1026                 'ext': 'mp4',
1027                 'title': '中一中男師變性 全校師生力挺',
1028                 'thumbnail': 're:^https?://.*\.jpg$',
1029             }
1030         },
1031         # Ooyala embed
1032         {
1033             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1034             'info_dict': {
1035                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1036                 'ext': 'mp4',
1037                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1038                 'title': 'This is what separates the Excel masters from the wannabes',
1039                 'duration': 191.933,
1040             },
1041             'params': {
1042                 # m3u8 downloads
1043                 'skip_download': True,
1044             }
1045         },
1046         # Contains a SMIL manifest
1047         {
1048             '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',
1049             'info_dict': {
1050                 'id': 'file',
1051                 'ext': 'flv',
1052                 'title': '+ Football: Lottery Champions League Europe',
1053                 'uploader': 'www.telewebion.com',
1054             },
1055             'params': {
1056                 # rtmpe downloads
1057                 'skip_download': True,
1058             }
1059         },
1060         # Brightcove URL in single quotes
1061         {
1062             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1063             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1064             'info_dict': {
1065                 'id': '4255764656001',
1066                 'ext': 'mp4',
1067                 'title': 'SN Presents: Russell Martin, World Citizen',
1068                 '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.',
1069                 'uploader': 'Rogers Sportsnet',
1070                 'uploader_id': '1704050871',
1071                 'upload_date': '20150525',
1072                 'timestamp': 1432570283,
1073             },
1074         },
1075         # Dailymotion Cloud video
1076         {
1077             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1078             'md5': '49444254273501a64675a7e68c502681',
1079             'info_dict': {
1080                 'id': '5585de919473990de4bee11b',
1081                 'ext': 'mp4',
1082                 'title': 'Le débat',
1083                 'thumbnail': 're:^https?://.*\.jpe?g$',
1084             }
1085         },
1086         # OnionStudios embed
1087         {
1088             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1089             'info_dict': {
1090                 'id': '2855',
1091                 'ext': 'mp4',
1092                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1093                 'thumbnail': 're:^https?://.*\.jpe?g$',
1094                 'uploader': 'ClickHole',
1095                 'uploader_id': 'clickhole',
1096             }
1097         },
1098         # SnagFilms embed
1099         {
1100             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1101             'info_dict': {
1102                 'id': '74849a00-85a9-11e1-9660-123139220831',
1103                 'ext': 'mp4',
1104                 'title': '#whilewewatch',
1105             }
1106         },
1107         # AdobeTVVideo embed
1108         {
1109             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1110             'md5': '43662b577c018ad707a63766462b1e87',
1111             'info_dict': {
1112                 'id': '2456',
1113                 'ext': 'mp4',
1114                 'title': 'New experience with Acrobat DC',
1115                 'description': 'New experience with Acrobat DC',
1116                 'duration': 248.667,
1117             },
1118         },
1119         # ScreenwaveMedia embed
1120         {
1121             'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1122             'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1123             'info_dict': {
1124                 'id': 'cinemasnob-55d26273809dd',
1125                 'ext': 'mp4',
1126                 'title': 'cinemasnob',
1127             },
1128         },
1129         # BrightcoveInPageEmbed embed
1130         {
1131             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1132             'info_dict': {
1133                 'id': '4238694884001',
1134                 'ext': 'flv',
1135                 'title': 'Tabletop: Dread, Last Thoughts',
1136                 'description': 'Tabletop: Dread, Last Thoughts',
1137                 'duration': 51690,
1138             },
1139         },
1140         # JWPlayer with M3U8
1141         {
1142             'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1143             'info_dict': {
1144                 'id': 'playlist',
1145                 'ext': 'mp4',
1146                 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1147                 'uploader': 'ren.tv',
1148             },
1149             'params': {
1150                 # m3u8 downloads
1151                 'skip_download': True,
1152             }
1153         },
1154         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1155         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1156         {
1157             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1158             'info_dict': {
1159                 'id': '4785848093001',
1160                 'ext': 'mp4',
1161                 'title': 'The Cardinal Pell Interview',
1162                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1163                 'uploader': 'GlobeCast Australia - GlobeStream',
1164                 'uploader_id': '2733773828001',
1165                 'upload_date': '20160304',
1166                 'timestamp': 1457083087,
1167             },
1168             'params': {
1169                 # m3u8 downloads
1170                 'skip_download': True,
1171             },
1172         },
1173         # Another form of arte.tv embed
1174         {
1175             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1176             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1177             'info_dict': {
1178                 'id': '030273-562_PLUS7-F',
1179                 'ext': 'mp4',
1180                 'title': 'ARTE Reportage - Nulle part, en France',
1181                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1182                 'upload_date': '20160409',
1183             },
1184         },
1185         # LiveLeak embed
1186         {
1187             'url': 'http://www.wykop.pl/link/3088787/',
1188             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1189             'info_dict': {
1190                 'id': '874_1459135191',
1191                 'ext': 'mp4',
1192                 'title': 'Man shows poor quality of new apartment building',
1193                 'description': 'The wall is like a sand pile.',
1194                 'uploader': 'Lake8737',
1195             }
1196         },
1197         # Duplicated embedded video URLs
1198         {
1199             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1200             'info_dict': {
1201                 'id': '149298443_480_16c25b74_2',
1202                 'ext': 'mp4',
1203                 'title': 'vs. Blue Orange Spring Game',
1204                 'uploader': 'www.hudl.com',
1205             },
1206         },
1207     ]
1208
1209     def report_following_redirect(self, new_url):
1210         """Report information extraction."""
1211         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1212
1213     def _extract_rss(self, url, video_id, doc):
1214         playlist_title = doc.find('./channel/title').text
1215         playlist_desc_el = doc.find('./channel/description')
1216         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1217
1218         entries = []
1219         for it in doc.findall('./channel/item'):
1220             next_url = xpath_text(it, 'link', fatal=False)
1221             if not next_url:
1222                 enclosure_nodes = it.findall('./enclosure')
1223                 for e in enclosure_nodes:
1224                     next_url = e.attrib.get('url')
1225                     if next_url:
1226                         break
1227
1228             if not next_url:
1229                 continue
1230
1231             entries.append({
1232                 '_type': 'url',
1233                 'url': next_url,
1234                 'title': it.find('title').text,
1235             })
1236
1237         return {
1238             '_type': 'playlist',
1239             'id': url,
1240             'title': playlist_title,
1241             'description': playlist_desc,
1242             'entries': entries,
1243         }
1244
1245     def _extract_camtasia(self, url, video_id, webpage):
1246         """ Returns None if no camtasia video can be found. """
1247
1248         camtasia_cfg = self._search_regex(
1249             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1250             webpage, 'camtasia configuration file', default=None)
1251         if camtasia_cfg is None:
1252             return None
1253
1254         title = self._html_search_meta('DC.title', webpage, fatal=True)
1255
1256         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1257         camtasia_cfg = self._download_xml(
1258             camtasia_url, video_id,
1259             note='Downloading camtasia configuration',
1260             errnote='Failed to download camtasia configuration')
1261         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1262
1263         entries = []
1264         for n in fileset_node.getchildren():
1265             url_n = n.find('./uri')
1266             if url_n is None:
1267                 continue
1268
1269             entries.append({
1270                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1271                 'title': '%s - %s' % (title, n.tag),
1272                 'url': compat_urlparse.urljoin(url, url_n.text),
1273                 'duration': float_or_none(n.find('./duration').text),
1274             })
1275
1276         return {
1277             '_type': 'playlist',
1278             'entries': entries,
1279             'title': title,
1280         }
1281
1282     def _real_extract(self, url):
1283         if url.startswith('//'):
1284             return {
1285                 '_type': 'url',
1286                 'url': self.http_scheme() + url,
1287             }
1288
1289         parsed_url = compat_urlparse.urlparse(url)
1290         if not parsed_url.scheme:
1291             default_search = self._downloader.params.get('default_search')
1292             if default_search is None:
1293                 default_search = 'fixup_error'
1294
1295             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1296                 if '/' in url:
1297                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1298                     return self.url_result('http://' + url)
1299                 elif default_search != 'fixup_error':
1300                     if default_search == 'auto_warning':
1301                         if re.match(r'^(?:url|URL)$', url):
1302                             raise ExtractorError(
1303                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1304                                 expected=True)
1305                         else:
1306                             self._downloader.report_warning(
1307                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1308                     return self.url_result('ytsearch:' + url)
1309
1310             if default_search in ('error', 'fixup_error'):
1311                 raise ExtractorError(
1312                     '%r is not a valid URL. '
1313                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1314                     % (url, url), expected=True)
1315             else:
1316                 if ':' not in default_search:
1317                     default_search += ':'
1318                 return self.url_result(default_search + url)
1319
1320         url, smuggled_data = unsmuggle_url(url)
1321         force_videoid = None
1322         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1323         if smuggled_data and 'force_videoid' in smuggled_data:
1324             force_videoid = smuggled_data['force_videoid']
1325             video_id = force_videoid
1326         else:
1327             video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1328
1329         self.to_screen('%s: Requesting header' % video_id)
1330
1331         head_req = HEADRequest(url)
1332         head_response = self._request_webpage(
1333             head_req, video_id,
1334             note=False, errnote='Could not send HEAD request to %s' % url,
1335             fatal=False)
1336
1337         if head_response is not False:
1338             # Check for redirect
1339             new_url = head_response.geturl()
1340             if url != new_url:
1341                 self.report_following_redirect(new_url)
1342                 if force_videoid:
1343                     new_url = smuggle_url(
1344                         new_url, {'force_videoid': force_videoid})
1345                 return self.url_result(new_url)
1346
1347         full_response = None
1348         if head_response is False:
1349             request = sanitized_Request(url)
1350             request.add_header('Accept-Encoding', '*')
1351             full_response = self._request_webpage(request, video_id)
1352             head_response = full_response
1353
1354         info_dict = {
1355             'id': video_id,
1356             'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1357             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1358         }
1359
1360         # Check for direct link to a video
1361         content_type = head_response.headers.get('Content-Type', '').lower()
1362         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1363         if m:
1364             format_id = m.group('format_id')
1365             if format_id.endswith('mpegurl'):
1366                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1367             elif format_id == 'f4m':
1368                 formats = self._extract_f4m_formats(url, video_id)
1369             else:
1370                 formats = [{
1371                     'format_id': m.group('format_id'),
1372                     'url': url,
1373                     'vcodec': 'none' if m.group('type') == 'audio' else None
1374                 }]
1375                 info_dict['direct'] = True
1376             self._sort_formats(formats)
1377             info_dict['formats'] = formats
1378             return info_dict
1379
1380         if not self._downloader.params.get('test', False) and not is_intentional:
1381             force = self._downloader.params.get('force_generic_extractor', False)
1382             self._downloader.report_warning(
1383                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1384
1385         if not full_response:
1386             request = sanitized_Request(url)
1387             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1388             # making it impossible to download only chunk of the file (yet we need only 512kB to
1389             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1390             # that will always result in downloading the whole file that is not desirable.
1391             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1392             # to accept raw bytes and being able to download only a chunk.
1393             # It may probably better to solve this by checking Content-Type for application/octet-stream
1394             # after HEAD request finishes, but not sure if we can rely on this.
1395             request.add_header('Accept-Encoding', '*')
1396             full_response = self._request_webpage(request, video_id)
1397
1398         first_bytes = full_response.read(512)
1399
1400         # Is it an M3U playlist?
1401         if first_bytes.startswith(b'#EXTM3U'):
1402             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1403             self._sort_formats(info_dict['formats'])
1404             return info_dict
1405
1406         # Maybe it's a direct link to a video?
1407         # Be careful not to download the whole thing!
1408         if not is_html(first_bytes):
1409             self._downloader.report_warning(
1410                 'URL could be a direct video link, returning it as such.')
1411             info_dict.update({
1412                 'direct': True,
1413                 'url': url,
1414             })
1415             return info_dict
1416
1417         webpage = self._webpage_read_content(
1418             full_response, url, video_id, prefix=first_bytes)
1419
1420         self.report_extraction(video_id)
1421
1422         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1423         try:
1424             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1425             if doc.tag == 'rss':
1426                 return self._extract_rss(url, video_id, doc)
1427             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1428                 smil = self._parse_smil(doc, url, video_id)
1429                 self._sort_formats(smil['formats'])
1430                 return smil
1431             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1432                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1433             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1434                 info_dict['formats'] = self._parse_mpd_formats(
1435                     doc, video_id, mpd_base_url=url.rpartition('/')[0])
1436                 self._sort_formats(info_dict['formats'])
1437                 return info_dict
1438             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1439                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1440                 self._sort_formats(info_dict['formats'])
1441                 return info_dict
1442         except compat_xml_parse_error:
1443             pass
1444
1445         # Is it a Camtasia project?
1446         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1447         if camtasia_res is not None:
1448             return camtasia_res
1449
1450         # Sometimes embedded video player is hidden behind percent encoding
1451         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1452         # Unescaping the whole page allows to handle those cases in a generic way
1453         webpage = compat_urllib_parse_unquote(webpage)
1454
1455         # it's tempting to parse this further, but you would
1456         # have to take into account all the variations like
1457         #   Video Title - Site Name
1458         #   Site Name | Video Title
1459         #   Video Title - Tagline | Site Name
1460         # and so on and so forth; it's just not practical
1461         video_title = self._og_search_title(
1462             webpage, default=None) or self._html_search_regex(
1463             r'(?s)<title>(.*?)</title>', webpage, 'video title',
1464             default='video')
1465
1466         # Try to detect age limit automatically
1467         age_limit = self._rta_search(webpage)
1468         # And then there are the jokers who advertise that they use RTA,
1469         # but actually don't.
1470         AGE_LIMIT_MARKERS = [
1471             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1472         ]
1473         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1474             age_limit = 18
1475
1476         # video uploader is domain name
1477         video_uploader = self._search_regex(
1478             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1479
1480         video_description = self._og_search_description(webpage, default=None)
1481         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1482
1483         # Helper method
1484         def _playlist_from_matches(matches, getter=None, ie=None):
1485             urlrs = orderedSet(
1486                 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1487                 for m in matches)
1488             return self.playlist_result(
1489                 urlrs, playlist_id=video_id, playlist_title=video_title)
1490
1491         # Look for Brightcove Legacy Studio embeds
1492         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1493         if bc_urls:
1494             self.to_screen('Brightcove video detected.')
1495             entries = [{
1496                 '_type': 'url',
1497                 'url': smuggle_url(bc_url, {'Referer': url}),
1498                 'ie_key': 'BrightcoveLegacy'
1499             } for bc_url in bc_urls]
1500
1501             return {
1502                 '_type': 'playlist',
1503                 'title': video_title,
1504                 'id': video_id,
1505                 'entries': entries,
1506             }
1507
1508         # Look for Brightcove New Studio embeds
1509         bc_urls = BrightcoveNewIE._extract_urls(webpage)
1510         if bc_urls:
1511             return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1512
1513         # Look for ThePlatform embeds
1514         tp_urls = ThePlatformIE._extract_urls(webpage)
1515         if tp_urls:
1516             return _playlist_from_matches(tp_urls, ie='ThePlatform')
1517
1518         # Look for embedded rtl.nl player
1519         matches = re.findall(
1520             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1521             webpage)
1522         if matches:
1523             return _playlist_from_matches(matches, ie='RtlNl')
1524
1525         vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1526         if vimeo_url is not None:
1527             return self.url_result(vimeo_url)
1528
1529         vid_me_embed_url = self._search_regex(
1530             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1531             webpage, 'vid.me embed', default=None)
1532         if vid_me_embed_url is not None:
1533             return self.url_result(vid_me_embed_url, 'Vidme')
1534
1535         # Look for embedded YouTube player
1536         matches = re.findall(r'''(?x)
1537             (?:
1538                 <iframe[^>]+?src=|
1539                 data-video-url=|
1540                 <embed[^>]+?src=|
1541                 embedSWF\(?:\s*|
1542                 new\s+SWFObject\(
1543             )
1544             (["\'])
1545                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1546                 (?:embed|v|p)/.+?)
1547             \1''', webpage)
1548         if matches:
1549             return _playlist_from_matches(
1550                 matches, lambda m: unescapeHTML(m[1]))
1551
1552         # Look for lazyYT YouTube embed
1553         matches = re.findall(
1554             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1555         if matches:
1556             return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1557
1558         # Look for embedded Dailymotion player
1559         matches = re.findall(
1560             r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1561         if matches:
1562             return _playlist_from_matches(
1563                 matches, lambda m: unescapeHTML(m[1]))
1564
1565         # Look for embedded Dailymotion playlist player (#3822)
1566         m = re.search(
1567             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1568         if m:
1569             playlists = re.findall(
1570                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1571             if playlists:
1572                 return _playlist_from_matches(
1573                     playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1574
1575         # Look for embedded Wistia player
1576         match = re.search(
1577             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1578         if match:
1579             embed_url = self._proto_relative_url(
1580                 unescapeHTML(match.group('url')))
1581             return {
1582                 '_type': 'url_transparent',
1583                 'url': embed_url,
1584                 'ie_key': 'Wistia',
1585                 'uploader': video_uploader,
1586             }
1587
1588         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1589         if match:
1590             return {
1591                 '_type': 'url_transparent',
1592                 'url': 'wistia:%s' % match.group('id'),
1593                 'ie_key': 'Wistia',
1594                 'uploader': video_uploader,
1595             }
1596
1597         match = re.search(
1598             r'''(?sx)
1599                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1600                 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1601             ''', webpage)
1602         if match:
1603             return self.url_result(self._proto_relative_url(
1604                 'wistia:%s' % match.group('id')), 'Wistia')
1605
1606         # Look for SVT player
1607         svt_url = SVTIE._extract_url(webpage)
1608         if svt_url:
1609             return self.url_result(svt_url, 'SVT')
1610
1611         # Look for embedded condenast player
1612         matches = re.findall(
1613             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1614             webpage)
1615         if matches:
1616             return {
1617                 '_type': 'playlist',
1618                 'entries': [{
1619                     '_type': 'url',
1620                     'ie_key': 'CondeNast',
1621                     'url': ma,
1622                 } for ma in matches],
1623                 'title': video_title,
1624                 'id': video_id,
1625             }
1626
1627         # Look for Bandcamp pages with custom domain
1628         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1629         if mobj is not None:
1630             burl = unescapeHTML(mobj.group(1))
1631             # Don't set the extractor because it can be a track url or an album
1632             return self.url_result(burl)
1633
1634         # Look for embedded Vevo player
1635         mobj = re.search(
1636             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1637         if mobj is not None:
1638             return self.url_result(mobj.group('url'))
1639
1640         # Look for embedded Viddler player
1641         mobj = re.search(
1642             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1643             webpage)
1644         if mobj is not None:
1645             return self.url_result(mobj.group('url'))
1646
1647         # Look for NYTimes player
1648         mobj = re.search(
1649             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1650             webpage)
1651         if mobj is not None:
1652             return self.url_result(mobj.group('url'))
1653
1654         # Look for Libsyn player
1655         mobj = re.search(
1656             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1657         if mobj is not None:
1658             return self.url_result(mobj.group('url'))
1659
1660         # Look for Ooyala videos
1661         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1662                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1663                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1664                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1665         if mobj is not None:
1666             return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1667
1668         # Look for multiple Ooyala embeds on SBN network websites
1669         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1670         if mobj is not None:
1671             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1672             if embeds:
1673                 return _playlist_from_matches(
1674                     embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1675
1676         # Look for Aparat videos
1677         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1678         if mobj is not None:
1679             return self.url_result(mobj.group(1), 'Aparat')
1680
1681         # Look for MPORA videos
1682         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1683         if mobj is not None:
1684             return self.url_result(mobj.group(1), 'Mpora')
1685
1686         # Look for embedded NovaMov-based player
1687         mobj = re.search(
1688             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1689                     (?P<url>http://(?:(?:embed|www)\.)?
1690                         (?:novamov\.com|
1691                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
1692                            videoweed\.(?:es|com)|
1693                            movshare\.(?:net|sx|ag)|
1694                            divxstage\.(?:eu|net|ch|co|at|ag))
1695                         /embed\.php.+?)\1''', webpage)
1696         if mobj is not None:
1697             return self.url_result(mobj.group('url'))
1698
1699         # Look for embedded Facebook player
1700         mobj = re.search(
1701             r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1702         if mobj is not None:
1703             return self.url_result(mobj.group('url'), 'Facebook')
1704
1705         # Look for embedded VK player
1706         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1707         if mobj is not None:
1708             return self.url_result(mobj.group('url'), 'VK')
1709
1710         # Look for embedded Odnoklassniki player
1711         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1712         if mobj is not None:
1713             return self.url_result(mobj.group('url'), 'Odnoklassniki')
1714
1715         # Look for embedded ivi player
1716         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1717         if mobj is not None:
1718             return self.url_result(mobj.group('url'), 'Ivi')
1719
1720         # Look for embedded Huffington Post player
1721         mobj = re.search(
1722             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1723         if mobj is not None:
1724             return self.url_result(mobj.group('url'), 'HuffPost')
1725
1726         # Look for embed.ly
1727         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1728         if mobj is not None:
1729             return self.url_result(mobj.group('url'))
1730         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1731         if mobj is not None:
1732             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1733
1734         # Look for funnyordie embed
1735         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1736         if matches:
1737             return _playlist_from_matches(
1738                 matches, getter=unescapeHTML, ie='FunnyOrDie')
1739
1740         # Look for BBC iPlayer embed
1741         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1742         if matches:
1743             return _playlist_from_matches(matches, ie='BBCCoUk')
1744
1745         # Look for embedded RUTV player
1746         rutv_url = RUTVIE._extract_url(webpage)
1747         if rutv_url:
1748             return self.url_result(rutv_url, 'RUTV')
1749
1750         # Look for embedded TVC player
1751         tvc_url = TVCIE._extract_url(webpage)
1752         if tvc_url:
1753             return self.url_result(tvc_url, 'TVC')
1754
1755         # Look for embedded SportBox player
1756         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1757         if sportbox_urls:
1758             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1759
1760         # Look for embedded PornHub player
1761         pornhub_url = PornHubIE._extract_url(webpage)
1762         if pornhub_url:
1763             return self.url_result(pornhub_url, 'PornHub')
1764
1765         # Look for embedded XHamster player
1766         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1767         if xhamster_urls:
1768             return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1769
1770         # Look for embedded TNAFlixNetwork player
1771         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1772         if tnaflix_urls:
1773             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1774
1775         # Look for embedded Tvigle player
1776         mobj = re.search(
1777             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1778         if mobj is not None:
1779             return self.url_result(mobj.group('url'), 'Tvigle')
1780
1781         # Look for embedded TED player
1782         mobj = re.search(
1783             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1784         if mobj is not None:
1785             return self.url_result(mobj.group('url'), 'TED')
1786
1787         # Look for embedded Ustream videos
1788         mobj = re.search(
1789             r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1790         if mobj is not None:
1791             return self.url_result(mobj.group('url'), 'Ustream')
1792
1793         # Look for embedded arte.tv player
1794         mobj = re.search(
1795             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1796             webpage)
1797         if mobj is not None:
1798             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1799
1800         # Look for embedded francetv player
1801         mobj = re.search(
1802             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1803             webpage)
1804         if mobj is not None:
1805             return self.url_result(mobj.group('url'))
1806
1807         # Look for embedded smotri.com player
1808         smotri_url = SmotriIE._extract_url(webpage)
1809         if smotri_url:
1810             return self.url_result(smotri_url, 'Smotri')
1811
1812         # Look for embedded Myvi.ru player
1813         myvi_url = MyviIE._extract_url(webpage)
1814         if myvi_url:
1815             return self.url_result(myvi_url)
1816
1817         # Look for embedded soundcloud player
1818         mobj = re.search(
1819             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1820             webpage)
1821         if mobj is not None:
1822             url = unescapeHTML(mobj.group('url'))
1823             return self.url_result(url)
1824
1825         # Look for embedded vulture.com player
1826         mobj = re.search(
1827             r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1828             webpage)
1829         if mobj is not None:
1830             url = unescapeHTML(mobj.group('url'))
1831             return self.url_result(url, ie='Vulture')
1832
1833         # Look for embedded mtvservices player
1834         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1835         if mtvservices_url:
1836             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1837
1838         # Look for embedded yahoo player
1839         mobj = re.search(
1840             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1841             webpage)
1842         if mobj is not None:
1843             return self.url_result(mobj.group('url'), 'Yahoo')
1844
1845         # Look for embedded sbs.com.au player
1846         mobj = re.search(
1847             r'''(?x)
1848             (?:
1849                 <meta\s+property="og:video"\s+content=|
1850                 <iframe[^>]+?src=
1851             )
1852             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1853             webpage)
1854         if mobj is not None:
1855             return self.url_result(mobj.group('url'), 'SBS')
1856
1857         # Look for embedded Cinchcast player
1858         mobj = re.search(
1859             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1860             webpage)
1861         if mobj is not None:
1862             return self.url_result(mobj.group('url'), 'Cinchcast')
1863
1864         mobj = re.search(
1865             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1866             webpage)
1867         if not mobj:
1868             mobj = re.search(
1869                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1870                 webpage)
1871         if mobj is not None:
1872             return self.url_result(mobj.group('url'), 'MLB')
1873
1874         mobj = re.search(
1875             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1876             webpage)
1877         if mobj is not None:
1878             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1879
1880         mobj = re.search(
1881             r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1882             webpage)
1883         if mobj is not None:
1884             return self.url_result(mobj.group('url'), 'Livestream')
1885
1886         # Look for Zapiks embed
1887         mobj = re.search(
1888             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1889         if mobj is not None:
1890             return self.url_result(mobj.group('url'), 'Zapiks')
1891
1892         # Look for Kaltura embeds
1893         mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1894                 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))
1895         if mobj is not None:
1896             return self.url_result(smuggle_url(
1897                 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1898                 {'source_url': url}), 'Kaltura')
1899
1900         # Look for Eagle.Platform embeds
1901         mobj = re.search(
1902             r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1903         if mobj is not None:
1904             return self.url_result(mobj.group('url'), 'EaglePlatform')
1905
1906         # Look for ClipYou (uses Eagle.Platform) embeds
1907         mobj = re.search(
1908             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1909         if mobj is not None:
1910             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1911
1912         # Look for Pladform embeds
1913         pladform_url = PladformIE._extract_url(webpage)
1914         if pladform_url:
1915             return self.url_result(pladform_url)
1916
1917         # Look for Videomore embeds
1918         videomore_url = VideomoreIE._extract_url(webpage)
1919         if videomore_url:
1920             return self.url_result(videomore_url)
1921
1922         # Look for Playwire embeds
1923         mobj = re.search(
1924             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1925         if mobj is not None:
1926             return self.url_result(mobj.group('url'))
1927
1928         # Look for 5min embeds
1929         mobj = re.search(
1930             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1931         if mobj is not None:
1932             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1933
1934         # Look for Crooks and Liars embeds
1935         mobj = re.search(
1936             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1937         if mobj is not None:
1938             return self.url_result(mobj.group('url'))
1939
1940         # Look for NBC Sports VPlayer embeds
1941         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1942         if nbc_sports_url:
1943             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1944
1945         # Look for Google Drive embeds
1946         google_drive_url = GoogleDriveIE._extract_url(webpage)
1947         if google_drive_url:
1948             return self.url_result(google_drive_url, 'GoogleDrive')
1949
1950         # Look for UDN embeds
1951         mobj = re.search(
1952             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1953         if mobj is not None:
1954             return self.url_result(
1955                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1956
1957         # Look for Senate ISVP iframe
1958         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1959         if senate_isvp_url:
1960             return self.url_result(senate_isvp_url, 'SenateISVP')
1961
1962         # Look for Dailymotion Cloud videos
1963         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1964         if dmcloud_url:
1965             return self.url_result(dmcloud_url, 'DailymotionCloud')
1966
1967         # Look for OnionStudios embeds
1968         onionstudios_url = OnionStudiosIE._extract_url(webpage)
1969         if onionstudios_url:
1970             return self.url_result(onionstudios_url)
1971
1972         # Look for ViewLift embeds
1973         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1974         if viewlift_url:
1975             return self.url_result(viewlift_url)
1976
1977         # Look for JWPlatform embeds
1978         jwplatform_url = JWPlatformIE._extract_url(webpage)
1979         if jwplatform_url:
1980             return self.url_result(jwplatform_url, 'JWPlatform')
1981
1982         # Look for ScreenwaveMedia embeds
1983         mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1984         if mobj is not None:
1985             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1986
1987         # Look for Digiteka embeds
1988         digiteka_url = DigitekaIE._extract_url(webpage)
1989         if digiteka_url:
1990             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1991
1992         # Look for Limelight embeds
1993         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1994         if mobj:
1995             lm = {
1996                 'Media': 'media',
1997                 'Channel': 'channel',
1998                 'ChannelList': 'channel_list',
1999             }
2000             return self.url_result('limelight:%s:%s' % (
2001                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2002
2003         # Look for AdobeTVVideo embeds
2004         mobj = re.search(
2005             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2006             webpage)
2007         if mobj is not None:
2008             return self.url_result(
2009                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2010                 'AdobeTVVideo')
2011
2012         # Look for Vine embeds
2013         mobj = re.search(
2014             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2015             webpage)
2016         if mobj is not None:
2017             return self.url_result(
2018                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2019
2020         # Look for Instagram embeds
2021         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2022         if instagram_embed_url is not None:
2023             return self.url_result(
2024                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2025
2026         # Look for LiveLeak embeds
2027         liveleak_url = LiveLeakIE._extract_url(webpage)
2028         if liveleak_url:
2029             return self.url_result(liveleak_url, 'LiveLeak')
2030
2031         # Look for 3Q SDN embeds
2032         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2033         if threeqsdn_url:
2034             return {
2035                 '_type': 'url_transparent',
2036                 'ie_key': ThreeQSDNIE.ie_key(),
2037                 'url': self._proto_relative_url(threeqsdn_url),
2038                 'title': video_title,
2039                 'description': video_description,
2040                 'thumbnail': video_thumbnail,
2041                 'uploader': video_uploader,
2042             }
2043
2044         def check_video(vurl):
2045             if YoutubeIE.suitable(vurl):
2046                 return True
2047             vpath = compat_urlparse.urlparse(vurl).path
2048             vext = determine_ext(vpath)
2049             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2050
2051         def filter_video(urls):
2052             return list(filter(check_video, urls))
2053
2054         # Start with something easy: JW Player in SWFObject
2055         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2056         if not found:
2057             # Look for gorilla-vid style embedding
2058             found = filter_video(re.findall(r'''(?sx)
2059                 (?:
2060                     jw_plugins|
2061                     JWPlayerOptions|
2062                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2063                 )
2064                 .*?
2065                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2066         if not found:
2067             # Broaden the search a little bit
2068             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2069         if not found:
2070             # Broaden the findall a little bit: JWPlayer JS loader
2071             found = filter_video(re.findall(
2072                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2073         if not found:
2074             # Flow player
2075             found = filter_video(re.findall(r'''(?xs)
2076                 flowplayer\("[^"]+",\s*
2077                     \{[^}]+?\}\s*,
2078                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2079                         ["']?url["']?\s*:\s*["']([^"']+)["']
2080             ''', webpage))
2081         if not found:
2082             # Cinerama player
2083             found = re.findall(
2084                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2085         if not found:
2086             # Try to find twitter cards info
2087             found = filter_video(re.findall(
2088                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2089         if not found:
2090             # We look for Open Graph info:
2091             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2092             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2093             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2094             if m_video_type is not None:
2095                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2096         if not found:
2097             # HTML5 video
2098             found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2099         if not found:
2100             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2101             found = re.search(
2102                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2103                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2104                 webpage)
2105             if not found:
2106                 # Look also in Refresh HTTP header
2107                 refresh_header = head_response.headers.get('Refresh')
2108                 if refresh_header:
2109                     # In python 2 response HTTP headers are bytestrings
2110                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2111                         refresh_header = refresh_header.decode('iso-8859-1')
2112                     found = re.search(REDIRECT_REGEX, refresh_header)
2113             if found:
2114                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2115                 self.report_following_redirect(new_url)
2116                 return {
2117                     '_type': 'url',
2118                     'url': new_url,
2119                 }
2120         if not found:
2121             raise UnsupportedError(url)
2122
2123         entries = []
2124         for video_url in orderedSet(found):
2125             video_url = unescapeHTML(video_url)
2126             video_url = video_url.replace('\\/', '/')
2127             video_url = compat_urlparse.urljoin(url, video_url)
2128             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2129
2130             # Sometimes, jwplayer extraction will result in a YouTube URL
2131             if YoutubeIE.suitable(video_url):
2132                 entries.append(self.url_result(video_url, 'Youtube'))
2133                 continue
2134
2135             # here's a fun little line of code for you:
2136             video_id = os.path.splitext(video_id)[0]
2137
2138             entry_info_dict = {
2139                 'id': video_id,
2140                 'uploader': video_uploader,
2141                 'title': video_title,
2142                 'age_limit': age_limit,
2143             }
2144
2145             ext = determine_ext(video_url)
2146             if ext == 'smil':
2147                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2148             elif ext == 'xspf':
2149                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2150             elif ext == 'm3u8':
2151                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2152             elif ext == 'mpd':
2153                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2154             elif ext == 'f4m':
2155                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2156             else:
2157                 entry_info_dict['url'] = video_url
2158
2159             if entry_info_dict.get('formats'):
2160                 self._sort_formats(entry_info_dict['formats'])
2161
2162             entries.append(entry_info_dict)
2163
2164         if len(entries) == 1:
2165             return entries[0]
2166         else:
2167             for num, e in enumerate(entries, start=1):
2168                 # 'url' results don't have a title
2169                 if e.get('title') is not None:
2170                     e['title'] = '%s (%d)' % (e['title'], num)
2171             return {
2172                 '_type': 'playlist',
2173                 'entries': entries,
2174             }