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

   1 # coding: 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_str,
  14     compat_urllib_parse_unquote,
  15     compat_urlparse,
  16     compat_xml_parse_error,
  17 )
  18 from ..utils import (
  19     determine_ext,
  20     ExtractorError,
  21     float_or_none,
  22     HEADRequest,
  23     is_html,
  24     js_to_json,
  25     orderedSet,
  26     sanitized_Request,
  27     smuggle_url,
  28     unescapeHTML,
  29     unified_strdate,
  30     unsmuggle_url,
  31     UnsupportedError,
  32     xpath_text,
  33 )
  34 from .commonprotocols import RtmpIE
  35 from .brightcove import (
  36     BrightcoveLegacyIE,
  37     BrightcoveNewIE,
  38 )
  39 from .nbc import NBCSportsVPlayerIE
  40 from .ooyala import OoyalaIE
  41 from .rutv import RUTVIE
  42 from .tvc import TVCIE
  43 from .sportbox import SportBoxEmbedIE
  44 from .smotri import SmotriIE
  45 from .myvi import MyviIE
  46 from .condenast import CondeNastIE
  47 from .udn import UDNEmbedIE
  48 from .senateisvp import SenateISVPIE
  49 from .svt import SVTIE
  50 from .pornhub import PornHubIE
  51 from .xhamster import XHamsterEmbedIE
  52 from .tnaflix import TNAFlixNetworkEmbedIE
  53 from .drtuber import DrTuberIE
  54 from .redtube import RedTubeIE
  55 from .vimeo import VimeoIE
  56 from .dailymotion import (
  57     DailymotionIE,
  58     DailymotionCloudIE,
  59 )
  60 from .dailymail import DailyMailIE
  61 from .onionstudios import OnionStudiosIE
  62 from .viewlift import ViewLiftEmbedIE
  63 from .mtv import MTVServicesEmbeddedIE
  64 from .pladform import PladformIE
  65 from .videomore import VideomoreIE
  66 from .webcaster import WebcasterFeedIE
  67 from .googledrive import GoogleDriveIE
  68 from .jwplatform import JWPlatformIE
  69 from .digiteka import DigitekaIE
  70 from .arkena import ArkenaIE
  71 from .instagram import InstagramIE
  72 from .liveleak import LiveLeakIE
  73 from .threeqsdn import ThreeQSDNIE
  74 from .theplatform import ThePlatformIE
  75 from .vessel import VesselIE
  76 from .kaltura import KalturaIE
  77 from .eagleplatform import EaglePlatformIE
  78 from .facebook import FacebookIE
  79 from .soundcloud import SoundcloudIE
  80 from .tunein import TuneInBaseIE
  81 from .vbox7 import Vbox7IE
  82 from .dbtv import DBTVIE
  83 from .piksel import PikselIE
  84 from .videa import VideaIE
  85 from .twentymin import TwentyMinutenIE
  86 from .ustream import UstreamIE
  87 from .openload import OpenloadIE
  88 from .videopress import VideoPressIE
  89 from .rutube import RutubeIE
  90 from .limelight import LimelightBaseIE
  91 from .anvato import AnvatoIE
  92 from .washingtonpost import WashingtonPostIE
  93 from .wistia import WistiaIE
  94 from .mediaset import MediasetIE
  95 from .joj import JojIE
  96
  97
  98 class GenericIE(InfoExtractor):
  99     IE_DESC = 'Generic downloader that works on some sites'
 100     _VALID_URL = r'.*'
 101     IE_NAME = 'generic'
 102     _TESTS = [
 103         # Direct link to a video
 104         {
 105             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
 106             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
 107             'info_dict': {
 108                 'id': 'trailer',
 109                 'ext': 'mp4',
 110                 'title': 'trailer',
 111                 'upload_date': '20100513',
 112             }
 113         },
 114         # Direct link to media delivered compressed (until Accept-Encoding is *)
 115         {
 116             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
 117             'md5': '128c42e68b13950268b648275386fc74',
 118             'info_dict': {
 119                 'id': 'FictionJunction-Parallel_Hearts',
 120                 'ext': 'flac',
 121                 'title': 'FictionJunction-Parallel_Hearts',
 122                 'upload_date': '20140522',
 123             },
 124             'expected_warnings': [
 125                 'URL could be a direct video link, returning it as such.'
 126             ],
 127             'skip': 'URL invalid',
 128         },
 129         # Direct download with broken HEAD
 130         {
 131             'url': 'http://ai-radio.org:8000/radio.opus',
 132             'info_dict': {
 133                 'id': 'radio',
 134                 'ext': 'opus',
 135                 'title': 'radio',
 136             },
 137             'params': {
 138                 'skip_download': True,  # infinite live stream
 139             },
 140             'expected_warnings': [
 141                 r'501.*Not Implemented',
 142                 r'400.*Bad Request',
 143             ],
 144         },
 145         # Direct link with incorrect MIME type
 146         {
 147             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 148             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 149             'info_dict': {
 150                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 151                 'id': '5_Lennart_Poettering_-_Systemd',
 152                 'ext': 'webm',
 153                 'title': '5_Lennart_Poettering_-_Systemd',
 154                 'upload_date': '20141120',
 155             },
 156             'expected_warnings': [
 157                 'URL could be a direct video link, returning it as such.'
 158             ]
 159         },
 160         # RSS feed
 161         {
 162             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 163             'info_dict': {
 164                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 165                 'title': 'Zero Punctuation',
 166                 'description': 're:.*groundbreaking video review series.*'
 167             },
 168             'playlist_mincount': 11,
 169         },
 170         # RSS feed with enclosure
 171         {
 172             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 173             'info_dict': {
 174                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 175                 'ext': 'm4v',
 176                 'upload_date': '20150228',
 177                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 178             }
 179         },
 180         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 181         {
 182             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 183             'info_dict': {
 184                 'id': 'smil',
 185                 'ext': 'mp4',
 186                 'title': 'Automatics, robotics and biocybernetics',
 187                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 188                 'upload_date': '20130627',
 189                 'formats': 'mincount:16',
 190                 'subtitles': 'mincount:1',
 191             },
 192             'params': {
 193                 'force_generic_extractor': True,
 194                 'skip_download': True,
 195             },
 196         },
 197         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 198         {
 199             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 200             'info_dict': {
 201                 'id': 'hds',
 202                 'ext': 'flv',
 203                 'title': 'hds',
 204                 'formats': 'mincount:1',
 205             },
 206             'params': {
 207                 'skip_download': True,
 208             },
 209         },
 210         # SMIL from https://www.restudy.dk/video/play/id/1637
 211         {
 212             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 213             'info_dict': {
 214                 'id': 'video_1637',
 215                 'ext': 'flv',
 216                 'title': 'video_1637',
 217                 'formats': 'mincount:3',
 218             },
 219             'params': {
 220                 'skip_download': True,
 221             },
 222         },
 223         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 224         {
 225             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 226             'info_dict': {
 227                 'id': 'smil-service',
 228                 'ext': 'flv',
 229                 'title': 'smil-service',
 230                 'formats': 'mincount:1',
 231             },
 232             'params': {
 233                 'skip_download': True,
 234             },
 235         },
 236         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 237         {
 238             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 239             'info_dict': {
 240                 'id': '4719370',
 241                 'ext': 'mp4',
 242                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 243                 'formats': 'mincount:3',
 244             },
 245             'params': {
 246                 'skip_download': True,
 247             },
 248         },
 249         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 250         {
 251             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 252             'info_dict': {
 253                 'id': 'mZlp2ctYIUEB',
 254                 'ext': 'mp4',
 255                 'title': 'Tikibad ontruimd wegens brand',
 256                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 257                 'thumbnail': r're:^https?://.*\.jpg$',
 258                 'duration': 33,
 259             },
 260             'params': {
 261                 'skip_download': True,
 262             },
 263         },
 264         # MPD from http://dash-mse-test.appspot.com/media.html
 265         {
 266             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 267             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 268             'info_dict': {
 269                 'id': 'car-20120827-manifest',
 270                 'ext': 'mp4',
 271                 'title': 'car-20120827-manifest',
 272                 'formats': 'mincount:9',
 273                 'upload_date': '20130904',
 274             },
 275             'params': {
 276                 'format': 'bestvideo',
 277             },
 278         },
 279         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 280         {
 281             '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',
 282             'info_dict': {
 283                 'id': 'content',
 284                 'ext': 'mp4',
 285                 'title': 'content',
 286                 'formats': 'mincount:8',
 287             },
 288             'params': {
 289                 # m3u8 downloads
 290                 'skip_download': True,
 291             },
 292             'skip': 'video gone',
 293         },
 294         # m3u8 served with Content-Type: text/plain
 295         {
 296             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 297             'info_dict': {
 298                 'id': 'index',
 299                 'ext': 'mp4',
 300                 'title': 'index',
 301                 'upload_date': '20140720',
 302                 'formats': 'mincount:11',
 303             },
 304             'params': {
 305                 # m3u8 downloads
 306                 'skip_download': True,
 307             },
 308             'skip': 'video gone',
 309         },
 310         # google redirect
 311         {
 312             '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',
 313             'info_dict': {
 314                 'id': 'cmQHVoWB5FY',
 315                 'ext': 'mp4',
 316                 'upload_date': '20130224',
 317                 'uploader_id': 'TheVerge',
 318                 'description': r're:^Chris Ziegler takes a look at the\.*',
 319                 'uploader': 'The Verge',
 320                 'title': 'First Firefox OS phones side-by-side',
 321             },
 322             'params': {
 323                 'skip_download': False,
 324             }
 325         },
 326         {
 327             # redirect in Refresh HTTP header
 328             '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',
 329             'info_dict': {
 330                 'id': 'pO8h3EaFRdo',
 331                 'ext': 'mp4',
 332                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 333                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 334                 'upload_date': '20150917',
 335                 'uploader_id': 'brtvofficial',
 336                 'uploader': 'Boiler Room',
 337             },
 338             'params': {
 339                 'skip_download': False,
 340             },
 341         },
 342         {
 343             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 344             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 345             'info_dict': {
 346                 'id': '13601338388002',
 347                 'ext': 'mp4',
 348                 'uploader': 'www.hodiho.fr',
 349                 'title': 'R\u00e9gis plante sa Jeep',
 350             }
 351         },
 352         # bandcamp page with custom domain
 353         {
 354             'add_ie': ['Bandcamp'],
 355             'url': 'http://bronyrock.com/track/the-pony-mash',
 356             'info_dict': {
 357                 'id': '3235767654',
 358                 'ext': 'mp3',
 359                 'title': 'The Pony Mash',
 360                 'uploader': 'M_Pallante',
 361             },
 362             'skip': 'There is a limit of 200 free downloads / month for the test song',
 363         },
 364         {
 365             # embedded brightcove video
 366             # it also tests brightcove videos that need to set the 'Referer'
 367             # in the http requests
 368             'add_ie': ['BrightcoveLegacy'],
 369             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 370             'info_dict': {
 371                 'id': '2765128793001',
 372                 'ext': 'mp4',
 373                 'title': 'Le cours de bourse : l’analyse technique',
 374                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 375                 'uploader': 'BFM BUSINESS',
 376             },
 377             'params': {
 378                 'skip_download': True,
 379             },
 380         },
 381         {
 382             # embedded with itemprop embedURL and video id spelled as `idVideo`
 383             'add_id': ['BrightcoveLegacy'],
 384             'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
 385             'info_dict': {
 386                 'id': '5255628253001',
 387                 'ext': 'mp4',
 388                 'title': 'md5:37c519b1128915607601e75a87995fc0',
 389                 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
 390                 'uploader': 'BFM BUSINESS',
 391                 'uploader_id': '876450612001',
 392                 'timestamp': 1482255315,
 393                 'upload_date': '20161220',
 394             },
 395             'params': {
 396                 'skip_download': True,
 397             },
 398         },
 399         {
 400             # https://github.com/rg3/youtube-dl/issues/2253
 401             'url': 'http://bcove.me/i6nfkrc3',
 402             'md5': '0ba9446db037002366bab3b3eb30c88c',
 403             'info_dict': {
 404                 'id': '3101154703001',
 405                 'ext': 'mp4',
 406                 'title': 'Still no power',
 407                 'uploader': 'thestar.com',
 408                 '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.',
 409             },
 410             'add_ie': ['BrightcoveLegacy'],
 411             'skip': 'video gone',
 412         },
 413         {
 414             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 415             'md5': 'fb973ecf6e4a78a67453647444222983',
 416             'info_dict': {
 417                 'id': '3414141473001',
 418                 'ext': 'mp4',
 419                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 420                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 421                 'uploader': 'Championat',
 422             },
 423         },
 424         {
 425             # https://github.com/rg3/youtube-dl/issues/3541
 426             'add_ie': ['BrightcoveLegacy'],
 427             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 428             'info_dict': {
 429                 'id': '3866516442001',
 430                 'ext': 'mp4',
 431                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 432                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 433                 'uploader': 'SBS Broadcasting',
 434             },
 435             'skip': 'Restricted to Netherlands',
 436             'params': {
 437                 'skip_download': True,  # m3u8 download
 438             },
 439         },
 440         {
 441             # Brightcove video in <iframe>
 442             'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
 443             'md5': '36d74ef5e37c8b4a2ce92880d208b968',
 444             'info_dict': {
 445                 'id': '5360463607001',
 446                 'ext': 'mp4',
 447                 'title': '叙利亚失明儿童在废墟上演唱《心跳》  呼吁获得正常童年生活',
 448                 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼（Zade Dirani）在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》（HEARTBEAT），为受到六年冲突影响的叙利亚儿童发出强烈呐喊，呼吁世界做出共同努力，使叙利亚儿童重新获得享有正常童年生活的权利。',
 449                 'uploader': 'United Nations',
 450                 'uploader_id': '1362235914001',
 451                 'timestamp': 1489593889,
 452                 'upload_date': '20170315',
 453             },
 454             'add_ie': ['BrightcoveLegacy'],
 455         },
 456         {
 457             # Brightcove with alternative playerID key
 458             'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
 459             'info_dict': {
 460                 'id': 'nmeth.2062_SV1',
 461                 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
 462             },
 463             'playlist': [{
 464                 'info_dict': {
 465                     'id': '2228375078001',
 466                     'ext': 'mp4',
 467                     'title': 'nmeth.2062-sv1',
 468                     'description': 'nmeth.2062-sv1',
 469                     'timestamp': 1363357591,
 470                     'upload_date': '20130315',
 471                     'uploader': 'Nature Publishing Group',
 472                     'uploader_id': '1964492299001',
 473                 },
 474             }],
 475         },
 476         {
 477             # Brightcove with UUID in videoPlayer
 478             'url': 'http://www8.hp.com/cn/zh/home.html',
 479             'info_dict': {
 480                 'id': '5255815316001',
 481                 'ext': 'mp4',
 482                 'title': 'Sprocket Video - China',
 483                 'description': 'Sprocket Video - China',
 484                 'uploader': 'HP-Video Gallery',
 485                 'timestamp': 1482263210,
 486                 'upload_date': '20161220',
 487                 'uploader_id': '1107601872001',
 488             },
 489             'params': {
 490                 'skip_download': True,  # m3u8 download
 491             },
 492             'skip': 'video rotates...weekly?',
 493         },
 494         {
 495             # Brightcove:new type [2].
 496             'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
 497             'md5': '2b35148fcf48da41c9fb4591650784f3',
 498             'info_dict': {
 499                 'id': '5348741021001',
 500                 'ext': 'mp4',
 501                 'upload_date': '20170306',
 502                 'uploader_id': '4191638492001',
 503                 'timestamp': 1488769918,
 504                 'title': 'VIDEO:  St. Thomas More earns first trip to basketball semis',
 505
 506             },
 507         },
 508         {
 509             # Alternative brightcove <video> attributes
 510             'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
 511             'info_dict': {
 512                 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
 513                 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
 514             },
 515             'playlist': [{
 516                 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
 517                 'info_dict': {
 518                     'id': '5311302538001',
 519                     'ext': 'mp4',
 520                     'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
 521                     'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
 522                     'timestamp': 1486321708,
 523                     'upload_date': '20170205',
 524                     'uploader_id': '800000640001',
 525                 },
 526                 'only_matching': True,
 527             }],
 528         },
 529         {
 530             # Brightcove with UUID in videoPlayer
 531             'url': 'http://www8.hp.com/cn/zh/home.html',
 532             'info_dict': {
 533                 'id': '5255815316001',
 534                 'ext': 'mp4',
 535                 'title': 'Sprocket Video - China',
 536                 'description': 'Sprocket Video - China',
 537                 'uploader': 'HP-Video Gallery',
 538                 'timestamp': 1482263210,
 539                 'upload_date': '20161220',
 540                 'uploader_id': '1107601872001',
 541             },
 542             'params': {
 543                 'skip_download': True,  # m3u8 download
 544             },
 545         },
 546         # ooyala video
 547         {
 548             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 549             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 550             'info_dict': {
 551                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 552                 'ext': 'mp4',
 553                 'title': '2cc213299525360.mov',  # that's what we get
 554                 'duration': 238.231,
 555             },
 556             'add_ie': ['Ooyala'],
 557         },
 558         {
 559             # ooyala video embedded with http://player.ooyala.com/iframe.js
 560             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 561             'info_dict': {
 562                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 563                 'ext': 'mp4',
 564                 'title': '"Steve Jobs: Man in the Machine" trailer',
 565                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 566                 'duration': 135.427,
 567             },
 568             'params': {
 569                 'skip_download': True,
 570             },
 571             'skip': 'movie expired',
 572         },
 573         # embed.ly video
 574         {
 575             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 576             'info_dict': {
 577                 'id': '9ODmcdjQcHQ',
 578                 'ext': 'mp4',
 579                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 580                 'upload_date': '20140225',
 581                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 582                 'uploader': 'Tested',
 583                 'uploader_id': 'testedcom',
 584             },
 585             # No need to test YoutubeIE here
 586             'params': {
 587                 'skip_download': True,
 588             },
 589         },
 590         # funnyordie embed
 591         {
 592             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 593             'info_dict': {
 594                 'id': '18e820ec3f',
 595                 'ext': 'mp4',
 596                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 597                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 598             },
 599             # HEAD requests lead to endless 301, while GET is OK
 600             'expected_warnings': ['301'],
 601         },
 602         # RUTV embed
 603         {
 604             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 605             'info_dict': {
 606                 'id': '776940',
 607                 'ext': 'mp4',
 608                 'title': 'Охотское море стало целиком российским',
 609                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 610             },
 611             'params': {
 612                 # m3u8 download
 613                 'skip_download': True,
 614             },
 615         },
 616         # TVC embed
 617         {
 618             '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/',
 619             'info_dict': {
 620                 'id': '55304',
 621                 'ext': 'mp4',
 622                 'title': 'Дошкольное воспитание',
 623             },
 624         },
 625         # SportBox embed
 626         {
 627             'url': 'http://www.vestifinance.ru/articles/25753',
 628             'info_dict': {
 629                 'id': '25753',
 630                 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 631             },
 632             'playlist': [{
 633                 'info_dict': {
 634                     'id': '370908',
 635                     'title': 'Госзаказ. День 3',
 636                     'ext': 'mp4',
 637                 }
 638             }, {
 639                 'info_dict': {
 640                     'id': '370905',
 641                     'title': 'Госзаказ. День 2',
 642                     'ext': 'mp4',
 643                 }
 644             }, {
 645                 'info_dict': {
 646                     'id': '370902',
 647                     'title': 'Госзаказ. День 1',
 648                     'ext': 'mp4',
 649                 }
 650             }],
 651             'params': {
 652                 # m3u8 download
 653                 'skip_download': True,
 654             },
 655         },
 656         # Myvi.ru embed
 657         {
 658             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 659             'info_dict': {
 660                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 661                 'ext': 'mp4',
 662                 'title': 'Ужастики, русский трейлер (2015)',
 663                 'thumbnail': r're:^https?://.*\.jpg$',
 664                 'duration': 153,
 665             }
 666         },
 667         # XHamster embed
 668         {
 669             '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',
 670             'info_dict': {
 671                 'id': 'showthread',
 672                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 673             },
 674             'playlist_mincount': 7,
 675             # This forum does not allow <iframe> syntaxes anymore
 676             # Now HTML tags are displayed as-is
 677             'skip': 'No videos on this page',
 678         },
 679         # Embedded TED video
 680         {
 681             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 682             'md5': '65fdff94098e4a607385a60c5177c638',
 683             'info_dict': {
 684                 'id': '1969',
 685                 'ext': 'mp4',
 686                 'title': 'Hidden miracles of the natural world',
 687                 'uploader': 'Louie Schwartzberg',
 688                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 689             }
 690         },
 691         # nowvideo embed hidden behind percent encoding
 692         {
 693             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 694             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 695             'info_dict': {
 696                 'id': '06e53103ca9aa',
 697                 'ext': 'flv',
 698                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 699                 'description': 'No description',
 700             },
 701         },
 702         # arte embed
 703         {
 704             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 705             'md5': '7653032cbb25bf6c80d80f217055fa43',
 706             'info_dict': {
 707                 'id': '048195-004_PLUS7-F',
 708                 'ext': 'flv',
 709                 'title': 'X:enius',
 710                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 711                 'upload_date': '20140320',
 712             },
 713             'params': {
 714                 'skip_download': 'Requires rtmpdump'
 715             },
 716             'skip': 'video gone',
 717         },
 718         # francetv embed
 719         {
 720             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 721             'info_dict': {
 722                 'id': 'EV_30231',
 723                 'ext': 'mp4',
 724                 'title': 'Alcaline, le concert avec Calogero',
 725                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 726                 'upload_date': '20150226',
 727                 'timestamp': 1424989860,
 728                 'duration': 5400,
 729             },
 730             'params': {
 731                 # m3u8 downloads
 732                 'skip_download': True,
 733             },
 734             'expected_warnings': [
 735                 'Forbidden'
 736             ]
 737         },
 738         # Condé Nast embed
 739         {
 740             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 741             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 742             'info_dict': {
 743                 'id': '53501be369702d3275860000',
 744                 'ext': 'mp4',
 745                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 746             }
 747         },
 748         # Dailymotion embed
 749         {
 750             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 751             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 752             'info_dict': {
 753                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 754                 'ext': 'mp4',
 755                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 756                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 757                 'uploader': 'Spi0n',
 758                 'uploader_id': 'xgditw',
 759                 'upload_date': '20140425',
 760                 'timestamp': 1398441542,
 761             },
 762             'add_ie': ['Dailymotion'],
 763         },
 764         # DailyMail embed
 765         {
 766             'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
 767             'info_dict': {
 768                 'id': '1495629',
 769                 'ext': 'mp4',
 770                 'title': 'Care worker punches elderly dementia patient in head 11 times',
 771                 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
 772             },
 773             'add_ie': ['DailyMail'],
 774             'params': {
 775                 'skip_download': True,
 776             },
 777         },
 778         # YouTube embed
 779         {
 780             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 781             'info_dict': {
 782                 'id': 'FXRb4ykk4S0',
 783                 'ext': 'mp4',
 784                 'title': 'The NBL Auction 2014',
 785                 'uploader': 'BADMINTON England',
 786                 'uploader_id': 'BADMINTONEvents',
 787                 'upload_date': '20140603',
 788                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 789             },
 790             'add_ie': ['Youtube'],
 791             'params': {
 792                 'skip_download': True,
 793             }
 794         },
 795         # MTVSercices embed
 796         {
 797             'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
 798             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
 799             'info_dict': {
 800                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
 801                 'ext': 'mp4',
 802                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
 803                 'description': 'Two valets share their love for movie star Liam Neesons.',
 804                 'timestamp': 1349922600,
 805                 'upload_date': '20121011',
 806             },
 807         },
 808         # YouTube embed via <data-embed-url="">
 809         {
 810             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 811             'info_dict': {
 812                 'id': '4vAffPZIT44',
 813                 'ext': 'mp4',
 814                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 815                 'uploader': 'Gameloft',
 816                 'uploader_id': 'gameloft',
 817                 'upload_date': '20140828',
 818                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 819             },
 820             'params': {
 821                 'skip_download': True,
 822             }
 823         },
 824         # YouTube <object> embed
 825         {
 826             'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
 827             'md5': '516718101ec834f74318df76259fb3cc',
 828             'info_dict': {
 829                 'id': 'msN87y-iEx0',
 830                 'ext': 'webm',
 831                 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
 832                 'upload_date': '20080526',
 833                 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
 834                 'uploader': 'Christopher Sykes',
 835                 'uploader_id': 'ChristopherJSykes',
 836             },
 837             'add_ie': ['Youtube'],
 838         },
 839         # Camtasia studio
 840         {
 841             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 842             'playlist': [{
 843                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 844                 'info_dict': {
 845                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 846                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 847                     'ext': 'flv',
 848                     'duration': 2235.90,
 849                 }
 850             }, {
 851                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 852                 'info_dict': {
 853                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 854                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 855                     'ext': 'flv',
 856                     'duration': 2235.93,
 857                 }
 858             }],
 859             'info_dict': {
 860                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 861             }
 862         },
 863         # Flowplayer
 864         {
 865             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 866             'md5': '9d65602bf31c6e20014319c7d07fba27',
 867             'info_dict': {
 868                 'id': '5123ea6d5e5a7',
 869                 'ext': 'mp4',
 870                 'age_limit': 18,
 871                 'uploader': 'www.handjobhub.com',
 872                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 873             }
 874         },
 875         # Multiple brightcove videos
 876         # https://github.com/rg3/youtube-dl/issues/2283
 877         {
 878             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 879             'info_dict': {
 880                 'id': 'always-never',
 881                 'title': 'Always / Never - The New Yorker',
 882             },
 883             'playlist_count': 3,
 884             'params': {
 885                 'extract_flat': False,
 886                 'skip_download': True,
 887             }
 888         },
 889         # MLB embed
 890         {
 891             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 892             'md5': '96f09a37e44da40dd083e12d9a683327',
 893             'info_dict': {
 894                 'id': '33322633',
 895                 'ext': 'mp4',
 896                 'title': 'Ump changes call to ball',
 897                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 898                 'duration': 48,
 899                 'timestamp': 1401537900,
 900                 'upload_date': '20140531',
 901                 'thumbnail': r're:^https?://.*\.jpg$',
 902             },
 903         },
 904         # Wistia embed
 905         {
 906             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 907             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 908             'info_dict': {
 909                 'id': '6e2wtrbdaf',
 910                 'ext': 'mov',
 911                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 912                 'description': 'a Paywall Videos video from Remilon',
 913                 'duration': 644.072,
 914                 'uploader': 'study.com',
 915                 'timestamp': 1459678540,
 916                 'upload_date': '20160403',
 917                 'filesize': 24687186,
 918             },
 919         },
 920         {
 921             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 922             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 923             'info_dict': {
 924                 'id': 'uxjb0lwrcz',
 925                 'ext': 'mp4',
 926                 'title': 'Conversation about Hexagonal Rails Part 1',
 927                 'description': 'a Martin Fowler video from ThoughtWorks',
 928                 'duration': 1715.0,
 929                 'uploader': 'thoughtworks.wistia.com',
 930                 'timestamp': 1401832161,
 931                 'upload_date': '20140603',
 932             },
 933         },
 934         # Wistia standard embed (async)
 935         {
 936             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 937             'info_dict': {
 938                 'id': '807fafadvk',
 939                 'ext': 'mp4',
 940                 'title': 'Drip Brennan Dunn Workshop',
 941                 'description': 'a JV Webinars video from getdrip-1',
 942                 'duration': 4986.95,
 943                 'timestamp': 1463607249,
 944                 'upload_date': '20160518',
 945             },
 946             'params': {
 947                 'skip_download': True,
 948             }
 949         },
 950         # Soundcloud embed
 951         {
 952             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 953             'info_dict': {
 954                 'id': '174391317',
 955                 'ext': 'mp3',
 956                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 957                 'uploader': 'Sophos Security',
 958                 'title': 'Chet Chat 171 - Oct 29, 2014',
 959                 'upload_date': '20141029',
 960             }
 961         },
 962         # Soundcloud multiple embeds
 963         {
 964             'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
 965             'info_dict': {
 966                 'id': '52809',
 967                 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
 968             },
 969             'playlist_mincount': 7,
 970         },
 971         # TuneIn station embed
 972         {
 973             'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
 974             'info_dict': {
 975                 'id': '204146',
 976                 'ext': 'mp3',
 977                 'title': 'CNRV',
 978                 'location': 'Paris, France',
 979                 'is_live': True,
 980             },
 981             'params': {
 982                 # Live stream
 983                 'skip_download': True,
 984             },
 985         },
 986         # Livestream embed
 987         {
 988             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 989             'info_dict': {
 990                 'id': '67864563',
 991                 'ext': 'flv',
 992                 'upload_date': '20141112',
 993                 'title': 'Rosetta #CometLanding webcast HL 10',
 994             }
 995         },
 996         # Another Livestream embed, without 'new.' in URL
 997         {
 998             'url': 'https://www.freespeech.org/',
 999             'info_dict': {
1000                 'id': '123537347',
1001                 'ext': 'mp4',
1002                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1003             },
1004             'params': {
1005                 # Live stream
1006                 'skip_download': True,
1007             },
1008         },
1009         # LazyYT
1010         {
1011             'url': 'https://skiplagged.com/',
1012             'info_dict': {
1013                 'id': 'skiplagged',
1014                 'title': 'Skiplagged: The smart way to find cheap flights',
1015             },
1016             'playlist_mincount': 1,
1017             'add_ie': ['Youtube'],
1018         },
1019         # Cinchcast embed
1020         {
1021             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1022             'info_dict': {
1023                 'id': '7141703',
1024                 'ext': 'mp3',
1025                 'upload_date': '20141126',
1026                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1027             }
1028         },
1029         # Cinerama player
1030         {
1031             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1032             'info_dict': {
1033                 'id': '730m_DandD_1901_512k',
1034                 'ext': 'mp4',
1035                 'uploader': 'www.abc.net.au',
1036                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1037             }
1038         },
1039         # embedded viddler video
1040         {
1041             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1042             'info_dict': {
1043                 'id': '4d03aad9',
1044                 'ext': 'mp4',
1045                 'uploader': 'deadspin',
1046                 'title': 'WALL-TO-GORTAT',
1047                 'timestamp': 1422285291,
1048                 'upload_date': '20150126',
1049             },
1050             'add_ie': ['Viddler'],
1051         },
1052         # Libsyn embed
1053         {
1054             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1055             'info_dict': {
1056                 'id': '3377616',
1057                 'ext': 'mp3',
1058                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1059                 'description': 'md5:601cb790edd05908957dae8aaa866465',
1060                 'upload_date': '20150220',
1061             },
1062             'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1063         },
1064         # jwplayer YouTube
1065         {
1066             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1067             'info_dict': {
1068                 'id': 'Mrj4DVp2zeA',
1069                 'ext': 'mp4',
1070                 'upload_date': '20150212',
1071                 'uploader': 'The National Archives UK',
1072                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1073                 'uploader_id': 'NationalArchives08',
1074                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1075             },
1076         },
1077         # jwplayer rtmp
1078         {
1079             'url': 'http://www.suffolk.edu/sjc/',
1080             'info_dict': {
1081                 'id': 'sjclive',
1082                 'ext': 'flv',
1083                 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1084                 'uploader': 'www.suffolk.edu',
1085             },
1086             'params': {
1087                 'skip_download': True,
1088             }
1089         },
1090         # Complex jwplayer
1091         {
1092             'url': 'http://www.indiedb.com/games/king-machine/videos',
1093             'info_dict': {
1094                 'id': 'videos',
1095                 'ext': 'mp4',
1096                 'title': 'king machine trailer 1',
1097                 'thumbnail': r're:^https?://.*\.jpg$',
1098             },
1099         },
1100         {
1101             # JWPlayer config passed as variable
1102             'url': 'http://www.txxx.com/videos/3326530/ariele/',
1103             'info_dict': {
1104                 'id': '3326530_hq',
1105                 'ext': 'mp4',
1106                 'title': 'ARIELE | Tube Cup',
1107                 'uploader': 'www.txxx.com',
1108                 'age_limit': 18,
1109             },
1110             'params': {
1111                 'skip_download': True,
1112             }
1113         },
1114         # rtl.nl embed
1115         {
1116             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1117             'playlist_mincount': 5,
1118             'info_dict': {
1119                 'id': 'aanslagen-kopenhagen',
1120                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1121             }
1122         },
1123         # Zapiks embed
1124         {
1125             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1126             'info_dict': {
1127                 'id': '118046',
1128                 'ext': 'mp4',
1129                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1130             }
1131         },
1132         # Kaltura embed (different embed code)
1133         {
1134             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1135             'info_dict': {
1136                 'id': '1_a52wc67y',
1137                 'ext': 'flv',
1138                 'upload_date': '20150127',
1139                 'uploader_id': 'PremierMedia',
1140                 'timestamp': int,
1141                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1142             },
1143         },
1144         # Kaltura embed with single quotes
1145         {
1146             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1147             'info_dict': {
1148                 'id': '0_izeg5utt',
1149                 'ext': 'mp4',
1150                 'title': '35871',
1151                 'timestamp': 1355743100,
1152                 'upload_date': '20121217',
1153                 'uploader_id': 'batchUser',
1154             },
1155             'add_ie': ['Kaltura'],
1156         },
1157         {
1158             # Kaltura embedded via quoted entry_id
1159             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1160             'info_dict': {
1161                 'id': '0_utuok90b',
1162                 'ext': 'mp4',
1163                 'title': '06_matthew_brender_raj_dutt',
1164                 'timestamp': 1466638791,
1165                 'upload_date': '20160622',
1166             },
1167             'add_ie': ['Kaltura'],
1168             'expected_warnings': [
1169                 'Could not send HEAD request'
1170             ],
1171             'params': {
1172                 'skip_download': True,
1173             }
1174         },
1175         {
1176             # Kaltura embedded, some fileExt broken (#11480)
1177             'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1178             'info_dict': {
1179                 'id': '1_sgtvehim',
1180                 'ext': 'mp4',
1181                 'title': 'Our "Standard Models" of particle physics and cosmology',
1182                 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1183                 'timestamp': 1321158993,
1184                 'upload_date': '20111113',
1185                 'uploader_id': 'kps1',
1186             },
1187             'add_ie': ['Kaltura'],
1188         },
1189         {
1190             # Kaltura iframe embed
1191             'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1192             'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1193             'info_dict': {
1194                 'id': '0_f2cfbpwy',
1195                 'ext': 'mp4',
1196                 'title': 'I. M. Pei: A Centennial Celebration',
1197                 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1198                 'upload_date': '20170403',
1199                 'uploader_id': 'batchUser',
1200                 'timestamp': 1491232186,
1201             },
1202             'add_ie': ['Kaltura'],
1203         },
1204         # EaglePlatform embed (generic URL)
1205         {
1206             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1207             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1208             'info_dict': {
1209                 'id': '227304',
1210                 'ext': 'mp4',
1211                 'title': 'Навальный вышел на свободу',
1212                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1213                 'thumbnail': r're:^https?://.*\.jpg$',
1214                 'duration': 87,
1215                 'view_count': int,
1216                 'age_limit': 0,
1217             },
1218             'params': {
1219                 'skip_download': True,
1220             },
1221         },
1222         # referrer protected EaglePlatform embed
1223         {
1224             'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1225             'info_dict': {
1226                 'id': '582306',
1227                 'ext': 'mp4',
1228                 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1229                 'thumbnail': r're:^https?://.*\.jpg$',
1230                 'duration': 3382,
1231                 'view_count': int,
1232             },
1233             'params': {
1234                 'skip_download': True,
1235             },
1236         },
1237         # ClipYou (EaglePlatform) embed (custom URL)
1238         {
1239             'url': 'http://muz-tv.ru/play/7129/',
1240             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1241             'info_dict': {
1242                 'id': '12820',
1243                 'ext': 'mp4',
1244                 'title': "'O Sole Mio",
1245                 'thumbnail': r're:^https?://.*\.jpg$',
1246                 'duration': 216,
1247                 'view_count': int,
1248             },
1249             'params': {
1250                 'skip_download': True,
1251             },
1252         },
1253         # Pladform embed
1254         {
1255             'url': 'http://muz-tv.ru/kinozal/view/7400/',
1256             'info_dict': {
1257                 'id': '100183293',
1258                 'ext': 'mp4',
1259                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1260                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1261                 'thumbnail': r're:^https?://.*\.jpg$',
1262                 'duration': 694,
1263                 'age_limit': 0,
1264             },
1265         },
1266         # Playwire embed
1267         {
1268             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1269             'info_dict': {
1270                 'id': '3519514',
1271                 'ext': 'mp4',
1272                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1273                 'thumbnail': r're:^https?://.*\.png$',
1274                 'duration': 45.115,
1275             },
1276         },
1277         # 5min embed
1278         {
1279             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1280             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1281             'info_dict': {
1282                 'id': '518726732',
1283                 'ext': 'mp4',
1284                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1285             },
1286         },
1287         # SVT embed
1288         {
1289             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1290             'info_dict': {
1291                 'id': '2900353',
1292                 'ext': 'flv',
1293                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1294                 'duration': 27,
1295                 'age_limit': 0,
1296             },
1297         },
1298         # Crooks and Liars embed
1299         {
1300             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1301             'info_dict': {
1302                 'id': '8RUoRhRi',
1303                 'ext': 'mp4',
1304                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1305                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1306                 'timestamp': 1428207000,
1307                 'upload_date': '20150405',
1308                 'uploader': 'Heather',
1309             },
1310         },
1311         # Crooks and Liars external embed
1312         {
1313             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1314             'info_dict': {
1315                 'id': 'MTE3MjUtMzQ2MzA',
1316                 'ext': 'mp4',
1317                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1318                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1319                 'timestamp': 1265032391,
1320                 'upload_date': '20100201',
1321                 'uploader': 'Heather',
1322             },
1323         },
1324         # NBC Sports vplayer embed
1325         {
1326             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1327             'info_dict': {
1328                 'id': 'ln7x1qSThw4k',
1329                 'ext': 'flv',
1330                 'title': "PFT Live: New leader in the 'new-look' defense",
1331                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1332                 'uploader': 'NBCU-SPORTS',
1333                 'upload_date': '20140107',
1334                 'timestamp': 1389118457,
1335             },
1336         },
1337         # NBC News embed
1338         {
1339             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1340             'md5': '1aa589c675898ae6d37a17913cf68d66',
1341             'info_dict': {
1342                 'id': '701714499682',
1343                 'ext': 'mp4',
1344                 'title': 'PREVIEW: On Assignment: David Letterman',
1345                 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1346             },
1347         },
1348         # UDN embed
1349         {
1350             'url': 'https://video.udn.com/news/300346',
1351             'md5': 'fd2060e988c326991037b9aff9df21a6',
1352             'info_dict': {
1353                 'id': '300346',
1354                 'ext': 'mp4',
1355                 'title': '中一中男師變性 全校師生力挺',
1356                 'thumbnail': r're:^https?://.*\.jpg$',
1357             },
1358             'params': {
1359                 # m3u8 download
1360                 'skip_download': True,
1361             },
1362         },
1363         # Ooyala embed
1364         {
1365             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1366             'info_dict': {
1367                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1368                 'ext': 'mp4',
1369                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1370                 'title': 'This is what separates the Excel masters from the wannabes',
1371                 'duration': 191.933,
1372             },
1373             'params': {
1374                 # m3u8 downloads
1375                 'skip_download': True,
1376             }
1377         },
1378         # Brightcove URL in single quotes
1379         {
1380             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1381             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1382             'info_dict': {
1383                 'id': '4255764656001',
1384                 'ext': 'mp4',
1385                 'title': 'SN Presents: Russell Martin, World Citizen',
1386                 '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.',
1387                 'uploader': 'Rogers Sportsnet',
1388                 'uploader_id': '1704050871',
1389                 'upload_date': '20150525',
1390                 'timestamp': 1432570283,
1391             },
1392         },
1393         # Dailymotion Cloud video
1394         {
1395             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1396             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1397             'info_dict': {
1398                 'id': 'x2uy8t3',
1399                 'ext': 'mp4',
1400                 'title': 'Sauvons les abeilles ! - Le débat',
1401                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1402                 'thumbnail': r're:^https?://.*\.jpe?g$',
1403                 'timestamp': 1434970506,
1404                 'upload_date': '20150622',
1405                 'uploader': 'Public Sénat',
1406                 'uploader_id': 'xa9gza',
1407             }
1408         },
1409         # OnionStudios embed
1410         {
1411             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1412             'info_dict': {
1413                 'id': '2855',
1414                 'ext': 'mp4',
1415                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1416                 'thumbnail': r're:^https?://.*\.jpe?g$',
1417                 'uploader': 'ClickHole',
1418                 'uploader_id': 'clickhole',
1419             }
1420         },
1421         # SnagFilms embed
1422         {
1423             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1424             'info_dict': {
1425                 'id': '74849a00-85a9-11e1-9660-123139220831',
1426                 'ext': 'mp4',
1427                 'title': '#whilewewatch',
1428             }
1429         },
1430         # AdobeTVVideo embed
1431         {
1432             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1433             'md5': '43662b577c018ad707a63766462b1e87',
1434             'info_dict': {
1435                 'id': '2456',
1436                 'ext': 'mp4',
1437                 'title': 'New experience with Acrobat DC',
1438                 'description': 'New experience with Acrobat DC',
1439                 'duration': 248.667,
1440             },
1441         },
1442         # BrightcoveInPageEmbed embed
1443         {
1444             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1445             'info_dict': {
1446                 'id': '4238694884001',
1447                 'ext': 'flv',
1448                 'title': 'Tabletop: Dread, Last Thoughts',
1449                 'description': 'Tabletop: Dread, Last Thoughts',
1450                 'duration': 51690,
1451             },
1452         },
1453         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1454         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1455         {
1456             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1457             'info_dict': {
1458                 'id': '4785848093001',
1459                 'ext': 'mp4',
1460                 'title': 'The Cardinal Pell Interview',
1461                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1462                 'uploader': 'GlobeCast Australia - GlobeStream',
1463                 'uploader_id': '2733773828001',
1464                 'upload_date': '20160304',
1465                 'timestamp': 1457083087,
1466             },
1467             'params': {
1468                 # m3u8 downloads
1469                 'skip_download': True,
1470             },
1471         },
1472         {
1473             # Brightcove embed with whitespace around attribute names
1474             'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1475             'info_dict': {
1476                 'id': '3167554373001',
1477                 'ext': 'mp4',
1478                 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1479                 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1480                 'uploader_id': '1079349493',
1481                 'upload_date': '20140207',
1482                 'timestamp': 1391810548,
1483             },
1484             'params': {
1485                 'skip_download': True,
1486             },
1487         },
1488         # Another form of arte.tv embed
1489         {
1490             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1491             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1492             'info_dict': {
1493                 'id': '030273-562_PLUS7-F',
1494                 'ext': 'mp4',
1495                 'title': 'ARTE Reportage - Nulle part, en France',
1496                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1497                 'upload_date': '20160409',
1498             },
1499         },
1500         # LiveLeak embed
1501         {
1502             'url': 'http://www.wykop.pl/link/3088787/',
1503             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1504             'info_dict': {
1505                 'id': '874_1459135191',
1506                 'ext': 'mp4',
1507                 'title': 'Man shows poor quality of new apartment building',
1508                 'description': 'The wall is like a sand pile.',
1509                 'uploader': 'Lake8737',
1510             }
1511         },
1512         # Duplicated embedded video URLs
1513         {
1514             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1515             'info_dict': {
1516                 'id': '149298443_480_16c25b74_2',
1517                 'ext': 'mp4',
1518                 'title': 'vs. Blue Orange Spring Game',
1519                 'uploader': 'www.hudl.com',
1520             },
1521         },
1522         # twitter:player:stream embed
1523         {
1524             'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1525             'info_dict': {
1526                 'id': 'master',
1527                 'ext': 'mp4',
1528                 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1529                 'uploader': 'www.rtl.be',
1530             },
1531             'params': {
1532                 # m3u8 downloads
1533                 'skip_download': True,
1534             },
1535         },
1536         # twitter:player embed
1537         {
1538             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1539             'md5': 'a3e0df96369831de324f0778e126653c',
1540             'info_dict': {
1541                 'id': '4909620399001',
1542                 'ext': 'mp4',
1543                 'title': 'What Do Black Holes Sound Like?',
1544                 'description': 'what do black holes sound like',
1545                 'upload_date': '20160524',
1546                 'uploader_id': '29913724001',
1547                 'timestamp': 1464107587,
1548                 'uploader': 'TheAtlantic',
1549             },
1550             'add_ie': ['BrightcoveLegacy'],
1551         },
1552         # Facebook <iframe> embed
1553         {
1554             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1555             'md5': 'fbcde74f534176ecb015849146dd3aee',
1556             'info_dict': {
1557                 'id': '599637780109885',
1558                 'ext': 'mp4',
1559                 'title': 'Facebook video #599637780109885',
1560             },
1561         },
1562         # Facebook <iframe> embed, plugin video
1563         {
1564             'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1565             'info_dict': {
1566                 'id': '1754168231264132',
1567                 'ext': 'mp4',
1568                 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1569                 'uploader': 'Tariq Ramadan (official)',
1570                 'timestamp': 1496758379,
1571                 'upload_date': '20170606',
1572             },
1573             'params': {
1574                 'skip_download': True,
1575             },
1576         },
1577         # Facebook API embed
1578         {
1579             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1580             'md5': 'a47372ee61b39a7b90287094d447d94e',
1581             'info_dict': {
1582                 'id': '10153467542406923',
1583                 'ext': 'mp4',
1584                 'title': 'Facebook video #10153467542406923',
1585             },
1586         },
1587         # Wordpress "YouTube Video Importer" plugin
1588         {
1589             'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1590             'md5': 'd16797741b560b485194eddda8121b48',
1591             'info_dict': {
1592                 'id': 'HNTXWDXV9Is',
1593                 'ext': 'mp4',
1594                 'title': 'Blue Devils Drumline Stanford lot 2016',
1595                 'upload_date': '20160627',
1596                 'uploader_id': 'GENOCIDE8GENERAL10',
1597                 'uploader': 'cylus cyrus',
1598             },
1599         },
1600         {
1601             # video stored on custom kaltura server
1602             'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1603             'md5': '537617d06e64dfed891fa1593c4b30cc',
1604             'info_dict': {
1605                 'id': '0_1iotm5bh',
1606                 'ext': 'mp4',
1607                 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1608                 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1609                 'uploader_id': 'videos.expansion@el-mundo.net',
1610                 'upload_date': '20150429',
1611                 'timestamp': 1430303472,
1612             },
1613             'add_ie': ['Kaltura'],
1614         },
1615         {
1616             # Non-standard Vimeo embed
1617             'url': 'https://openclassrooms.com/courses/understanding-the-web',
1618             'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1619             'info_dict': {
1620                 'id': '148867247',
1621                 'ext': 'mp4',
1622                 'title': 'Understanding the web - Teaser',
1623                 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1624                 'upload_date': '20151214',
1625                 'uploader': 'OpenClassrooms',
1626                 'uploader_id': 'openclassrooms',
1627             },
1628             'add_ie': ['Vimeo'],
1629         },
1630         {
1631             # generic vimeo embed that requires original URL passed as Referer
1632             'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1633             'only_matching': True,
1634         },
1635         {
1636             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1637             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1638             'info_dict': {
1639                 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1640                 'ext': 'mp4',
1641                 'title': 'Big Buck Bunny',
1642                 'description': 'Royalty free test video',
1643                 'timestamp': 1432816365,
1644                 'upload_date': '20150528',
1645                 'is_live': False,
1646             },
1647             'params': {
1648                 'skip_download': True,
1649             },
1650             'add_ie': [ArkenaIE.ie_key()],
1651         },
1652         {
1653             'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1654             'info_dict': {
1655                 'id': '1c7141f46c',
1656                 'ext': 'mp4',
1657                 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1658             },
1659             'params': {
1660                 'skip_download': True,
1661             },
1662             'add_ie': [Vbox7IE.ie_key()],
1663         },
1664         {
1665             # DBTV embeds
1666             'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1667             'info_dict': {
1668                 'id': '43254897',
1669                 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1670             },
1671             'playlist_mincount': 3,
1672         },
1673         {
1674             # Videa embeds
1675             'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1676             'info_dict': {
1677                 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1678                 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1679             },
1680             'playlist_mincount': 2,
1681         },
1682         {
1683             # 20 minuten embed
1684             'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1685             'info_dict': {
1686                 'id': '523629',
1687                 'ext': 'mp4',
1688                 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1689                 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1690             },
1691             'params': {
1692                 'skip_download': True,
1693             },
1694             'add_ie': [TwentyMinutenIE.ie_key()],
1695         },
1696         {
1697             # VideoPress embed
1698             'url': 'https://en.support.wordpress.com/videopress/',
1699             'info_dict': {
1700                 'id': 'OcobLTqC',
1701                 'ext': 'm4v',
1702                 'title': 'IMG_5786',
1703                 'timestamp': 1435711927,
1704                 'upload_date': '20150701',
1705             },
1706             'params': {
1707                 'skip_download': True,
1708             },
1709             'add_ie': [VideoPressIE.ie_key()],
1710         },
1711         {
1712             # Rutube embed
1713             'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1714             'info_dict': {
1715                 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1716                 'ext': 'flv',
1717                 'title': 'Магаззино: Казань 2',
1718                 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1719                 'uploader': 'Магаззино',
1720                 'upload_date': '20170228',
1721                 'uploader_id': '996642',
1722             },
1723             'params': {
1724                 'skip_download': True,
1725             },
1726             'add_ie': [RutubeIE.ie_key()],
1727         },
1728         {
1729             # ThePlatform embedded with whitespaces in URLs
1730             'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1731             'only_matching': True,
1732         },
1733         {
1734             # Senate ISVP iframe https
1735             'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1736             'md5': 'fb8c70b0b515e5037981a2492099aab8',
1737             'info_dict': {
1738                 'id': 'govtaff020316',
1739                 'ext': 'mp4',
1740                 'title': 'Integrated Senate Video Player',
1741             },
1742             'add_ie': [SenateISVPIE.ie_key()],
1743         },
1744         {
1745             # Limelight embeds (1 channel embed + 4 media embeds)
1746             'url': 'http://www.sedona.com/FacilitatorTraining2017',
1747             'info_dict': {
1748                 'id': 'FacilitatorTraining2017',
1749                 'title': 'Facilitator Training 2017',
1750             },
1751             'playlist_mincount': 5,
1752         },
1753         {
1754             'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1755             'info_dict': {
1756                 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1757                 'title': 'Standoff with Walnut Creek murder suspect ends',
1758                 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1759             },
1760             'playlist_mincount': 4,
1761         },
1762         {
1763             # WashingtonPost embed
1764             'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1765             'info_dict': {
1766                 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1767                 'ext': 'mp4',
1768                 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1769                 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1770                 'timestamp': 1455216756,
1771                 'uploader': 'The Washington Post',
1772                 'upload_date': '20160211',
1773             },
1774             'add_ie': [WashingtonPostIE.ie_key()],
1775         },
1776         {
1777             # Mediaset embed
1778             'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1779             'info_dict': {
1780                 'id': '720642',
1781                 'ext': 'mp4',
1782                 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1783             },
1784             'params': {
1785                 'skip_download': True,
1786             },
1787             'add_ie': [MediasetIE.ie_key()],
1788         },
1789         {
1790             # JOJ.sk embeds
1791             'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1792             'info_dict': {
1793                 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1794                 'title': 'Slovenskom sa prehnala vlna silných búrok',
1795             },
1796             'playlist_mincount': 5,
1797             'add_ie': [JojIE.ie_key()],
1798         },
1799         {
1800             # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1801             'url': 'https://tvrain.ru/amp/418921/',
1802             'md5': 'cc00413936695987e8de148b67d14f1d',
1803             'info_dict': {
1804                 'id': '418921',
1805                 'ext': 'mp4',
1806                 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1807             },
1808         },
1809         # {
1810         #     # TODO: find another test
1811         #     # http://schema.org/VideoObject
1812         #     'url': 'https://flipagram.com/f/nyvTSJMKId',
1813         #     'md5': '888dcf08b7ea671381f00fab74692755',
1814         #     'info_dict': {
1815         #         'id': 'nyvTSJMKId',
1816         #         'ext': 'mp4',
1817         #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1818         #         'description': '#love for cats.',
1819         #         'timestamp': 1461244995,
1820         #         'upload_date': '20160421',
1821         #     },
1822         #     'params': {
1823         #         'force_generic_extractor': True,
1824         #     },
1825         # }
1826     ]
1827
1828     def report_following_redirect(self, new_url):
1829         """Report information extraction."""
1830         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1831
1832     def _extract_rss(self, url, video_id, doc):
1833         playlist_title = doc.find('./channel/title').text
1834         playlist_desc_el = doc.find('./channel/description')
1835         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1836
1837         entries = []
1838         for it in doc.findall('./channel/item'):
1839             next_url = xpath_text(it, 'link', fatal=False)
1840             if not next_url:
1841                 enclosure_nodes = it.findall('./enclosure')
1842                 for e in enclosure_nodes:
1843                     next_url = e.attrib.get('url')
1844                     if next_url:
1845                         break
1846
1847             if not next_url:
1848                 continue
1849
1850             entries.append({
1851                 '_type': 'url_transparent',
1852                 'url': next_url,
1853                 'title': it.find('title').text,
1854             })
1855
1856         return {
1857             '_type': 'playlist',
1858             'id': url,
1859             'title': playlist_title,
1860             'description': playlist_desc,
1861             'entries': entries,
1862         }
1863
1864     def _extract_camtasia(self, url, video_id, webpage):
1865         """ Returns None if no camtasia video can be found. """
1866
1867         camtasia_cfg = self._search_regex(
1868             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1869             webpage, 'camtasia configuration file', default=None)
1870         if camtasia_cfg is None:
1871             return None
1872
1873         title = self._html_search_meta('DC.title', webpage, fatal=True)
1874
1875         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1876         camtasia_cfg = self._download_xml(
1877             camtasia_url, video_id,
1878             note='Downloading camtasia configuration',
1879             errnote='Failed to download camtasia configuration')
1880         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1881
1882         entries = []
1883         for n in fileset_node.getchildren():
1884             url_n = n.find('./uri')
1885             if url_n is None:
1886                 continue
1887
1888             entries.append({
1889                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1890                 'title': '%s - %s' % (title, n.tag),
1891                 'url': compat_urlparse.urljoin(url, url_n.text),
1892                 'duration': float_or_none(n.find('./duration').text),
1893             })
1894
1895         return {
1896             '_type': 'playlist',
1897             'entries': entries,
1898             'title': title,
1899         }
1900
1901     def _real_extract(self, url):
1902         if url.startswith('//'):
1903             return {
1904                 '_type': 'url',
1905                 'url': self.http_scheme() + url,
1906             }
1907
1908         parsed_url = compat_urlparse.urlparse(url)
1909         if not parsed_url.scheme:
1910             default_search = self._downloader.params.get('default_search')
1911             if default_search is None:
1912                 default_search = 'fixup_error'
1913
1914             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1915                 if '/' in url:
1916                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1917                     return self.url_result('http://' + url)
1918                 elif default_search != 'fixup_error':
1919                     if default_search == 'auto_warning':
1920                         if re.match(r'^(?:url|URL)$', url):
1921                             raise ExtractorError(
1922                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1923                                 expected=True)
1924                         else:
1925                             self._downloader.report_warning(
1926                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1927                     return self.url_result('ytsearch:' + url)
1928
1929             if default_search in ('error', 'fixup_error'):
1930                 raise ExtractorError(
1931                     '%r is not a valid URL. '
1932                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1933                     % (url, url), expected=True)
1934             else:
1935                 if ':' not in default_search:
1936                     default_search += ':'
1937                 return self.url_result(default_search + url)
1938
1939         url, smuggled_data = unsmuggle_url(url)
1940         force_videoid = None
1941         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1942         if smuggled_data and 'force_videoid' in smuggled_data:
1943             force_videoid = smuggled_data['force_videoid']
1944             video_id = force_videoid
1945         else:
1946             video_id = self._generic_id(url)
1947
1948         self.to_screen('%s: Requesting header' % video_id)
1949
1950         head_req = HEADRequest(url)
1951         head_response = self._request_webpage(
1952             head_req, video_id,
1953             note=False, errnote='Could not send HEAD request to %s' % url,
1954             fatal=False)
1955
1956         if head_response is not False:
1957             # Check for redirect
1958             new_url = head_response.geturl()
1959             if url != new_url:
1960                 self.report_following_redirect(new_url)
1961                 if force_videoid:
1962                     new_url = smuggle_url(
1963                         new_url, {'force_videoid': force_videoid})
1964                 return self.url_result(new_url)
1965
1966         full_response = None
1967         if head_response is False:
1968             request = sanitized_Request(url)
1969             request.add_header('Accept-Encoding', '*')
1970             full_response = self._request_webpage(request, video_id)
1971             head_response = full_response
1972
1973         info_dict = {
1974             'id': video_id,
1975             'title': self._generic_title(url),
1976             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1977         }
1978
1979         # Check for direct link to a video
1980         content_type = head_response.headers.get('Content-Type', '').lower()
1981         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1982         if m:
1983             format_id = compat_str(m.group('format_id'))
1984             if format_id.endswith('mpegurl'):
1985                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1986             elif format_id == 'f4m':
1987                 formats = self._extract_f4m_formats(url, video_id)
1988             else:
1989                 formats = [{
1990                     'format_id': format_id,
1991                     'url': url,
1992                     'vcodec': 'none' if m.group('type') == 'audio' else None
1993                 }]
1994                 info_dict['direct'] = True
1995             self._sort_formats(formats)
1996             info_dict['formats'] = formats
1997             return info_dict
1998
1999         if not self._downloader.params.get('test', False) and not is_intentional:
2000             force = self._downloader.params.get('force_generic_extractor', False)
2001             self._downloader.report_warning(
2002                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2003
2004         if not full_response:
2005             request = sanitized_Request(url)
2006             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2007             # making it impossible to download only chunk of the file (yet we need only 512kB to
2008             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2009             # that will always result in downloading the whole file that is not desirable.
2010             # Therefore for extraction pass we have to override Accept-Encoding to any in order
2011             # to accept raw bytes and being able to download only a chunk.
2012             # It may probably better to solve this by checking Content-Type for application/octet-stream
2013             # after HEAD request finishes, but not sure if we can rely on this.
2014             request.add_header('Accept-Encoding', '*')
2015             full_response = self._request_webpage(request, video_id)
2016
2017         first_bytes = full_response.read(512)
2018
2019         # Is it an M3U playlist?
2020         if first_bytes.startswith(b'#EXTM3U'):
2021             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2022             self._sort_formats(info_dict['formats'])
2023             return info_dict
2024
2025         # Maybe it's a direct link to a video?
2026         # Be careful not to download the whole thing!
2027         if not is_html(first_bytes):
2028             self._downloader.report_warning(
2029                 'URL could be a direct video link, returning it as such.')
2030             info_dict.update({
2031                 'direct': True,
2032                 'url': url,
2033             })
2034             return info_dict
2035
2036         webpage = self._webpage_read_content(
2037             full_response, url, video_id, prefix=first_bytes)
2038
2039         self.report_extraction(video_id)
2040
2041         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2042         try:
2043             doc = compat_etree_fromstring(webpage.encode('utf-8'))
2044             if doc.tag == 'rss':
2045                 return self._extract_rss(url, video_id, doc)
2046             elif doc.tag == 'SmoothStreamingMedia':
2047                 info_dict['formats'] = self._parse_ism_formats(doc, url)
2048                 self._sort_formats(info_dict['formats'])
2049                 return info_dict
2050             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2051                 smil = self._parse_smil(doc, url, video_id)
2052                 self._sort_formats(smil['formats'])
2053                 return smil
2054             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2055                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2056             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2057                 info_dict['formats'] = self._parse_mpd_formats(
2058                     doc, video_id,
2059                     mpd_base_url=full_response.geturl().rpartition('/')[0],
2060                     mpd_url=url)
2061                 self._sort_formats(info_dict['formats'])
2062                 return info_dict
2063             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2064                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2065                 self._sort_formats(info_dict['formats'])
2066                 return info_dict
2067         except compat_xml_parse_error:
2068             pass
2069
2070         # Is it a Camtasia project?
2071         camtasia_res = self._extract_camtasia(url, video_id, webpage)
2072         if camtasia_res is not None:
2073             return camtasia_res
2074
2075         # Sometimes embedded video player is hidden behind percent encoding
2076         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2077         # Unescaping the whole page allows to handle those cases in a generic way
2078         webpage = compat_urllib_parse_unquote(webpage)
2079
2080         # it's tempting to parse this further, but you would
2081         # have to take into account all the variations like
2082         #   Video Title - Site Name
2083         #   Site Name | Video Title
2084         #   Video Title - Tagline | Site Name
2085         # and so on and so forth; it's just not practical
2086         video_title = self._og_search_title(
2087             webpage, default=None) or self._html_search_regex(
2088             r'(?s)<title>(.*?)</title>', webpage, 'video title',
2089             default='video')
2090
2091         # Try to detect age limit automatically
2092         age_limit = self._rta_search(webpage)
2093         # And then there are the jokers who advertise that they use RTA,
2094         # but actually don't.
2095         AGE_LIMIT_MARKERS = [
2096             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2097         ]
2098         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2099             age_limit = 18
2100
2101         # video uploader is domain name
2102         video_uploader = self._search_regex(
2103             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2104
2105         video_description = self._og_search_description(webpage, default=None)
2106         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2107
2108         info_dict.update({
2109             'title': video_title,
2110             'description': video_description,
2111             'thumbnail': video_thumbnail,
2112             'age_limit': age_limit,
2113         })
2114
2115         # Look for Brightcove Legacy Studio embeds
2116         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2117         if bc_urls:
2118             entries = [{
2119                 '_type': 'url',
2120                 'url': smuggle_url(bc_url, {'Referer': url}),
2121                 'ie_key': 'BrightcoveLegacy'
2122             } for bc_url in bc_urls]
2123
2124             return {
2125                 '_type': 'playlist',
2126                 'title': video_title,
2127                 'id': video_id,
2128                 'entries': entries,
2129             }
2130
2131         # Look for Brightcove New Studio embeds
2132         bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2133         if bc_urls:
2134             return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2135
2136         # Look for ThePlatform embeds
2137         tp_urls = ThePlatformIE._extract_urls(webpage)
2138         if tp_urls:
2139             return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2140
2141         # Look for Vessel embeds
2142         vessel_urls = VesselIE._extract_urls(webpage)
2143         if vessel_urls:
2144             return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2145
2146         # Look for embedded rtl.nl player
2147         matches = re.findall(
2148             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2149             webpage)
2150         if matches:
2151             return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2152
2153         vimeo_urls = VimeoIE._extract_urls(url, webpage)
2154         if vimeo_urls:
2155             return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2156
2157         vid_me_embed_url = self._search_regex(
2158             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2159             webpage, 'vid.me embed', default=None)
2160         if vid_me_embed_url is not None:
2161             return self.url_result(vid_me_embed_url, 'Vidme')
2162
2163         # Look for embedded YouTube player
2164         matches = re.findall(r'''(?x)
2165             (?:
2166                 <iframe[^>]+?src=|
2167                 data-video-url=|
2168                 <embed[^>]+?src=|
2169                 embedSWF\(?:\s*|
2170                 <object[^>]+data=|
2171                 new\s+SWFObject\(
2172             )
2173             (["\'])
2174                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2175                 (?:embed|v|p)/.+?)
2176             \1''', webpage)
2177         if matches:
2178             return self.playlist_from_matches(
2179                 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2180
2181         # Look for lazyYT YouTube embed
2182         matches = re.findall(
2183             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2184         if matches:
2185             return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2186
2187         # Look for Wordpress "YouTube Video Importer" plugin
2188         matches = re.findall(r'''(?x)<div[^>]+
2189             class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2190             data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2191         if matches:
2192             return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2193
2194         matches = DailymotionIE._extract_urls(webpage)
2195         if matches:
2196             return self.playlist_from_matches(matches, video_id, video_title)
2197
2198         # Look for embedded Dailymotion playlist player (#3822)
2199         m = re.search(
2200             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2201         if m:
2202             playlists = re.findall(
2203                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2204             if playlists:
2205                 return self.playlist_from_matches(
2206                     playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2207
2208         # Look for DailyMail embeds
2209         dailymail_urls = DailyMailIE._extract_urls(webpage)
2210         if dailymail_urls:
2211             return self.playlist_from_matches(
2212                 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2213
2214         # Look for embedded Wistia player
2215         wistia_url = WistiaIE._extract_url(webpage)
2216         if wistia_url:
2217             return {
2218                 '_type': 'url_transparent',
2219                 'url': self._proto_relative_url(wistia_url),
2220                 'ie_key': WistiaIE.ie_key(),
2221                 'uploader': video_uploader,
2222             }
2223
2224         # Look for SVT player
2225         svt_url = SVTIE._extract_url(webpage)
2226         if svt_url:
2227             return self.url_result(svt_url, 'SVT')
2228
2229         # Look for Bandcamp pages with custom domain
2230         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2231         if mobj is not None:
2232             burl = unescapeHTML(mobj.group(1))
2233             # Don't set the extractor because it can be a track url or an album
2234             return self.url_result(burl)
2235
2236         # Look for embedded Vevo player
2237         mobj = re.search(
2238             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2239         if mobj is not None:
2240             return self.url_result(mobj.group('url'))
2241
2242         # Look for embedded Viddler player
2243         mobj = re.search(
2244             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2245             webpage)
2246         if mobj is not None:
2247             return self.url_result(mobj.group('url'))
2248
2249         # Look for NYTimes player
2250         mobj = re.search(
2251             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2252             webpage)
2253         if mobj is not None:
2254             return self.url_result(mobj.group('url'))
2255
2256         # Look for Libsyn player
2257         mobj = re.search(
2258             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2259         if mobj is not None:
2260             return self.url_result(mobj.group('url'))
2261
2262         # Look for Ooyala videos
2263         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2264                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2265                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2266                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2267         if mobj is not None:
2268             embed_token = self._search_regex(
2269                 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2270                 webpage, 'ooyala embed token', default=None)
2271             return OoyalaIE._build_url_result(smuggle_url(
2272                 mobj.group('ec'), {
2273                     'domain': url,
2274                     'embed_token': embed_token,
2275                 }))
2276
2277         # Look for multiple Ooyala embeds on SBN network websites
2278         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2279         if mobj is not None:
2280             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2281             if embeds:
2282                 return self.playlist_from_matches(
2283                     embeds, video_id, video_title,
2284                     getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2285
2286         # Look for Aparat videos
2287         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2288         if mobj is not None:
2289             return self.url_result(mobj.group(1), 'Aparat')
2290
2291         # Look for MPORA videos
2292         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2293         if mobj is not None:
2294             return self.url_result(mobj.group(1), 'Mpora')
2295
2296         # Look for embedded NovaMov-based player
2297         mobj = re.search(
2298             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2299                     (?P<url>http://(?:(?:embed|www)\.)?
2300                         (?:novamov\.com|
2301                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
2302                            videoweed\.(?:es|com)|
2303                            movshare\.(?:net|sx|ag)|
2304                            divxstage\.(?:eu|net|ch|co|at|ag))
2305                         /embed\.php.+?)\1''', webpage)
2306         if mobj is not None:
2307             return self.url_result(mobj.group('url'))
2308
2309         # Look for embedded Facebook player
2310         facebook_urls = FacebookIE._extract_urls(webpage)
2311         if facebook_urls:
2312             return self.playlist_from_matches(facebook_urls, video_id, video_title)
2313
2314         # Look for embedded VK player
2315         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2316         if mobj is not None:
2317             return self.url_result(mobj.group('url'), 'VK')
2318
2319         # Look for embedded Odnoklassniki player
2320         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2321         if mobj is not None:
2322             return self.url_result(mobj.group('url'), 'Odnoklassniki')
2323
2324         # Look for embedded ivi player
2325         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2326         if mobj is not None:
2327             return self.url_result(mobj.group('url'), 'Ivi')
2328
2329         # Look for embedded Huffington Post player
2330         mobj = re.search(
2331             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2332         if mobj is not None:
2333             return self.url_result(mobj.group('url'), 'HuffPost')
2334
2335         # Look for embed.ly
2336         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2337         if mobj is not None:
2338             return self.url_result(mobj.group('url'))
2339         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2340         if mobj is not None:
2341             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2342
2343         # Look for funnyordie embed
2344         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2345         if matches:
2346             return self.playlist_from_matches(
2347                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2348
2349         # Look for BBC iPlayer embed
2350         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2351         if matches:
2352             return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2353
2354         # Look for embedded RUTV player
2355         rutv_url = RUTVIE._extract_url(webpage)
2356         if rutv_url:
2357             return self.url_result(rutv_url, 'RUTV')
2358
2359         # Look for embedded TVC player
2360         tvc_url = TVCIE._extract_url(webpage)
2361         if tvc_url:
2362             return self.url_result(tvc_url, 'TVC')
2363
2364         # Look for embedded SportBox player
2365         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2366         if sportbox_urls:
2367             return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2368
2369         # Look for embedded XHamster player
2370         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2371         if xhamster_urls:
2372             return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2373
2374         # Look for embedded TNAFlixNetwork player
2375         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2376         if tnaflix_urls:
2377             return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2378
2379         # Look for embedded PornHub player
2380         pornhub_urls = PornHubIE._extract_urls(webpage)
2381         if pornhub_urls:
2382             return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2383
2384         # Look for embedded DrTuber player
2385         drtuber_urls = DrTuberIE._extract_urls(webpage)
2386         if drtuber_urls:
2387             return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2388
2389         # Look for embedded RedTube player
2390         redtube_urls = RedTubeIE._extract_urls(webpage)
2391         if redtube_urls:
2392             return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2393
2394         # Look for embedded Tvigle player
2395         mobj = re.search(
2396             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2397         if mobj is not None:
2398             return self.url_result(mobj.group('url'), 'Tvigle')
2399
2400         # Look for embedded TED player
2401         mobj = re.search(
2402             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2403         if mobj is not None:
2404             return self.url_result(mobj.group('url'), 'TED')
2405
2406         # Look for embedded Ustream videos
2407         ustream_url = UstreamIE._extract_url(webpage)
2408         if ustream_url:
2409             return self.url_result(ustream_url, UstreamIE.ie_key())
2410
2411         # Look for embedded arte.tv player
2412         mobj = re.search(
2413             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2414             webpage)
2415         if mobj is not None:
2416             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2417
2418         # Look for embedded francetv player
2419         mobj = re.search(
2420             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2421             webpage)
2422         if mobj is not None:
2423             return self.url_result(mobj.group('url'))
2424
2425         # Look for embedded smotri.com player
2426         smotri_url = SmotriIE._extract_url(webpage)
2427         if smotri_url:
2428             return self.url_result(smotri_url, 'Smotri')
2429
2430         # Look for embedded Myvi.ru player
2431         myvi_url = MyviIE._extract_url(webpage)
2432         if myvi_url:
2433             return self.url_result(myvi_url)
2434
2435         # Look for embedded soundcloud player
2436         soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2437         if soundcloud_urls:
2438             return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2439
2440         # Look for tunein player
2441         tunein_urls = TuneInBaseIE._extract_urls(webpage)
2442         if tunein_urls:
2443             return self.playlist_from_matches(tunein_urls, video_id, video_title)
2444
2445         # Look for embedded mtvservices player
2446         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2447         if mtvservices_url:
2448             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2449
2450         # Look for embedded yahoo player
2451         mobj = re.search(
2452             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2453             webpage)
2454         if mobj is not None:
2455             return self.url_result(mobj.group('url'), 'Yahoo')
2456
2457         # Look for embedded sbs.com.au player
2458         mobj = re.search(
2459             r'''(?x)
2460             (?:
2461                 <meta\s+property="og:video"\s+content=|
2462                 <iframe[^>]+?src=
2463             )
2464             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2465             webpage)
2466         if mobj is not None:
2467             return self.url_result(mobj.group('url'), 'SBS')
2468
2469         # Look for embedded Cinchcast player
2470         mobj = re.search(
2471             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2472             webpage)
2473         if mobj is not None:
2474             return self.url_result(mobj.group('url'), 'Cinchcast')
2475
2476         mobj = re.search(
2477             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2478             webpage)
2479         if not mobj:
2480             mobj = re.search(
2481                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2482                 webpage)
2483         if mobj is not None:
2484             return self.url_result(mobj.group('url'), 'MLB')
2485
2486         mobj = re.search(
2487             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2488             webpage)
2489         if mobj is not None:
2490             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2491
2492         mobj = re.search(
2493             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2494             webpage)
2495         if mobj is not None:
2496             return self.url_result(mobj.group('url'), 'Livestream')
2497
2498         # Look for Zapiks embed
2499         mobj = re.search(
2500             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2501         if mobj is not None:
2502             return self.url_result(mobj.group('url'), 'Zapiks')
2503
2504         # Look for Kaltura embeds
2505         kaltura_url = KalturaIE._extract_url(webpage)
2506         if kaltura_url:
2507             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2508
2509         # Look for EaglePlatform embeds
2510         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2511         if eagleplatform_url:
2512             return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2513
2514         # Look for ClipYou (uses EaglePlatform) embeds
2515         mobj = re.search(
2516             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2517         if mobj is not None:
2518             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2519
2520         # Look for Pladform embeds
2521         pladform_url = PladformIE._extract_url(webpage)
2522         if pladform_url:
2523             return self.url_result(pladform_url)
2524
2525         # Look for Videomore embeds
2526         videomore_url = VideomoreIE._extract_url(webpage)
2527         if videomore_url:
2528             return self.url_result(videomore_url)
2529
2530         # Look for Webcaster embeds
2531         webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2532         if webcaster_url:
2533             return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2534
2535         # Look for Playwire embeds
2536         mobj = re.search(
2537             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2538         if mobj is not None:
2539             return self.url_result(mobj.group('url'))
2540
2541         # Look for 5min embeds
2542         mobj = re.search(
2543             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2544         if mobj is not None:
2545             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2546
2547         # Look for Crooks and Liars embeds
2548         mobj = re.search(
2549             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2550         if mobj is not None:
2551             return self.url_result(mobj.group('url'))
2552
2553         # Look for NBC Sports VPlayer embeds
2554         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2555         if nbc_sports_url:
2556             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2557
2558         # Look for NBC News embeds
2559         nbc_news_embed_url = re.search(
2560             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2561         if nbc_news_embed_url:
2562             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2563
2564         # Look for Google Drive embeds
2565         google_drive_url = GoogleDriveIE._extract_url(webpage)
2566         if google_drive_url:
2567             return self.url_result(google_drive_url, 'GoogleDrive')
2568
2569         # Look for UDN embeds
2570         mobj = re.search(
2571             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2572         if mobj is not None:
2573             return self.url_result(
2574                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2575
2576         # Look for Senate ISVP iframe
2577         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2578         if senate_isvp_url:
2579             return self.url_result(senate_isvp_url, 'SenateISVP')
2580
2581         # Look for Dailymotion Cloud videos
2582         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2583         if dmcloud_url:
2584             return self.url_result(dmcloud_url, 'DailymotionCloud')
2585
2586         # Look for OnionStudios embeds
2587         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2588         if onionstudios_url:
2589             return self.url_result(onionstudios_url)
2590
2591         # Look for ViewLift embeds
2592         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2593         if viewlift_url:
2594             return self.url_result(viewlift_url)
2595
2596         # Look for JWPlatform embeds
2597         jwplatform_url = JWPlatformIE._extract_url(webpage)
2598         if jwplatform_url:
2599             return self.url_result(jwplatform_url, 'JWPlatform')
2600
2601         # Look for Digiteka embeds
2602         digiteka_url = DigitekaIE._extract_url(webpage)
2603         if digiteka_url:
2604             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2605
2606         # Look for Arkena embeds
2607         arkena_url = ArkenaIE._extract_url(webpage)
2608         if arkena_url:
2609             return self.url_result(arkena_url, ArkenaIE.ie_key())
2610
2611         # Look for Piksel embeds
2612         piksel_url = PikselIE._extract_url(webpage)
2613         if piksel_url:
2614             return self.url_result(piksel_url, PikselIE.ie_key())
2615
2616         # Look for Limelight embeds
2617         limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2618         if limelight_urls:
2619             return self.playlist_result(
2620                 limelight_urls, video_id, video_title, video_description)
2621
2622         # Look for Anvato embeds
2623         anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2624         if anvato_urls:
2625             return self.playlist_result(
2626                 anvato_urls, video_id, video_title, video_description)
2627
2628         # Look for AdobeTVVideo embeds
2629         mobj = re.search(
2630             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2631             webpage)
2632         if mobj is not None:
2633             return self.url_result(
2634                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2635                 'AdobeTVVideo')
2636
2637         # Look for Vine embeds
2638         mobj = re.search(
2639             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2640             webpage)
2641         if mobj is not None:
2642             return self.url_result(
2643                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2644
2645         # Look for VODPlatform embeds
2646         mobj = re.search(
2647             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2648             webpage)
2649         if mobj is not None:
2650             return self.url_result(
2651                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2652
2653         # Look for Mangomolo embeds
2654         mobj = re.search(
2655             r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2656                 (?:
2657                     video\?.*?\bid=(?P<video_id>\d+)|
2658                     index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2659                 ).+?)\1''', webpage)
2660         if mobj is not None:
2661             info = {
2662                 '_type': 'url_transparent',
2663                 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2664                 'title': video_title,
2665                 'description': video_description,
2666                 'thumbnail': video_thumbnail,
2667                 'uploader': video_uploader,
2668             }
2669             video_id = mobj.group('video_id')
2670             if video_id:
2671                 info.update({
2672                     'ie_key': 'MangomoloVideo',
2673                     'id': video_id,
2674                 })
2675             else:
2676                 info.update({
2677                     'ie_key': 'MangomoloLive',
2678                     'id': mobj.group('channel_id'),
2679                 })
2680             return info
2681
2682         # Look for Instagram embeds
2683         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2684         if instagram_embed_url is not None:
2685             return self.url_result(
2686                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2687
2688         # Look for LiveLeak embeds
2689         liveleak_url = LiveLeakIE._extract_url(webpage)
2690         if liveleak_url:
2691             return self.url_result(liveleak_url, 'LiveLeak')
2692
2693         # Look for 3Q SDN embeds
2694         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2695         if threeqsdn_url:
2696             return {
2697                 '_type': 'url_transparent',
2698                 'ie_key': ThreeQSDNIE.ie_key(),
2699                 'url': self._proto_relative_url(threeqsdn_url),
2700                 'title': video_title,
2701                 'description': video_description,
2702                 'thumbnail': video_thumbnail,
2703                 'uploader': video_uploader,
2704             }
2705
2706         # Look for VBOX7 embeds
2707         vbox7_url = Vbox7IE._extract_url(webpage)
2708         if vbox7_url:
2709             return self.url_result(vbox7_url, Vbox7IE.ie_key())
2710
2711         # Look for DBTV embeds
2712         dbtv_urls = DBTVIE._extract_urls(webpage)
2713         if dbtv_urls:
2714             return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2715
2716         # Look for Videa embeds
2717         videa_urls = VideaIE._extract_urls(webpage)
2718         if videa_urls:
2719             return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2720
2721         # Look for 20 minuten embeds
2722         twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2723         if twentymin_urls:
2724             return self.playlist_from_matches(
2725                 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2726
2727         # Look for Openload embeds
2728         openload_urls = OpenloadIE._extract_urls(webpage)
2729         if openload_urls:
2730             return self.playlist_from_matches(
2731                 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2732
2733         # Look for VideoPress embeds
2734         videopress_urls = VideoPressIE._extract_urls(webpage)
2735         if videopress_urls:
2736             return self.playlist_from_matches(
2737                 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2738
2739         # Look for Rutube embeds
2740         rutube_urls = RutubeIE._extract_urls(webpage)
2741         if rutube_urls:
2742             return self.playlist_from_matches(
2743                 rutube_urls, ie=RutubeIE.ie_key())
2744
2745         # Look for WashingtonPost embeds
2746         wapo_urls = WashingtonPostIE._extract_urls(webpage)
2747         if wapo_urls:
2748             return self.playlist_from_matches(
2749                 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2750
2751         # Look for Mediaset embeds
2752         mediaset_urls = MediasetIE._extract_urls(webpage)
2753         if mediaset_urls:
2754             return self.playlist_from_matches(
2755                 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2756
2757         # Look for JOJ.sk embeds
2758         joj_urls = JojIE._extract_urls(webpage)
2759         if joj_urls:
2760             return self.playlist_from_matches(
2761                 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2762
2763         def merge_dicts(dict1, dict2):
2764             merged = {}
2765             for k, v in dict1.items():
2766                 if v is not None:
2767                     merged[k] = v
2768             for k, v in dict2.items():
2769                 if v is None:
2770                     continue
2771                 if (k not in merged or
2772                         (isinstance(v, compat_str) and v and
2773                             isinstance(merged[k], compat_str) and
2774                             not merged[k])):
2775                     merged[k] = v
2776             return merged
2777
2778         # Looking for http://schema.org/VideoObject
2779         json_ld = self._search_json_ld(
2780             webpage, video_id, default={}, expected_type='VideoObject')
2781         if json_ld.get('url'):
2782             return merge_dicts(json_ld, info_dict)
2783
2784         # Look for HTML5 media
2785         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2786         if entries:
2787             for entry in entries:
2788                 entry.update({
2789                     'id': video_id,
2790                     'title': video_title,
2791                 })
2792                 self._sort_formats(entry['formats'])
2793             return self.playlist_result(entries)
2794
2795         jwplayer_data = self._find_jwplayer_data(
2796             webpage, video_id, transform_source=js_to_json)
2797         if jwplayer_data:
2798             info = self._parse_jwplayer_data(
2799                 jwplayer_data, video_id, require_title=False, base_url=url)
2800             return merge_dicts(info, info_dict)
2801
2802         def check_video(vurl):
2803             if YoutubeIE.suitable(vurl):
2804                 return True
2805             if RtmpIE.suitable(vurl):
2806                 return True
2807             vpath = compat_urlparse.urlparse(vurl).path
2808             vext = determine_ext(vpath)
2809             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2810
2811         def filter_video(urls):
2812             return list(filter(check_video, urls))
2813
2814         # Start with something easy: JW Player in SWFObject
2815         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2816         if not found:
2817             # Look for gorilla-vid style embedding
2818             found = filter_video(re.findall(r'''(?sx)
2819                 (?:
2820                     jw_plugins|
2821                     JWPlayerOptions|
2822                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2823                 )
2824                 .*?
2825                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2826         if not found:
2827             # Broaden the search a little bit
2828             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2829         if not found:
2830             # Broaden the findall a little bit: JWPlayer JS loader
2831             found = filter_video(re.findall(
2832                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2833         if not found:
2834             # Flow player
2835             found = filter_video(re.findall(r'''(?xs)
2836                 flowplayer\("[^"]+",\s*
2837                     \{[^}]+?\}\s*,
2838                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2839                         ["']?url["']?\s*:\s*["']([^"']+)["']
2840             ''', webpage))
2841         if not found:
2842             # Cinerama player
2843             found = re.findall(
2844                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2845         if not found:
2846             # Try to find twitter cards info
2847             # twitter:player:stream should be checked before twitter:player since
2848             # it is expected to contain a raw stream (see
2849             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2850             found = filter_video(re.findall(
2851                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2852         if not found:
2853             # We look for Open Graph info:
2854             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2855             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2856             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2857             if m_video_type is not None:
2858                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2859         if not found:
2860             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2861             found = re.search(
2862                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2863                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2864                 webpage)
2865             if not found:
2866                 # Look also in Refresh HTTP header
2867                 refresh_header = head_response.headers.get('Refresh')
2868                 if refresh_header:
2869                     # In python 2 response HTTP headers are bytestrings
2870                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2871                         refresh_header = refresh_header.decode('iso-8859-1')
2872                     found = re.search(REDIRECT_REGEX, refresh_header)
2873             if found:
2874                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2875                 if new_url != url:
2876                     self.report_following_redirect(new_url)
2877                     return {
2878                         '_type': 'url',
2879                         'url': new_url,
2880                     }
2881                 else:
2882                     found = None
2883
2884         if not found:
2885             # twitter:player is a https URL to iframe player that may or may not
2886             # be supported by youtube-dl thus this is checked the very last (see
2887             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2888             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2889             if embed_url:
2890                 return self.url_result(embed_url)
2891
2892         if not found:
2893             raise UnsupportedError(url)
2894
2895         entries = []
2896         for video_url in orderedSet(found):
2897             video_url = unescapeHTML(video_url)
2898             video_url = video_url.replace('\\/', '/')
2899             video_url = compat_urlparse.urljoin(url, video_url)
2900             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2901
2902             # Sometimes, jwplayer extraction will result in a YouTube URL
2903             if YoutubeIE.suitable(video_url):
2904                 entries.append(self.url_result(video_url, 'Youtube'))
2905                 continue
2906
2907             # here's a fun little line of code for you:
2908             video_id = os.path.splitext(video_id)[0]
2909
2910             entry_info_dict = {
2911                 'id': video_id,
2912                 'uploader': video_uploader,
2913                 'title': video_title,
2914                 'age_limit': age_limit,
2915             }
2916
2917             if RtmpIE.suitable(video_url):
2918                 entry_info_dict.update({
2919                     '_type': 'url_transparent',
2920                     'ie_key': RtmpIE.ie_key(),
2921                     'url': video_url,
2922                 })
2923                 entries.append(entry_info_dict)
2924                 continue
2925
2926             ext = determine_ext(video_url)
2927             if ext == 'smil':
2928                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2929             elif ext == 'xspf':
2930                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2931             elif ext == 'm3u8':
2932                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2933             elif ext == 'mpd':
2934                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2935             elif ext == 'f4m':
2936                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2937             elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2938                 # Just matching .ism/manifest is not enough to be reliably sure
2939                 # whether it's actually an ISM manifest or some other streaming
2940                 # manifest since there are various streaming URL formats
2941                 # possible (see [1]) as well as some other shenanigans like
2942                 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2943                 # so on.
2944                 # Thus the most reasonable way to solve this is to delegate
2945                 # to generic extractor in order to look into the contents of
2946                 # the manifest itself.
2947                 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2948                 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2949                 entry_info_dict = self.url_result(
2950                     smuggle_url(video_url, {'to_generic': True}),
2951                     GenericIE.ie_key())
2952             else:
2953                 entry_info_dict['url'] = video_url
2954
2955             if entry_info_dict.get('formats'):
2956                 self._sort_formats(entry_info_dict['formats'])
2957
2958             entries.append(entry_info_dict)
2959
2960         if len(entries) == 1:
2961             return entries[0]
2962         else:
2963             for num, e in enumerate(entries, start=1):
2964                 # 'url' results don't have a title
2965                 if e.get('title') is not None:
2966                     e['title'] = '%s (%d)' % (e['title'], num)
2967             return {
2968                 '_type': 'playlist',
2969                 'entries': entries,
2970             }