_ 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 .nexx import (
  40     NexxIE,
  41     NexxEmbedIE,
  42 )
  43 from .nbc import NBCSportsVPlayerIE
  44 from .ooyala import OoyalaIE
  45 from .rutv import RUTVIE
  46 from .tvc import TVCIE
  47 from .sportbox import SportBoxEmbedIE
  48 from .smotri import SmotriIE
  49 from .myvi import MyviIE
  50 from .condenast import CondeNastIE
  51 from .udn import UDNEmbedIE
  52 from .senateisvp import SenateISVPIE
  53 from .svt import SVTIE
  54 from .pornhub import PornHubIE
  55 from .xhamster import XHamsterEmbedIE
  56 from .tnaflix import TNAFlixNetworkEmbedIE
  57 from .drtuber import DrTuberIE
  58 from .redtube import RedTubeIE
  59 from .vimeo import VimeoIE
  60 from .dailymotion import (
  61     DailymotionIE,
  62     DailymotionCloudIE,
  63 )
  64 from .dailymail import DailyMailIE
  65 from .onionstudios import OnionStudiosIE
  66 from .viewlift import ViewLiftEmbedIE
  67 from .mtv import MTVServicesEmbeddedIE
  68 from .pladform import PladformIE
  69 from .videomore import VideomoreIE
  70 from .webcaster import WebcasterFeedIE
  71 from .googledrive import GoogleDriveIE
  72 from .jwplatform import JWPlatformIE
  73 from .digiteka import DigitekaIE
  74 from .arkena import ArkenaIE
  75 from .instagram import InstagramIE
  76 from .liveleak import LiveLeakIE
  77 from .threeqsdn import ThreeQSDNIE
  78 from .theplatform import ThePlatformIE
  79 from .vessel import VesselIE
  80 from .kaltura import KalturaIE
  81 from .eagleplatform import EaglePlatformIE
  82 from .facebook import FacebookIE
  83 from .soundcloud import SoundcloudIE
  84 from .tunein import TuneInBaseIE
  85 from .vbox7 import Vbox7IE
  86 from .dbtv import DBTVIE
  87 from .piksel import PikselIE
  88 from .videa import VideaIE
  89 from .twentymin import TwentyMinutenIE
  90 from .ustream import UstreamIE
  91 from .openload import OpenloadIE
  92 from .videopress import VideoPressIE
  93 from .rutube import RutubeIE
  94 from .limelight import LimelightBaseIE
  95 from .anvato import AnvatoIE
  96 from .washingtonpost import WashingtonPostIE
  97 from .wistia import WistiaIE
  98 from .mediaset import MediasetIE
  99 from .joj import JojIE
 100
 101
 102 class GenericIE(InfoExtractor):
 103     IE_DESC = 'Generic downloader that works on some sites'
 104     _VALID_URL = r'.*'
 105     IE_NAME = 'generic'
 106     _TESTS = [
 107         # Direct link to a video
 108         {
 109             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
 110             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
 111             'info_dict': {
 112                 'id': 'trailer',
 113                 'ext': 'mp4',
 114                 'title': 'trailer',
 115                 'upload_date': '20100513',
 116             }
 117         },
 118         # Direct link to media delivered compressed (until Accept-Encoding is *)
 119         {
 120             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
 121             'md5': '128c42e68b13950268b648275386fc74',
 122             'info_dict': {
 123                 'id': 'FictionJunction-Parallel_Hearts',
 124                 'ext': 'flac',
 125                 'title': 'FictionJunction-Parallel_Hearts',
 126                 'upload_date': '20140522',
 127             },
 128             'expected_warnings': [
 129                 'URL could be a direct video link, returning it as such.'
 130             ],
 131             'skip': 'URL invalid',
 132         },
 133         # Direct download with broken HEAD
 134         {
 135             'url': 'http://ai-radio.org:8000/radio.opus',
 136             'info_dict': {
 137                 'id': 'radio',
 138                 'ext': 'opus',
 139                 'title': 'radio',
 140             },
 141             'params': {
 142                 'skip_download': True,  # infinite live stream
 143             },
 144             'expected_warnings': [
 145                 r'501.*Not Implemented',
 146                 r'400.*Bad Request',
 147             ],
 148         },
 149         # Direct link with incorrect MIME type
 150         {
 151             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 152             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 153             'info_dict': {
 154                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 155                 'id': '5_Lennart_Poettering_-_Systemd',
 156                 'ext': 'webm',
 157                 'title': '5_Lennart_Poettering_-_Systemd',
 158                 'upload_date': '20141120',
 159             },
 160             'expected_warnings': [
 161                 'URL could be a direct video link, returning it as such.'
 162             ]
 163         },
 164         # RSS feed
 165         {
 166             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 167             'info_dict': {
 168                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 169                 'title': 'Zero Punctuation',
 170                 'description': 're:.*groundbreaking video review series.*'
 171             },
 172             'playlist_mincount': 11,
 173         },
 174         # RSS feed with enclosure
 175         {
 176             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 177             'info_dict': {
 178                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 179                 'ext': 'm4v',
 180                 'upload_date': '20150228',
 181                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 182             }
 183         },
 184         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 185         {
 186             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 187             'info_dict': {
 188                 'id': 'smil',
 189                 'ext': 'mp4',
 190                 'title': 'Automatics, robotics and biocybernetics',
 191                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 192                 'upload_date': '20130627',
 193                 'formats': 'mincount:16',
 194                 'subtitles': 'mincount:1',
 195             },
 196             'params': {
 197                 'force_generic_extractor': True,
 198                 'skip_download': True,
 199             },
 200         },
 201         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 202         {
 203             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 204             'info_dict': {
 205                 'id': 'hds',
 206                 'ext': 'flv',
 207                 'title': 'hds',
 208                 'formats': 'mincount:1',
 209             },
 210             'params': {
 211                 'skip_download': True,
 212             },
 213         },
 214         # SMIL from https://www.restudy.dk/video/play/id/1637
 215         {
 216             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 217             'info_dict': {
 218                 'id': 'video_1637',
 219                 'ext': 'flv',
 220                 'title': 'video_1637',
 221                 'formats': 'mincount:3',
 222             },
 223             'params': {
 224                 'skip_download': True,
 225             },
 226         },
 227         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 228         {
 229             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 230             'info_dict': {
 231                 'id': 'smil-service',
 232                 'ext': 'flv',
 233                 'title': 'smil-service',
 234                 'formats': 'mincount:1',
 235             },
 236             'params': {
 237                 'skip_download': True,
 238             },
 239         },
 240         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 241         {
 242             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 243             'info_dict': {
 244                 'id': '4719370',
 245                 'ext': 'mp4',
 246                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 247                 'formats': 'mincount:3',
 248             },
 249             'params': {
 250                 'skip_download': True,
 251             },
 252         },
 253         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 254         {
 255             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 256             'info_dict': {
 257                 'id': 'mZlp2ctYIUEB',
 258                 'ext': 'mp4',
 259                 'title': 'Tikibad ontruimd wegens brand',
 260                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 261                 'thumbnail': r're:^https?://.*\.jpg$',
 262                 'duration': 33,
 263             },
 264             'params': {
 265                 'skip_download': True,
 266             },
 267         },
 268         # MPD from http://dash-mse-test.appspot.com/media.html
 269         {
 270             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 271             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 272             'info_dict': {
 273                 'id': 'car-20120827-manifest',
 274                 'ext': 'mp4',
 275                 'title': 'car-20120827-manifest',
 276                 'formats': 'mincount:9',
 277                 'upload_date': '20130904',
 278             },
 279             'params': {
 280                 'format': 'bestvideo',
 281             },
 282         },
 283         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 284         {
 285             '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',
 286             'info_dict': {
 287                 'id': 'content',
 288                 'ext': 'mp4',
 289                 'title': 'content',
 290                 'formats': 'mincount:8',
 291             },
 292             'params': {
 293                 # m3u8 downloads
 294                 'skip_download': True,
 295             },
 296             'skip': 'video gone',
 297         },
 298         # m3u8 served with Content-Type: text/plain
 299         {
 300             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 301             'info_dict': {
 302                 'id': 'index',
 303                 'ext': 'mp4',
 304                 'title': 'index',
 305                 'upload_date': '20140720',
 306                 'formats': 'mincount:11',
 307             },
 308             'params': {
 309                 # m3u8 downloads
 310                 'skip_download': True,
 311             },
 312             'skip': 'video gone',
 313         },
 314         # google redirect
 315         {
 316             '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',
 317             'info_dict': {
 318                 'id': 'cmQHVoWB5FY',
 319                 'ext': 'mp4',
 320                 'upload_date': '20130224',
 321                 'uploader_id': 'TheVerge',
 322                 'description': r're:^Chris Ziegler takes a look at the\.*',
 323                 'uploader': 'The Verge',
 324                 'title': 'First Firefox OS phones side-by-side',
 325             },
 326             'params': {
 327                 'skip_download': False,
 328             }
 329         },
 330         {
 331             # redirect in Refresh HTTP header
 332             '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',
 333             'info_dict': {
 334                 'id': 'pO8h3EaFRdo',
 335                 'ext': 'mp4',
 336                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 337                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 338                 'upload_date': '20150917',
 339                 'uploader_id': 'brtvofficial',
 340                 'uploader': 'Boiler Room',
 341             },
 342             'params': {
 343                 'skip_download': False,
 344             },
 345         },
 346         {
 347             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 348             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 349             'info_dict': {
 350                 'id': '13601338388002',
 351                 'ext': 'mp4',
 352                 'uploader': 'www.hodiho.fr',
 353                 'title': 'R\u00e9gis plante sa Jeep',
 354             }
 355         },
 356         # bandcamp page with custom domain
 357         {
 358             'add_ie': ['Bandcamp'],
 359             'url': 'http://bronyrock.com/track/the-pony-mash',
 360             'info_dict': {
 361                 'id': '3235767654',
 362                 'ext': 'mp3',
 363                 'title': 'The Pony Mash',
 364                 'uploader': 'M_Pallante',
 365             },
 366             'skip': 'There is a limit of 200 free downloads / month for the test song',
 367         },
 368         {
 369             # embedded brightcove video
 370             # it also tests brightcove videos that need to set the 'Referer'
 371             # in the http requests
 372             'add_ie': ['BrightcoveLegacy'],
 373             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 374             'info_dict': {
 375                 'id': '2765128793001',
 376                 'ext': 'mp4',
 377                 'title': 'Le cours de bourse : l’analyse technique',
 378                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 379                 'uploader': 'BFM BUSINESS',
 380             },
 381             'params': {
 382                 'skip_download': True,
 383             },
 384         },
 385         {
 386             # embedded with itemprop embedURL and video id spelled as `idVideo`
 387             'add_id': ['BrightcoveLegacy'],
 388             'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
 389             'info_dict': {
 390                 'id': '5255628253001',
 391                 'ext': 'mp4',
 392                 'title': 'md5:37c519b1128915607601e75a87995fc0',
 393                 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
 394                 'uploader': 'BFM BUSINESS',
 395                 'uploader_id': '876450612001',
 396                 'timestamp': 1482255315,
 397                 'upload_date': '20161220',
 398             },
 399             'params': {
 400                 'skip_download': True,
 401             },
 402         },
 403         {
 404             # https://github.com/rg3/youtube-dl/issues/2253
 405             'url': 'http://bcove.me/i6nfkrc3',
 406             'md5': '0ba9446db037002366bab3b3eb30c88c',
 407             'info_dict': {
 408                 'id': '3101154703001',
 409                 'ext': 'mp4',
 410                 'title': 'Still no power',
 411                 'uploader': 'thestar.com',
 412                 '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.',
 413             },
 414             'add_ie': ['BrightcoveLegacy'],
 415             'skip': 'video gone',
 416         },
 417         {
 418             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 419             'md5': 'fb973ecf6e4a78a67453647444222983',
 420             'info_dict': {
 421                 'id': '3414141473001',
 422                 'ext': 'mp4',
 423                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 424                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 425                 'uploader': 'Championat',
 426             },
 427         },
 428         {
 429             # https://github.com/rg3/youtube-dl/issues/3541
 430             'add_ie': ['BrightcoveLegacy'],
 431             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 432             'info_dict': {
 433                 'id': '3866516442001',
 434                 'ext': 'mp4',
 435                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 436                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 437                 'uploader': 'SBS Broadcasting',
 438             },
 439             'skip': 'Restricted to Netherlands',
 440             'params': {
 441                 'skip_download': True,  # m3u8 download
 442             },
 443         },
 444         {
 445             # Brightcove video in <iframe>
 446             'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
 447             'md5': '36d74ef5e37c8b4a2ce92880d208b968',
 448             'info_dict': {
 449                 'id': '5360463607001',
 450                 'ext': 'mp4',
 451                 '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',
 452                 '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。',
 453                 'uploader': 'United Nations',
 454                 'uploader_id': '1362235914001',
 455                 'timestamp': 1489593889,
 456                 'upload_date': '20170315',
 457             },
 458             'add_ie': ['BrightcoveLegacy'],
 459         },
 460         {
 461             # Brightcove with alternative playerID key
 462             'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
 463             'info_dict': {
 464                 'id': 'nmeth.2062_SV1',
 465                 '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',
 466             },
 467             'playlist': [{
 468                 'info_dict': {
 469                     'id': '2228375078001',
 470                     'ext': 'mp4',
 471                     'title': 'nmeth.2062-sv1',
 472                     'description': 'nmeth.2062-sv1',
 473                     'timestamp': 1363357591,
 474                     'upload_date': '20130315',
 475                     'uploader': 'Nature Publishing Group',
 476                     'uploader_id': '1964492299001',
 477                 },
 478             }],
 479         },
 480         {
 481             # Brightcove with UUID in videoPlayer
 482             'url': 'http://www8.hp.com/cn/zh/home.html',
 483             'info_dict': {
 484                 'id': '5255815316001',
 485                 'ext': 'mp4',
 486                 'title': 'Sprocket Video - China',
 487                 'description': 'Sprocket Video - China',
 488                 'uploader': 'HP-Video Gallery',
 489                 'timestamp': 1482263210,
 490                 'upload_date': '20161220',
 491                 'uploader_id': '1107601872001',
 492             },
 493             'params': {
 494                 'skip_download': True,  # m3u8 download
 495             },
 496             'skip': 'video rotates...weekly?',
 497         },
 498         {
 499             # Brightcove:new type [2].
 500             'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
 501             'md5': '2b35148fcf48da41c9fb4591650784f3',
 502             'info_dict': {
 503                 'id': '5348741021001',
 504                 'ext': 'mp4',
 505                 'upload_date': '20170306',
 506                 'uploader_id': '4191638492001',
 507                 'timestamp': 1488769918,
 508                 'title': 'VIDEO:  St. Thomas More earns first trip to basketball semis',
 509
 510             },
 511         },
 512         {
 513             # Alternative brightcove <video> attributes
 514             '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/',
 515             'info_dict': {
 516                 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
 517                 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
 518             },
 519             'playlist': [{
 520                 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
 521                 'info_dict': {
 522                     'id': '5311302538001',
 523                     'ext': 'mp4',
 524                     'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
 525                     'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
 526                     'timestamp': 1486321708,
 527                     'upload_date': '20170205',
 528                     'uploader_id': '800000640001',
 529                 },
 530                 'only_matching': True,
 531             }],
 532         },
 533         {
 534             # Brightcove with UUID in videoPlayer
 535             'url': 'http://www8.hp.com/cn/zh/home.html',
 536             'info_dict': {
 537                 'id': '5255815316001',
 538                 'ext': 'mp4',
 539                 'title': 'Sprocket Video - China',
 540                 'description': 'Sprocket Video - China',
 541                 'uploader': 'HP-Video Gallery',
 542                 'timestamp': 1482263210,
 543                 'upload_date': '20161220',
 544                 'uploader_id': '1107601872001',
 545             },
 546             'params': {
 547                 'skip_download': True,  # m3u8 download
 548             },
 549         },
 550         # ooyala video
 551         {
 552             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 553             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 554             'info_dict': {
 555                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 556                 'ext': 'mp4',
 557                 'title': '2cc213299525360.mov',  # that's what we get
 558                 'duration': 238.231,
 559             },
 560             'add_ie': ['Ooyala'],
 561         },
 562         {
 563             # ooyala video embedded with http://player.ooyala.com/iframe.js
 564             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 565             'info_dict': {
 566                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 567                 'ext': 'mp4',
 568                 'title': '"Steve Jobs: Man in the Machine" trailer',
 569                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 570                 'duration': 135.427,
 571             },
 572             'params': {
 573                 'skip_download': True,
 574             },
 575             'skip': 'movie expired',
 576         },
 577         # embed.ly video
 578         {
 579             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 580             'info_dict': {
 581                 'id': '9ODmcdjQcHQ',
 582                 'ext': 'mp4',
 583                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 584                 'upload_date': '20140225',
 585                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 586                 'uploader': 'Tested',
 587                 'uploader_id': 'testedcom',
 588             },
 589             # No need to test YoutubeIE here
 590             'params': {
 591                 'skip_download': True,
 592             },
 593         },
 594         # funnyordie embed
 595         {
 596             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 597             'info_dict': {
 598                 'id': '18e820ec3f',
 599                 'ext': 'mp4',
 600                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 601                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 602             },
 603             # HEAD requests lead to endless 301, while GET is OK
 604             'expected_warnings': ['301'],
 605         },
 606         # RUTV embed
 607         {
 608             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 609             'info_dict': {
 610                 'id': '776940',
 611                 'ext': 'mp4',
 612                 'title': 'Охотское море стало целиком российским',
 613                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 614             },
 615             'params': {
 616                 # m3u8 download
 617                 'skip_download': True,
 618             },
 619         },
 620         # TVC embed
 621         {
 622             '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/',
 623             'info_dict': {
 624                 'id': '55304',
 625                 'ext': 'mp4',
 626                 'title': 'Дошкольное воспитание',
 627             },
 628         },
 629         # SportBox embed
 630         {
 631             'url': 'http://www.vestifinance.ru/articles/25753',
 632             'info_dict': {
 633                 'id': '25753',
 634                 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 635             },
 636             'playlist': [{
 637                 'info_dict': {
 638                     'id': '370908',
 639                     'title': 'Госзаказ. День 3',
 640                     'ext': 'mp4',
 641                 }
 642             }, {
 643                 'info_dict': {
 644                     'id': '370905',
 645                     'title': 'Госзаказ. День 2',
 646                     'ext': 'mp4',
 647                 }
 648             }, {
 649                 'info_dict': {
 650                     'id': '370902',
 651                     'title': 'Госзаказ. День 1',
 652                     'ext': 'mp4',
 653                 }
 654             }],
 655             'params': {
 656                 # m3u8 download
 657                 'skip_download': True,
 658             },
 659         },
 660         # Myvi.ru embed
 661         {
 662             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 663             'info_dict': {
 664                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 665                 'ext': 'mp4',
 666                 'title': 'Ужастики, русский трейлер (2015)',
 667                 'thumbnail': r're:^https?://.*\.jpg$',
 668                 'duration': 153,
 669             }
 670         },
 671         # XHamster embed
 672         {
 673             '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',
 674             'info_dict': {
 675                 'id': 'showthread',
 676                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 677             },
 678             'playlist_mincount': 7,
 679             # This forum does not allow <iframe> syntaxes anymore
 680             # Now HTML tags are displayed as-is
 681             'skip': 'No videos on this page',
 682         },
 683         # Embedded TED video
 684         {
 685             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 686             'md5': '65fdff94098e4a607385a60c5177c638',
 687             'info_dict': {
 688                 'id': '1969',
 689                 'ext': 'mp4',
 690                 'title': 'Hidden miracles of the natural world',
 691                 'uploader': 'Louie Schwartzberg',
 692                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 693             }
 694         },
 695         # nowvideo embed hidden behind percent encoding
 696         {
 697             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 698             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 699             'info_dict': {
 700                 'id': '06e53103ca9aa',
 701                 'ext': 'flv',
 702                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 703                 'description': 'No description',
 704             },
 705         },
 706         # arte embed
 707         {
 708             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 709             'md5': '7653032cbb25bf6c80d80f217055fa43',
 710             'info_dict': {
 711                 'id': '048195-004_PLUS7-F',
 712                 'ext': 'flv',
 713                 'title': 'X:enius',
 714                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 715                 'upload_date': '20140320',
 716             },
 717             'params': {
 718                 'skip_download': 'Requires rtmpdump'
 719             },
 720             'skip': 'video gone',
 721         },
 722         # francetv embed
 723         {
 724             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 725             'info_dict': {
 726                 'id': 'EV_30231',
 727                 'ext': 'mp4',
 728                 'title': 'Alcaline, le concert avec Calogero',
 729                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 730                 'upload_date': '20150226',
 731                 'timestamp': 1424989860,
 732                 'duration': 5400,
 733             },
 734             'params': {
 735                 # m3u8 downloads
 736                 'skip_download': True,
 737             },
 738             'expected_warnings': [
 739                 'Forbidden'
 740             ]
 741         },
 742         # Condé Nast embed
 743         {
 744             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 745             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 746             'info_dict': {
 747                 'id': '53501be369702d3275860000',
 748                 'ext': 'mp4',
 749                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 750             }
 751         },
 752         # Dailymotion embed
 753         {
 754             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 755             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 756             'info_dict': {
 757                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 758                 'ext': 'mp4',
 759                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 760                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 761                 'uploader': 'Spi0n',
 762                 'uploader_id': 'xgditw',
 763                 'upload_date': '20140425',
 764                 'timestamp': 1398441542,
 765             },
 766             'add_ie': ['Dailymotion'],
 767         },
 768         # DailyMail embed
 769         {
 770             'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
 771             'info_dict': {
 772                 'id': '1495629',
 773                 'ext': 'mp4',
 774                 'title': 'Care worker punches elderly dementia patient in head 11 times',
 775                 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
 776             },
 777             'add_ie': ['DailyMail'],
 778             'params': {
 779                 'skip_download': True,
 780             },
 781         },
 782         # YouTube embed
 783         {
 784             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 785             'info_dict': {
 786                 'id': 'FXRb4ykk4S0',
 787                 'ext': 'mp4',
 788                 'title': 'The NBL Auction 2014',
 789                 'uploader': 'BADMINTON England',
 790                 'uploader_id': 'BADMINTONEvents',
 791                 'upload_date': '20140603',
 792                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 793             },
 794             'add_ie': ['Youtube'],
 795             'params': {
 796                 'skip_download': True,
 797             }
 798         },
 799         # MTVSercices embed
 800         {
 801             'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
 802             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
 803             'info_dict': {
 804                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
 805                 'ext': 'mp4',
 806                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
 807                 'description': 'Two valets share their love for movie star Liam Neesons.',
 808                 'timestamp': 1349922600,
 809                 'upload_date': '20121011',
 810             },
 811         },
 812         # YouTube embed via <data-embed-url="">
 813         {
 814             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 815             'info_dict': {
 816                 'id': '4vAffPZIT44',
 817                 'ext': 'mp4',
 818                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 819                 'uploader': 'Gameloft',
 820                 'uploader_id': 'gameloft',
 821                 'upload_date': '20140828',
 822                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 823             },
 824             'params': {
 825                 'skip_download': True,
 826             }
 827         },
 828         # YouTube <object> embed
 829         {
 830             'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
 831             'md5': '516718101ec834f74318df76259fb3cc',
 832             'info_dict': {
 833                 'id': 'msN87y-iEx0',
 834                 'ext': 'webm',
 835                 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
 836                 'upload_date': '20080526',
 837                 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
 838                 'uploader': 'Christopher Sykes',
 839                 'uploader_id': 'ChristopherJSykes',
 840             },
 841             'add_ie': ['Youtube'],
 842         },
 843         # Camtasia studio
 844         {
 845             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 846             'playlist': [{
 847                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 848                 'info_dict': {
 849                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 850                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 851                     'ext': 'flv',
 852                     'duration': 2235.90,
 853                 }
 854             }, {
 855                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 856                 'info_dict': {
 857                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 858                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 859                     'ext': 'flv',
 860                     'duration': 2235.93,
 861                 }
 862             }],
 863             'info_dict': {
 864                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 865             }
 866         },
 867         # Flowplayer
 868         {
 869             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 870             'md5': '9d65602bf31c6e20014319c7d07fba27',
 871             'info_dict': {
 872                 'id': '5123ea6d5e5a7',
 873                 'ext': 'mp4',
 874                 'age_limit': 18,
 875                 'uploader': 'www.handjobhub.com',
 876                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 877             }
 878         },
 879         # Multiple brightcove videos
 880         # https://github.com/rg3/youtube-dl/issues/2283
 881         {
 882             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 883             'info_dict': {
 884                 'id': 'always-never',
 885                 'title': 'Always / Never - The New Yorker',
 886             },
 887             'playlist_count': 3,
 888             'params': {
 889                 'extract_flat': False,
 890                 'skip_download': True,
 891             }
 892         },
 893         # MLB embed
 894         {
 895             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 896             'md5': '96f09a37e44da40dd083e12d9a683327',
 897             'info_dict': {
 898                 'id': '33322633',
 899                 'ext': 'mp4',
 900                 'title': 'Ump changes call to ball',
 901                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 902                 'duration': 48,
 903                 'timestamp': 1401537900,
 904                 'upload_date': '20140531',
 905                 'thumbnail': r're:^https?://.*\.jpg$',
 906             },
 907         },
 908         # Wistia embed
 909         {
 910             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 911             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 912             'info_dict': {
 913                 'id': '6e2wtrbdaf',
 914                 'ext': 'mov',
 915                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 916                 'description': 'a Paywall Videos video from Remilon',
 917                 'duration': 644.072,
 918                 'uploader': 'study.com',
 919                 'timestamp': 1459678540,
 920                 'upload_date': '20160403',
 921                 'filesize': 24687186,
 922             },
 923         },
 924         {
 925             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 926             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 927             'info_dict': {
 928                 'id': 'uxjb0lwrcz',
 929                 'ext': 'mp4',
 930                 'title': 'Conversation about Hexagonal Rails Part 1',
 931                 'description': 'a Martin Fowler video from ThoughtWorks',
 932                 'duration': 1715.0,
 933                 'uploader': 'thoughtworks.wistia.com',
 934                 'timestamp': 1401832161,
 935                 'upload_date': '20140603',
 936             },
 937         },
 938         # Wistia standard embed (async)
 939         {
 940             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 941             'info_dict': {
 942                 'id': '807fafadvk',
 943                 'ext': 'mp4',
 944                 'title': 'Drip Brennan Dunn Workshop',
 945                 'description': 'a JV Webinars video from getdrip-1',
 946                 'duration': 4986.95,
 947                 'timestamp': 1463607249,
 948                 'upload_date': '20160518',
 949             },
 950             'params': {
 951                 'skip_download': True,
 952             }
 953         },
 954         # Soundcloud embed
 955         {
 956             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 957             'info_dict': {
 958                 'id': '174391317',
 959                 'ext': 'mp3',
 960                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 961                 'uploader': 'Sophos Security',
 962                 'title': 'Chet Chat 171 - Oct 29, 2014',
 963                 'upload_date': '20141029',
 964             }
 965         },
 966         # Soundcloud multiple embeds
 967         {
 968             'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
 969             'info_dict': {
 970                 'id': '52809',
 971                 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
 972             },
 973             'playlist_mincount': 7,
 974         },
 975         # TuneIn station embed
 976         {
 977             'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
 978             'info_dict': {
 979                 'id': '204146',
 980                 'ext': 'mp3',
 981                 'title': 'CNRV',
 982                 'location': 'Paris, France',
 983                 'is_live': True,
 984             },
 985             'params': {
 986                 # Live stream
 987                 'skip_download': True,
 988             },
 989         },
 990         # Livestream embed
 991         {
 992             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 993             'info_dict': {
 994                 'id': '67864563',
 995                 'ext': 'flv',
 996                 'upload_date': '20141112',
 997                 'title': 'Rosetta #CometLanding webcast HL 10',
 998             }
 999         },
1000         # Another Livestream embed, without 'new.' in URL
1001         {
1002             'url': 'https://www.freespeech.org/',
1003             'info_dict': {
1004                 'id': '123537347',
1005                 'ext': 'mp4',
1006                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1007             },
1008             'params': {
1009                 # Live stream
1010                 'skip_download': True,
1011             },
1012         },
1013         # LazyYT
1014         {
1015             'url': 'https://skiplagged.com/',
1016             'info_dict': {
1017                 'id': 'skiplagged',
1018                 'title': 'Skiplagged: The smart way to find cheap flights',
1019             },
1020             'playlist_mincount': 1,
1021             'add_ie': ['Youtube'],
1022         },
1023         # Cinchcast embed
1024         {
1025             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1026             'info_dict': {
1027                 'id': '7141703',
1028                 'ext': 'mp3',
1029                 'upload_date': '20141126',
1030                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1031             }
1032         },
1033         # Cinerama player
1034         {
1035             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1036             'info_dict': {
1037                 'id': '730m_DandD_1901_512k',
1038                 'ext': 'mp4',
1039                 'uploader': 'www.abc.net.au',
1040                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1041             }
1042         },
1043         # embedded viddler video
1044         {
1045             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1046             'info_dict': {
1047                 'id': '4d03aad9',
1048                 'ext': 'mp4',
1049                 'uploader': 'deadspin',
1050                 'title': 'WALL-TO-GORTAT',
1051                 'timestamp': 1422285291,
1052                 'upload_date': '20150126',
1053             },
1054             'add_ie': ['Viddler'],
1055         },
1056         # Libsyn embed
1057         {
1058             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1059             'info_dict': {
1060                 'id': '3377616',
1061                 'ext': 'mp3',
1062                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1063                 'description': 'md5:601cb790edd05908957dae8aaa866465',
1064                 'upload_date': '20150220',
1065             },
1066             'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1067         },
1068         # jwplayer YouTube
1069         {
1070             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1071             'info_dict': {
1072                 'id': 'Mrj4DVp2zeA',
1073                 'ext': 'mp4',
1074                 'upload_date': '20150212',
1075                 'uploader': 'The National Archives UK',
1076                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1077                 'uploader_id': 'NationalArchives08',
1078                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1079             },
1080         },
1081         # jwplayer rtmp
1082         {
1083             'url': 'http://www.suffolk.edu/sjc/',
1084             'info_dict': {
1085                 'id': 'sjclive',
1086                 'ext': 'flv',
1087                 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1088                 'uploader': 'www.suffolk.edu',
1089             },
1090             'params': {
1091                 'skip_download': True,
1092             }
1093         },
1094         # Complex jwplayer
1095         {
1096             'url': 'http://www.indiedb.com/games/king-machine/videos',
1097             'info_dict': {
1098                 'id': 'videos',
1099                 'ext': 'mp4',
1100                 'title': 'king machine trailer 1',
1101                 'thumbnail': r're:^https?://.*\.jpg$',
1102             },
1103         },
1104         {
1105             # JWPlayer config passed as variable
1106             'url': 'http://www.txxx.com/videos/3326530/ariele/',
1107             'info_dict': {
1108                 'id': '3326530_hq',
1109                 'ext': 'mp4',
1110                 'title': 'ARIELE | Tube Cup',
1111                 'uploader': 'www.txxx.com',
1112                 'age_limit': 18,
1113             },
1114             'params': {
1115                 'skip_download': True,
1116             }
1117         },
1118         # rtl.nl embed
1119         {
1120             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1121             'playlist_mincount': 5,
1122             'info_dict': {
1123                 'id': 'aanslagen-kopenhagen',
1124                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1125             }
1126         },
1127         # Zapiks embed
1128         {
1129             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1130             'info_dict': {
1131                 'id': '118046',
1132                 'ext': 'mp4',
1133                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1134             }
1135         },
1136         # Kaltura embed (different embed code)
1137         {
1138             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1139             'info_dict': {
1140                 'id': '1_a52wc67y',
1141                 'ext': 'flv',
1142                 'upload_date': '20150127',
1143                 'uploader_id': 'PremierMedia',
1144                 'timestamp': int,
1145                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1146             },
1147         },
1148         # Kaltura embed with single quotes
1149         {
1150             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1151             'info_dict': {
1152                 'id': '0_izeg5utt',
1153                 'ext': 'mp4',
1154                 'title': '35871',
1155                 'timestamp': 1355743100,
1156                 'upload_date': '20121217',
1157                 'uploader_id': 'batchUser',
1158             },
1159             'add_ie': ['Kaltura'],
1160         },
1161         {
1162             # Kaltura embedded via quoted entry_id
1163             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1164             'info_dict': {
1165                 'id': '0_utuok90b',
1166                 'ext': 'mp4',
1167                 'title': '06_matthew_brender_raj_dutt',
1168                 'timestamp': 1466638791,
1169                 'upload_date': '20160622',
1170             },
1171             'add_ie': ['Kaltura'],
1172             'expected_warnings': [
1173                 'Could not send HEAD request'
1174             ],
1175             'params': {
1176                 'skip_download': True,
1177             }
1178         },
1179         {
1180             # Kaltura embedded, some fileExt broken (#11480)
1181             'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1182             'info_dict': {
1183                 'id': '1_sgtvehim',
1184                 'ext': 'mp4',
1185                 'title': 'Our "Standard Models" of particle physics and cosmology',
1186                 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1187                 'timestamp': 1321158993,
1188                 'upload_date': '20111113',
1189                 'uploader_id': 'kps1',
1190             },
1191             'add_ie': ['Kaltura'],
1192         },
1193         {
1194             # Kaltura iframe embed
1195             'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1196             'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1197             'info_dict': {
1198                 'id': '0_f2cfbpwy',
1199                 'ext': 'mp4',
1200                 'title': 'I. M. Pei: A Centennial Celebration',
1201                 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1202                 'upload_date': '20170403',
1203                 'uploader_id': 'batchUser',
1204                 'timestamp': 1491232186,
1205             },
1206             'add_ie': ['Kaltura'],
1207         },
1208         # EaglePlatform embed (generic URL)
1209         {
1210             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1211             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1212             'info_dict': {
1213                 'id': '227304',
1214                 'ext': 'mp4',
1215                 'title': 'Навальный вышел на свободу',
1216                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1217                 'thumbnail': r're:^https?://.*\.jpg$',
1218                 'duration': 87,
1219                 'view_count': int,
1220                 'age_limit': 0,
1221             },
1222             'params': {
1223                 'skip_download': True,
1224             },
1225         },
1226         # referrer protected EaglePlatform embed
1227         {
1228             'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1229             'info_dict': {
1230                 'id': '582306',
1231                 'ext': 'mp4',
1232                 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1233                 'thumbnail': r're:^https?://.*\.jpg$',
1234                 'duration': 3382,
1235                 'view_count': int,
1236             },
1237             'params': {
1238                 'skip_download': True,
1239             },
1240         },
1241         # ClipYou (EaglePlatform) embed (custom URL)
1242         {
1243             'url': 'http://muz-tv.ru/play/7129/',
1244             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1245             'info_dict': {
1246                 'id': '12820',
1247                 'ext': 'mp4',
1248                 'title': "'O Sole Mio",
1249                 'thumbnail': r're:^https?://.*\.jpg$',
1250                 'duration': 216,
1251                 'view_count': int,
1252             },
1253             'params': {
1254                 'skip_download': True,
1255             },
1256         },
1257         # Pladform embed
1258         {
1259             'url': 'http://muz-tv.ru/kinozal/view/7400/',
1260             'info_dict': {
1261                 'id': '100183293',
1262                 'ext': 'mp4',
1263                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1264                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1265                 'thumbnail': r're:^https?://.*\.jpg$',
1266                 'duration': 694,
1267                 'age_limit': 0,
1268             },
1269         },
1270         # Playwire embed
1271         {
1272             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1273             'info_dict': {
1274                 'id': '3519514',
1275                 'ext': 'mp4',
1276                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1277                 'thumbnail': r're:^https?://.*\.png$',
1278                 'duration': 45.115,
1279             },
1280         },
1281         # 5min embed
1282         {
1283             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1284             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1285             'info_dict': {
1286                 'id': '518726732',
1287                 'ext': 'mp4',
1288                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1289             },
1290         },
1291         # SVT embed
1292         {
1293             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1294             'info_dict': {
1295                 'id': '2900353',
1296                 'ext': 'flv',
1297                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1298                 'duration': 27,
1299                 'age_limit': 0,
1300             },
1301         },
1302         # Crooks and Liars embed
1303         {
1304             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1305             'info_dict': {
1306                 'id': '8RUoRhRi',
1307                 'ext': 'mp4',
1308                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1309                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1310                 'timestamp': 1428207000,
1311                 'upload_date': '20150405',
1312                 'uploader': 'Heather',
1313             },
1314         },
1315         # Crooks and Liars external embed
1316         {
1317             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1318             'info_dict': {
1319                 'id': 'MTE3MjUtMzQ2MzA',
1320                 'ext': 'mp4',
1321                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1322                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1323                 'timestamp': 1265032391,
1324                 'upload_date': '20100201',
1325                 'uploader': 'Heather',
1326             },
1327         },
1328         # NBC Sports vplayer embed
1329         {
1330             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1331             'info_dict': {
1332                 'id': 'ln7x1qSThw4k',
1333                 'ext': 'flv',
1334                 'title': "PFT Live: New leader in the 'new-look' defense",
1335                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1336                 'uploader': 'NBCU-SPORTS',
1337                 'upload_date': '20140107',
1338                 'timestamp': 1389118457,
1339             },
1340         },
1341         # NBC News embed
1342         {
1343             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1344             'md5': '1aa589c675898ae6d37a17913cf68d66',
1345             'info_dict': {
1346                 'id': '701714499682',
1347                 'ext': 'mp4',
1348                 'title': 'PREVIEW: On Assignment: David Letterman',
1349                 '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.',
1350             },
1351         },
1352         # UDN embed
1353         {
1354             'url': 'https://video.udn.com/news/300346',
1355             'md5': 'fd2060e988c326991037b9aff9df21a6',
1356             'info_dict': {
1357                 'id': '300346',
1358                 'ext': 'mp4',
1359                 'title': '中一中男師變性 全校師生力挺',
1360                 'thumbnail': r're:^https?://.*\.jpg$',
1361             },
1362             'params': {
1363                 # m3u8 download
1364                 'skip_download': True,
1365             },
1366         },
1367         # Ooyala embed
1368         {
1369             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1370             'info_dict': {
1371                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1372                 'ext': 'mp4',
1373                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1374                 'title': 'This is what separates the Excel masters from the wannabes',
1375                 'duration': 191.933,
1376             },
1377             'params': {
1378                 # m3u8 downloads
1379                 'skip_download': True,
1380             }
1381         },
1382         # Brightcove URL in single quotes
1383         {
1384             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1385             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1386             'info_dict': {
1387                 'id': '4255764656001',
1388                 'ext': 'mp4',
1389                 'title': 'SN Presents: Russell Martin, World Citizen',
1390                 '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.',
1391                 'uploader': 'Rogers Sportsnet',
1392                 'uploader_id': '1704050871',
1393                 'upload_date': '20150525',
1394                 'timestamp': 1432570283,
1395             },
1396         },
1397         # Dailymotion Cloud video
1398         {
1399             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1400             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1401             'info_dict': {
1402                 'id': 'x2uy8t3',
1403                 'ext': 'mp4',
1404                 'title': 'Sauvons les abeilles ! - Le débat',
1405                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1406                 'thumbnail': r're:^https?://.*\.jpe?g$',
1407                 'timestamp': 1434970506,
1408                 'upload_date': '20150622',
1409                 'uploader': 'Public Sénat',
1410                 'uploader_id': 'xa9gza',
1411             }
1412         },
1413         # OnionStudios embed
1414         {
1415             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1416             'info_dict': {
1417                 'id': '2855',
1418                 'ext': 'mp4',
1419                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1420                 'thumbnail': r're:^https?://.*\.jpe?g$',
1421                 'uploader': 'ClickHole',
1422                 'uploader_id': 'clickhole',
1423             }
1424         },
1425         # SnagFilms embed
1426         {
1427             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1428             'info_dict': {
1429                 'id': '74849a00-85a9-11e1-9660-123139220831',
1430                 'ext': 'mp4',
1431                 'title': '#whilewewatch',
1432             }
1433         },
1434         # AdobeTVVideo embed
1435         {
1436             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1437             'md5': '43662b577c018ad707a63766462b1e87',
1438             'info_dict': {
1439                 'id': '2456',
1440                 'ext': 'mp4',
1441                 'title': 'New experience with Acrobat DC',
1442                 'description': 'New experience with Acrobat DC',
1443                 'duration': 248.667,
1444             },
1445         },
1446         # BrightcoveInPageEmbed embed
1447         {
1448             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1449             'info_dict': {
1450                 'id': '4238694884001',
1451                 'ext': 'flv',
1452                 'title': 'Tabletop: Dread, Last Thoughts',
1453                 'description': 'Tabletop: Dread, Last Thoughts',
1454                 'duration': 51690,
1455             },
1456         },
1457         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1458         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1459         {
1460             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1461             'info_dict': {
1462                 'id': '4785848093001',
1463                 'ext': 'mp4',
1464                 'title': 'The Cardinal Pell Interview',
1465                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1466                 'uploader': 'GlobeCast Australia - GlobeStream',
1467                 'uploader_id': '2733773828001',
1468                 'upload_date': '20160304',
1469                 'timestamp': 1457083087,
1470             },
1471             'params': {
1472                 # m3u8 downloads
1473                 'skip_download': True,
1474             },
1475         },
1476         {
1477             # Brightcove embed with whitespace around attribute names
1478             'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1479             'info_dict': {
1480                 'id': '3167554373001',
1481                 'ext': 'mp4',
1482                 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1483                 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1484                 'uploader_id': '1079349493',
1485                 'upload_date': '20140207',
1486                 'timestamp': 1391810548,
1487             },
1488             'params': {
1489                 'skip_download': True,
1490             },
1491         },
1492         # Another form of arte.tv embed
1493         {
1494             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1495             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1496             'info_dict': {
1497                 'id': '030273-562_PLUS7-F',
1498                 'ext': 'mp4',
1499                 'title': 'ARTE Reportage - Nulle part, en France',
1500                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1501                 'upload_date': '20160409',
1502             },
1503         },
1504         # LiveLeak embed
1505         {
1506             'url': 'http://www.wykop.pl/link/3088787/',
1507             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1508             'info_dict': {
1509                 'id': '874_1459135191',
1510                 'ext': 'mp4',
1511                 'title': 'Man shows poor quality of new apartment building',
1512                 'description': 'The wall is like a sand pile.',
1513                 'uploader': 'Lake8737',
1514             }
1515         },
1516         # Duplicated embedded video URLs
1517         {
1518             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1519             'info_dict': {
1520                 'id': '149298443_480_16c25b74_2',
1521                 'ext': 'mp4',
1522                 'title': 'vs. Blue Orange Spring Game',
1523                 'uploader': 'www.hudl.com',
1524             },
1525         },
1526         # twitter:player:stream embed
1527         {
1528             'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1529             'info_dict': {
1530                 'id': 'master',
1531                 'ext': 'mp4',
1532                 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1533                 'uploader': 'www.rtl.be',
1534             },
1535             'params': {
1536                 # m3u8 downloads
1537                 'skip_download': True,
1538             },
1539         },
1540         # twitter:player embed
1541         {
1542             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1543             'md5': 'a3e0df96369831de324f0778e126653c',
1544             'info_dict': {
1545                 'id': '4909620399001',
1546                 'ext': 'mp4',
1547                 'title': 'What Do Black Holes Sound Like?',
1548                 'description': 'what do black holes sound like',
1549                 'upload_date': '20160524',
1550                 'uploader_id': '29913724001',
1551                 'timestamp': 1464107587,
1552                 'uploader': 'TheAtlantic',
1553             },
1554             'add_ie': ['BrightcoveLegacy'],
1555         },
1556         # Nexx embed
1557         {
1558             'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1559             'info_dict': {
1560                 'id': '247746',
1561                 'ext': 'mp4',
1562                 'title': "Yesterday's Jam (OV)",
1563                 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1564                 'timestamp': 1492594816,
1565                 'upload_date': '20170419',
1566             },
1567             'params': {
1568                 'format': 'bestvideo',
1569                 'skip_download': True,
1570             },
1571         },
1572         # Nexx iFrame embed
1573         {
1574             'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html',
1575             'info_dict': {
1576                 'id': '161464',
1577                 'ext': 'mp4',
1578                 'title': 'Nervenkitzel Achterbahn',
1579                 'alt_title': 'Karussellbauer in Deutschland',
1580                 'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
1581                 'release_year': 2005,
1582                 'creator': 'SPIEGEL TV',
1583                 'thumbnail': r're:^https?://.*\.jpg$',
1584                 'duration': 2761,
1585                 'timestamp': 1394021479,
1586                 'upload_date': '20140305',
1587             },
1588             'params': {
1589                 'format': 'bestvideo',
1590                 'skip_download': True,
1591             },
1592         },
1593         # Facebook <iframe> embed
1594         {
1595             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1596             'md5': 'fbcde74f534176ecb015849146dd3aee',
1597             'info_dict': {
1598                 'id': '599637780109885',
1599                 'ext': 'mp4',
1600                 'title': 'Facebook video #599637780109885',
1601             },
1602         },
1603         # Facebook <iframe> embed, plugin video
1604         {
1605             'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1606             'info_dict': {
1607                 'id': '1754168231264132',
1608                 'ext': 'mp4',
1609                 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1610                 'uploader': 'Tariq Ramadan (official)',
1611                 'timestamp': 1496758379,
1612                 'upload_date': '20170606',
1613             },
1614             'params': {
1615                 'skip_download': True,
1616             },
1617         },
1618         # Facebook API embed
1619         {
1620             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1621             'md5': 'a47372ee61b39a7b90287094d447d94e',
1622             'info_dict': {
1623                 'id': '10153467542406923',
1624                 'ext': 'mp4',
1625                 'title': 'Facebook video #10153467542406923',
1626             },
1627         },
1628         # Wordpress "YouTube Video Importer" plugin
1629         {
1630             'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1631             'md5': 'd16797741b560b485194eddda8121b48',
1632             'info_dict': {
1633                 'id': 'HNTXWDXV9Is',
1634                 'ext': 'mp4',
1635                 'title': 'Blue Devils Drumline Stanford lot 2016',
1636                 'upload_date': '20160627',
1637                 'uploader_id': 'GENOCIDE8GENERAL10',
1638                 'uploader': 'cylus cyrus',
1639             },
1640         },
1641         {
1642             # video stored on custom kaltura server
1643             'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1644             'md5': '537617d06e64dfed891fa1593c4b30cc',
1645             'info_dict': {
1646                 'id': '0_1iotm5bh',
1647                 'ext': 'mp4',
1648                 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1649                 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1650                 'uploader_id': 'videos.expansion@el-mundo.net',
1651                 'upload_date': '20150429',
1652                 'timestamp': 1430303472,
1653             },
1654             'add_ie': ['Kaltura'],
1655         },
1656         {
1657             # Non-standard Vimeo embed
1658             'url': 'https://openclassrooms.com/courses/understanding-the-web',
1659             'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1660             'info_dict': {
1661                 'id': '148867247',
1662                 'ext': 'mp4',
1663                 'title': 'Understanding the web - Teaser',
1664                 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1665                 'upload_date': '20151214',
1666                 'uploader': 'OpenClassrooms',
1667                 'uploader_id': 'openclassrooms',
1668             },
1669             'add_ie': ['Vimeo'],
1670         },
1671         {
1672             # generic vimeo embed that requires original URL passed as Referer
1673             'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1674             'only_matching': True,
1675         },
1676         {
1677             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1678             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1679             'info_dict': {
1680                 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1681                 'ext': 'mp4',
1682                 'title': 'Big Buck Bunny',
1683                 'description': 'Royalty free test video',
1684                 'timestamp': 1432816365,
1685                 'upload_date': '20150528',
1686                 'is_live': False,
1687             },
1688             'params': {
1689                 'skip_download': True,
1690             },
1691             'add_ie': [ArkenaIE.ie_key()],
1692         },
1693         {
1694             '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/',
1695             'info_dict': {
1696                 'id': '1c7141f46c',
1697                 'ext': 'mp4',
1698                 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1699             },
1700             'params': {
1701                 'skip_download': True,
1702             },
1703             'add_ie': [Vbox7IE.ie_key()],
1704         },
1705         {
1706             # DBTV embeds
1707             'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1708             'info_dict': {
1709                 'id': '43254897',
1710                 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1711             },
1712             'playlist_mincount': 3,
1713         },
1714         {
1715             # Videa embeds
1716             'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1717             'info_dict': {
1718                 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1719                 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1720             },
1721             'playlist_mincount': 2,
1722         },
1723         {
1724             # 20 minuten embed
1725             'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1726             'info_dict': {
1727                 'id': '523629',
1728                 'ext': 'mp4',
1729                 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1730                 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1731             },
1732             'params': {
1733                 'skip_download': True,
1734             },
1735             'add_ie': [TwentyMinutenIE.ie_key()],
1736         },
1737         {
1738             # VideoPress embed
1739             'url': 'https://en.support.wordpress.com/videopress/',
1740             'info_dict': {
1741                 'id': 'OcobLTqC',
1742                 'ext': 'm4v',
1743                 'title': 'IMG_5786',
1744                 'timestamp': 1435711927,
1745                 'upload_date': '20150701',
1746             },
1747             'params': {
1748                 'skip_download': True,
1749             },
1750             'add_ie': [VideoPressIE.ie_key()],
1751         },
1752         {
1753             # Rutube embed
1754             'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1755             'info_dict': {
1756                 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1757                 'ext': 'flv',
1758                 'title': 'Магаззино: Казань 2',
1759                 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1760                 'uploader': 'Магаззино',
1761                 'upload_date': '20170228',
1762                 'uploader_id': '996642',
1763             },
1764             'params': {
1765                 'skip_download': True,
1766             },
1767             'add_ie': [RutubeIE.ie_key()],
1768         },
1769         {
1770             # ThePlatform embedded with whitespaces in URLs
1771             'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1772             'only_matching': True,
1773         },
1774         {
1775             # Senate ISVP iframe https
1776             'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1777             'md5': 'fb8c70b0b515e5037981a2492099aab8',
1778             'info_dict': {
1779                 'id': 'govtaff020316',
1780                 'ext': 'mp4',
1781                 'title': 'Integrated Senate Video Player',
1782             },
1783             'add_ie': [SenateISVPIE.ie_key()],
1784         },
1785         {
1786             # Limelight embeds (1 channel embed + 4 media embeds)
1787             'url': 'http://www.sedona.com/FacilitatorTraining2017',
1788             'info_dict': {
1789                 'id': 'FacilitatorTraining2017',
1790                 'title': 'Facilitator Training 2017',
1791             },
1792             'playlist_mincount': 5,
1793         },
1794         {
1795             'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1796             'info_dict': {
1797                 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1798                 'title': 'Standoff with Walnut Creek murder suspect ends',
1799                 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1800             },
1801             'playlist_mincount': 4,
1802         },
1803         {
1804             # WashingtonPost embed
1805             'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1806             'info_dict': {
1807                 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1808                 'ext': 'mp4',
1809                 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1810                 '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.',
1811                 'timestamp': 1455216756,
1812                 'uploader': 'The Washington Post',
1813                 'upload_date': '20160211',
1814             },
1815             'add_ie': [WashingtonPostIE.ie_key()],
1816         },
1817         {
1818             # Mediaset embed
1819             'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1820             'info_dict': {
1821                 'id': '720642',
1822                 'ext': 'mp4',
1823                 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1824             },
1825             'params': {
1826                 'skip_download': True,
1827             },
1828             'add_ie': [MediasetIE.ie_key()],
1829         },
1830         {
1831             # JOJ.sk embeds
1832             'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1833             'info_dict': {
1834                 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1835                 'title': 'Slovenskom sa prehnala vlna silných búrok',
1836             },
1837             'playlist_mincount': 5,
1838             'add_ie': [JojIE.ie_key()],
1839         },
1840         {
1841             # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1842             'url': 'https://tvrain.ru/amp/418921/',
1843             'md5': 'cc00413936695987e8de148b67d14f1d',
1844             'info_dict': {
1845                 'id': '418921',
1846                 'ext': 'mp4',
1847                 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1848             },
1849         },
1850         # {
1851         #     # TODO: find another test
1852         #     # http://schema.org/VideoObject
1853         #     'url': 'https://flipagram.com/f/nyvTSJMKId',
1854         #     'md5': '888dcf08b7ea671381f00fab74692755',
1855         #     'info_dict': {
1856         #         'id': 'nyvTSJMKId',
1857         #         'ext': 'mp4',
1858         #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1859         #         'description': '#love for cats.',
1860         #         'timestamp': 1461244995,
1861         #         'upload_date': '20160421',
1862         #     },
1863         #     'params': {
1864         #         'force_generic_extractor': True,
1865         #     },
1866         # }
1867     ]
1868
1869     def report_following_redirect(self, new_url):
1870         """Report information extraction."""
1871         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1872
1873     def _extract_rss(self, url, video_id, doc):
1874         playlist_title = doc.find('./channel/title').text
1875         playlist_desc_el = doc.find('./channel/description')
1876         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1877
1878         entries = []
1879         for it in doc.findall('./channel/item'):
1880             next_url = xpath_text(it, 'link', fatal=False)
1881             if not next_url:
1882                 enclosure_nodes = it.findall('./enclosure')
1883                 for e in enclosure_nodes:
1884                     next_url = e.attrib.get('url')
1885                     if next_url:
1886                         break
1887
1888             if not next_url:
1889                 continue
1890
1891             entries.append({
1892                 '_type': 'url_transparent',
1893                 'url': next_url,
1894                 'title': it.find('title').text,
1895             })
1896
1897         return {
1898             '_type': 'playlist',
1899             'id': url,
1900             'title': playlist_title,
1901             'description': playlist_desc,
1902             'entries': entries,
1903         }
1904
1905     def _extract_camtasia(self, url, video_id, webpage):
1906         """ Returns None if no camtasia video can be found. """
1907
1908         camtasia_cfg = self._search_regex(
1909             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1910             webpage, 'camtasia configuration file', default=None)
1911         if camtasia_cfg is None:
1912             return None
1913
1914         title = self._html_search_meta('DC.title', webpage, fatal=True)
1915
1916         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1917         camtasia_cfg = self._download_xml(
1918             camtasia_url, video_id,
1919             note='Downloading camtasia configuration',
1920             errnote='Failed to download camtasia configuration')
1921         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1922
1923         entries = []
1924         for n in fileset_node.getchildren():
1925             url_n = n.find('./uri')
1926             if url_n is None:
1927                 continue
1928
1929             entries.append({
1930                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1931                 'title': '%s - %s' % (title, n.tag),
1932                 'url': compat_urlparse.urljoin(url, url_n.text),
1933                 'duration': float_or_none(n.find('./duration').text),
1934             })
1935
1936         return {
1937             '_type': 'playlist',
1938             'entries': entries,
1939             'title': title,
1940         }
1941
1942     def _real_extract(self, url):
1943         if url.startswith('//'):
1944             return {
1945                 '_type': 'url',
1946                 'url': self.http_scheme() + url,
1947             }
1948
1949         parsed_url = compat_urlparse.urlparse(url)
1950         if not parsed_url.scheme:
1951             default_search = self._downloader.params.get('default_search')
1952             if default_search is None:
1953                 default_search = 'fixup_error'
1954
1955             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1956                 if '/' in url:
1957                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1958                     return self.url_result('http://' + url)
1959                 elif default_search != 'fixup_error':
1960                     if default_search == 'auto_warning':
1961                         if re.match(r'^(?:url|URL)$', url):
1962                             raise ExtractorError(
1963                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1964                                 expected=True)
1965                         else:
1966                             self._downloader.report_warning(
1967                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1968                     return self.url_result('ytsearch:' + url)
1969
1970             if default_search in ('error', 'fixup_error'):
1971                 raise ExtractorError(
1972                     '%r is not a valid URL. '
1973                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1974                     % (url, url), expected=True)
1975             else:
1976                 if ':' not in default_search:
1977                     default_search += ':'
1978                 return self.url_result(default_search + url)
1979
1980         url, smuggled_data = unsmuggle_url(url)
1981         force_videoid = None
1982         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1983         if smuggled_data and 'force_videoid' in smuggled_data:
1984             force_videoid = smuggled_data['force_videoid']
1985             video_id = force_videoid
1986         else:
1987             video_id = self._generic_id(url)
1988
1989         self.to_screen('%s: Requesting header' % video_id)
1990
1991         head_req = HEADRequest(url)
1992         head_response = self._request_webpage(
1993             head_req, video_id,
1994             note=False, errnote='Could not send HEAD request to %s' % url,
1995             fatal=False)
1996
1997         if head_response is not False:
1998             # Check for redirect
1999             new_url = head_response.geturl()
2000             if url != new_url:
2001                 self.report_following_redirect(new_url)
2002                 if force_videoid:
2003                     new_url = smuggle_url(
2004                         new_url, {'force_videoid': force_videoid})
2005                 return self.url_result(new_url)
2006
2007         full_response = None
2008         if head_response is False:
2009             request = sanitized_Request(url)
2010             request.add_header('Accept-Encoding', '*')
2011             full_response = self._request_webpage(request, video_id)
2012             head_response = full_response
2013
2014         info_dict = {
2015             'id': video_id,
2016             'title': self._generic_title(url),
2017             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2018         }
2019
2020         # Check for direct link to a video
2021         content_type = head_response.headers.get('Content-Type', '').lower()
2022         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2023         if m:
2024             format_id = compat_str(m.group('format_id'))
2025             if format_id.endswith('mpegurl'):
2026                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2027             elif format_id == 'f4m':
2028                 formats = self._extract_f4m_formats(url, video_id)
2029             else:
2030                 formats = [{
2031                     'format_id': format_id,
2032                     'url': url,
2033                     'vcodec': 'none' if m.group('type') == 'audio' else None
2034                 }]
2035                 info_dict['direct'] = True
2036             self._sort_formats(formats)
2037             info_dict['formats'] = formats
2038             return info_dict
2039
2040         if not self._downloader.params.get('test', False) and not is_intentional:
2041             force = self._downloader.params.get('force_generic_extractor', False)
2042             self._downloader.report_warning(
2043                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2044
2045         if not full_response:
2046             request = sanitized_Request(url)
2047             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2048             # making it impossible to download only chunk of the file (yet we need only 512kB to
2049             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2050             # that will always result in downloading the whole file that is not desirable.
2051             # Therefore for extraction pass we have to override Accept-Encoding to any in order
2052             # to accept raw bytes and being able to download only a chunk.
2053             # It may probably better to solve this by checking Content-Type for application/octet-stream
2054             # after HEAD request finishes, but not sure if we can rely on this.
2055             request.add_header('Accept-Encoding', '*')
2056             full_response = self._request_webpage(request, video_id)
2057
2058         first_bytes = full_response.read(512)
2059
2060         # Is it an M3U playlist?
2061         if first_bytes.startswith(b'#EXTM3U'):
2062             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2063             self._sort_formats(info_dict['formats'])
2064             return info_dict
2065
2066         # Maybe it's a direct link to a video?
2067         # Be careful not to download the whole thing!
2068         if not is_html(first_bytes):
2069             self._downloader.report_warning(
2070                 'URL could be a direct video link, returning it as such.')
2071             info_dict.update({
2072                 'direct': True,
2073                 'url': url,
2074             })
2075             return info_dict
2076
2077         webpage = self._webpage_read_content(
2078             full_response, url, video_id, prefix=first_bytes)
2079
2080         self.report_extraction(video_id)
2081
2082         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2083         try:
2084             doc = compat_etree_fromstring(webpage.encode('utf-8'))
2085             if doc.tag == 'rss':
2086                 return self._extract_rss(url, video_id, doc)
2087             elif doc.tag == 'SmoothStreamingMedia':
2088                 info_dict['formats'] = self._parse_ism_formats(doc, url)
2089                 self._sort_formats(info_dict['formats'])
2090                 return info_dict
2091             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2092                 smil = self._parse_smil(doc, url, video_id)
2093                 self._sort_formats(smil['formats'])
2094                 return smil
2095             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2096                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2097             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2098                 info_dict['formats'] = self._parse_mpd_formats(
2099                     doc, video_id,
2100                     mpd_base_url=full_response.geturl().rpartition('/')[0],
2101                     mpd_url=url)
2102                 self._sort_formats(info_dict['formats'])
2103                 return info_dict
2104             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2105                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2106                 self._sort_formats(info_dict['formats'])
2107                 return info_dict
2108         except compat_xml_parse_error:
2109             pass
2110
2111         # Is it a Camtasia project?
2112         camtasia_res = self._extract_camtasia(url, video_id, webpage)
2113         if camtasia_res is not None:
2114             return camtasia_res
2115
2116         # Sometimes embedded video player is hidden behind percent encoding
2117         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2118         # Unescaping the whole page allows to handle those cases in a generic way
2119         webpage = compat_urllib_parse_unquote(webpage)
2120
2121         # it's tempting to parse this further, but you would
2122         # have to take into account all the variations like
2123         #   Video Title - Site Name
2124         #   Site Name | Video Title
2125         #   Video Title - Tagline | Site Name
2126         # and so on and so forth; it's just not practical
2127         video_title = self._og_search_title(
2128             webpage, default=None) or self._html_search_regex(
2129             r'(?s)<title>(.*?)</title>', webpage, 'video title',
2130             default='video')
2131
2132         # Try to detect age limit automatically
2133         age_limit = self._rta_search(webpage)
2134         # And then there are the jokers who advertise that they use RTA,
2135         # but actually don't.
2136         AGE_LIMIT_MARKERS = [
2137             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2138         ]
2139         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2140             age_limit = 18
2141
2142         # video uploader is domain name
2143         video_uploader = self._search_regex(
2144             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2145
2146         video_description = self._og_search_description(webpage, default=None)
2147         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2148
2149         info_dict.update({
2150             'title': video_title,
2151             'description': video_description,
2152             'thumbnail': video_thumbnail,
2153             'age_limit': age_limit,
2154         })
2155
2156         # Look for Brightcove Legacy Studio embeds
2157         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2158         if bc_urls:
2159             entries = [{
2160                 '_type': 'url',
2161                 'url': smuggle_url(bc_url, {'Referer': url}),
2162                 'ie_key': 'BrightcoveLegacy'
2163             } for bc_url in bc_urls]
2164
2165             return {
2166                 '_type': 'playlist',
2167                 'title': video_title,
2168                 'id': video_id,
2169                 'entries': entries,
2170             }
2171
2172         # Look for Brightcove New Studio embeds
2173         bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2174         if bc_urls:
2175             return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2176
2177         # Look for Nexx embeds
2178         nexx_urls = NexxIE._extract_urls(webpage)
2179         if nexx_urls:
2180             return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2181
2182         # Look for Nexx iFrame embeds
2183         nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2184         if nexx_embed_urls:
2185             return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2186
2187         # Look for ThePlatform embeds
2188         tp_urls = ThePlatformIE._extract_urls(webpage)
2189         if tp_urls:
2190             return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2191
2192         # Look for Vessel embeds
2193         vessel_urls = VesselIE._extract_urls(webpage)
2194         if vessel_urls:
2195             return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2196
2197         # Look for embedded rtl.nl player
2198         matches = re.findall(
2199             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2200             webpage)
2201         if matches:
2202             return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2203
2204         vimeo_urls = VimeoIE._extract_urls(url, webpage)
2205         if vimeo_urls:
2206             return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2207
2208         vid_me_embed_url = self._search_regex(
2209             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2210             webpage, 'vid.me embed', default=None)
2211         if vid_me_embed_url is not None:
2212             return self.url_result(vid_me_embed_url, 'Vidme')
2213
2214         # Look for embedded YouTube player
2215         matches = re.findall(r'''(?x)
2216             (?:
2217                 <iframe[^>]+?src=|
2218                 data-video-url=|
2219                 <embed[^>]+?src=|
2220                 embedSWF\(?:\s*|
2221                 <object[^>]+data=|
2222                 new\s+SWFObject\(
2223             )
2224             (["\'])
2225                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2226                 (?:embed|v|p)/.+?)
2227             \1''', webpage)
2228         if matches:
2229             return self.playlist_from_matches(
2230                 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2231
2232         # Look for lazyYT YouTube embed
2233         matches = re.findall(
2234             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2235         if matches:
2236             return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2237
2238         # Look for Wordpress "YouTube Video Importer" plugin
2239         matches = re.findall(r'''(?x)<div[^>]+
2240             class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2241             data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2242         if matches:
2243             return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2244
2245         matches = DailymotionIE._extract_urls(webpage)
2246         if matches:
2247             return self.playlist_from_matches(matches, video_id, video_title)
2248
2249         # Look for embedded Dailymotion playlist player (#3822)
2250         m = re.search(
2251             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2252         if m:
2253             playlists = re.findall(
2254                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2255             if playlists:
2256                 return self.playlist_from_matches(
2257                     playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2258
2259         # Look for DailyMail embeds
2260         dailymail_urls = DailyMailIE._extract_urls(webpage)
2261         if dailymail_urls:
2262             return self.playlist_from_matches(
2263                 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2264
2265         # Look for embedded Wistia player
2266         wistia_url = WistiaIE._extract_url(webpage)
2267         if wistia_url:
2268             return {
2269                 '_type': 'url_transparent',
2270                 'url': self._proto_relative_url(wistia_url),
2271                 'ie_key': WistiaIE.ie_key(),
2272                 'uploader': video_uploader,
2273             }
2274
2275         # Look for SVT player
2276         svt_url = SVTIE._extract_url(webpage)
2277         if svt_url:
2278             return self.url_result(svt_url, 'SVT')
2279
2280         # Look for Bandcamp pages with custom domain
2281         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2282         if mobj is not None:
2283             burl = unescapeHTML(mobj.group(1))
2284             # Don't set the extractor because it can be a track url or an album
2285             return self.url_result(burl)
2286
2287         # Look for embedded Vevo player
2288         mobj = re.search(
2289             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2290         if mobj is not None:
2291             return self.url_result(mobj.group('url'))
2292
2293         # Look for embedded Viddler player
2294         mobj = re.search(
2295             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2296             webpage)
2297         if mobj is not None:
2298             return self.url_result(mobj.group('url'))
2299
2300         # Look for NYTimes player
2301         mobj = re.search(
2302             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2303             webpage)
2304         if mobj is not None:
2305             return self.url_result(mobj.group('url'))
2306
2307         # Look for Libsyn player
2308         mobj = re.search(
2309             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2310         if mobj is not None:
2311             return self.url_result(mobj.group('url'))
2312
2313         # Look for Ooyala videos
2314         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2315                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2316                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2317                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2318         if mobj is not None:
2319             embed_token = self._search_regex(
2320                 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2321                 webpage, 'ooyala embed token', default=None)
2322             return OoyalaIE._build_url_result(smuggle_url(
2323                 mobj.group('ec'), {
2324                     'domain': url,
2325                     'embed_token': embed_token,
2326                 }))
2327
2328         # Look for multiple Ooyala embeds on SBN network websites
2329         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2330         if mobj is not None:
2331             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2332             if embeds:
2333                 return self.playlist_from_matches(
2334                     embeds, video_id, video_title,
2335                     getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2336
2337         # Look for Aparat videos
2338         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2339         if mobj is not None:
2340             return self.url_result(mobj.group(1), 'Aparat')
2341
2342         # Look for MPORA videos
2343         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2344         if mobj is not None:
2345             return self.url_result(mobj.group(1), 'Mpora')
2346
2347         # Look for embedded NovaMov-based player
2348         mobj = re.search(
2349             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2350                     (?P<url>http://(?:(?:embed|www)\.)?
2351                         (?:novamov\.com|
2352                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
2353                            videoweed\.(?:es|com)|
2354                            movshare\.(?:net|sx|ag)|
2355                            divxstage\.(?:eu|net|ch|co|at|ag))
2356                         /embed\.php.+?)\1''', webpage)
2357         if mobj is not None:
2358             return self.url_result(mobj.group('url'))
2359
2360         # Look for embedded Facebook player
2361         facebook_urls = FacebookIE._extract_urls(webpage)
2362         if facebook_urls:
2363             return self.playlist_from_matches(facebook_urls, video_id, video_title)
2364
2365         # Look for embedded VK player
2366         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2367         if mobj is not None:
2368             return self.url_result(mobj.group('url'), 'VK')
2369
2370         # Look for embedded Odnoklassniki player
2371         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2372         if mobj is not None:
2373             return self.url_result(mobj.group('url'), 'Odnoklassniki')
2374
2375         # Look for embedded ivi player
2376         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2377         if mobj is not None:
2378             return self.url_result(mobj.group('url'), 'Ivi')
2379
2380         # Look for embedded Huffington Post player
2381         mobj = re.search(
2382             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2383         if mobj is not None:
2384             return self.url_result(mobj.group('url'), 'HuffPost')
2385
2386         # Look for embed.ly
2387         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2388         if mobj is not None:
2389             return self.url_result(mobj.group('url'))
2390         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2391         if mobj is not None:
2392             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2393
2394         # Look for funnyordie embed
2395         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2396         if matches:
2397             return self.playlist_from_matches(
2398                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2399
2400         # Look for BBC iPlayer embed
2401         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2402         if matches:
2403             return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2404
2405         # Look for embedded RUTV player
2406         rutv_url = RUTVIE._extract_url(webpage)
2407         if rutv_url:
2408             return self.url_result(rutv_url, 'RUTV')
2409
2410         # Look for embedded TVC player
2411         tvc_url = TVCIE._extract_url(webpage)
2412         if tvc_url:
2413             return self.url_result(tvc_url, 'TVC')
2414
2415         # Look for embedded SportBox player
2416         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2417         if sportbox_urls:
2418             return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2419
2420         # Look for embedded XHamster player
2421         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2422         if xhamster_urls:
2423             return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2424
2425         # Look for embedded TNAFlixNetwork player
2426         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2427         if tnaflix_urls:
2428             return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2429
2430         # Look for embedded PornHub player
2431         pornhub_urls = PornHubIE._extract_urls(webpage)
2432         if pornhub_urls:
2433             return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2434
2435         # Look for embedded DrTuber player
2436         drtuber_urls = DrTuberIE._extract_urls(webpage)
2437         if drtuber_urls:
2438             return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2439
2440         # Look for embedded RedTube player
2441         redtube_urls = RedTubeIE._extract_urls(webpage)
2442         if redtube_urls:
2443             return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2444
2445         # Look for embedded Tvigle player
2446         mobj = re.search(
2447             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2448         if mobj is not None:
2449             return self.url_result(mobj.group('url'), 'Tvigle')
2450
2451         # Look for embedded TED player
2452         mobj = re.search(
2453             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2454         if mobj is not None:
2455             return self.url_result(mobj.group('url'), 'TED')
2456
2457         # Look for embedded Ustream videos
2458         ustream_url = UstreamIE._extract_url(webpage)
2459         if ustream_url:
2460             return self.url_result(ustream_url, UstreamIE.ie_key())
2461
2462         # Look for embedded arte.tv player
2463         mobj = re.search(
2464             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2465             webpage)
2466         if mobj is not None:
2467             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2468
2469         # Look for embedded francetv player
2470         mobj = re.search(
2471             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2472             webpage)
2473         if mobj is not None:
2474             return self.url_result(mobj.group('url'))
2475
2476         # Look for embedded smotri.com player
2477         smotri_url = SmotriIE._extract_url(webpage)
2478         if smotri_url:
2479             return self.url_result(smotri_url, 'Smotri')
2480
2481         # Look for embedded Myvi.ru player
2482         myvi_url = MyviIE._extract_url(webpage)
2483         if myvi_url:
2484             return self.url_result(myvi_url)
2485
2486         # Look for embedded soundcloud player
2487         soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2488         if soundcloud_urls:
2489             return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2490
2491         # Look for tunein player
2492         tunein_urls = TuneInBaseIE._extract_urls(webpage)
2493         if tunein_urls:
2494             return self.playlist_from_matches(tunein_urls, video_id, video_title)
2495
2496         # Look for embedded mtvservices player
2497         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2498         if mtvservices_url:
2499             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2500
2501         # Look for embedded yahoo player
2502         mobj = re.search(
2503             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2504             webpage)
2505         if mobj is not None:
2506             return self.url_result(mobj.group('url'), 'Yahoo')
2507
2508         # Look for embedded sbs.com.au player
2509         mobj = re.search(
2510             r'''(?x)
2511             (?:
2512                 <meta\s+property="og:video"\s+content=|
2513                 <iframe[^>]+?src=
2514             )
2515             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2516             webpage)
2517         if mobj is not None:
2518             return self.url_result(mobj.group('url'), 'SBS')
2519
2520         # Look for embedded Cinchcast player
2521         mobj = re.search(
2522             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2523             webpage)
2524         if mobj is not None:
2525             return self.url_result(mobj.group('url'), 'Cinchcast')
2526
2527         mobj = re.search(
2528             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2529             webpage)
2530         if not mobj:
2531             mobj = re.search(
2532                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2533                 webpage)
2534         if mobj is not None:
2535             return self.url_result(mobj.group('url'), 'MLB')
2536
2537         mobj = re.search(
2538             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2539             webpage)
2540         if mobj is not None:
2541             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2542
2543         mobj = re.search(
2544             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2545             webpage)
2546         if mobj is not None:
2547             return self.url_result(mobj.group('url'), 'Livestream')
2548
2549         # Look for Zapiks embed
2550         mobj = re.search(
2551             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2552         if mobj is not None:
2553             return self.url_result(mobj.group('url'), 'Zapiks')
2554
2555         # Look for Kaltura embeds
2556         kaltura_url = KalturaIE._extract_url(webpage)
2557         if kaltura_url:
2558             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2559
2560         # Look for EaglePlatform embeds
2561         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2562         if eagleplatform_url:
2563             return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2564
2565         # Look for ClipYou (uses EaglePlatform) embeds
2566         mobj = re.search(
2567             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2568         if mobj is not None:
2569             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2570
2571         # Look for Pladform embeds
2572         pladform_url = PladformIE._extract_url(webpage)
2573         if pladform_url:
2574             return self.url_result(pladform_url)
2575
2576         # Look for Videomore embeds
2577         videomore_url = VideomoreIE._extract_url(webpage)
2578         if videomore_url:
2579             return self.url_result(videomore_url)
2580
2581         # Look for Webcaster embeds
2582         webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2583         if webcaster_url:
2584             return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2585
2586         # Look for Playwire embeds
2587         mobj = re.search(
2588             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2589         if mobj is not None:
2590             return self.url_result(mobj.group('url'))
2591
2592         # Look for 5min embeds
2593         mobj = re.search(
2594             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2595         if mobj is not None:
2596             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2597
2598         # Look for Crooks and Liars embeds
2599         mobj = re.search(
2600             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2601         if mobj is not None:
2602             return self.url_result(mobj.group('url'))
2603
2604         # Look for NBC Sports VPlayer embeds
2605         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2606         if nbc_sports_url:
2607             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2608
2609         # Look for NBC News embeds
2610         nbc_news_embed_url = re.search(
2611             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2612         if nbc_news_embed_url:
2613             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2614
2615         # Look for Google Drive embeds
2616         google_drive_url = GoogleDriveIE._extract_url(webpage)
2617         if google_drive_url:
2618             return self.url_result(google_drive_url, 'GoogleDrive')
2619
2620         # Look for UDN embeds
2621         mobj = re.search(
2622             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2623         if mobj is not None:
2624             return self.url_result(
2625                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2626
2627         # Look for Senate ISVP iframe
2628         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2629         if senate_isvp_url:
2630             return self.url_result(senate_isvp_url, 'SenateISVP')
2631
2632         # Look for Dailymotion Cloud videos
2633         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2634         if dmcloud_url:
2635             return self.url_result(dmcloud_url, 'DailymotionCloud')
2636
2637         # Look for OnionStudios embeds
2638         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2639         if onionstudios_url:
2640             return self.url_result(onionstudios_url)
2641
2642         # Look for ViewLift embeds
2643         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2644         if viewlift_url:
2645             return self.url_result(viewlift_url)
2646
2647         # Look for JWPlatform embeds
2648         jwplatform_url = JWPlatformIE._extract_url(webpage)
2649         if jwplatform_url:
2650             return self.url_result(jwplatform_url, 'JWPlatform')
2651
2652         # Look for Digiteka embeds
2653         digiteka_url = DigitekaIE._extract_url(webpage)
2654         if digiteka_url:
2655             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2656
2657         # Look for Arkena embeds
2658         arkena_url = ArkenaIE._extract_url(webpage)
2659         if arkena_url:
2660             return self.url_result(arkena_url, ArkenaIE.ie_key())
2661
2662         # Look for Piksel embeds
2663         piksel_url = PikselIE._extract_url(webpage)
2664         if piksel_url:
2665             return self.url_result(piksel_url, PikselIE.ie_key())
2666
2667         # Look for Limelight embeds
2668         limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2669         if limelight_urls:
2670             return self.playlist_result(
2671                 limelight_urls, video_id, video_title, video_description)
2672
2673         # Look for Anvato embeds
2674         anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2675         if anvato_urls:
2676             return self.playlist_result(
2677                 anvato_urls, video_id, video_title, video_description)
2678
2679         # Look for AdobeTVVideo embeds
2680         mobj = re.search(
2681             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2682             webpage)
2683         if mobj is not None:
2684             return self.url_result(
2685                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2686                 'AdobeTVVideo')
2687
2688         # Look for Vine embeds
2689         mobj = re.search(
2690             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2691             webpage)
2692         if mobj is not None:
2693             return self.url_result(
2694                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2695
2696         # Look for VODPlatform embeds
2697         mobj = re.search(
2698             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2699             webpage)
2700         if mobj is not None:
2701             return self.url_result(
2702                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2703
2704         # Look for Mangomolo embeds
2705         mobj = re.search(
2706             r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2707                 (?:
2708                     video\?.*?\bid=(?P<video_id>\d+)|
2709                     index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2710                 ).+?)\1''', webpage)
2711         if mobj is not None:
2712             info = {
2713                 '_type': 'url_transparent',
2714                 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2715                 'title': video_title,
2716                 'description': video_description,
2717                 'thumbnail': video_thumbnail,
2718                 'uploader': video_uploader,
2719             }
2720             video_id = mobj.group('video_id')
2721             if video_id:
2722                 info.update({
2723                     'ie_key': 'MangomoloVideo',
2724                     'id': video_id,
2725                 })
2726             else:
2727                 info.update({
2728                     'ie_key': 'MangomoloLive',
2729                     'id': mobj.group('channel_id'),
2730                 })
2731             return info
2732
2733         # Look for Instagram embeds
2734         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2735         if instagram_embed_url is not None:
2736             return self.url_result(
2737                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2738
2739         # Look for LiveLeak embeds
2740         liveleak_url = LiveLeakIE._extract_url(webpage)
2741         if liveleak_url:
2742             return self.url_result(liveleak_url, 'LiveLeak')
2743
2744         # Look for 3Q SDN embeds
2745         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2746         if threeqsdn_url:
2747             return {
2748                 '_type': 'url_transparent',
2749                 'ie_key': ThreeQSDNIE.ie_key(),
2750                 'url': self._proto_relative_url(threeqsdn_url),
2751                 'title': video_title,
2752                 'description': video_description,
2753                 'thumbnail': video_thumbnail,
2754                 'uploader': video_uploader,
2755             }
2756
2757         # Look for VBOX7 embeds
2758         vbox7_url = Vbox7IE._extract_url(webpage)
2759         if vbox7_url:
2760             return self.url_result(vbox7_url, Vbox7IE.ie_key())
2761
2762         # Look for DBTV embeds
2763         dbtv_urls = DBTVIE._extract_urls(webpage)
2764         if dbtv_urls:
2765             return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2766
2767         # Look for Videa embeds
2768         videa_urls = VideaIE._extract_urls(webpage)
2769         if videa_urls:
2770             return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2771
2772         # Look for 20 minuten embeds
2773         twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2774         if twentymin_urls:
2775             return self.playlist_from_matches(
2776                 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2777
2778         # Look for Openload embeds
2779         openload_urls = OpenloadIE._extract_urls(webpage)
2780         if openload_urls:
2781             return self.playlist_from_matches(
2782                 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2783
2784         # Look for VideoPress embeds
2785         videopress_urls = VideoPressIE._extract_urls(webpage)
2786         if videopress_urls:
2787             return self.playlist_from_matches(
2788                 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2789
2790         # Look for Rutube embeds
2791         rutube_urls = RutubeIE._extract_urls(webpage)
2792         if rutube_urls:
2793             return self.playlist_from_matches(
2794                 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2795
2796         # Look for WashingtonPost embeds
2797         wapo_urls = WashingtonPostIE._extract_urls(webpage)
2798         if wapo_urls:
2799             return self.playlist_from_matches(
2800                 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2801
2802         # Look for Mediaset embeds
2803         mediaset_urls = MediasetIE._extract_urls(webpage)
2804         if mediaset_urls:
2805             return self.playlist_from_matches(
2806                 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2807
2808         # Look for JOJ.sk embeds
2809         joj_urls = JojIE._extract_urls(webpage)
2810         if joj_urls:
2811             return self.playlist_from_matches(
2812                 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2813
2814         def merge_dicts(dict1, dict2):
2815             merged = {}
2816             for k, v in dict1.items():
2817                 if v is not None:
2818                     merged[k] = v
2819             for k, v in dict2.items():
2820                 if v is None:
2821                     continue
2822                 if (k not in merged or
2823                         (isinstance(v, compat_str) and v and
2824                             isinstance(merged[k], compat_str) and
2825                             not merged[k])):
2826                     merged[k] = v
2827             return merged
2828
2829         # Looking for http://schema.org/VideoObject
2830         json_ld = self._search_json_ld(
2831             webpage, video_id, default={}, expected_type='VideoObject')
2832         if json_ld.get('url'):
2833             return merge_dicts(json_ld, info_dict)
2834
2835         # Look for HTML5 media
2836         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2837         if entries:
2838             for entry in entries:
2839                 entry.update({
2840                     'id': video_id,
2841                     'title': video_title,
2842                 })
2843                 self._sort_formats(entry['formats'])
2844             return self.playlist_result(entries)
2845
2846         jwplayer_data = self._find_jwplayer_data(
2847             webpage, video_id, transform_source=js_to_json)
2848         if jwplayer_data:
2849             info = self._parse_jwplayer_data(
2850                 jwplayer_data, video_id, require_title=False, base_url=url)
2851             return merge_dicts(info, info_dict)
2852
2853         def check_video(vurl):
2854             if YoutubeIE.suitable(vurl):
2855                 return True
2856             if RtmpIE.suitable(vurl):
2857                 return True
2858             vpath = compat_urlparse.urlparse(vurl).path
2859             vext = determine_ext(vpath)
2860             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2861
2862         def filter_video(urls):
2863             return list(filter(check_video, urls))
2864
2865         # Start with something easy: JW Player in SWFObject
2866         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2867         if not found:
2868             # Look for gorilla-vid style embedding
2869             found = filter_video(re.findall(r'''(?sx)
2870                 (?:
2871                     jw_plugins|
2872                     JWPlayerOptions|
2873                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2874                 )
2875                 .*?
2876                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2877         if not found:
2878             # Broaden the search a little bit
2879             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2880         if not found:
2881             # Broaden the findall a little bit: JWPlayer JS loader
2882             found = filter_video(re.findall(
2883                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2884         if not found:
2885             # Flow player
2886             found = filter_video(re.findall(r'''(?xs)
2887                 flowplayer\("[^"]+",\s*
2888                     \{[^}]+?\}\s*,
2889                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2890                         ["']?url["']?\s*:\s*["']([^"']+)["']
2891             ''', webpage))
2892         if not found:
2893             # Cinerama player
2894             found = re.findall(
2895                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2896         if not found:
2897             # Try to find twitter cards info
2898             # twitter:player:stream should be checked before twitter:player since
2899             # it is expected to contain a raw stream (see
2900             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2901             found = filter_video(re.findall(
2902                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2903         if not found:
2904             # We look for Open Graph info:
2905             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2906             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2907             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2908             if m_video_type is not None:
2909                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2910         if not found:
2911             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2912             found = re.search(
2913                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2914                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2915                 webpage)
2916             if not found:
2917                 # Look also in Refresh HTTP header
2918                 refresh_header = head_response.headers.get('Refresh')
2919                 if refresh_header:
2920                     # In python 2 response HTTP headers are bytestrings
2921                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2922                         refresh_header = refresh_header.decode('iso-8859-1')
2923                     found = re.search(REDIRECT_REGEX, refresh_header)
2924             if found:
2925                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2926                 if new_url != url:
2927                     self.report_following_redirect(new_url)
2928                     return {
2929                         '_type': 'url',
2930                         'url': new_url,
2931                     }
2932                 else:
2933                     found = None
2934
2935         if not found:
2936             # twitter:player is a https URL to iframe player that may or may not
2937             # be supported by youtube-dl thus this is checked the very last (see
2938             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2939             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2940             if embed_url:
2941                 return self.url_result(embed_url)
2942
2943         if not found:
2944             raise UnsupportedError(url)
2945
2946         entries = []
2947         for video_url in orderedSet(found):
2948             video_url = unescapeHTML(video_url)
2949             video_url = video_url.replace('\\/', '/')
2950             video_url = compat_urlparse.urljoin(url, video_url)
2951             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2952
2953             # Sometimes, jwplayer extraction will result in a YouTube URL
2954             if YoutubeIE.suitable(video_url):
2955                 entries.append(self.url_result(video_url, 'Youtube'))
2956                 continue
2957
2958             # here's a fun little line of code for you:
2959             video_id = os.path.splitext(video_id)[0]
2960
2961             entry_info_dict = {
2962                 'id': video_id,
2963                 'uploader': video_uploader,
2964                 'title': video_title,
2965                 'age_limit': age_limit,
2966             }
2967
2968             if RtmpIE.suitable(video_url):
2969                 entry_info_dict.update({
2970                     '_type': 'url_transparent',
2971                     'ie_key': RtmpIE.ie_key(),
2972                     'url': video_url,
2973                 })
2974                 entries.append(entry_info_dict)
2975                 continue
2976
2977             ext = determine_ext(video_url)
2978             if ext == 'smil':
2979                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2980             elif ext == 'xspf':
2981                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2982             elif ext == 'm3u8':
2983                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2984             elif ext == 'mpd':
2985                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2986             elif ext == 'f4m':
2987                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2988             elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2989                 # Just matching .ism/manifest is not enough to be reliably sure
2990                 # whether it's actually an ISM manifest or some other streaming
2991                 # manifest since there are various streaming URL formats
2992                 # possible (see [1]) as well as some other shenanigans like
2993                 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2994                 # so on.
2995                 # Thus the most reasonable way to solve this is to delegate
2996                 # to generic extractor in order to look into the contents of
2997                 # the manifest itself.
2998                 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2999                 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3000                 entry_info_dict = self.url_result(
3001                     smuggle_url(video_url, {'to_generic': True}),
3002                     GenericIE.ie_key())
3003             else:
3004                 entry_info_dict['url'] = video_url
3005
3006             if entry_info_dict.get('formats'):
3007                 self._sort_formats(entry_info_dict['formats'])
3008
3009             entries.append(entry_info_dict)
3010
3011         if len(entries) == 1:
3012             return entries[0]
3013         else:
3014             for num, e in enumerate(entries, start=1):
3015                 # 'url' results don't have a title
3016                 if e.get('title') is not None:
3017                     e['title'] = '%s (%d)' % (e['title'], num)
3018             return {
3019                 '_type': 'playlist',
3020                 'entries': entries,
3021             }