_ 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_urllib_parse_unquote,
  14     compat_urlparse,
  15     compat_xml_parse_error,
  16 )
  17 from ..utils import (
  18     determine_ext,
  19     ExtractorError,
  20     float_or_none,
  21     HEADRequest,
  22     is_html,
  23     js_to_json,
  24     orderedSet,
  25     sanitized_Request,
  26     smuggle_url,
  27     unescapeHTML,
  28     unified_strdate,
  29     unsmuggle_url,
  30     UnsupportedError,
  31     xpath_text,
  32 )
  33 from .commonprotocols import RtmpIE
  34 from .brightcove import (
  35     BrightcoveLegacyIE,
  36     BrightcoveNewIE,
  37 )
  38 from .nbc import NBCSportsVPlayerIE
  39 from .ooyala import OoyalaIE
  40 from .rutv import RUTVIE
  41 from .tvc import TVCIE
  42 from .sportbox import SportBoxEmbedIE
  43 from .smotri import SmotriIE
  44 from .myvi import MyviIE
  45 from .condenast import CondeNastIE
  46 from .udn import UDNEmbedIE
  47 from .senateisvp import SenateISVPIE
  48 from .svt import SVTIE
  49 from .pornhub import PornHubIE
  50 from .xhamster import XHamsterEmbedIE
  51 from .tnaflix import TNAFlixNetworkEmbedIE
  52 from .drtuber import DrTuberIE
  53 from .redtube import RedTubeIE
  54 from .vimeo import VimeoIE
  55 from .dailymotion import (
  56     DailymotionIE,
  57     DailymotionCloudIE,
  58 )
  59 from .onionstudios import OnionStudiosIE
  60 from .viewlift import ViewLiftEmbedIE
  61 from .mtv import MTVServicesEmbeddedIE
  62 from .pladform import PladformIE
  63 from .videomore import VideomoreIE
  64 from .webcaster import WebcasterFeedIE
  65 from .googledrive import GoogleDriveIE
  66 from .jwplatform import JWPlatformIE
  67 from .digiteka import DigitekaIE
  68 from .arkena import ArkenaIE
  69 from .instagram import InstagramIE
  70 from .liveleak import LiveLeakIE
  71 from .threeqsdn import ThreeQSDNIE
  72 from .theplatform import ThePlatformIE
  73 from .vessel import VesselIE
  74 from .kaltura import KalturaIE
  75 from .eagleplatform import EaglePlatformIE
  76 from .facebook import FacebookIE
  77 from .soundcloud import SoundcloudIE
  78 from .tunein import TuneInBaseIE
  79 from .vbox7 import Vbox7IE
  80 from .dbtv import DBTVIE
  81 from .piksel import PikselIE
  82 from .videa import VideaIE
  83 from .twentymin import TwentyMinutenIE
  84 from .ustream import UstreamIE
  85 from .openload import OpenloadIE
  86 from .videopress import VideoPressIE
  87 from .rutube import RutubeIE
  88 from .limelight import LimelightBaseIE
  89 from .anvato import AnvatoIE
  90 from .washingtonpost import WashingtonPostIE
  91
  92
  93 class GenericIE(InfoExtractor):
  94     IE_DESC = 'Generic downloader that works on some sites'
  95     _VALID_URL = r'.*'
  96     IE_NAME = 'generic'
  97     _TESTS = [
  98         # Direct link to a video
  99         {
 100             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
 101             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
 102             'info_dict': {
 103                 'id': 'trailer',
 104                 'ext': 'mp4',
 105                 'title': 'trailer',
 106                 'upload_date': '20100513',
 107             }
 108         },
 109         # Direct link to media delivered compressed (until Accept-Encoding is *)
 110         {
 111             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
 112             'md5': '128c42e68b13950268b648275386fc74',
 113             'info_dict': {
 114                 'id': 'FictionJunction-Parallel_Hearts',
 115                 'ext': 'flac',
 116                 'title': 'FictionJunction-Parallel_Hearts',
 117                 'upload_date': '20140522',
 118             },
 119             'expected_warnings': [
 120                 'URL could be a direct video link, returning it as such.'
 121             ],
 122             'skip': 'URL invalid',
 123         },
 124         # Direct download with broken HEAD
 125         {
 126             'url': 'http://ai-radio.org:8000/radio.opus',
 127             'info_dict': {
 128                 'id': 'radio',
 129                 'ext': 'opus',
 130                 'title': 'radio',
 131             },
 132             'params': {
 133                 'skip_download': True,  # infinite live stream
 134             },
 135             'expected_warnings': [
 136                 r'501.*Not Implemented',
 137                 r'400.*Bad Request',
 138             ],
 139         },
 140         # Direct link with incorrect MIME type
 141         {
 142             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 143             'md5': '4ccbebe5f36706d85221f204d7eb5913',
 144             'info_dict': {
 145                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
 146                 'id': '5_Lennart_Poettering_-_Systemd',
 147                 'ext': 'webm',
 148                 'title': '5_Lennart_Poettering_-_Systemd',
 149                 'upload_date': '20141120',
 150             },
 151             'expected_warnings': [
 152                 'URL could be a direct video link, returning it as such.'
 153             ]
 154         },
 155         # RSS feed
 156         {
 157             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 158             'info_dict': {
 159                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
 160                 'title': 'Zero Punctuation',
 161                 'description': 're:.*groundbreaking video review series.*'
 162             },
 163             'playlist_mincount': 11,
 164         },
 165         # RSS feed with enclosure
 166         {
 167             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
 168             'info_dict': {
 169                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 170                 'ext': 'm4v',
 171                 'upload_date': '20150228',
 172                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
 173             }
 174         },
 175         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
 176         {
 177             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
 178             'info_dict': {
 179                 'id': 'smil',
 180                 'ext': 'mp4',
 181                 'title': 'Automatics, robotics and biocybernetics',
 182                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
 183                 'upload_date': '20130627',
 184                 'formats': 'mincount:16',
 185                 'subtitles': 'mincount:1',
 186             },
 187             'params': {
 188                 'force_generic_extractor': True,
 189                 'skip_download': True,
 190             },
 191         },
 192         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
 193         {
 194             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
 195             'info_dict': {
 196                 'id': 'hds',
 197                 'ext': 'flv',
 198                 'title': 'hds',
 199                 'formats': 'mincount:1',
 200             },
 201             'params': {
 202                 'skip_download': True,
 203             },
 204         },
 205         # SMIL from https://www.restudy.dk/video/play/id/1637
 206         {
 207             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
 208             'info_dict': {
 209                 'id': 'video_1637',
 210                 'ext': 'flv',
 211                 'title': 'video_1637',
 212                 'formats': 'mincount:3',
 213             },
 214             'params': {
 215                 'skip_download': True,
 216             },
 217         },
 218         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
 219         {
 220             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
 221             'info_dict': {
 222                 'id': 'smil-service',
 223                 'ext': 'flv',
 224                 'title': 'smil-service',
 225                 'formats': 'mincount:1',
 226             },
 227             'params': {
 228                 'skip_download': True,
 229             },
 230         },
 231         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
 232         {
 233             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
 234             'info_dict': {
 235                 'id': '4719370',
 236                 'ext': 'mp4',
 237                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
 238                 'formats': 'mincount:3',
 239             },
 240             'params': {
 241                 'skip_download': True,
 242             },
 243         },
 244         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
 245         {
 246             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
 247             'info_dict': {
 248                 'id': 'mZlp2ctYIUEB',
 249                 'ext': 'mp4',
 250                 'title': 'Tikibad ontruimd wegens brand',
 251                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
 252                 'thumbnail': r're:^https?://.*\.jpg$',
 253                 'duration': 33,
 254             },
 255             'params': {
 256                 'skip_download': True,
 257             },
 258         },
 259         # MPD from http://dash-mse-test.appspot.com/media.html
 260         {
 261             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
 262             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
 263             'info_dict': {
 264                 'id': 'car-20120827-manifest',
 265                 'ext': 'mp4',
 266                 'title': 'car-20120827-manifest',
 267                 'formats': 'mincount:9',
 268                 'upload_date': '20130904',
 269             },
 270             'params': {
 271                 'format': 'bestvideo',
 272             },
 273         },
 274         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
 275         {
 276             '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',
 277             'info_dict': {
 278                 'id': 'content',
 279                 'ext': 'mp4',
 280                 'title': 'content',
 281                 'formats': 'mincount:8',
 282             },
 283             'params': {
 284                 # m3u8 downloads
 285                 'skip_download': True,
 286             },
 287             'skip': 'video gone',
 288         },
 289         # m3u8 served with Content-Type: text/plain
 290         {
 291             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
 292             'info_dict': {
 293                 'id': 'index',
 294                 'ext': 'mp4',
 295                 'title': 'index',
 296                 'upload_date': '20140720',
 297                 'formats': 'mincount:11',
 298             },
 299             'params': {
 300                 # m3u8 downloads
 301                 'skip_download': True,
 302             },
 303             'skip': 'video gone',
 304         },
 305         # google redirect
 306         {
 307             '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',
 308             'info_dict': {
 309                 'id': 'cmQHVoWB5FY',
 310                 'ext': 'mp4',
 311                 'upload_date': '20130224',
 312                 'uploader_id': 'TheVerge',
 313                 'description': r're:^Chris Ziegler takes a look at the\.*',
 314                 'uploader': 'The Verge',
 315                 'title': 'First Firefox OS phones side-by-side',
 316             },
 317             'params': {
 318                 'skip_download': False,
 319             }
 320         },
 321         {
 322             # redirect in Refresh HTTP header
 323             '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',
 324             'info_dict': {
 325                 'id': 'pO8h3EaFRdo',
 326                 'ext': 'mp4',
 327                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
 328                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
 329                 'upload_date': '20150917',
 330                 'uploader_id': 'brtvofficial',
 331                 'uploader': 'Boiler Room',
 332             },
 333             'params': {
 334                 'skip_download': False,
 335             },
 336         },
 337         {
 338             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
 339             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
 340             'info_dict': {
 341                 'id': '13601338388002',
 342                 'ext': 'mp4',
 343                 'uploader': 'www.hodiho.fr',
 344                 'title': 'R\u00e9gis plante sa Jeep',
 345             }
 346         },
 347         # bandcamp page with custom domain
 348         {
 349             'add_ie': ['Bandcamp'],
 350             'url': 'http://bronyrock.com/track/the-pony-mash',
 351             'info_dict': {
 352                 'id': '3235767654',
 353                 'ext': 'mp3',
 354                 'title': 'The Pony Mash',
 355                 'uploader': 'M_Pallante',
 356             },
 357             'skip': 'There is a limit of 200 free downloads / month for the test song',
 358         },
 359         {
 360             # embedded brightcove video
 361             # it also tests brightcove videos that need to set the 'Referer'
 362             # in the http requests
 363             'add_ie': ['BrightcoveLegacy'],
 364             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
 365             'info_dict': {
 366                 'id': '2765128793001',
 367                 'ext': 'mp4',
 368                 'title': 'Le cours de bourse : l’analyse technique',
 369                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
 370                 'uploader': 'BFM BUSINESS',
 371             },
 372             'params': {
 373                 'skip_download': True,
 374             },
 375         },
 376         {
 377             # embedded with itemprop embedURL and video id spelled as `idVideo`
 378             'add_id': ['BrightcoveLegacy'],
 379             'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
 380             'info_dict': {
 381                 'id': '5255628253001',
 382                 'ext': 'mp4',
 383                 'title': 'md5:37c519b1128915607601e75a87995fc0',
 384                 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
 385                 'uploader': 'BFM BUSINESS',
 386                 'uploader_id': '876450612001',
 387                 'timestamp': 1482255315,
 388                 'upload_date': '20161220',
 389             },
 390             'params': {
 391                 'skip_download': True,
 392             },
 393         },
 394         {
 395             # https://github.com/rg3/youtube-dl/issues/2253
 396             'url': 'http://bcove.me/i6nfkrc3',
 397             'md5': '0ba9446db037002366bab3b3eb30c88c',
 398             'info_dict': {
 399                 'id': '3101154703001',
 400                 'ext': 'mp4',
 401                 'title': 'Still no power',
 402                 'uploader': 'thestar.com',
 403                 '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.',
 404             },
 405             'add_ie': ['BrightcoveLegacy'],
 406             'skip': 'video gone',
 407         },
 408         {
 409             'url': 'http://www.championat.com/video/football/v/87/87499.html',
 410             'md5': 'fb973ecf6e4a78a67453647444222983',
 411             'info_dict': {
 412                 'id': '3414141473001',
 413                 'ext': 'mp4',
 414                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
 415                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
 416                 'uploader': 'Championat',
 417             },
 418         },
 419         {
 420             # https://github.com/rg3/youtube-dl/issues/3541
 421             'add_ie': ['BrightcoveLegacy'],
 422             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
 423             'info_dict': {
 424                 'id': '3866516442001',
 425                 'ext': 'mp4',
 426                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
 427                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
 428                 'uploader': 'SBS Broadcasting',
 429             },
 430             'skip': 'Restricted to Netherlands',
 431             'params': {
 432                 'skip_download': True,  # m3u8 download
 433             },
 434         },
 435         {
 436             # Brightcove video in <iframe>
 437             'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
 438             'md5': '36d74ef5e37c8b4a2ce92880d208b968',
 439             'info_dict': {
 440                 'id': '5360463607001',
 441                 'ext': 'mp4',
 442                 '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',
 443                 '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。',
 444                 'uploader': 'United Nations',
 445                 'uploader_id': '1362235914001',
 446                 'timestamp': 1489593889,
 447                 'upload_date': '20170315',
 448             },
 449             'add_ie': ['BrightcoveLegacy'],
 450         },
 451         {
 452             # Brightcove with alternative playerID key
 453             'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
 454             'info_dict': {
 455                 'id': 'nmeth.2062_SV1',
 456                 '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',
 457             },
 458             'playlist': [{
 459                 'info_dict': {
 460                     'id': '2228375078001',
 461                     'ext': 'mp4',
 462                     'title': 'nmeth.2062-sv1',
 463                     'description': 'nmeth.2062-sv1',
 464                     'timestamp': 1363357591,
 465                     'upload_date': '20130315',
 466                     'uploader': 'Nature Publishing Group',
 467                     'uploader_id': '1964492299001',
 468                 },
 469             }],
 470         },
 471         {
 472             # Brightcove with UUID in videoPlayer
 473             'url': 'http://www8.hp.com/cn/zh/home.html',
 474             'info_dict': {
 475                 'id': '5255815316001',
 476                 'ext': 'mp4',
 477                 'title': 'Sprocket Video - China',
 478                 'description': 'Sprocket Video - China',
 479                 'uploader': 'HP-Video Gallery',
 480                 'timestamp': 1482263210,
 481                 'upload_date': '20161220',
 482                 'uploader_id': '1107601872001',
 483             },
 484             'params': {
 485                 'skip_download': True,  # m3u8 download
 486             },
 487             'skip': 'video rotates...weekly?',
 488         },
 489         {
 490             # Brightcove:new type [2].
 491             'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
 492             'md5': '2b35148fcf48da41c9fb4591650784f3',
 493             'info_dict': {
 494                 'id': '5348741021001',
 495                 'ext': 'mp4',
 496                 'upload_date': '20170306',
 497                 'uploader_id': '4191638492001',
 498                 'timestamp': 1488769918,
 499                 'title': 'VIDEO:  St. Thomas More earns first trip to basketball semis',
 500
 501             },
 502         },
 503         {
 504             # Alternative brightcove <video> attributes
 505             '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/',
 506             'info_dict': {
 507                 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
 508                 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
 509             },
 510             'playlist': [{
 511                 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
 512                 'info_dict': {
 513                     'id': '5311302538001',
 514                     'ext': 'mp4',
 515                     'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
 516                     'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
 517                     'timestamp': 1486321708,
 518                     'upload_date': '20170205',
 519                     'uploader_id': '800000640001',
 520                 },
 521                 'only_matching': True,
 522             }],
 523         },
 524         {
 525             # Brightcove with UUID in videoPlayer
 526             'url': 'http://www8.hp.com/cn/zh/home.html',
 527             'info_dict': {
 528                 'id': '5255815316001',
 529                 'ext': 'mp4',
 530                 'title': 'Sprocket Video - China',
 531                 'description': 'Sprocket Video - China',
 532                 'uploader': 'HP-Video Gallery',
 533                 'timestamp': 1482263210,
 534                 'upload_date': '20161220',
 535                 'uploader_id': '1107601872001',
 536             },
 537             'params': {
 538                 'skip_download': True,  # m3u8 download
 539             },
 540         },
 541         # ooyala video
 542         {
 543             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
 544             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
 545             'info_dict': {
 546                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
 547                 'ext': 'mp4',
 548                 'title': '2cc213299525360.mov',  # that's what we get
 549                 'duration': 238.231,
 550             },
 551             'add_ie': ['Ooyala'],
 552         },
 553         {
 554             # ooyala video embedded with http://player.ooyala.com/iframe.js
 555             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
 556             'info_dict': {
 557                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
 558                 'ext': 'mp4',
 559                 'title': '"Steve Jobs: Man in the Machine" trailer',
 560                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
 561                 'duration': 135.427,
 562             },
 563             'params': {
 564                 'skip_download': True,
 565             },
 566             'skip': 'movie expired',
 567         },
 568         # embed.ly video
 569         {
 570             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
 571             'info_dict': {
 572                 'id': '9ODmcdjQcHQ',
 573                 'ext': 'mp4',
 574                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
 575                 'upload_date': '20140225',
 576                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
 577                 'uploader': 'Tested',
 578                 'uploader_id': 'testedcom',
 579             },
 580             # No need to test YoutubeIE here
 581             'params': {
 582                 'skip_download': True,
 583             },
 584         },
 585         # funnyordie embed
 586         {
 587             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
 588             'info_dict': {
 589                 'id': '18e820ec3f',
 590                 'ext': 'mp4',
 591                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
 592                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
 593             },
 594             # HEAD requests lead to endless 301, while GET is OK
 595             'expected_warnings': ['301'],
 596         },
 597         # RUTV embed
 598         {
 599             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
 600             'info_dict': {
 601                 'id': '776940',
 602                 'ext': 'mp4',
 603                 'title': 'Охотское море стало целиком российским',
 604                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
 605             },
 606             'params': {
 607                 # m3u8 download
 608                 'skip_download': True,
 609             },
 610         },
 611         # TVC embed
 612         {
 613             '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/',
 614             'info_dict': {
 615                 'id': '55304',
 616                 'ext': 'mp4',
 617                 'title': 'Дошкольное воспитание',
 618             },
 619         },
 620         # SportBox embed
 621         {
 622             'url': 'http://www.vestifinance.ru/articles/25753',
 623             'info_dict': {
 624                 'id': '25753',
 625                 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
 626             },
 627             'playlist': [{
 628                 'info_dict': {
 629                     'id': '370908',
 630                     'title': 'Госзаказ. День 3',
 631                     'ext': 'mp4',
 632                 }
 633             }, {
 634                 'info_dict': {
 635                     'id': '370905',
 636                     'title': 'Госзаказ. День 2',
 637                     'ext': 'mp4',
 638                 }
 639             }, {
 640                 'info_dict': {
 641                     'id': '370902',
 642                     'title': 'Госзаказ. День 1',
 643                     'ext': 'mp4',
 644                 }
 645             }],
 646             'params': {
 647                 # m3u8 download
 648                 'skip_download': True,
 649             },
 650         },
 651         # Myvi.ru embed
 652         {
 653             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
 654             'info_dict': {
 655                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
 656                 'ext': 'mp4',
 657                 'title': 'Ужастики, русский трейлер (2015)',
 658                 'thumbnail': r're:^https?://.*\.jpg$',
 659                 'duration': 153,
 660             }
 661         },
 662         # XHamster embed
 663         {
 664             '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',
 665             'info_dict': {
 666                 'id': 'showthread',
 667                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
 668             },
 669             'playlist_mincount': 7,
 670             # This forum does not allow <iframe> syntaxes anymore
 671             # Now HTML tags are displayed as-is
 672             'skip': 'No videos on this page',
 673         },
 674         # Embedded TED video
 675         {
 676             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
 677             'md5': '65fdff94098e4a607385a60c5177c638',
 678             'info_dict': {
 679                 'id': '1969',
 680                 'ext': 'mp4',
 681                 'title': 'Hidden miracles of the natural world',
 682                 'uploader': 'Louie Schwartzberg',
 683                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
 684             }
 685         },
 686         # nowvideo embed hidden behind percent encoding
 687         {
 688             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
 689             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
 690             'info_dict': {
 691                 'id': '06e53103ca9aa',
 692                 'ext': 'flv',
 693                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
 694                 'description': 'No description',
 695             },
 696         },
 697         # arte embed
 698         {
 699             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
 700             'md5': '7653032cbb25bf6c80d80f217055fa43',
 701             'info_dict': {
 702                 'id': '048195-004_PLUS7-F',
 703                 'ext': 'flv',
 704                 'title': 'X:enius',
 705                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
 706                 'upload_date': '20140320',
 707             },
 708             'params': {
 709                 'skip_download': 'Requires rtmpdump'
 710             },
 711             'skip': 'video gone',
 712         },
 713         # francetv embed
 714         {
 715             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
 716             'info_dict': {
 717                 'id': 'EV_30231',
 718                 'ext': 'mp4',
 719                 'title': 'Alcaline, le concert avec Calogero',
 720                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
 721                 'upload_date': '20150226',
 722                 'timestamp': 1424989860,
 723                 'duration': 5400,
 724             },
 725             'params': {
 726                 # m3u8 downloads
 727                 'skip_download': True,
 728             },
 729             'expected_warnings': [
 730                 'Forbidden'
 731             ]
 732         },
 733         # Condé Nast embed
 734         {
 735             'url': 'http://www.wired.com/2014/04/honda-asimo/',
 736             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
 737             'info_dict': {
 738                 'id': '53501be369702d3275860000',
 739                 'ext': 'mp4',
 740                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
 741             }
 742         },
 743         # Dailymotion embed
 744         {
 745             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
 746             'md5': '441aeeb82eb72c422c7f14ec533999cd',
 747             'info_dict': {
 748                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
 749                 'ext': 'mp4',
 750                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
 751                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
 752                 'uploader': 'Spi0n',
 753                 'uploader_id': 'xgditw',
 754                 'upload_date': '20140425',
 755                 'timestamp': 1398441542,
 756             },
 757             'add_ie': ['Dailymotion'],
 758         },
 759         # YouTube embed
 760         {
 761             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
 762             'info_dict': {
 763                 'id': 'FXRb4ykk4S0',
 764                 'ext': 'mp4',
 765                 'title': 'The NBL Auction 2014',
 766                 'uploader': 'BADMINTON England',
 767                 'uploader_id': 'BADMINTONEvents',
 768                 'upload_date': '20140603',
 769                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
 770             },
 771             'add_ie': ['Youtube'],
 772             'params': {
 773                 'skip_download': True,
 774             }
 775         },
 776         # MTVSercices embed
 777         {
 778             'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
 779             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
 780             'info_dict': {
 781                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
 782                 'ext': 'mp4',
 783                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
 784                 'description': 'Two valets share their love for movie star Liam Neesons.',
 785                 'timestamp': 1349922600,
 786                 'upload_date': '20121011',
 787             },
 788         },
 789         # YouTube embed via <data-embed-url="">
 790         {
 791             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
 792             'info_dict': {
 793                 'id': '4vAffPZIT44',
 794                 'ext': 'mp4',
 795                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
 796                 'uploader': 'Gameloft',
 797                 'uploader_id': 'gameloft',
 798                 'upload_date': '20140828',
 799                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
 800             },
 801             'params': {
 802                 'skip_download': True,
 803             }
 804         },
 805         # YouTube <object> embed
 806         {
 807             'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
 808             'md5': '516718101ec834f74318df76259fb3cc',
 809             'info_dict': {
 810                 'id': 'msN87y-iEx0',
 811                 'ext': 'webm',
 812                 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
 813                 'upload_date': '20080526',
 814                 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
 815                 'uploader': 'Christopher Sykes',
 816                 'uploader_id': 'ChristopherJSykes',
 817             },
 818             'add_ie': ['Youtube'],
 819         },
 820         # Camtasia studio
 821         {
 822             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
 823             'playlist': [{
 824                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
 825                 'info_dict': {
 826                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 827                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
 828                     'ext': 'flv',
 829                     'duration': 2235.90,
 830                 }
 831             }, {
 832                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
 833                 'info_dict': {
 834                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
 835                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
 836                     'ext': 'flv',
 837                     'duration': 2235.93,
 838                 }
 839             }],
 840             'info_dict': {
 841                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
 842             }
 843         },
 844         # Flowplayer
 845         {
 846             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
 847             'md5': '9d65602bf31c6e20014319c7d07fba27',
 848             'info_dict': {
 849                 'id': '5123ea6d5e5a7',
 850                 'ext': 'mp4',
 851                 'age_limit': 18,
 852                 'uploader': 'www.handjobhub.com',
 853                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
 854             }
 855         },
 856         # Multiple brightcove videos
 857         # https://github.com/rg3/youtube-dl/issues/2283
 858         {
 859             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
 860             'info_dict': {
 861                 'id': 'always-never',
 862                 'title': 'Always / Never - The New Yorker',
 863             },
 864             'playlist_count': 3,
 865             'params': {
 866                 'extract_flat': False,
 867                 'skip_download': True,
 868             }
 869         },
 870         # MLB embed
 871         {
 872             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
 873             'md5': '96f09a37e44da40dd083e12d9a683327',
 874             'info_dict': {
 875                 'id': '33322633',
 876                 'ext': 'mp4',
 877                 'title': 'Ump changes call to ball',
 878                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
 879                 'duration': 48,
 880                 'timestamp': 1401537900,
 881                 'upload_date': '20140531',
 882                 'thumbnail': r're:^https?://.*\.jpg$',
 883             },
 884         },
 885         # Wistia embed
 886         {
 887             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
 888             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
 889             'info_dict': {
 890                 'id': '6e2wtrbdaf',
 891                 'ext': 'mov',
 892                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
 893                 'description': 'a Paywall Videos video from Remilon',
 894                 'duration': 644.072,
 895                 'uploader': 'study.com',
 896                 'timestamp': 1459678540,
 897                 'upload_date': '20160403',
 898                 'filesize': 24687186,
 899             },
 900         },
 901         {
 902             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
 903             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
 904             'info_dict': {
 905                 'id': 'uxjb0lwrcz',
 906                 'ext': 'mp4',
 907                 'title': 'Conversation about Hexagonal Rails Part 1',
 908                 'description': 'a Martin Fowler video from ThoughtWorks',
 909                 'duration': 1715.0,
 910                 'uploader': 'thoughtworks.wistia.com',
 911                 'timestamp': 1401832161,
 912                 'upload_date': '20140603',
 913             },
 914         },
 915         # Wistia standard embed (async)
 916         {
 917             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
 918             'info_dict': {
 919                 'id': '807fafadvk',
 920                 'ext': 'mp4',
 921                 'title': 'Drip Brennan Dunn Workshop',
 922                 'description': 'a JV Webinars video from getdrip-1',
 923                 'duration': 4986.95,
 924                 'timestamp': 1463607249,
 925                 'upload_date': '20160518',
 926             },
 927             'params': {
 928                 'skip_download': True,
 929             }
 930         },
 931         # Soundcloud embed
 932         {
 933             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
 934             'info_dict': {
 935                 'id': '174391317',
 936                 'ext': 'mp3',
 937                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
 938                 'uploader': 'Sophos Security',
 939                 'title': 'Chet Chat 171 - Oct 29, 2014',
 940                 'upload_date': '20141029',
 941             }
 942         },
 943         # Soundcloud multiple embeds
 944         {
 945             'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
 946             'info_dict': {
 947                 'id': '52809',
 948                 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
 949             },
 950             'playlist_mincount': 7,
 951         },
 952         # TuneIn station embed
 953         {
 954             'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
 955             'info_dict': {
 956                 'id': '204146',
 957                 'ext': 'mp3',
 958                 'title': 'CNRV',
 959                 'location': 'Paris, France',
 960                 'is_live': True,
 961             },
 962             'params': {
 963                 # Live stream
 964                 'skip_download': True,
 965             },
 966         },
 967         # Livestream embed
 968         {
 969             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
 970             'info_dict': {
 971                 'id': '67864563',
 972                 'ext': 'flv',
 973                 'upload_date': '20141112',
 974                 'title': 'Rosetta #CometLanding webcast HL 10',
 975             }
 976         },
 977         # Another Livestream embed, without 'new.' in URL
 978         {
 979             'url': 'https://www.freespeech.org/',
 980             'info_dict': {
 981                 'id': '123537347',
 982                 'ext': 'mp4',
 983                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 984             },
 985             'params': {
 986                 # Live stream
 987                 'skip_download': True,
 988             },
 989         },
 990         # LazyYT
 991         {
 992             'url': 'https://skiplagged.com/',
 993             'info_dict': {
 994                 'id': 'skiplagged',
 995                 'title': 'Skiplagged: The smart way to find cheap flights',
 996             },
 997             'playlist_mincount': 1,
 998             'add_ie': ['Youtube'],
 999         },
1000         # Cinchcast embed
1001         {
1002             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1003             'info_dict': {
1004                 'id': '7141703',
1005                 'ext': 'mp3',
1006                 'upload_date': '20141126',
1007                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1008             }
1009         },
1010         # Cinerama player
1011         {
1012             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1013             'info_dict': {
1014                 'id': '730m_DandD_1901_512k',
1015                 'ext': 'mp4',
1016                 'uploader': 'www.abc.net.au',
1017                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1018             }
1019         },
1020         # embedded viddler video
1021         {
1022             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1023             'info_dict': {
1024                 'id': '4d03aad9',
1025                 'ext': 'mp4',
1026                 'uploader': 'deadspin',
1027                 'title': 'WALL-TO-GORTAT',
1028                 'timestamp': 1422285291,
1029                 'upload_date': '20150126',
1030             },
1031             'add_ie': ['Viddler'],
1032         },
1033         # Libsyn embed
1034         {
1035             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1036             'info_dict': {
1037                 'id': '3377616',
1038                 'ext': 'mp3',
1039                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1040                 'description': 'md5:601cb790edd05908957dae8aaa866465',
1041                 'upload_date': '20150220',
1042             },
1043             'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1044         },
1045         # jwplayer YouTube
1046         {
1047             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1048             'info_dict': {
1049                 'id': 'Mrj4DVp2zeA',
1050                 'ext': 'mp4',
1051                 'upload_date': '20150212',
1052                 'uploader': 'The National Archives UK',
1053                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1054                 'uploader_id': 'NationalArchives08',
1055                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1056             },
1057         },
1058         # jwplayer rtmp
1059         {
1060             'url': 'http://www.suffolk.edu/sjc/',
1061             'info_dict': {
1062                 'id': 'sjclive',
1063                 'ext': 'flv',
1064                 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1065                 'uploader': 'www.suffolk.edu',
1066             },
1067             'params': {
1068                 'skip_download': True,
1069             }
1070         },
1071         # Complex jwplayer
1072         {
1073             'url': 'http://www.indiedb.com/games/king-machine/videos',
1074             'info_dict': {
1075                 'id': 'videos',
1076                 'ext': 'mp4',
1077                 'title': 'king machine trailer 1',
1078                 'thumbnail': r're:^https?://.*\.jpg$',
1079             },
1080         },
1081         {
1082             # JWPlayer config passed as variable
1083             'url': 'http://www.txxx.com/videos/3326530/ariele/',
1084             'info_dict': {
1085                 'id': '3326530_hq',
1086                 'ext': 'mp4',
1087                 'title': 'ARIELE | Tube Cup',
1088                 'uploader': 'www.txxx.com',
1089                 'age_limit': 18,
1090             },
1091             'params': {
1092                 'skip_download': True,
1093             }
1094         },
1095         # rtl.nl embed
1096         {
1097             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1098             'playlist_mincount': 5,
1099             'info_dict': {
1100                 'id': 'aanslagen-kopenhagen',
1101                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1102             }
1103         },
1104         # Zapiks embed
1105         {
1106             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1107             'info_dict': {
1108                 'id': '118046',
1109                 'ext': 'mp4',
1110                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1111             }
1112         },
1113         # Kaltura embed (different embed code)
1114         {
1115             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1116             'info_dict': {
1117                 'id': '1_a52wc67y',
1118                 'ext': 'flv',
1119                 'upload_date': '20150127',
1120                 'uploader_id': 'PremierMedia',
1121                 'timestamp': int,
1122                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1123             },
1124         },
1125         # Kaltura embed with single quotes
1126         {
1127             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1128             'info_dict': {
1129                 'id': '0_izeg5utt',
1130                 'ext': 'mp4',
1131                 'title': '35871',
1132                 'timestamp': 1355743100,
1133                 'upload_date': '20121217',
1134                 'uploader_id': 'batchUser',
1135             },
1136             'add_ie': ['Kaltura'],
1137         },
1138         {
1139             # Kaltura embedded via quoted entry_id
1140             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1141             'info_dict': {
1142                 'id': '0_utuok90b',
1143                 'ext': 'mp4',
1144                 'title': '06_matthew_brender_raj_dutt',
1145                 'timestamp': 1466638791,
1146                 'upload_date': '20160622',
1147             },
1148             'add_ie': ['Kaltura'],
1149             'expected_warnings': [
1150                 'Could not send HEAD request'
1151             ],
1152             'params': {
1153                 'skip_download': True,
1154             }
1155         },
1156         {
1157             # Kaltura embedded, some fileExt broken (#11480)
1158             'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1159             'info_dict': {
1160                 'id': '1_sgtvehim',
1161                 'ext': 'mp4',
1162                 'title': 'Our "Standard Models" of particle physics and cosmology',
1163                 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1164                 'timestamp': 1321158993,
1165                 'upload_date': '20111113',
1166                 'uploader_id': 'kps1',
1167             },
1168             'add_ie': ['Kaltura'],
1169         },
1170         {
1171             # Kaltura iframe embed
1172             'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1173             'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1174             'info_dict': {
1175                 'id': '0_f2cfbpwy',
1176                 'ext': 'mp4',
1177                 'title': 'I. M. Pei: A Centennial Celebration',
1178                 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1179                 'upload_date': '20170403',
1180                 'uploader_id': 'batchUser',
1181                 'timestamp': 1491232186,
1182             },
1183             'add_ie': ['Kaltura'],
1184         },
1185         # Eagle.Platform embed (generic URL)
1186         {
1187             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1188             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1189             'info_dict': {
1190                 'id': '227304',
1191                 'ext': 'mp4',
1192                 'title': 'Навальный вышел на свободу',
1193                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1194                 'thumbnail': r're:^https?://.*\.jpg$',
1195                 'duration': 87,
1196                 'view_count': int,
1197                 'age_limit': 0,
1198             },
1199         },
1200         # ClipYou (Eagle.Platform) embed (custom URL)
1201         {
1202             'url': 'http://muz-tv.ru/play/7129/',
1203             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1204             'info_dict': {
1205                 'id': '12820',
1206                 'ext': 'mp4',
1207                 'title': "'O Sole Mio",
1208                 'thumbnail': r're:^https?://.*\.jpg$',
1209                 'duration': 216,
1210                 'view_count': int,
1211             },
1212         },
1213         # Pladform embed
1214         {
1215             'url': 'http://muz-tv.ru/kinozal/view/7400/',
1216             'info_dict': {
1217                 'id': '100183293',
1218                 'ext': 'mp4',
1219                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1220                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1221                 'thumbnail': r're:^https?://.*\.jpg$',
1222                 'duration': 694,
1223                 'age_limit': 0,
1224             },
1225         },
1226         # Playwire embed
1227         {
1228             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1229             'info_dict': {
1230                 'id': '3519514',
1231                 'ext': 'mp4',
1232                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1233                 'thumbnail': r're:^https?://.*\.png$',
1234                 'duration': 45.115,
1235             },
1236         },
1237         # 5min embed
1238         {
1239             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1240             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1241             'info_dict': {
1242                 'id': '518726732',
1243                 'ext': 'mp4',
1244                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1245             },
1246         },
1247         # SVT embed
1248         {
1249             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1250             'info_dict': {
1251                 'id': '2900353',
1252                 'ext': 'flv',
1253                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1254                 'duration': 27,
1255                 'age_limit': 0,
1256             },
1257         },
1258         # Crooks and Liars embed
1259         {
1260             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1261             'info_dict': {
1262                 'id': '8RUoRhRi',
1263                 'ext': 'mp4',
1264                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1265                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1266                 'timestamp': 1428207000,
1267                 'upload_date': '20150405',
1268                 'uploader': 'Heather',
1269             },
1270         },
1271         # Crooks and Liars external embed
1272         {
1273             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1274             'info_dict': {
1275                 'id': 'MTE3MjUtMzQ2MzA',
1276                 'ext': 'mp4',
1277                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1278                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1279                 'timestamp': 1265032391,
1280                 'upload_date': '20100201',
1281                 'uploader': 'Heather',
1282             },
1283         },
1284         # NBC Sports vplayer embed
1285         {
1286             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1287             'info_dict': {
1288                 'id': 'ln7x1qSThw4k',
1289                 'ext': 'flv',
1290                 'title': "PFT Live: New leader in the 'new-look' defense",
1291                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1292                 'uploader': 'NBCU-SPORTS',
1293                 'upload_date': '20140107',
1294                 'timestamp': 1389118457,
1295             },
1296         },
1297         # NBC News embed
1298         {
1299             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1300             'md5': '1aa589c675898ae6d37a17913cf68d66',
1301             'info_dict': {
1302                 'id': '701714499682',
1303                 'ext': 'mp4',
1304                 'title': 'PREVIEW: On Assignment: David Letterman',
1305                 '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.',
1306             },
1307         },
1308         # UDN embed
1309         {
1310             'url': 'https://video.udn.com/news/300346',
1311             'md5': 'fd2060e988c326991037b9aff9df21a6',
1312             'info_dict': {
1313                 'id': '300346',
1314                 'ext': 'mp4',
1315                 'title': '中一中男師變性 全校師生力挺',
1316                 'thumbnail': r're:^https?://.*\.jpg$',
1317             },
1318             'params': {
1319                 # m3u8 download
1320                 'skip_download': True,
1321             },
1322         },
1323         # Ooyala embed
1324         {
1325             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1326             'info_dict': {
1327                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1328                 'ext': 'mp4',
1329                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1330                 'title': 'This is what separates the Excel masters from the wannabes',
1331                 'duration': 191.933,
1332             },
1333             'params': {
1334                 # m3u8 downloads
1335                 'skip_download': True,
1336             }
1337         },
1338         # Brightcove URL in single quotes
1339         {
1340             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1341             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1342             'info_dict': {
1343                 'id': '4255764656001',
1344                 'ext': 'mp4',
1345                 'title': 'SN Presents: Russell Martin, World Citizen',
1346                 '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.',
1347                 'uploader': 'Rogers Sportsnet',
1348                 'uploader_id': '1704050871',
1349                 'upload_date': '20150525',
1350                 'timestamp': 1432570283,
1351             },
1352         },
1353         # Dailymotion Cloud video
1354         {
1355             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1356             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1357             'info_dict': {
1358                 'id': 'x2uy8t3',
1359                 'ext': 'mp4',
1360                 'title': 'Sauvons les abeilles ! - Le débat',
1361                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1362                 'thumbnail': r're:^https?://.*\.jpe?g$',
1363                 'timestamp': 1434970506,
1364                 'upload_date': '20150622',
1365                 'uploader': 'Public Sénat',
1366                 'uploader_id': 'xa9gza',
1367             }
1368         },
1369         # OnionStudios embed
1370         {
1371             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1372             'info_dict': {
1373                 'id': '2855',
1374                 'ext': 'mp4',
1375                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1376                 'thumbnail': r're:^https?://.*\.jpe?g$',
1377                 'uploader': 'ClickHole',
1378                 'uploader_id': 'clickhole',
1379             }
1380         },
1381         # SnagFilms embed
1382         {
1383             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1384             'info_dict': {
1385                 'id': '74849a00-85a9-11e1-9660-123139220831',
1386                 'ext': 'mp4',
1387                 'title': '#whilewewatch',
1388             }
1389         },
1390         # AdobeTVVideo embed
1391         {
1392             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1393             'md5': '43662b577c018ad707a63766462b1e87',
1394             'info_dict': {
1395                 'id': '2456',
1396                 'ext': 'mp4',
1397                 'title': 'New experience with Acrobat DC',
1398                 'description': 'New experience with Acrobat DC',
1399                 'duration': 248.667,
1400             },
1401         },
1402         # BrightcoveInPageEmbed embed
1403         {
1404             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1405             'info_dict': {
1406                 'id': '4238694884001',
1407                 'ext': 'flv',
1408                 'title': 'Tabletop: Dread, Last Thoughts',
1409                 'description': 'Tabletop: Dread, Last Thoughts',
1410                 'duration': 51690,
1411             },
1412         },
1413         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1414         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1415         {
1416             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1417             'info_dict': {
1418                 'id': '4785848093001',
1419                 'ext': 'mp4',
1420                 'title': 'The Cardinal Pell Interview',
1421                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1422                 'uploader': 'GlobeCast Australia - GlobeStream',
1423                 'uploader_id': '2733773828001',
1424                 'upload_date': '20160304',
1425                 'timestamp': 1457083087,
1426             },
1427             'params': {
1428                 # m3u8 downloads
1429                 'skip_download': True,
1430             },
1431         },
1432         {
1433             # Brightcove embed with whitespace around attribute names
1434             'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1435             'info_dict': {
1436                 'id': '3167554373001',
1437                 'ext': 'mp4',
1438                 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1439                 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1440                 'uploader_id': '1079349493',
1441                 'upload_date': '20140207',
1442                 'timestamp': 1391810548,
1443             },
1444             'params': {
1445                 'skip_download': True,
1446             },
1447         },
1448         # Another form of arte.tv embed
1449         {
1450             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1451             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1452             'info_dict': {
1453                 'id': '030273-562_PLUS7-F',
1454                 'ext': 'mp4',
1455                 'title': 'ARTE Reportage - Nulle part, en France',
1456                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1457                 'upload_date': '20160409',
1458             },
1459         },
1460         # LiveLeak embed
1461         {
1462             'url': 'http://www.wykop.pl/link/3088787/',
1463             'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1464             'info_dict': {
1465                 'id': '874_1459135191',
1466                 'ext': 'mp4',
1467                 'title': 'Man shows poor quality of new apartment building',
1468                 'description': 'The wall is like a sand pile.',
1469                 'uploader': 'Lake8737',
1470             }
1471         },
1472         # Duplicated embedded video URLs
1473         {
1474             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1475             'info_dict': {
1476                 'id': '149298443_480_16c25b74_2',
1477                 'ext': 'mp4',
1478                 'title': 'vs. Blue Orange Spring Game',
1479                 'uploader': 'www.hudl.com',
1480             },
1481         },
1482         # twitter:player:stream embed
1483         {
1484             'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1485             'info_dict': {
1486                 'id': 'master',
1487                 'ext': 'mp4',
1488                 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1489                 'uploader': 'www.rtl.be',
1490             },
1491             'params': {
1492                 # m3u8 downloads
1493                 'skip_download': True,
1494             },
1495         },
1496         # twitter:player embed
1497         {
1498             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1499             'md5': 'a3e0df96369831de324f0778e126653c',
1500             'info_dict': {
1501                 'id': '4909620399001',
1502                 'ext': 'mp4',
1503                 'title': 'What Do Black Holes Sound Like?',
1504                 'description': 'what do black holes sound like',
1505                 'upload_date': '20160524',
1506                 'uploader_id': '29913724001',
1507                 'timestamp': 1464107587,
1508                 'uploader': 'TheAtlantic',
1509             },
1510             'add_ie': ['BrightcoveLegacy'],
1511         },
1512         # Facebook <iframe> embed
1513         {
1514             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1515             'md5': 'fbcde74f534176ecb015849146dd3aee',
1516             'info_dict': {
1517                 'id': '599637780109885',
1518                 'ext': 'mp4',
1519                 'title': 'Facebook video #599637780109885',
1520             },
1521         },
1522         # Facebook API embed
1523         {
1524             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1525             'md5': 'a47372ee61b39a7b90287094d447d94e',
1526             'info_dict': {
1527                 'id': '10153467542406923',
1528                 'ext': 'mp4',
1529                 'title': 'Facebook video #10153467542406923',
1530             },
1531         },
1532         # Wordpress "YouTube Video Importer" plugin
1533         {
1534             'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1535             'md5': 'd16797741b560b485194eddda8121b48',
1536             'info_dict': {
1537                 'id': 'HNTXWDXV9Is',
1538                 'ext': 'mp4',
1539                 'title': 'Blue Devils Drumline Stanford lot 2016',
1540                 'upload_date': '20160627',
1541                 'uploader_id': 'GENOCIDE8GENERAL10',
1542                 'uploader': 'cylus cyrus',
1543             },
1544         },
1545         {
1546             # video stored on custom kaltura server
1547             'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1548             'md5': '537617d06e64dfed891fa1593c4b30cc',
1549             'info_dict': {
1550                 'id': '0_1iotm5bh',
1551                 'ext': 'mp4',
1552                 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1553                 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1554                 'uploader_id': 'videos.expansion@el-mundo.net',
1555                 'upload_date': '20150429',
1556                 'timestamp': 1430303472,
1557             },
1558             'add_ie': ['Kaltura'],
1559         },
1560         {
1561             # Non-standard Vimeo embed
1562             'url': 'https://openclassrooms.com/courses/understanding-the-web',
1563             'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1564             'info_dict': {
1565                 'id': '148867247',
1566                 'ext': 'mp4',
1567                 'title': 'Understanding the web - Teaser',
1568                 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1569                 'upload_date': '20151214',
1570                 'uploader': 'OpenClassrooms',
1571                 'uploader_id': 'openclassrooms',
1572             },
1573             'add_ie': ['Vimeo'],
1574         },
1575         {
1576             # generic vimeo embed that requires original URL passed as Referer
1577             'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1578             'only_matching': True,
1579         },
1580         {
1581             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1582             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1583             'info_dict': {
1584                 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1585                 'ext': 'mp4',
1586                 'title': 'Big Buck Bunny',
1587                 'description': 'Royalty free test video',
1588                 'timestamp': 1432816365,
1589                 'upload_date': '20150528',
1590                 'is_live': False,
1591             },
1592             'params': {
1593                 'skip_download': True,
1594             },
1595             'add_ie': [ArkenaIE.ie_key()],
1596         },
1597         {
1598             '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/',
1599             'info_dict': {
1600                 'id': '1c7141f46c',
1601                 'ext': 'mp4',
1602                 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1603             },
1604             'params': {
1605                 'skip_download': True,
1606             },
1607             'add_ie': [Vbox7IE.ie_key()],
1608         },
1609         {
1610             # DBTV embeds
1611             'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1612             'info_dict': {
1613                 'id': '43254897',
1614                 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1615             },
1616             'playlist_mincount': 3,
1617         },
1618         {
1619             # Videa embeds
1620             'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1621             'info_dict': {
1622                 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1623                 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1624             },
1625             'playlist_mincount': 2,
1626         },
1627         {
1628             # 20 minuten embed
1629             'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1630             'info_dict': {
1631                 'id': '523629',
1632                 'ext': 'mp4',
1633                 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1634                 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1635             },
1636             'params': {
1637                 'skip_download': True,
1638             },
1639             'add_ie': [TwentyMinutenIE.ie_key()],
1640         },
1641         {
1642             # VideoPress embed
1643             'url': 'https://en.support.wordpress.com/videopress/',
1644             'info_dict': {
1645                 'id': 'OcobLTqC',
1646                 'ext': 'm4v',
1647                 'title': 'IMG_5786',
1648                 'timestamp': 1435711927,
1649                 'upload_date': '20150701',
1650             },
1651             'params': {
1652                 'skip_download': True,
1653             },
1654             'add_ie': [VideoPressIE.ie_key()],
1655         },
1656         {
1657             # Rutube embed
1658             'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1659             'info_dict': {
1660                 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1661                 'ext': 'flv',
1662                 'title': 'Магаззино: Казань 2',
1663                 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1664                 'uploader': 'Магаззино',
1665                 'upload_date': '20170228',
1666                 'uploader_id': '996642',
1667             },
1668             'params': {
1669                 'skip_download': True,
1670             },
1671             'add_ie': [RutubeIE.ie_key()],
1672         },
1673         {
1674             # ThePlatform embedded with whitespaces in URLs
1675             'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1676             'only_matching': True,
1677         },
1678         {
1679             # Senate ISVP iframe https
1680             'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1681             'md5': 'fb8c70b0b515e5037981a2492099aab8',
1682             'info_dict': {
1683                 'id': 'govtaff020316',
1684                 'ext': 'mp4',
1685                 'title': 'Integrated Senate Video Player',
1686             },
1687             'add_ie': [SenateISVPIE.ie_key()],
1688         },
1689         {
1690             # Limelight embeds (1 channel embed + 4 media embeds)
1691             'url': 'http://www.sedona.com/FacilitatorTraining2017',
1692             'info_dict': {
1693                 'id': 'FacilitatorTraining2017',
1694                 'title': 'Facilitator Training 2017',
1695             },
1696             'playlist_mincount': 5,
1697         },
1698         {
1699             'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1700             'info_dict': {
1701                 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1702                 'title': 'Standoff with Walnut Creek murder suspect ends',
1703                 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1704             },
1705             'playlist_mincount': 4,
1706         },
1707         {
1708             # WashingtonPost embed
1709             'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1710             'info_dict': {
1711                 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1712                 'ext': 'mp4',
1713                 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1714                 '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.',
1715                 'timestamp': 1455216756,
1716                 'uploader': 'The Washington Post',
1717                 'upload_date': '20160211',
1718             },
1719             'add_ie': [WashingtonPostIE.ie_key()],
1720         },
1721         # {
1722         #     # TODO: find another test
1723         #     # http://schema.org/VideoObject
1724         #     'url': 'https://flipagram.com/f/nyvTSJMKId',
1725         #     'md5': '888dcf08b7ea671381f00fab74692755',
1726         #     'info_dict': {
1727         #         'id': 'nyvTSJMKId',
1728         #         'ext': 'mp4',
1729         #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1730         #         'description': '#love for cats.',
1731         #         'timestamp': 1461244995,
1732         #         'upload_date': '20160421',
1733         #     },
1734         #     'params': {
1735         #         'force_generic_extractor': True,
1736         #     },
1737         # }
1738     ]
1739
1740     def report_following_redirect(self, new_url):
1741         """Report information extraction."""
1742         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1743
1744     def _extract_rss(self, url, video_id, doc):
1745         playlist_title = doc.find('./channel/title').text
1746         playlist_desc_el = doc.find('./channel/description')
1747         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1748
1749         entries = []
1750         for it in doc.findall('./channel/item'):
1751             next_url = xpath_text(it, 'link', fatal=False)
1752             if not next_url:
1753                 enclosure_nodes = it.findall('./enclosure')
1754                 for e in enclosure_nodes:
1755                     next_url = e.attrib.get('url')
1756                     if next_url:
1757                         break
1758
1759             if not next_url:
1760                 continue
1761
1762             entries.append({
1763                 '_type': 'url_transparent',
1764                 'url': next_url,
1765                 'title': it.find('title').text,
1766             })
1767
1768         return {
1769             '_type': 'playlist',
1770             'id': url,
1771             'title': playlist_title,
1772             'description': playlist_desc,
1773             'entries': entries,
1774         }
1775
1776     def _extract_camtasia(self, url, video_id, webpage):
1777         """ Returns None if no camtasia video can be found. """
1778
1779         camtasia_cfg = self._search_regex(
1780             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1781             webpage, 'camtasia configuration file', default=None)
1782         if camtasia_cfg is None:
1783             return None
1784
1785         title = self._html_search_meta('DC.title', webpage, fatal=True)
1786
1787         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1788         camtasia_cfg = self._download_xml(
1789             camtasia_url, video_id,
1790             note='Downloading camtasia configuration',
1791             errnote='Failed to download camtasia configuration')
1792         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1793
1794         entries = []
1795         for n in fileset_node.getchildren():
1796             url_n = n.find('./uri')
1797             if url_n is None:
1798                 continue
1799
1800             entries.append({
1801                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1802                 'title': '%s - %s' % (title, n.tag),
1803                 'url': compat_urlparse.urljoin(url, url_n.text),
1804                 'duration': float_or_none(n.find('./duration').text),
1805             })
1806
1807         return {
1808             '_type': 'playlist',
1809             'entries': entries,
1810             'title': title,
1811         }
1812
1813     def _real_extract(self, url):
1814         if url.startswith('//'):
1815             return {
1816                 '_type': 'url',
1817                 'url': self.http_scheme() + url,
1818             }
1819
1820         parsed_url = compat_urlparse.urlparse(url)
1821         if not parsed_url.scheme:
1822             default_search = self._downloader.params.get('default_search')
1823             if default_search is None:
1824                 default_search = 'fixup_error'
1825
1826             if default_search in ('auto', 'auto_warning', 'fixup_error'):
1827                 if '/' in url:
1828                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1829                     return self.url_result('http://' + url)
1830                 elif default_search != 'fixup_error':
1831                     if default_search == 'auto_warning':
1832                         if re.match(r'^(?:url|URL)$', url):
1833                             raise ExtractorError(
1834                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
1835                                 expected=True)
1836                         else:
1837                             self._downloader.report_warning(
1838                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
1839                     return self.url_result('ytsearch:' + url)
1840
1841             if default_search in ('error', 'fixup_error'):
1842                 raise ExtractorError(
1843                     '%r is not a valid URL. '
1844                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
1845                     % (url, url), expected=True)
1846             else:
1847                 if ':' not in default_search:
1848                     default_search += ':'
1849                 return self.url_result(default_search + url)
1850
1851         url, smuggled_data = unsmuggle_url(url)
1852         force_videoid = None
1853         is_intentional = smuggled_data and smuggled_data.get('to_generic')
1854         if smuggled_data and 'force_videoid' in smuggled_data:
1855             force_videoid = smuggled_data['force_videoid']
1856             video_id = force_videoid
1857         else:
1858             video_id = self._generic_id(url)
1859
1860         self.to_screen('%s: Requesting header' % video_id)
1861
1862         head_req = HEADRequest(url)
1863         head_response = self._request_webpage(
1864             head_req, video_id,
1865             note=False, errnote='Could not send HEAD request to %s' % url,
1866             fatal=False)
1867
1868         if head_response is not False:
1869             # Check for redirect
1870             new_url = head_response.geturl()
1871             if url != new_url:
1872                 self.report_following_redirect(new_url)
1873                 if force_videoid:
1874                     new_url = smuggle_url(
1875                         new_url, {'force_videoid': force_videoid})
1876                 return self.url_result(new_url)
1877
1878         full_response = None
1879         if head_response is False:
1880             request = sanitized_Request(url)
1881             request.add_header('Accept-Encoding', '*')
1882             full_response = self._request_webpage(request, video_id)
1883             head_response = full_response
1884
1885         info_dict = {
1886             'id': video_id,
1887             'title': self._generic_title(url),
1888             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1889         }
1890
1891         # Check for direct link to a video
1892         content_type = head_response.headers.get('Content-Type', '').lower()
1893         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1894         if m:
1895             format_id = m.group('format_id')
1896             if format_id.endswith('mpegurl'):
1897                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1898             elif format_id == 'f4m':
1899                 formats = self._extract_f4m_formats(url, video_id)
1900             else:
1901                 formats = [{
1902                     'format_id': m.group('format_id'),
1903                     'url': url,
1904                     'vcodec': 'none' if m.group('type') == 'audio' else None
1905                 }]
1906                 info_dict['direct'] = True
1907             self._sort_formats(formats)
1908             info_dict['formats'] = formats
1909             return info_dict
1910
1911         if not self._downloader.params.get('test', False) and not is_intentional:
1912             force = self._downloader.params.get('force_generic_extractor', False)
1913             self._downloader.report_warning(
1914                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1915
1916         if not full_response:
1917             request = sanitized_Request(url)
1918             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1919             # making it impossible to download only chunk of the file (yet we need only 512kB to
1920             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1921             # that will always result in downloading the whole file that is not desirable.
1922             # Therefore for extraction pass we have to override Accept-Encoding to any in order
1923             # to accept raw bytes and being able to download only a chunk.
1924             # It may probably better to solve this by checking Content-Type for application/octet-stream
1925             # after HEAD request finishes, but not sure if we can rely on this.
1926             request.add_header('Accept-Encoding', '*')
1927             full_response = self._request_webpage(request, video_id)
1928
1929         first_bytes = full_response.read(512)
1930
1931         # Is it an M3U playlist?
1932         if first_bytes.startswith(b'#EXTM3U'):
1933             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1934             self._sort_formats(info_dict['formats'])
1935             return info_dict
1936
1937         # Maybe it's a direct link to a video?
1938         # Be careful not to download the whole thing!
1939         if not is_html(first_bytes):
1940             self._downloader.report_warning(
1941                 'URL could be a direct video link, returning it as such.')
1942             info_dict.update({
1943                 'direct': True,
1944                 'url': url,
1945             })
1946             return info_dict
1947
1948         webpage = self._webpage_read_content(
1949             full_response, url, video_id, prefix=first_bytes)
1950
1951         self.report_extraction(video_id)
1952
1953         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1954         try:
1955             doc = compat_etree_fromstring(webpage.encode('utf-8'))
1956             if doc.tag == 'rss':
1957                 return self._extract_rss(url, video_id, doc)
1958             elif doc.tag == 'SmoothStreamingMedia':
1959                 info_dict['formats'] = self._parse_ism_formats(doc, url)
1960                 self._sort_formats(info_dict['formats'])
1961                 return info_dict
1962             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1963                 smil = self._parse_smil(doc, url, video_id)
1964                 self._sort_formats(smil['formats'])
1965                 return smil
1966             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1967                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1968             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1969                 info_dict['formats'] = self._parse_mpd_formats(
1970                     doc, video_id,
1971                     mpd_base_url=full_response.geturl().rpartition('/')[0],
1972                     mpd_url=url)
1973                 self._sort_formats(info_dict['formats'])
1974                 return info_dict
1975             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1976                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1977                 self._sort_formats(info_dict['formats'])
1978                 return info_dict
1979         except compat_xml_parse_error:
1980             pass
1981
1982         # Is it a Camtasia project?
1983         camtasia_res = self._extract_camtasia(url, video_id, webpage)
1984         if camtasia_res is not None:
1985             return camtasia_res
1986
1987         # Sometimes embedded video player is hidden behind percent encoding
1988         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1989         # Unescaping the whole page allows to handle those cases in a generic way
1990         webpage = compat_urllib_parse_unquote(webpage)
1991
1992         # it's tempting to parse this further, but you would
1993         # have to take into account all the variations like
1994         #   Video Title - Site Name
1995         #   Site Name | Video Title
1996         #   Video Title - Tagline | Site Name
1997         # and so on and so forth; it's just not practical
1998         video_title = self._og_search_title(
1999             webpage, default=None) or self._html_search_regex(
2000             r'(?s)<title>(.*?)</title>', webpage, 'video title',
2001             default='video')
2002
2003         # Try to detect age limit automatically
2004         age_limit = self._rta_search(webpage)
2005         # And then there are the jokers who advertise that they use RTA,
2006         # but actually don't.
2007         AGE_LIMIT_MARKERS = [
2008             r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2009         ]
2010         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2011             age_limit = 18
2012
2013         # video uploader is domain name
2014         video_uploader = self._search_regex(
2015             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2016
2017         video_description = self._og_search_description(webpage, default=None)
2018         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2019
2020         # Look for Brightcove Legacy Studio embeds
2021         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2022         if bc_urls:
2023             entries = [{
2024                 '_type': 'url',
2025                 'url': smuggle_url(bc_url, {'Referer': url}),
2026                 'ie_key': 'BrightcoveLegacy'
2027             } for bc_url in bc_urls]
2028
2029             return {
2030                 '_type': 'playlist',
2031                 'title': video_title,
2032                 'id': video_id,
2033                 'entries': entries,
2034             }
2035
2036         # Look for Brightcove New Studio embeds
2037         bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2038         if bc_urls:
2039             return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2040
2041         # Look for ThePlatform embeds
2042         tp_urls = ThePlatformIE._extract_urls(webpage)
2043         if tp_urls:
2044             return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2045
2046         # Look for Vessel embeds
2047         vessel_urls = VesselIE._extract_urls(webpage)
2048         if vessel_urls:
2049             return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2050
2051         # Look for embedded rtl.nl player
2052         matches = re.findall(
2053             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2054             webpage)
2055         if matches:
2056             return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2057
2058         vimeo_urls = VimeoIE._extract_urls(url, webpage)
2059         if vimeo_urls:
2060             return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2061
2062         vid_me_embed_url = self._search_regex(
2063             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2064             webpage, 'vid.me embed', default=None)
2065         if vid_me_embed_url is not None:
2066             return self.url_result(vid_me_embed_url, 'Vidme')
2067
2068         # Look for embedded YouTube player
2069         matches = re.findall(r'''(?x)
2070             (?:
2071                 <iframe[^>]+?src=|
2072                 data-video-url=|
2073                 <embed[^>]+?src=|
2074                 embedSWF\(?:\s*|
2075                 <object[^>]+data=|
2076                 new\s+SWFObject\(
2077             )
2078             (["\'])
2079                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2080                 (?:embed|v|p)/.+?)
2081             \1''', webpage)
2082         if matches:
2083             return self.playlist_from_matches(
2084                 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2085
2086         # Look for lazyYT YouTube embed
2087         matches = re.findall(
2088             r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2089         if matches:
2090             return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2091
2092         # Look for Wordpress "YouTube Video Importer" plugin
2093         matches = re.findall(r'''(?x)<div[^>]+
2094             class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2095             data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2096         if matches:
2097             return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2098
2099         matches = DailymotionIE._extract_urls(webpage)
2100         if matches:
2101             return self.playlist_from_matches(matches, video_id, video_title)
2102
2103         # Look for embedded Dailymotion playlist player (#3822)
2104         m = re.search(
2105             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2106         if m:
2107             playlists = re.findall(
2108                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2109             if playlists:
2110                 return self.playlist_from_matches(
2111                     playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2112
2113         # Look for embedded Wistia player
2114         match = re.search(
2115             r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
2116         if match:
2117             embed_url = self._proto_relative_url(
2118                 unescapeHTML(match.group('url')))
2119             return {
2120                 '_type': 'url_transparent',
2121                 'url': embed_url,
2122                 'ie_key': 'Wistia',
2123                 'uploader': video_uploader,
2124             }
2125
2126         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
2127         if match:
2128             return {
2129                 '_type': 'url_transparent',
2130                 'url': 'wistia:%s' % match.group('id'),
2131                 'ie_key': 'Wistia',
2132                 'uploader': video_uploader,
2133             }
2134
2135         match = re.search(
2136             r'''(?sx)
2137                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
2138                 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
2139             ''', webpage)
2140         if match:
2141             return self.url_result(self._proto_relative_url(
2142                 'wistia:%s' % match.group('id')), 'Wistia')
2143
2144         # Look for SVT player
2145         svt_url = SVTIE._extract_url(webpage)
2146         if svt_url:
2147             return self.url_result(svt_url, 'SVT')
2148
2149         # Look for embedded condenast player
2150         matches = re.findall(
2151             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2152             webpage)
2153         if matches:
2154             return {
2155                 '_type': 'playlist',
2156                 'entries': [{
2157                     '_type': 'url',
2158                     'ie_key': 'CondeNast',
2159                     'url': ma,
2160                 } for ma in matches],
2161                 'title': video_title,
2162                 'id': video_id,
2163             }
2164
2165         # Look for Bandcamp pages with custom domain
2166         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2167         if mobj is not None:
2168             burl = unescapeHTML(mobj.group(1))
2169             # Don't set the extractor because it can be a track url or an album
2170             return self.url_result(burl)
2171
2172         # Look for embedded Vevo player
2173         mobj = re.search(
2174             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2175         if mobj is not None:
2176             return self.url_result(mobj.group('url'))
2177
2178         # Look for embedded Viddler player
2179         mobj = re.search(
2180             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2181             webpage)
2182         if mobj is not None:
2183             return self.url_result(mobj.group('url'))
2184
2185         # Look for NYTimes player
2186         mobj = re.search(
2187             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2188             webpage)
2189         if mobj is not None:
2190             return self.url_result(mobj.group('url'))
2191
2192         # Look for Libsyn player
2193         mobj = re.search(
2194             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2195         if mobj is not None:
2196             return self.url_result(mobj.group('url'))
2197
2198         # Look for Ooyala videos
2199         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2200                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2201                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2202                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2203         if mobj is not None:
2204             embed_token = self._search_regex(
2205                 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2206                 webpage, 'ooyala embed token', default=None)
2207             return OoyalaIE._build_url_result(smuggle_url(
2208                 mobj.group('ec'), {
2209                     'domain': url,
2210                     'embed_token': embed_token,
2211                 }))
2212
2213         # Look for multiple Ooyala embeds on SBN network websites
2214         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2215         if mobj is not None:
2216             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2217             if embeds:
2218                 return self.playlist_from_matches(
2219                     embeds, video_id, video_title,
2220                     getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2221
2222         # Look for Aparat videos
2223         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2224         if mobj is not None:
2225             return self.url_result(mobj.group(1), 'Aparat')
2226
2227         # Look for MPORA videos
2228         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2229         if mobj is not None:
2230             return self.url_result(mobj.group(1), 'Mpora')
2231
2232         # Look for embedded NovaMov-based player
2233         mobj = re.search(
2234             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2235                     (?P<url>http://(?:(?:embed|www)\.)?
2236                         (?:novamov\.com|
2237                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
2238                            videoweed\.(?:es|com)|
2239                            movshare\.(?:net|sx|ag)|
2240                            divxstage\.(?:eu|net|ch|co|at|ag))
2241                         /embed\.php.+?)\1''', webpage)
2242         if mobj is not None:
2243             return self.url_result(mobj.group('url'))
2244
2245         # Look for embedded Facebook player
2246         facebook_url = FacebookIE._extract_url(webpage)
2247         if facebook_url is not None:
2248             return self.url_result(facebook_url, 'Facebook')
2249
2250         # Look for embedded VK player
2251         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2252         if mobj is not None:
2253             return self.url_result(mobj.group('url'), 'VK')
2254
2255         # Look for embedded Odnoklassniki player
2256         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2257         if mobj is not None:
2258             return self.url_result(mobj.group('url'), 'Odnoklassniki')
2259
2260         # Look for embedded ivi player
2261         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2262         if mobj is not None:
2263             return self.url_result(mobj.group('url'), 'Ivi')
2264
2265         # Look for embedded Huffington Post player
2266         mobj = re.search(
2267             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2268         if mobj is not None:
2269             return self.url_result(mobj.group('url'), 'HuffPost')
2270
2271         # Look for embed.ly
2272         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2273         if mobj is not None:
2274             return self.url_result(mobj.group('url'))
2275         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2276         if mobj is not None:
2277             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2278
2279         # Look for funnyordie embed
2280         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2281         if matches:
2282             return self.playlist_from_matches(
2283                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2284
2285         # Look for BBC iPlayer embed
2286         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2287         if matches:
2288             return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2289
2290         # Look for embedded RUTV player
2291         rutv_url = RUTVIE._extract_url(webpage)
2292         if rutv_url:
2293             return self.url_result(rutv_url, 'RUTV')
2294
2295         # Look for embedded TVC player
2296         tvc_url = TVCIE._extract_url(webpage)
2297         if tvc_url:
2298             return self.url_result(tvc_url, 'TVC')
2299
2300         # Look for embedded SportBox player
2301         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2302         if sportbox_urls:
2303             return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2304
2305         # Look for embedded XHamster player
2306         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2307         if xhamster_urls:
2308             return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2309
2310         # Look for embedded TNAFlixNetwork player
2311         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2312         if tnaflix_urls:
2313             return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2314
2315         # Look for embedded PornHub player
2316         pornhub_urls = PornHubIE._extract_urls(webpage)
2317         if pornhub_urls:
2318             return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2319
2320         # Look for embedded DrTuber player
2321         drtuber_urls = DrTuberIE._extract_urls(webpage)
2322         if drtuber_urls:
2323             return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2324
2325         # Look for embedded RedTube player
2326         redtube_urls = RedTubeIE._extract_urls(webpage)
2327         if redtube_urls:
2328             return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2329
2330         # Look for embedded Tvigle player
2331         mobj = re.search(
2332             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2333         if mobj is not None:
2334             return self.url_result(mobj.group('url'), 'Tvigle')
2335
2336         # Look for embedded TED player
2337         mobj = re.search(
2338             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2339         if mobj is not None:
2340             return self.url_result(mobj.group('url'), 'TED')
2341
2342         # Look for embedded Ustream videos
2343         ustream_url = UstreamIE._extract_url(webpage)
2344         if ustream_url:
2345             return self.url_result(ustream_url, UstreamIE.ie_key())
2346
2347         # Look for embedded arte.tv player
2348         mobj = re.search(
2349             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2350             webpage)
2351         if mobj is not None:
2352             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2353
2354         # Look for embedded francetv player
2355         mobj = re.search(
2356             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2357             webpage)
2358         if mobj is not None:
2359             return self.url_result(mobj.group('url'))
2360
2361         # Look for embedded smotri.com player
2362         smotri_url = SmotriIE._extract_url(webpage)
2363         if smotri_url:
2364             return self.url_result(smotri_url, 'Smotri')
2365
2366         # Look for embedded Myvi.ru player
2367         myvi_url = MyviIE._extract_url(webpage)
2368         if myvi_url:
2369             return self.url_result(myvi_url)
2370
2371         # Look for embedded soundcloud player
2372         soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2373         if soundcloud_urls:
2374             return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2375
2376         # Look for tunein player
2377         tunein_urls = TuneInBaseIE._extract_urls(webpage)
2378         if tunein_urls:
2379             return self.playlist_from_matches(tunein_urls, video_id, video_title)
2380
2381         # Look for embedded mtvservices player
2382         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2383         if mtvservices_url:
2384             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2385
2386         # Look for embedded yahoo player
2387         mobj = re.search(
2388             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2389             webpage)
2390         if mobj is not None:
2391             return self.url_result(mobj.group('url'), 'Yahoo')
2392
2393         # Look for embedded sbs.com.au player
2394         mobj = re.search(
2395             r'''(?x)
2396             (?:
2397                 <meta\s+property="og:video"\s+content=|
2398                 <iframe[^>]+?src=
2399             )
2400             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2401             webpage)
2402         if mobj is not None:
2403             return self.url_result(mobj.group('url'), 'SBS')
2404
2405         # Look for embedded Cinchcast player
2406         mobj = re.search(
2407             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2408             webpage)
2409         if mobj is not None:
2410             return self.url_result(mobj.group('url'), 'Cinchcast')
2411
2412         mobj = re.search(
2413             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2414             webpage)
2415         if not mobj:
2416             mobj = re.search(
2417                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2418                 webpage)
2419         if mobj is not None:
2420             return self.url_result(mobj.group('url'), 'MLB')
2421
2422         mobj = re.search(
2423             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2424             webpage)
2425         if mobj is not None:
2426             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2427
2428         mobj = re.search(
2429             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2430             webpage)
2431         if mobj is not None:
2432             return self.url_result(mobj.group('url'), 'Livestream')
2433
2434         # Look for Zapiks embed
2435         mobj = re.search(
2436             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2437         if mobj is not None:
2438             return self.url_result(mobj.group('url'), 'Zapiks')
2439
2440         # Look for Kaltura embeds
2441         kaltura_url = KalturaIE._extract_url(webpage)
2442         if kaltura_url:
2443             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2444
2445         # Look for Eagle.Platform embeds
2446         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2447         if eagleplatform_url:
2448             return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2449
2450         # Look for ClipYou (uses Eagle.Platform) embeds
2451         mobj = re.search(
2452             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2453         if mobj is not None:
2454             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2455
2456         # Look for Pladform embeds
2457         pladform_url = PladformIE._extract_url(webpage)
2458         if pladform_url:
2459             return self.url_result(pladform_url)
2460
2461         # Look for Videomore embeds
2462         videomore_url = VideomoreIE._extract_url(webpage)
2463         if videomore_url:
2464             return self.url_result(videomore_url)
2465
2466         # Look for Webcaster embeds
2467         webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2468         if webcaster_url:
2469             return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2470
2471         # Look for Playwire embeds
2472         mobj = re.search(
2473             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2474         if mobj is not None:
2475             return self.url_result(mobj.group('url'))
2476
2477         # Look for 5min embeds
2478         mobj = re.search(
2479             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2480         if mobj is not None:
2481             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2482
2483         # Look for Crooks and Liars embeds
2484         mobj = re.search(
2485             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2486         if mobj is not None:
2487             return self.url_result(mobj.group('url'))
2488
2489         # Look for NBC Sports VPlayer embeds
2490         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2491         if nbc_sports_url:
2492             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2493
2494         # Look for NBC News embeds
2495         nbc_news_embed_url = re.search(
2496             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2497         if nbc_news_embed_url:
2498             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2499
2500         # Look for Google Drive embeds
2501         google_drive_url = GoogleDriveIE._extract_url(webpage)
2502         if google_drive_url:
2503             return self.url_result(google_drive_url, 'GoogleDrive')
2504
2505         # Look for UDN embeds
2506         mobj = re.search(
2507             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2508         if mobj is not None:
2509             return self.url_result(
2510                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2511
2512         # Look for Senate ISVP iframe
2513         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2514         if senate_isvp_url:
2515             return self.url_result(senate_isvp_url, 'SenateISVP')
2516
2517         # Look for Dailymotion Cloud videos
2518         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2519         if dmcloud_url:
2520             return self.url_result(dmcloud_url, 'DailymotionCloud')
2521
2522         # Look for OnionStudios embeds
2523         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2524         if onionstudios_url:
2525             return self.url_result(onionstudios_url)
2526
2527         # Look for ViewLift embeds
2528         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2529         if viewlift_url:
2530             return self.url_result(viewlift_url)
2531
2532         # Look for JWPlatform embeds
2533         jwplatform_url = JWPlatformIE._extract_url(webpage)
2534         if jwplatform_url:
2535             return self.url_result(jwplatform_url, 'JWPlatform')
2536
2537         # Look for Digiteka embeds
2538         digiteka_url = DigitekaIE._extract_url(webpage)
2539         if digiteka_url:
2540             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2541
2542         # Look for Arkena embeds
2543         arkena_url = ArkenaIE._extract_url(webpage)
2544         if arkena_url:
2545             return self.url_result(arkena_url, ArkenaIE.ie_key())
2546
2547         # Look for Piksel embeds
2548         piksel_url = PikselIE._extract_url(webpage)
2549         if piksel_url:
2550             return self.url_result(piksel_url, PikselIE.ie_key())
2551
2552         # Look for Limelight embeds
2553         limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2554         if limelight_urls:
2555             return self.playlist_result(
2556                 limelight_urls, video_id, video_title, video_description)
2557
2558         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2559         if mobj:
2560             lm = {
2561                 'Media': 'media',
2562                 'Channel': 'channel',
2563                 'ChannelList': 'channel_list',
2564             }
2565             return self.url_result(smuggle_url('limelight:%s:%s' % (
2566                 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2567                 'Limelight%s' % mobj.group(1), mobj.group(2))
2568
2569         mobj = re.search(
2570             r'''(?sx)
2571                 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2572                     <param[^>]+
2573                         name=(["\'])flashVars\2[^>]+
2574                         value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2575             ''', webpage)
2576         if mobj:
2577             return self.url_result(smuggle_url(
2578                 'limelight:media:%s' % mobj.group('id'),
2579                 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2580
2581         # Look for Anvato embeds
2582         anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2583         if anvato_urls:
2584             return self.playlist_result(
2585                 anvato_urls, video_id, video_title, video_description)
2586
2587         # Look for AdobeTVVideo embeds
2588         mobj = re.search(
2589             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2590             webpage)
2591         if mobj is not None:
2592             return self.url_result(
2593                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2594                 'AdobeTVVideo')
2595
2596         # Look for Vine embeds
2597         mobj = re.search(
2598             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2599             webpage)
2600         if mobj is not None:
2601             return self.url_result(
2602                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2603
2604         # Look for VODPlatform embeds
2605         mobj = re.search(
2606             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2607             webpage)
2608         if mobj is not None:
2609             return self.url_result(
2610                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2611
2612         # Look for Mangomolo embeds
2613         mobj = re.search(
2614             r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2615                 (?:
2616                     video\?.*?\bid=(?P<video_id>\d+)|
2617                     index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2618                 ).+?)\1''', webpage)
2619         if mobj is not None:
2620             info = {
2621                 '_type': 'url_transparent',
2622                 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2623                 'title': video_title,
2624                 'description': video_description,
2625                 'thumbnail': video_thumbnail,
2626                 'uploader': video_uploader,
2627             }
2628             video_id = mobj.group('video_id')
2629             if video_id:
2630                 info.update({
2631                     'ie_key': 'MangomoloVideo',
2632                     'id': video_id,
2633                 })
2634             else:
2635                 info.update({
2636                     'ie_key': 'MangomoloLive',
2637                     'id': mobj.group('channel_id'),
2638                 })
2639             return info
2640
2641         # Look for Instagram embeds
2642         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2643         if instagram_embed_url is not None:
2644             return self.url_result(
2645                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2646
2647         # Look for LiveLeak embeds
2648         liveleak_url = LiveLeakIE._extract_url(webpage)
2649         if liveleak_url:
2650             return self.url_result(liveleak_url, 'LiveLeak')
2651
2652         # Look for 3Q SDN embeds
2653         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2654         if threeqsdn_url:
2655             return {
2656                 '_type': 'url_transparent',
2657                 'ie_key': ThreeQSDNIE.ie_key(),
2658                 'url': self._proto_relative_url(threeqsdn_url),
2659                 'title': video_title,
2660                 'description': video_description,
2661                 'thumbnail': video_thumbnail,
2662                 'uploader': video_uploader,
2663             }
2664
2665         # Look for VBOX7 embeds
2666         vbox7_url = Vbox7IE._extract_url(webpage)
2667         if vbox7_url:
2668             return self.url_result(vbox7_url, Vbox7IE.ie_key())
2669
2670         # Look for DBTV embeds
2671         dbtv_urls = DBTVIE._extract_urls(webpage)
2672         if dbtv_urls:
2673             return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2674
2675         # Look for Videa embeds
2676         videa_urls = VideaIE._extract_urls(webpage)
2677         if videa_urls:
2678             return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2679
2680         # Look for 20 minuten embeds
2681         twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2682         if twentymin_urls:
2683             return self.playlist_from_matches(
2684                 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2685
2686         # Look for Openload embeds
2687         openload_urls = OpenloadIE._extract_urls(webpage)
2688         if openload_urls:
2689             return self.playlist_from_matches(
2690                 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2691
2692         # Look for VideoPress embeds
2693         videopress_urls = VideoPressIE._extract_urls(webpage)
2694         if videopress_urls:
2695             return self.playlist_from_matches(
2696                 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2697
2698         # Look for Rutube embeds
2699         rutube_urls = RutubeIE._extract_urls(webpage)
2700         if rutube_urls:
2701             return self.playlist_from_matches(
2702                 rutube_urls, ie=RutubeIE.ie_key())
2703
2704         # Look for WashingtonPost embeds
2705         wapo_urls = WashingtonPostIE._extract_urls(webpage)
2706         if wapo_urls:
2707             return self.playlist_from_matches(
2708                 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2709
2710         # Looking for http://schema.org/VideoObject
2711         json_ld = self._search_json_ld(
2712             webpage, video_id, default={}, expected_type='VideoObject')
2713         if json_ld.get('url'):
2714             info_dict.update({
2715                 'title': video_title or info_dict['title'],
2716                 'description': video_description,
2717                 'thumbnail': video_thumbnail,
2718                 'age_limit': age_limit
2719             })
2720             info_dict.update(json_ld)
2721             return info_dict
2722
2723         # Look for HTML5 media
2724         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2725         if entries:
2726             for entry in entries:
2727                 entry.update({
2728                     'id': video_id,
2729                     'title': video_title,
2730                 })
2731                 self._sort_formats(entry['formats'])
2732             return self.playlist_result(entries)
2733
2734         jwplayer_data = self._find_jwplayer_data(
2735             webpage, video_id, transform_source=js_to_json)
2736         if jwplayer_data:
2737             info = self._parse_jwplayer_data(
2738                 jwplayer_data, video_id, require_title=False, base_url=url)
2739             if not info.get('title'):
2740                 info['title'] = video_title
2741             return info
2742
2743         def check_video(vurl):
2744             if YoutubeIE.suitable(vurl):
2745                 return True
2746             if RtmpIE.suitable(vurl):
2747                 return True
2748             vpath = compat_urlparse.urlparse(vurl).path
2749             vext = determine_ext(vpath)
2750             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2751
2752         def filter_video(urls):
2753             return list(filter(check_video, urls))
2754
2755         # Start with something easy: JW Player in SWFObject
2756         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2757         if not found:
2758             # Look for gorilla-vid style embedding
2759             found = filter_video(re.findall(r'''(?sx)
2760                 (?:
2761                     jw_plugins|
2762                     JWPlayerOptions|
2763                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2764                 )
2765                 .*?
2766                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2767         if not found:
2768             # Broaden the search a little bit
2769             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2770         if not found:
2771             # Broaden the findall a little bit: JWPlayer JS loader
2772             found = filter_video(re.findall(
2773                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2774         if not found:
2775             # Flow player
2776             found = filter_video(re.findall(r'''(?xs)
2777                 flowplayer\("[^"]+",\s*
2778                     \{[^}]+?\}\s*,
2779                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2780                         ["']?url["']?\s*:\s*["']([^"']+)["']
2781             ''', webpage))
2782         if not found:
2783             # Cinerama player
2784             found = re.findall(
2785                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2786         if not found:
2787             # Try to find twitter cards info
2788             # twitter:player:stream should be checked before twitter:player since
2789             # it is expected to contain a raw stream (see
2790             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2791             found = filter_video(re.findall(
2792                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2793         if not found:
2794             # We look for Open Graph info:
2795             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2796             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2797             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2798             if m_video_type is not None:
2799                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2800         if not found:
2801             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2802             found = re.search(
2803                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2804                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2805                 webpage)
2806             if not found:
2807                 # Look also in Refresh HTTP header
2808                 refresh_header = head_response.headers.get('Refresh')
2809                 if refresh_header:
2810                     # In python 2 response HTTP headers are bytestrings
2811                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2812                         refresh_header = refresh_header.decode('iso-8859-1')
2813                     found = re.search(REDIRECT_REGEX, refresh_header)
2814             if found:
2815                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2816                 if new_url != url:
2817                     self.report_following_redirect(new_url)
2818                     return {
2819                         '_type': 'url',
2820                         'url': new_url,
2821                     }
2822                 else:
2823                     found = None
2824
2825         if not found:
2826             # twitter:player is a https URL to iframe player that may or may not
2827             # be supported by youtube-dl thus this is checked the very last (see
2828             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2829             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2830             if embed_url:
2831                 return self.url_result(embed_url)
2832
2833         if not found:
2834             raise UnsupportedError(url)
2835
2836         entries = []
2837         for video_url in orderedSet(found):
2838             video_url = unescapeHTML(video_url)
2839             video_url = video_url.replace('\\/', '/')
2840             video_url = compat_urlparse.urljoin(url, video_url)
2841             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2842
2843             # Sometimes, jwplayer extraction will result in a YouTube URL
2844             if YoutubeIE.suitable(video_url):
2845                 entries.append(self.url_result(video_url, 'Youtube'))
2846                 continue
2847
2848             # here's a fun little line of code for you:
2849             video_id = os.path.splitext(video_id)[0]
2850
2851             entry_info_dict = {
2852                 'id': video_id,
2853                 'uploader': video_uploader,
2854                 'title': video_title,
2855                 'age_limit': age_limit,
2856             }
2857
2858             if RtmpIE.suitable(video_url):
2859                 entry_info_dict.update({
2860                     '_type': 'url_transparent',
2861                     'ie_key': RtmpIE.ie_key(),
2862                     'url': video_url,
2863                 })
2864                 entries.append(entry_info_dict)
2865                 continue
2866
2867             ext = determine_ext(video_url)
2868             if ext == 'smil':
2869                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2870             elif ext == 'xspf':
2871                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2872             elif ext == 'm3u8':
2873                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2874             elif ext == 'mpd':
2875                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2876             elif ext == 'f4m':
2877                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2878             elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2879                 # Just matching .ism/manifest is not enough to be reliably sure
2880                 # whether it's actually an ISM manifest or some other streaming
2881                 # manifest since there are various streaming URL formats
2882                 # possible (see [1]) as well as some other shenanigans like
2883                 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2884                 # so on.
2885                 # Thus the most reasonable way to solve this is to delegate
2886                 # to generic extractor in order to look into the contents of
2887                 # the manifest itself.
2888                 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2889                 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2890                 entry_info_dict = self.url_result(
2891                     smuggle_url(video_url, {'to_generic': True}),
2892                     GenericIE.ie_key())
2893             else:
2894                 entry_info_dict['url'] = video_url
2895
2896             if entry_info_dict.get('formats'):
2897                 self._sort_formats(entry_info_dict['formats'])
2898
2899             entries.append(entry_info_dict)
2900
2901         if len(entries) == 1:
2902             return entries[0]
2903         else:
2904             for num, e in enumerate(entries, start=1):
2905                 # 'url' results don't have a title
2906                 if e.get('title') is not None:
2907                     e['title'] = '%s (%d)' % (e['title'], num)
2908             return {
2909                 '_type': 'playlist',
2910                 'entries': entries,
2911             }