generic.py 140 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. is_html,
  21. js_to_json,
  22. KNOWN_EXTENSIONS,
  23. merge_dicts,
  24. mimetype2ext,
  25. orderedSet,
  26. sanitized_Request,
  27. smuggle_url,
  28. unescapeHTML,
  29. unified_strdate,
  30. unified_timestamp,
  31. unsmuggle_url,
  32. UnsupportedError,
  33. xpath_text,
  34. )
  35. from .commonprotocols import RtmpIE
  36. from .brightcove import (
  37. BrightcoveLegacyIE,
  38. BrightcoveNewIE,
  39. )
  40. from .nexx import (
  41. NexxIE,
  42. NexxEmbedIE,
  43. )
  44. from .nbc import NBCSportsVPlayerIE
  45. from .ooyala import OoyalaIE
  46. from .rutv import RUTVIE
  47. from .tvc import TVCIE
  48. from .sportbox import SportBoxIE
  49. from .smotri import SmotriIE
  50. from .myvi import MyviIE
  51. from .condenast import CondeNastIE
  52. from .udn import UDNEmbedIE
  53. from .senateisvp import SenateISVPIE
  54. from .svt import SVTIE
  55. from .pornhub import PornHubIE
  56. from .xhamster import XHamsterEmbedIE
  57. from .tnaflix import TNAFlixNetworkEmbedIE
  58. from .drtuber import DrTuberIE
  59. from .redtube import RedTubeIE
  60. from .tube8 import Tube8IE
  61. from .mofosex import MofosexEmbedIE
  62. from .spankwire import SpankwireIE
  63. from .youporn import YouPornIE
  64. from .vimeo import VimeoIE
  65. from .dailymotion import DailymotionIE
  66. from .dailymail import DailyMailIE
  67. from .onionstudios import OnionStudiosIE
  68. from .viewlift import ViewLiftEmbedIE
  69. from .mtv import MTVServicesEmbeddedIE
  70. from .pladform import PladformIE
  71. from .videomore import VideomoreIE
  72. from .webcaster import WebcasterFeedIE
  73. from .googledrive import GoogleDriveIE
  74. from .jwplatform import JWPlatformIE
  75. from .digiteka import DigitekaIE
  76. from .arkena import ArkenaIE
  77. from .instagram import InstagramIE
  78. from .liveleak import LiveLeakIE
  79. from .threeqsdn import ThreeQSDNIE
  80. from .theplatform import ThePlatformIE
  81. from .kaltura import KalturaIE
  82. from .eagleplatform import EaglePlatformIE
  83. from .facebook import FacebookIE
  84. from .soundcloud import SoundcloudEmbedIE
  85. from .tunein import TuneInBaseIE
  86. from .vbox7 import Vbox7IE
  87. from .dbtv import DBTVIE
  88. from .piksel import PikselIE
  89. from .videa import VideaIE
  90. from .twentymin import TwentyMinutenIE
  91. from .ustream import UstreamIE
  92. from .arte import ArteTVEmbedIE
  93. from .videopress import VideoPressIE
  94. from .rutube import RutubeIE
  95. from .limelight import LimelightBaseIE
  96. from .anvato import AnvatoIE
  97. from .washingtonpost import WashingtonPostIE
  98. from .wistia import WistiaIE
  99. from .mediaset import MediasetIE
  100. from .joj import JojIE
  101. from .megaphone import MegaphoneIE
  102. from .vzaar import VzaarIE
  103. from .channel9 import Channel9IE
  104. from .vshare import VShareIE
  105. from .mediasite import MediasiteIE
  106. from .springboardplatform import SpringboardPlatformIE
  107. from .yapfiles import YapFilesIE
  108. from .vice import ViceIE
  109. from .xfileshare import XFileShareIE
  110. from .cloudflarestream import CloudflareStreamIE
  111. from .peertube import PeerTubeIE
  112. from .teachable import TeachableIE
  113. from .indavideo import IndavideoEmbedIE
  114. from .apa import APAIE
  115. from .foxnews import FoxNewsIE
  116. from .viqeo import ViqeoIE
  117. from .expressen import ExpressenIE
  118. from .zype import ZypeIE
  119. from .odnoklassniki import OdnoklassnikiIE
  120. from .kinja import KinjaEmbedIE
  121. class GenericIE(InfoExtractor):
  122. IE_DESC = 'Generic downloader that works on some sites'
  123. _VALID_URL = r'.*'
  124. IE_NAME = 'generic'
  125. _TESTS = [
  126. # Direct link to a video
  127. {
  128. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  129. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  130. 'info_dict': {
  131. 'id': 'trailer',
  132. 'ext': 'mp4',
  133. 'title': 'trailer',
  134. 'upload_date': '20100513',
  135. }
  136. },
  137. # Direct link to media delivered compressed (until Accept-Encoding is *)
  138. {
  139. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  140. 'md5': '128c42e68b13950268b648275386fc74',
  141. 'info_dict': {
  142. 'id': 'FictionJunction-Parallel_Hearts',
  143. 'ext': 'flac',
  144. 'title': 'FictionJunction-Parallel_Hearts',
  145. 'upload_date': '20140522',
  146. },
  147. 'expected_warnings': [
  148. 'URL could be a direct video link, returning it as such.'
  149. ],
  150. 'skip': 'URL invalid',
  151. },
  152. # Direct download with broken HEAD
  153. {
  154. 'url': 'http://ai-radio.org:8000/radio.opus',
  155. 'info_dict': {
  156. 'id': 'radio',
  157. 'ext': 'opus',
  158. 'title': 'radio',
  159. },
  160. 'params': {
  161. 'skip_download': True, # infinite live stream
  162. },
  163. 'expected_warnings': [
  164. r'501.*Not Implemented',
  165. r'400.*Bad Request',
  166. ],
  167. },
  168. # Direct link with incorrect MIME type
  169. {
  170. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  171. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  172. 'info_dict': {
  173. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  174. 'id': '5_Lennart_Poettering_-_Systemd',
  175. 'ext': 'webm',
  176. 'title': '5_Lennart_Poettering_-_Systemd',
  177. 'upload_date': '20141120',
  178. },
  179. 'expected_warnings': [
  180. 'URL could be a direct video link, returning it as such.'
  181. ]
  182. },
  183. # RSS feed
  184. {
  185. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  186. 'info_dict': {
  187. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  188. 'title': 'Zero Punctuation',
  189. 'description': 're:.*groundbreaking video review series.*'
  190. },
  191. 'playlist_mincount': 11,
  192. },
  193. # RSS feed with enclosure
  194. {
  195. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  196. 'info_dict': {
  197. 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  198. 'title': 'MSNBC Rachel Maddow (video)',
  199. 'description': 're:.*her unique approach to storytelling.*',
  200. },
  201. 'playlist': [{
  202. 'info_dict': {
  203. 'ext': 'mov',
  204. 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
  205. 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
  206. 'description': 're:.*her unique approach to storytelling.*',
  207. 'upload_date': '20201204',
  208. },
  209. }],
  210. },
  211. # RSS feed with enclosures and unsupported link URLs
  212. {
  213. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  214. 'info_dict': {
  215. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  216. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  217. 'title': 'Hello Internet',
  218. },
  219. 'playlist_mincount': 100,
  220. },
  221. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  222. {
  223. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  224. 'info_dict': {
  225. 'id': 'smil',
  226. 'ext': 'mp4',
  227. 'title': 'Automatics, robotics and biocybernetics',
  228. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  229. 'upload_date': '20130627',
  230. 'formats': 'mincount:16',
  231. 'subtitles': 'mincount:1',
  232. },
  233. 'params': {
  234. 'force_generic_extractor': True,
  235. 'skip_download': True,
  236. },
  237. },
  238. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  239. {
  240. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  241. 'info_dict': {
  242. 'id': 'hds',
  243. 'ext': 'flv',
  244. 'title': 'hds',
  245. 'formats': 'mincount:1',
  246. },
  247. 'params': {
  248. 'skip_download': True,
  249. },
  250. },
  251. # SMIL from https://www.restudy.dk/video/play/id/1637
  252. {
  253. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  254. 'info_dict': {
  255. 'id': 'video_1637',
  256. 'ext': 'flv',
  257. 'title': 'video_1637',
  258. 'formats': 'mincount:3',
  259. },
  260. 'params': {
  261. 'skip_download': True,
  262. },
  263. },
  264. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  265. {
  266. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  267. 'info_dict': {
  268. 'id': 'smil-service',
  269. 'ext': 'flv',
  270. 'title': 'smil-service',
  271. 'formats': 'mincount:1',
  272. },
  273. 'params': {
  274. 'skip_download': True,
  275. },
  276. },
  277. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  278. {
  279. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  280. 'info_dict': {
  281. 'id': '4719370',
  282. 'ext': 'mp4',
  283. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  284. 'formats': 'mincount:3',
  285. },
  286. 'params': {
  287. 'skip_download': True,
  288. },
  289. },
  290. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  291. {
  292. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  293. 'info_dict': {
  294. 'id': 'mZlp2ctYIUEB',
  295. 'ext': 'mp4',
  296. 'title': 'Tikibad ontruimd wegens brand',
  297. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  298. 'thumbnail': r're:^https?://.*\.jpg$',
  299. 'duration': 33,
  300. },
  301. 'params': {
  302. 'skip_download': True,
  303. },
  304. },
  305. # MPD from http://dash-mse-test.appspot.com/media.html
  306. {
  307. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  308. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  309. 'info_dict': {
  310. 'id': 'car-20120827-manifest',
  311. 'ext': 'mp4',
  312. 'title': 'car-20120827-manifest',
  313. 'formats': 'mincount:9',
  314. 'upload_date': '20130904',
  315. },
  316. 'params': {
  317. 'format': 'bestvideo',
  318. },
  319. },
  320. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  321. {
  322. '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',
  323. 'info_dict': {
  324. 'id': 'content',
  325. 'ext': 'mp4',
  326. 'title': 'content',
  327. 'formats': 'mincount:8',
  328. },
  329. 'params': {
  330. # m3u8 downloads
  331. 'skip_download': True,
  332. },
  333. 'skip': 'video gone',
  334. },
  335. # m3u8 served with Content-Type: text/plain
  336. {
  337. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  338. 'info_dict': {
  339. 'id': 'index',
  340. 'ext': 'mp4',
  341. 'title': 'index',
  342. 'upload_date': '20140720',
  343. 'formats': 'mincount:11',
  344. },
  345. 'params': {
  346. # m3u8 downloads
  347. 'skip_download': True,
  348. },
  349. 'skip': 'video gone',
  350. },
  351. # google redirect
  352. {
  353. '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',
  354. 'info_dict': {
  355. 'id': 'cmQHVoWB5FY',
  356. 'ext': 'mp4',
  357. 'upload_date': '20130224',
  358. 'uploader_id': 'TheVerge',
  359. 'description': r're:^Chris Ziegler takes a look at the\.*',
  360. 'uploader': 'The Verge',
  361. 'title': 'First Firefox OS phones side-by-side',
  362. },
  363. 'params': {
  364. 'skip_download': False,
  365. }
  366. },
  367. {
  368. # redirect in Refresh HTTP header
  369. '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',
  370. 'info_dict': {
  371. 'id': 'pO8h3EaFRdo',
  372. 'ext': 'mp4',
  373. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  374. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  375. 'upload_date': '20150917',
  376. 'uploader_id': 'brtvofficial',
  377. 'uploader': 'Boiler Room',
  378. },
  379. 'params': {
  380. 'skip_download': False,
  381. },
  382. },
  383. {
  384. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  385. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  386. 'info_dict': {
  387. 'id': '13601338388002',
  388. 'ext': 'mp4',
  389. 'uploader': 'www.hodiho.fr',
  390. 'title': 'R\u00e9gis plante sa Jeep',
  391. }
  392. },
  393. # bandcamp page with custom domain
  394. {
  395. 'add_ie': ['Bandcamp'],
  396. 'url': 'http://bronyrock.com/track/the-pony-mash',
  397. 'info_dict': {
  398. 'id': '3235767654',
  399. 'ext': 'mp3',
  400. 'title': 'The Pony Mash',
  401. 'uploader': 'M_Pallante',
  402. },
  403. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  404. },
  405. {
  406. # embedded brightcove video
  407. # it also tests brightcove videos that need to set the 'Referer'
  408. # in the http requests
  409. 'add_ie': ['BrightcoveLegacy'],
  410. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  411. 'info_dict': {
  412. 'id': '2765128793001',
  413. 'ext': 'mp4',
  414. 'title': 'Le cours de bourse : l’analyse technique',
  415. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  416. 'uploader': 'BFM BUSINESS',
  417. },
  418. 'params': {
  419. 'skip_download': True,
  420. },
  421. },
  422. {
  423. # embedded with itemprop embedURL and video id spelled as `idVideo`
  424. 'add_id': ['BrightcoveLegacy'],
  425. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  426. 'info_dict': {
  427. 'id': '5255628253001',
  428. 'ext': 'mp4',
  429. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  430. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  431. 'uploader': 'BFM BUSINESS',
  432. 'uploader_id': '876450612001',
  433. 'timestamp': 1482255315,
  434. 'upload_date': '20161220',
  435. },
  436. 'params': {
  437. 'skip_download': True,
  438. },
  439. },
  440. {
  441. # https://github.com/ytdl-org/youtube-dl/issues/2253
  442. 'url': 'http://bcove.me/i6nfkrc3',
  443. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  444. 'info_dict': {
  445. 'id': '3101154703001',
  446. 'ext': 'mp4',
  447. 'title': 'Still no power',
  448. 'uploader': 'thestar.com',
  449. '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.',
  450. },
  451. 'add_ie': ['BrightcoveLegacy'],
  452. 'skip': 'video gone',
  453. },
  454. {
  455. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  456. 'md5': 'fb973ecf6e4a78a67453647444222983',
  457. 'info_dict': {
  458. 'id': '3414141473001',
  459. 'ext': 'mp4',
  460. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  461. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  462. 'uploader': 'Championat',
  463. },
  464. },
  465. {
  466. # https://github.com/ytdl-org/youtube-dl/issues/3541
  467. 'add_ie': ['BrightcoveLegacy'],
  468. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  469. 'info_dict': {
  470. 'id': '3866516442001',
  471. 'ext': 'mp4',
  472. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  473. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  474. 'uploader': 'SBS Broadcasting',
  475. },
  476. 'skip': 'Restricted to Netherlands',
  477. 'params': {
  478. 'skip_download': True, # m3u8 download
  479. },
  480. },
  481. {
  482. # Brightcove video in <iframe>
  483. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  484. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  485. 'info_dict': {
  486. 'id': '5360463607001',
  487. 'ext': 'mp4',
  488. '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',
  489. '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。',
  490. 'uploader': 'United Nations',
  491. 'uploader_id': '1362235914001',
  492. 'timestamp': 1489593889,
  493. 'upload_date': '20170315',
  494. },
  495. 'add_ie': ['BrightcoveLegacy'],
  496. },
  497. {
  498. # Brightcove with alternative playerID key
  499. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  500. 'info_dict': {
  501. 'id': 'nmeth.2062_SV1',
  502. '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',
  503. },
  504. 'playlist': [{
  505. 'info_dict': {
  506. 'id': '2228375078001',
  507. 'ext': 'mp4',
  508. 'title': 'nmeth.2062-sv1',
  509. 'description': 'nmeth.2062-sv1',
  510. 'timestamp': 1363357591,
  511. 'upload_date': '20130315',
  512. 'uploader': 'Nature Publishing Group',
  513. 'uploader_id': '1964492299001',
  514. },
  515. }],
  516. },
  517. {
  518. # Brightcove with UUID in videoPlayer
  519. 'url': 'http://www8.hp.com/cn/zh/home.html',
  520. 'info_dict': {
  521. 'id': '5255815316001',
  522. 'ext': 'mp4',
  523. 'title': 'Sprocket Video - China',
  524. 'description': 'Sprocket Video - China',
  525. 'uploader': 'HP-Video Gallery',
  526. 'timestamp': 1482263210,
  527. 'upload_date': '20161220',
  528. 'uploader_id': '1107601872001',
  529. },
  530. 'params': {
  531. 'skip_download': True, # m3u8 download
  532. },
  533. 'skip': 'video rotates...weekly?',
  534. },
  535. {
  536. # Brightcove:new type [2].
  537. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  538. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  539. 'info_dict': {
  540. 'id': '5348741021001',
  541. 'ext': 'mp4',
  542. 'upload_date': '20170306',
  543. 'uploader_id': '4191638492001',
  544. 'timestamp': 1488769918,
  545. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  546. },
  547. },
  548. {
  549. # Alternative brightcove <video> attributes
  550. '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/',
  551. 'info_dict': {
  552. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  553. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  554. },
  555. 'playlist': [{
  556. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  557. 'info_dict': {
  558. 'id': '5311302538001',
  559. 'ext': 'mp4',
  560. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  561. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  562. 'timestamp': 1486321708,
  563. 'upload_date': '20170205',
  564. 'uploader_id': '800000640001',
  565. },
  566. 'only_matching': True,
  567. }],
  568. },
  569. {
  570. # Brightcove with UUID in videoPlayer
  571. 'url': 'http://www8.hp.com/cn/zh/home.html',
  572. 'info_dict': {
  573. 'id': '5255815316001',
  574. 'ext': 'mp4',
  575. 'title': 'Sprocket Video - China',
  576. 'description': 'Sprocket Video - China',
  577. 'uploader': 'HP-Video Gallery',
  578. 'timestamp': 1482263210,
  579. 'upload_date': '20161220',
  580. 'uploader_id': '1107601872001',
  581. },
  582. 'params': {
  583. 'skip_download': True, # m3u8 download
  584. },
  585. },
  586. # ooyala video
  587. {
  588. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  589. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  590. 'info_dict': {
  591. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  592. 'ext': 'mp4',
  593. 'title': '2cc213299525360.mov', # that's what we get
  594. 'duration': 238.231,
  595. },
  596. 'add_ie': ['Ooyala'],
  597. },
  598. {
  599. # ooyala video embedded with http://player.ooyala.com/iframe.js
  600. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  601. 'info_dict': {
  602. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  603. 'ext': 'mp4',
  604. 'title': '"Steve Jobs: Man in the Machine" trailer',
  605. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  606. 'duration': 135.427,
  607. },
  608. 'params': {
  609. 'skip_download': True,
  610. },
  611. 'skip': 'movie expired',
  612. },
  613. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  614. {
  615. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  616. 'info_dict': {
  617. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  618. 'ext': 'mp4',
  619. 'title': 'Steampunk Fest Comes to Honesdale',
  620. 'duration': 43.276,
  621. },
  622. 'params': {
  623. 'skip_download': True,
  624. }
  625. },
  626. # embed.ly video
  627. {
  628. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  629. 'info_dict': {
  630. 'id': '9ODmcdjQcHQ',
  631. 'ext': 'mp4',
  632. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  633. 'upload_date': '20140225',
  634. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  635. 'uploader': 'Tested',
  636. 'uploader_id': 'testedcom',
  637. },
  638. # No need to test YoutubeIE here
  639. 'params': {
  640. 'skip_download': True,
  641. },
  642. },
  643. # funnyordie embed
  644. {
  645. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  646. 'info_dict': {
  647. 'id': '18e820ec3f',
  648. 'ext': 'mp4',
  649. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  650. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  651. },
  652. # HEAD requests lead to endless 301, while GET is OK
  653. 'expected_warnings': ['301'],
  654. },
  655. # RUTV embed
  656. {
  657. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  658. 'info_dict': {
  659. 'id': '776940',
  660. 'ext': 'mp4',
  661. 'title': 'Охотское море стало целиком российским',
  662. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  663. },
  664. 'params': {
  665. # m3u8 download
  666. 'skip_download': True,
  667. },
  668. },
  669. # TVC embed
  670. {
  671. '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/',
  672. 'info_dict': {
  673. 'id': '55304',
  674. 'ext': 'mp4',
  675. 'title': 'Дошкольное воспитание',
  676. },
  677. },
  678. # SportBox embed
  679. {
  680. 'url': 'http://www.vestifinance.ru/articles/25753',
  681. 'info_dict': {
  682. 'id': '25753',
  683. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  684. },
  685. 'playlist': [{
  686. 'info_dict': {
  687. 'id': '370908',
  688. 'title': 'Госзаказ. День 3',
  689. 'ext': 'mp4',
  690. }
  691. }, {
  692. 'info_dict': {
  693. 'id': '370905',
  694. 'title': 'Госзаказ. День 2',
  695. 'ext': 'mp4',
  696. }
  697. }, {
  698. 'info_dict': {
  699. 'id': '370902',
  700. 'title': 'Госзаказ. День 1',
  701. 'ext': 'mp4',
  702. }
  703. }],
  704. 'params': {
  705. # m3u8 download
  706. 'skip_download': True,
  707. },
  708. },
  709. # Myvi.ru embed
  710. {
  711. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  712. 'info_dict': {
  713. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  714. 'ext': 'mp4',
  715. 'title': 'Ужастики, русский трейлер (2015)',
  716. 'thumbnail': r're:^https?://.*\.jpg$',
  717. 'duration': 153,
  718. }
  719. },
  720. # XHamster embed
  721. {
  722. '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',
  723. 'info_dict': {
  724. 'id': 'showthread',
  725. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  726. },
  727. 'playlist_mincount': 7,
  728. # This forum does not allow <iframe> syntaxes anymore
  729. # Now HTML tags are displayed as-is
  730. 'skip': 'No videos on this page',
  731. },
  732. # Embedded TED video
  733. {
  734. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  735. 'md5': '65fdff94098e4a607385a60c5177c638',
  736. 'info_dict': {
  737. 'id': '1969',
  738. 'ext': 'mp4',
  739. 'title': 'Hidden miracles of the natural world',
  740. 'uploader': 'Louie Schwartzberg',
  741. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  742. }
  743. },
  744. # nowvideo embed hidden behind percent encoding
  745. {
  746. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  747. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  748. 'info_dict': {
  749. 'id': '06e53103ca9aa',
  750. 'ext': 'flv',
  751. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  752. 'description': 'No description',
  753. },
  754. },
  755. # arte embed
  756. {
  757. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  758. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  759. 'info_dict': {
  760. 'id': '048195-004_PLUS7-F',
  761. 'ext': 'flv',
  762. 'title': 'X:enius',
  763. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  764. 'upload_date': '20140320',
  765. },
  766. 'params': {
  767. 'skip_download': 'Requires rtmpdump'
  768. },
  769. 'skip': 'video gone',
  770. },
  771. # francetv embed
  772. {
  773. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  774. 'info_dict': {
  775. 'id': 'EV_30231',
  776. 'ext': 'mp4',
  777. 'title': 'Alcaline, le concert avec Calogero',
  778. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  779. 'upload_date': '20150226',
  780. 'timestamp': 1424989860,
  781. 'duration': 5400,
  782. },
  783. 'params': {
  784. # m3u8 downloads
  785. 'skip_download': True,
  786. },
  787. 'expected_warnings': [
  788. 'Forbidden'
  789. ]
  790. },
  791. # Condé Nast embed
  792. {
  793. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  794. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  795. 'info_dict': {
  796. 'id': '53501be369702d3275860000',
  797. 'ext': 'mp4',
  798. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  799. }
  800. },
  801. # Dailymotion embed
  802. {
  803. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  804. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  805. 'info_dict': {
  806. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  807. 'ext': 'mp4',
  808. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  809. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  810. 'uploader': 'Spi0n',
  811. 'uploader_id': 'xgditw',
  812. 'upload_date': '20140425',
  813. 'timestamp': 1398441542,
  814. },
  815. 'add_ie': ['Dailymotion'],
  816. },
  817. # DailyMail embed
  818. {
  819. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  820. 'info_dict': {
  821. 'id': '1495629',
  822. 'ext': 'mp4',
  823. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  824. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  825. },
  826. 'add_ie': ['DailyMail'],
  827. 'params': {
  828. 'skip_download': True,
  829. },
  830. },
  831. # YouTube embed
  832. {
  833. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  834. 'info_dict': {
  835. 'id': 'FXRb4ykk4S0',
  836. 'ext': 'mp4',
  837. 'title': 'The NBL Auction 2014',
  838. 'uploader': 'BADMINTON England',
  839. 'uploader_id': 'BADMINTONEvents',
  840. 'upload_date': '20140603',
  841. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  842. },
  843. 'add_ie': ['Youtube'],
  844. 'params': {
  845. 'skip_download': True,
  846. }
  847. },
  848. # MTVServices embed
  849. {
  850. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  851. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  852. 'info_dict': {
  853. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  854. 'ext': 'mp4',
  855. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  856. 'description': 'Two valets share their love for movie star Liam Neesons.',
  857. 'timestamp': 1349922600,
  858. 'upload_date': '20121011',
  859. },
  860. },
  861. # YouTube embed via <data-embed-url="">
  862. {
  863. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  864. 'info_dict': {
  865. 'id': '4vAffPZIT44',
  866. 'ext': 'mp4',
  867. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  868. 'uploader': 'Gameloft',
  869. 'uploader_id': 'gameloft',
  870. 'upload_date': '20140828',
  871. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  872. },
  873. 'params': {
  874. 'skip_download': True,
  875. }
  876. },
  877. # YouTube <object> embed
  878. {
  879. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  880. 'md5': '516718101ec834f74318df76259fb3cc',
  881. 'info_dict': {
  882. 'id': 'msN87y-iEx0',
  883. 'ext': 'webm',
  884. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  885. 'upload_date': '20080526',
  886. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  887. 'uploader': 'Christopher Sykes',
  888. 'uploader_id': 'ChristopherJSykes',
  889. },
  890. 'add_ie': ['Youtube'],
  891. },
  892. # Camtasia studio
  893. {
  894. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  895. 'playlist': [{
  896. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  897. 'info_dict': {
  898. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  899. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  900. 'ext': 'flv',
  901. 'duration': 2235.90,
  902. }
  903. }, {
  904. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  905. 'info_dict': {
  906. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  907. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  908. 'ext': 'flv',
  909. 'duration': 2235.93,
  910. }
  911. }],
  912. 'info_dict': {
  913. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  914. }
  915. },
  916. # Flowplayer
  917. {
  918. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  919. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  920. 'info_dict': {
  921. 'id': '5123ea6d5e5a7',
  922. 'ext': 'mp4',
  923. 'age_limit': 18,
  924. 'uploader': 'www.handjobhub.com',
  925. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  926. }
  927. },
  928. # Multiple brightcove videos
  929. # https://github.com/ytdl-org/youtube-dl/issues/2283
  930. {
  931. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  932. 'info_dict': {
  933. 'id': 'always-never',
  934. 'title': 'Always / Never - The New Yorker',
  935. },
  936. 'playlist_count': 3,
  937. 'params': {
  938. 'extract_flat': False,
  939. 'skip_download': True,
  940. }
  941. },
  942. # MLB embed
  943. {
  944. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  945. 'md5': '96f09a37e44da40dd083e12d9a683327',
  946. 'info_dict': {
  947. 'id': '33322633',
  948. 'ext': 'mp4',
  949. 'title': 'Ump changes call to ball',
  950. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  951. 'duration': 48,
  952. 'timestamp': 1401537900,
  953. 'upload_date': '20140531',
  954. 'thumbnail': r're:^https?://.*\.jpg$',
  955. },
  956. },
  957. # Wistia embed
  958. {
  959. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  960. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  961. 'info_dict': {
  962. 'id': '6e2wtrbdaf',
  963. 'ext': 'mov',
  964. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  965. 'description': 'a Paywall Videos video from Remilon',
  966. 'duration': 644.072,
  967. 'uploader': 'study.com',
  968. 'timestamp': 1459678540,
  969. 'upload_date': '20160403',
  970. 'filesize': 24687186,
  971. },
  972. },
  973. {
  974. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  975. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  976. 'info_dict': {
  977. 'id': 'uxjb0lwrcz',
  978. 'ext': 'mp4',
  979. 'title': 'Conversation about Hexagonal Rails Part 1',
  980. 'description': 'a Martin Fowler video from ThoughtWorks',
  981. 'duration': 1715.0,
  982. 'uploader': 'thoughtworks.wistia.com',
  983. 'timestamp': 1401832161,
  984. 'upload_date': '20140603',
  985. },
  986. },
  987. # Wistia standard embed (async)
  988. {
  989. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  990. 'info_dict': {
  991. 'id': '807fafadvk',
  992. 'ext': 'mp4',
  993. 'title': 'Drip Brennan Dunn Workshop',
  994. 'description': 'a JV Webinars video from getdrip-1',
  995. 'duration': 4986.95,
  996. 'timestamp': 1463607249,
  997. 'upload_date': '20160518',
  998. },
  999. 'params': {
  1000. 'skip_download': True,
  1001. }
  1002. },
  1003. # Soundcloud embed
  1004. {
  1005. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  1006. 'info_dict': {
  1007. 'id': '174391317',
  1008. 'ext': 'mp3',
  1009. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  1010. 'uploader': 'Sophos Security',
  1011. 'title': 'Chet Chat 171 - Oct 29, 2014',
  1012. 'upload_date': '20141029',
  1013. }
  1014. },
  1015. # Soundcloud multiple embeds
  1016. {
  1017. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1018. 'info_dict': {
  1019. 'id': '52809',
  1020. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1021. },
  1022. 'playlist_mincount': 7,
  1023. },
  1024. # TuneIn station embed
  1025. {
  1026. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1027. 'info_dict': {
  1028. 'id': '204146',
  1029. 'ext': 'mp3',
  1030. 'title': 'CNRV',
  1031. 'location': 'Paris, France',
  1032. 'is_live': True,
  1033. },
  1034. 'params': {
  1035. # Live stream
  1036. 'skip_download': True,
  1037. },
  1038. },
  1039. # Livestream embed
  1040. {
  1041. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1042. 'info_dict': {
  1043. 'id': '67864563',
  1044. 'ext': 'flv',
  1045. 'upload_date': '20141112',
  1046. 'title': 'Rosetta #CometLanding webcast HL 10',
  1047. }
  1048. },
  1049. # Another Livestream embed, without 'new.' in URL
  1050. {
  1051. 'url': 'https://www.freespeech.org/',
  1052. 'info_dict': {
  1053. 'id': '123537347',
  1054. 'ext': 'mp4',
  1055. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1056. },
  1057. 'params': {
  1058. # Live stream
  1059. 'skip_download': True,
  1060. },
  1061. },
  1062. # LazyYT
  1063. {
  1064. 'url': 'https://skiplagged.com/',
  1065. 'info_dict': {
  1066. 'id': 'skiplagged',
  1067. 'title': 'Skiplagged: The smart way to find cheap flights',
  1068. },
  1069. 'playlist_mincount': 1,
  1070. 'add_ie': ['Youtube'],
  1071. },
  1072. # Cinchcast embed
  1073. {
  1074. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1075. 'info_dict': {
  1076. 'id': '7141703',
  1077. 'ext': 'mp3',
  1078. 'upload_date': '20141126',
  1079. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1080. }
  1081. },
  1082. # Cinerama player
  1083. {
  1084. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1085. 'info_dict': {
  1086. 'id': '730m_DandD_1901_512k',
  1087. 'ext': 'mp4',
  1088. 'uploader': 'www.abc.net.au',
  1089. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1090. }
  1091. },
  1092. # embedded viddler video
  1093. {
  1094. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1095. 'info_dict': {
  1096. 'id': '4d03aad9',
  1097. 'ext': 'mp4',
  1098. 'uploader': 'deadspin',
  1099. 'title': 'WALL-TO-GORTAT',
  1100. 'timestamp': 1422285291,
  1101. 'upload_date': '20150126',
  1102. },
  1103. 'add_ie': ['Viddler'],
  1104. },
  1105. # Libsyn embed
  1106. {
  1107. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1108. 'info_dict': {
  1109. 'id': '3377616',
  1110. 'ext': 'mp3',
  1111. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1112. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1113. 'upload_date': '20150220',
  1114. },
  1115. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1116. },
  1117. # jwplayer YouTube
  1118. {
  1119. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1120. 'info_dict': {
  1121. 'id': 'Mrj4DVp2zeA',
  1122. 'ext': 'mp4',
  1123. 'upload_date': '20150212',
  1124. 'uploader': 'The National Archives UK',
  1125. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1126. 'uploader_id': 'NationalArchives08',
  1127. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1128. },
  1129. },
  1130. # jwplayer rtmp
  1131. {
  1132. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1133. 'info_dict': {
  1134. 'id': 'live',
  1135. 'ext': 'flv',
  1136. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1137. 'uploader': 'www.suffolk.edu',
  1138. },
  1139. 'params': {
  1140. 'skip_download': True,
  1141. },
  1142. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1143. },
  1144. # Complex jwplayer
  1145. {
  1146. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1147. 'info_dict': {
  1148. 'id': 'videos',
  1149. 'ext': 'mp4',
  1150. 'title': 'king machine trailer 1',
  1151. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1152. 'thumbnail': r're:^https?://.*\.jpg$',
  1153. },
  1154. },
  1155. {
  1156. # JWPlayer config passed as variable
  1157. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1158. 'info_dict': {
  1159. 'id': '3326530_hq',
  1160. 'ext': 'mp4',
  1161. 'title': 'ARIELE | Tube Cup',
  1162. 'uploader': 'www.txxx.com',
  1163. 'age_limit': 18,
  1164. },
  1165. 'params': {
  1166. 'skip_download': True,
  1167. }
  1168. },
  1169. {
  1170. # JWPlatform iframe
  1171. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1172. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1173. 'info_dict': {
  1174. 'id': 'O0c5JcKT',
  1175. 'ext': 'mp4',
  1176. 'upload_date': '20171122',
  1177. 'timestamp': 1511366290,
  1178. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1179. },
  1180. 'add_ie': [JWPlatformIE.ie_key()],
  1181. },
  1182. {
  1183. # Video.js embed, multiple formats
  1184. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1185. 'info_dict': {
  1186. 'id': 'yygqldloqIk',
  1187. 'ext': 'mp4',
  1188. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1189. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1190. 'upload_date': '20130314',
  1191. 'uploader': 'PROстое3D',
  1192. 'uploader_id': 'PROstoe3D',
  1193. },
  1194. 'params': {
  1195. 'skip_download': True,
  1196. },
  1197. },
  1198. {
  1199. # Video.js embed, single format
  1200. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1201. 'info_dict': {
  1202. 'id': 'watch',
  1203. 'ext': 'mp4',
  1204. 'title': 'Step 1 - Good Foundation',
  1205. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1206. },
  1207. 'params': {
  1208. 'skip_download': True,
  1209. },
  1210. },
  1211. # rtl.nl embed
  1212. {
  1213. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1214. 'playlist_mincount': 5,
  1215. 'info_dict': {
  1216. 'id': 'aanslagen-kopenhagen',
  1217. 'title': 'Aanslagen Kopenhagen',
  1218. }
  1219. },
  1220. # Zapiks embed
  1221. {
  1222. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1223. 'info_dict': {
  1224. 'id': '118046',
  1225. 'ext': 'mp4',
  1226. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1227. }
  1228. },
  1229. # Kaltura embed (different embed code)
  1230. {
  1231. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1232. 'info_dict': {
  1233. 'id': '1_a52wc67y',
  1234. 'ext': 'flv',
  1235. 'upload_date': '20150127',
  1236. 'uploader_id': 'PremierMedia',
  1237. 'timestamp': int,
  1238. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1239. },
  1240. },
  1241. # Kaltura embed with single quotes
  1242. {
  1243. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1244. 'info_dict': {
  1245. 'id': '0_izeg5utt',
  1246. 'ext': 'mp4',
  1247. 'title': '35871',
  1248. 'timestamp': 1355743100,
  1249. 'upload_date': '20121217',
  1250. 'uploader_id': 'cplapp@learn360.com',
  1251. },
  1252. 'add_ie': ['Kaltura'],
  1253. },
  1254. {
  1255. # Kaltura embedded via quoted entry_id
  1256. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1257. 'info_dict': {
  1258. 'id': '0_utuok90b',
  1259. 'ext': 'mp4',
  1260. 'title': '06_matthew_brender_raj_dutt',
  1261. 'timestamp': 1466638791,
  1262. 'upload_date': '20160622',
  1263. },
  1264. 'add_ie': ['Kaltura'],
  1265. 'expected_warnings': [
  1266. 'Could not send HEAD request'
  1267. ],
  1268. 'params': {
  1269. 'skip_download': True,
  1270. }
  1271. },
  1272. {
  1273. # Kaltura embedded, some fileExt broken (#11480)
  1274. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1275. 'info_dict': {
  1276. 'id': '1_sgtvehim',
  1277. 'ext': 'mp4',
  1278. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1279. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1280. 'timestamp': 1321158993,
  1281. 'upload_date': '20111113',
  1282. 'uploader_id': 'kps1',
  1283. },
  1284. 'add_ie': ['Kaltura'],
  1285. },
  1286. {
  1287. # Kaltura iframe embed
  1288. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1289. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1290. 'info_dict': {
  1291. 'id': '0_f2cfbpwy',
  1292. 'ext': 'mp4',
  1293. 'title': 'I. M. Pei: A Centennial Celebration',
  1294. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1295. 'upload_date': '20170403',
  1296. 'uploader_id': 'batchUser',
  1297. 'timestamp': 1491232186,
  1298. },
  1299. 'add_ie': ['Kaltura'],
  1300. },
  1301. {
  1302. # Kaltura iframe embed, more sophisticated
  1303. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1304. 'info_dict': {
  1305. 'id': '1_9gzouybz',
  1306. 'ext': 'mp4',
  1307. 'title': 'lecture-05sep2017',
  1308. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1309. 'upload_date': '20170913',
  1310. 'uploader_id': 'eps2',
  1311. 'timestamp': 1505340777,
  1312. },
  1313. 'params': {
  1314. 'skip_download': True,
  1315. },
  1316. 'add_ie': ['Kaltura'],
  1317. },
  1318. {
  1319. # meta twitter:player
  1320. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1321. 'info_dict': {
  1322. 'id': '0_01b42zps',
  1323. 'ext': 'mp4',
  1324. 'title': 'Main Twerk (Video)',
  1325. 'upload_date': '20171208',
  1326. 'uploader_id': 'sebastian.salinas@thechive.com',
  1327. 'timestamp': 1512713057,
  1328. },
  1329. 'params': {
  1330. 'skip_download': True,
  1331. },
  1332. 'add_ie': ['Kaltura'],
  1333. },
  1334. # referrer protected EaglePlatform embed
  1335. {
  1336. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1337. 'info_dict': {
  1338. 'id': '582306',
  1339. 'ext': 'mp4',
  1340. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1341. 'thumbnail': r're:^https?://.*\.jpg$',
  1342. 'duration': 3382,
  1343. 'view_count': int,
  1344. },
  1345. 'params': {
  1346. 'skip_download': True,
  1347. },
  1348. },
  1349. # ClipYou (EaglePlatform) embed (custom URL)
  1350. {
  1351. 'url': 'http://muz-tv.ru/play/7129/',
  1352. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1353. 'info_dict': {
  1354. 'id': '12820',
  1355. 'ext': 'mp4',
  1356. 'title': "'O Sole Mio",
  1357. 'thumbnail': r're:^https?://.*\.jpg$',
  1358. 'duration': 216,
  1359. 'view_count': int,
  1360. },
  1361. 'params': {
  1362. 'skip_download': True,
  1363. },
  1364. 'skip': 'This video is unavailable.',
  1365. },
  1366. # Pladform embed
  1367. {
  1368. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1369. 'info_dict': {
  1370. 'id': '100183293',
  1371. 'ext': 'mp4',
  1372. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1373. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1374. 'thumbnail': r're:^https?://.*\.jpg$',
  1375. 'duration': 694,
  1376. 'age_limit': 0,
  1377. },
  1378. 'skip': 'HTTP Error 404: Not Found',
  1379. },
  1380. # Playwire embed
  1381. {
  1382. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1383. 'info_dict': {
  1384. 'id': '3519514',
  1385. 'ext': 'mp4',
  1386. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1387. 'thumbnail': r're:^https?://.*\.png$',
  1388. 'duration': 45.115,
  1389. },
  1390. },
  1391. # 5min embed
  1392. {
  1393. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1394. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1395. 'info_dict': {
  1396. 'id': '518726732',
  1397. 'ext': 'mp4',
  1398. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1399. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1400. 'timestamp': 1427237531,
  1401. 'uploader': 'Crunch Report',
  1402. 'upload_date': '20150324',
  1403. },
  1404. 'params': {
  1405. # m3u8 download
  1406. 'skip_download': True,
  1407. },
  1408. },
  1409. # Crooks and Liars embed
  1410. {
  1411. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1412. 'info_dict': {
  1413. 'id': '8RUoRhRi',
  1414. 'ext': 'mp4',
  1415. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1416. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1417. 'timestamp': 1428207000,
  1418. 'upload_date': '20150405',
  1419. 'uploader': 'Heather',
  1420. },
  1421. },
  1422. # Crooks and Liars external embed
  1423. {
  1424. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1425. 'info_dict': {
  1426. 'id': 'MTE3MjUtMzQ2MzA',
  1427. 'ext': 'mp4',
  1428. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1429. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1430. 'timestamp': 1265032391,
  1431. 'upload_date': '20100201',
  1432. 'uploader': 'Heather',
  1433. },
  1434. },
  1435. # NBC Sports vplayer embed
  1436. {
  1437. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1438. 'info_dict': {
  1439. 'id': 'ln7x1qSThw4k',
  1440. 'ext': 'flv',
  1441. 'title': "PFT Live: New leader in the 'new-look' defense",
  1442. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1443. 'uploader': 'NBCU-SPORTS',
  1444. 'upload_date': '20140107',
  1445. 'timestamp': 1389118457,
  1446. },
  1447. 'skip': 'Invalid Page URL',
  1448. },
  1449. # NBC News embed
  1450. {
  1451. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1452. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1453. 'info_dict': {
  1454. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1455. 'ext': 'mp4',
  1456. 'title': 'David Letterman: A Preview',
  1457. '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.',
  1458. 'upload_date': '20160609',
  1459. 'timestamp': 1465431544,
  1460. 'uploader': 'NBCU-NEWS',
  1461. },
  1462. },
  1463. # UDN embed
  1464. {
  1465. 'url': 'https://video.udn.com/news/300346',
  1466. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1467. 'info_dict': {
  1468. 'id': '300346',
  1469. 'ext': 'mp4',
  1470. 'title': '中一中男師變性 全校師生力挺',
  1471. 'thumbnail': r're:^https?://.*\.jpg$',
  1472. },
  1473. 'params': {
  1474. # m3u8 download
  1475. 'skip_download': True,
  1476. },
  1477. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1478. },
  1479. # Brightcove URL in single quotes
  1480. {
  1481. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1482. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1483. 'info_dict': {
  1484. 'id': '4255764656001',
  1485. 'ext': 'mp4',
  1486. 'title': 'SN Presents: Russell Martin, World Citizen',
  1487. '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.',
  1488. 'uploader': 'Rogers Sportsnet',
  1489. 'uploader_id': '1704050871',
  1490. 'upload_date': '20150525',
  1491. 'timestamp': 1432570283,
  1492. },
  1493. },
  1494. # Kinja embed
  1495. {
  1496. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1497. 'info_dict': {
  1498. 'id': '106351',
  1499. 'ext': 'mp4',
  1500. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1501. 'description': 'Migrated from OnionStudios',
  1502. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1503. 'uploader': 'clickhole',
  1504. 'upload_date': '20150527',
  1505. 'timestamp': 1432744860,
  1506. }
  1507. },
  1508. # SnagFilms embed
  1509. {
  1510. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1511. 'info_dict': {
  1512. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1513. 'ext': 'mp4',
  1514. 'title': '#whilewewatch',
  1515. }
  1516. },
  1517. # AdobeTVVideo embed
  1518. {
  1519. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1520. 'md5': '43662b577c018ad707a63766462b1e87',
  1521. 'info_dict': {
  1522. 'id': '2456',
  1523. 'ext': 'mp4',
  1524. 'title': 'New experience with Acrobat DC',
  1525. 'description': 'New experience with Acrobat DC',
  1526. 'duration': 248.667,
  1527. },
  1528. },
  1529. # BrightcoveInPageEmbed embed
  1530. {
  1531. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1532. 'info_dict': {
  1533. 'id': '4238694884001',
  1534. 'ext': 'flv',
  1535. 'title': 'Tabletop: Dread, Last Thoughts',
  1536. 'description': 'Tabletop: Dread, Last Thoughts',
  1537. 'duration': 51690,
  1538. },
  1539. },
  1540. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1541. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1542. {
  1543. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1544. 'info_dict': {
  1545. 'id': '4785848093001',
  1546. 'ext': 'mp4',
  1547. 'title': 'The Cardinal Pell Interview',
  1548. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1549. 'uploader': 'GlobeCast Australia - GlobeStream',
  1550. 'uploader_id': '2733773828001',
  1551. 'upload_date': '20160304',
  1552. 'timestamp': 1457083087,
  1553. },
  1554. 'params': {
  1555. # m3u8 downloads
  1556. 'skip_download': True,
  1557. },
  1558. },
  1559. {
  1560. # Brightcove embed with whitespace around attribute names
  1561. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1562. 'info_dict': {
  1563. 'id': '3167554373001',
  1564. 'ext': 'mp4',
  1565. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1566. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1567. 'uploader_id': '1079349493',
  1568. 'upload_date': '20140207',
  1569. 'timestamp': 1391810548,
  1570. },
  1571. 'params': {
  1572. 'skip_download': True,
  1573. },
  1574. },
  1575. # Another form of arte.tv embed
  1576. {
  1577. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1578. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1579. 'info_dict': {
  1580. 'id': '030273-562_PLUS7-F',
  1581. 'ext': 'mp4',
  1582. 'title': 'ARTE Reportage - Nulle part, en France',
  1583. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1584. 'upload_date': '20160409',
  1585. },
  1586. },
  1587. # LiveLeak embed
  1588. {
  1589. 'url': 'http://www.wykop.pl/link/3088787/',
  1590. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1591. 'info_dict': {
  1592. 'id': '874_1459135191',
  1593. 'ext': 'mp4',
  1594. 'title': 'Man shows poor quality of new apartment building',
  1595. 'description': 'The wall is like a sand pile.',
  1596. 'uploader': 'Lake8737',
  1597. },
  1598. 'add_ie': [LiveLeakIE.ie_key()],
  1599. },
  1600. # Another LiveLeak embed pattern (#13336)
  1601. {
  1602. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1603. 'info_dict': {
  1604. 'id': '2eb_1496309988',
  1605. 'ext': 'mp4',
  1606. 'title': 'Thief robs place where everyone was armed',
  1607. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1608. 'uploader': 'brazilwtf',
  1609. },
  1610. 'add_ie': [LiveLeakIE.ie_key()],
  1611. },
  1612. # Duplicated embedded video URLs
  1613. {
  1614. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1615. 'info_dict': {
  1616. 'id': '149298443_480_16c25b74_2',
  1617. 'ext': 'mp4',
  1618. 'title': 'vs. Blue Orange Spring Game',
  1619. 'uploader': 'www.hudl.com',
  1620. },
  1621. },
  1622. # twitter:player:stream embed
  1623. {
  1624. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1625. 'info_dict': {
  1626. 'id': 'master',
  1627. 'ext': 'mp4',
  1628. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1629. 'uploader': 'www.rtl.be',
  1630. },
  1631. 'params': {
  1632. # m3u8 downloads
  1633. 'skip_download': True,
  1634. },
  1635. },
  1636. # twitter:player embed
  1637. {
  1638. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1639. 'md5': 'a3e0df96369831de324f0778e126653c',
  1640. 'info_dict': {
  1641. 'id': '4909620399001',
  1642. 'ext': 'mp4',
  1643. 'title': 'What Do Black Holes Sound Like?',
  1644. 'description': 'what do black holes sound like',
  1645. 'upload_date': '20160524',
  1646. 'uploader_id': '29913724001',
  1647. 'timestamp': 1464107587,
  1648. 'uploader': 'TheAtlantic',
  1649. },
  1650. 'add_ie': ['BrightcoveLegacy'],
  1651. },
  1652. # Facebook <iframe> embed
  1653. {
  1654. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1655. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1656. 'info_dict': {
  1657. 'id': '599637780109885',
  1658. 'ext': 'mp4',
  1659. 'title': 'Facebook video #599637780109885',
  1660. },
  1661. },
  1662. # Facebook <iframe> embed, plugin video
  1663. {
  1664. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1665. 'info_dict': {
  1666. 'id': '1754168231264132',
  1667. 'ext': 'mp4',
  1668. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1669. 'uploader': 'Tariq Ramadan (official)',
  1670. 'timestamp': 1496758379,
  1671. 'upload_date': '20170606',
  1672. },
  1673. 'params': {
  1674. 'skip_download': True,
  1675. },
  1676. },
  1677. # Facebook API embed
  1678. {
  1679. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1680. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1681. 'info_dict': {
  1682. 'id': '10153467542406923',
  1683. 'ext': 'mp4',
  1684. 'title': 'Facebook video #10153467542406923',
  1685. },
  1686. },
  1687. # Wordpress "YouTube Video Importer" plugin
  1688. {
  1689. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1690. 'md5': 'd16797741b560b485194eddda8121b48',
  1691. 'info_dict': {
  1692. 'id': 'HNTXWDXV9Is',
  1693. 'ext': 'mp4',
  1694. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1695. 'upload_date': '20160627',
  1696. 'uploader_id': 'GENOCIDE8GENERAL10',
  1697. 'uploader': 'cylus cyrus',
  1698. },
  1699. },
  1700. {
  1701. # video stored on custom kaltura server
  1702. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1703. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1704. 'info_dict': {
  1705. 'id': '0_1iotm5bh',
  1706. 'ext': 'mp4',
  1707. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1708. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1709. 'uploader_id': 'videos.expansion@el-mundo.net',
  1710. 'upload_date': '20150429',
  1711. 'timestamp': 1430303472,
  1712. },
  1713. 'add_ie': ['Kaltura'],
  1714. },
  1715. {
  1716. # multiple kaltura embeds, nsfw
  1717. 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
  1718. 'info_dict': {
  1719. 'id': 'kamila-avec-video-jaime-sadomie',
  1720. 'title': "Kamila avec vídeo “J'aime sadomie”",
  1721. },
  1722. 'playlist_count': 8,
  1723. },
  1724. {
  1725. # Non-standard Vimeo embed
  1726. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1727. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1728. 'info_dict': {
  1729. 'id': '148867247',
  1730. 'ext': 'mp4',
  1731. 'title': 'Understanding the web - Teaser',
  1732. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1733. 'upload_date': '20151214',
  1734. 'uploader': 'OpenClassrooms',
  1735. 'uploader_id': 'openclassrooms',
  1736. },
  1737. 'add_ie': ['Vimeo'],
  1738. },
  1739. {
  1740. # generic vimeo embed that requires original URL passed as Referer
  1741. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1742. 'only_matching': True,
  1743. },
  1744. {
  1745. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1746. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1747. 'info_dict': {
  1748. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1749. 'ext': 'mp4',
  1750. 'title': 'Big Buck Bunny',
  1751. 'description': 'Royalty free test video',
  1752. 'timestamp': 1432816365,
  1753. 'upload_date': '20150528',
  1754. 'is_live': False,
  1755. },
  1756. 'params': {
  1757. 'skip_download': True,
  1758. },
  1759. 'add_ie': [ArkenaIE.ie_key()],
  1760. },
  1761. {
  1762. '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/',
  1763. 'info_dict': {
  1764. 'id': '1c7141f46c',
  1765. 'ext': 'mp4',
  1766. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1767. },
  1768. 'params': {
  1769. 'skip_download': True,
  1770. },
  1771. 'add_ie': [Vbox7IE.ie_key()],
  1772. },
  1773. {
  1774. # DBTV embeds
  1775. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1776. 'info_dict': {
  1777. 'id': '43254897',
  1778. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1779. },
  1780. 'playlist_mincount': 3,
  1781. },
  1782. {
  1783. # Videa embeds
  1784. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1785. 'info_dict': {
  1786. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1787. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1788. },
  1789. 'playlist_mincount': 2,
  1790. },
  1791. {
  1792. # 20 minuten embed
  1793. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1794. 'info_dict': {
  1795. 'id': '523629',
  1796. 'ext': 'mp4',
  1797. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1798. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1799. },
  1800. 'params': {
  1801. 'skip_download': True,
  1802. },
  1803. 'add_ie': [TwentyMinutenIE.ie_key()],
  1804. },
  1805. {
  1806. # VideoPress embed
  1807. 'url': 'https://en.support.wordpress.com/videopress/',
  1808. 'info_dict': {
  1809. 'id': 'OcobLTqC',
  1810. 'ext': 'm4v',
  1811. 'title': 'IMG_5786',
  1812. 'timestamp': 1435711927,
  1813. 'upload_date': '20150701',
  1814. },
  1815. 'params': {
  1816. 'skip_download': True,
  1817. },
  1818. 'add_ie': [VideoPressIE.ie_key()],
  1819. },
  1820. {
  1821. # Rutube embed
  1822. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1823. 'info_dict': {
  1824. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1825. 'ext': 'flv',
  1826. 'title': 'Магаззино: Казань 2',
  1827. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1828. 'uploader': 'Магаззино',
  1829. 'upload_date': '20170228',
  1830. 'uploader_id': '996642',
  1831. },
  1832. 'params': {
  1833. 'skip_download': True,
  1834. },
  1835. 'add_ie': [RutubeIE.ie_key()],
  1836. },
  1837. {
  1838. # ThePlatform embedded with whitespaces in URLs
  1839. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1840. 'only_matching': True,
  1841. },
  1842. {
  1843. # Senate ISVP iframe https
  1844. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1845. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1846. 'info_dict': {
  1847. 'id': 'govtaff020316',
  1848. 'ext': 'mp4',
  1849. 'title': 'Integrated Senate Video Player',
  1850. },
  1851. 'add_ie': [SenateISVPIE.ie_key()],
  1852. },
  1853. {
  1854. # Limelight embeds (1 channel embed + 4 media embeds)
  1855. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1856. 'info_dict': {
  1857. 'id': 'FacilitatorTraining2017',
  1858. 'title': 'Facilitator Training 2017',
  1859. },
  1860. 'playlist_mincount': 5,
  1861. },
  1862. {
  1863. # Limelight embed (LimelightPlayerUtil.embed)
  1864. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1865. 'info_dict': {
  1866. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1867. 'ext': 'mp4',
  1868. 'title': '07448641',
  1869. 'timestamp': 1499890639,
  1870. 'upload_date': '20170712',
  1871. },
  1872. 'params': {
  1873. 'skip_download': True,
  1874. },
  1875. 'add_ie': ['LimelightMedia'],
  1876. },
  1877. {
  1878. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1879. 'info_dict': {
  1880. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1881. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1882. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1883. },
  1884. 'playlist_mincount': 4,
  1885. },
  1886. {
  1887. # WashingtonPost embed
  1888. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1889. 'info_dict': {
  1890. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1891. 'ext': 'mp4',
  1892. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1893. '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.',
  1894. 'timestamp': 1455216756,
  1895. 'uploader': 'The Washington Post',
  1896. 'upload_date': '20160211',
  1897. },
  1898. 'add_ie': [WashingtonPostIE.ie_key()],
  1899. },
  1900. {
  1901. # Mediaset embed
  1902. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1903. 'info_dict': {
  1904. 'id': '720642',
  1905. 'ext': 'mp4',
  1906. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1907. },
  1908. 'params': {
  1909. 'skip_download': True,
  1910. },
  1911. 'add_ie': [MediasetIE.ie_key()],
  1912. },
  1913. {
  1914. # JOJ.sk embeds
  1915. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1916. 'info_dict': {
  1917. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1918. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1919. },
  1920. 'playlist_mincount': 5,
  1921. 'add_ie': [JojIE.ie_key()],
  1922. },
  1923. {
  1924. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1925. 'url': 'https://tvrain.ru/amp/418921/',
  1926. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1927. 'info_dict': {
  1928. 'id': '418921',
  1929. 'ext': 'mp4',
  1930. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1931. },
  1932. },
  1933. {
  1934. # vzaar embed
  1935. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1936. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1937. 'info_dict': {
  1938. 'id': '8707641',
  1939. 'ext': 'mp4',
  1940. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1941. },
  1942. },
  1943. {
  1944. # multiple HTML5 videos on one page
  1945. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1946. 'info_dict': {
  1947. 'id': 'keyscenarios',
  1948. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1949. },
  1950. 'playlist_count': 4,
  1951. },
  1952. {
  1953. # vshare embed
  1954. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1955. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1956. 'info_dict': {
  1957. 'id': '0f64ce6',
  1958. 'title': 'vl14062007715967',
  1959. 'ext': 'mp4',
  1960. }
  1961. },
  1962. {
  1963. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1964. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1965. 'info_dict': {
  1966. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1967. 'ext': 'mp4',
  1968. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1969. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1970. 'timestamp': 1474354800,
  1971. 'upload_date': '20160920',
  1972. }
  1973. },
  1974. {
  1975. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1976. 'info_dict': {
  1977. 'id': '1731611',
  1978. 'ext': 'mp4',
  1979. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1980. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1981. 'timestamp': 1516100691,
  1982. 'upload_date': '20180116',
  1983. },
  1984. 'params': {
  1985. 'skip_download': True,
  1986. },
  1987. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1988. },
  1989. {
  1990. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1991. 'info_dict': {
  1992. 'id': 'uPDB5I9wfp8',
  1993. 'ext': 'webm',
  1994. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1995. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  1996. 'upload_date': '20160219',
  1997. 'uploader': 'Pocoyo - Português (BR)',
  1998. 'uploader_id': 'PocoyoBrazil',
  1999. },
  2000. 'add_ie': [YoutubeIE.ie_key()],
  2001. 'params': {
  2002. 'skip_download': True,
  2003. },
  2004. },
  2005. {
  2006. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  2007. 'info_dict': {
  2008. 'id': 'vMDE4NzI1Mjgt690b',
  2009. 'ext': 'mp4',
  2010. 'title': 'Котята',
  2011. },
  2012. 'add_ie': [YapFilesIE.ie_key()],
  2013. 'params': {
  2014. 'skip_download': True,
  2015. },
  2016. },
  2017. {
  2018. # CloudflareStream embed
  2019. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  2020. 'info_dict': {
  2021. 'id': '31c9291ab41fac05471db4e73aa11717',
  2022. 'ext': 'mp4',
  2023. 'title': '31c9291ab41fac05471db4e73aa11717',
  2024. },
  2025. 'add_ie': [CloudflareStreamIE.ie_key()],
  2026. 'params': {
  2027. 'skip_download': True,
  2028. },
  2029. },
  2030. {
  2031. # PeerTube embed
  2032. 'url': 'https://joinpeertube.org/fr/home/',
  2033. 'info_dict': {
  2034. 'id': 'home',
  2035. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2036. },
  2037. 'playlist_count': 2,
  2038. },
  2039. {
  2040. # Indavideo embed
  2041. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2042. 'info_dict': {
  2043. 'id': '1693903',
  2044. 'ext': 'mp4',
  2045. 'title': 'Így kell otthon hamburgert sütni',
  2046. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2047. 'timestamp': 1426330212,
  2048. 'upload_date': '20150314',
  2049. 'uploader': 'StreetKitchen',
  2050. 'uploader_id': '546363',
  2051. },
  2052. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2053. 'params': {
  2054. 'skip_download': True,
  2055. },
  2056. },
  2057. {
  2058. # APA embed via JWPlatform embed
  2059. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2060. 'info_dict': {
  2061. 'id': 'jjv85FdZ',
  2062. 'ext': 'mp4',
  2063. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2064. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2065. 'thumbnail': r're:^https?://.*\.jpg$',
  2066. 'duration': 254,
  2067. 'timestamp': 1519211149,
  2068. 'upload_date': '20180221',
  2069. },
  2070. 'params': {
  2071. 'skip_download': True,
  2072. },
  2073. },
  2074. {
  2075. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2076. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2077. 'info_dict': {
  2078. 'id': '83645793',
  2079. 'title': 'Lock up and get excited',
  2080. 'ext': 'mp4'
  2081. },
  2082. 'skip': 'TODO: fix nested playlists processing in tests',
  2083. },
  2084. {
  2085. # Viqeo embeds
  2086. 'url': 'https://viqeo.tv/',
  2087. 'info_dict': {
  2088. 'id': 'viqeo',
  2089. 'title': 'All-new video platform',
  2090. },
  2091. 'playlist_count': 6,
  2092. },
  2093. {
  2094. # Squarespace video embed, 2019-08-28
  2095. 'url': 'http://ootboxford.com',
  2096. 'info_dict': {
  2097. 'id': 'Tc7b_JGdZfw',
  2098. 'title': 'Out of the Blue, at Childish Things 10',
  2099. 'ext': 'mp4',
  2100. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2101. 'uploader_id': 'helendouglashouse',
  2102. 'uploader': 'Helen & Douglas House',
  2103. 'upload_date': '20140328',
  2104. },
  2105. 'params': {
  2106. 'skip_download': True,
  2107. },
  2108. },
  2109. {
  2110. # Zype embed
  2111. 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2112. 'info_dict': {
  2113. 'id': '5b400b834b32992a310622b9',
  2114. 'ext': 'mp4',
  2115. 'title': 'Smoky Barbecue Favorites',
  2116. 'thumbnail': r're:^https?://.*\.jpe?g',
  2117. 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  2118. 'upload_date': '20170909',
  2119. 'timestamp': 1504915200,
  2120. },
  2121. 'add_ie': [ZypeIE.ie_key()],
  2122. 'params': {
  2123. 'skip_download': True,
  2124. },
  2125. },
  2126. {
  2127. # videojs embed
  2128. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2129. 'info_dict': {
  2130. 'id': 'shell',
  2131. 'ext': 'mp4',
  2132. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2133. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2134. 'thumbnail': r're:^https?://.*\.jpg$',
  2135. },
  2136. 'params': {
  2137. 'skip_download': True,
  2138. },
  2139. 'expected_warnings': ['Failed to download MPD manifest'],
  2140. },
  2141. {
  2142. # DailyMotion embed with DM.player
  2143. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2144. 'info_dict': {
  2145. 'id': 'k6aKkGHd9FJs4mtJN39',
  2146. 'ext': 'mp4',
  2147. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2148. 'description': 'This video is private.',
  2149. 'uploader_id': 'x1jf30l',
  2150. 'uploader': 'beIN SPORTS USA',
  2151. 'upload_date': '20190528',
  2152. 'timestamp': 1559062971,
  2153. },
  2154. 'params': {
  2155. 'skip_download': True,
  2156. },
  2157. },
  2158. # {
  2159. # # TODO: find another test
  2160. # # http://schema.org/VideoObject
  2161. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2162. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2163. # 'info_dict': {
  2164. # 'id': 'nyvTSJMKId',
  2165. # 'ext': 'mp4',
  2166. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2167. # 'description': '#love for cats.',
  2168. # 'timestamp': 1461244995,
  2169. # 'upload_date': '20160421',
  2170. # },
  2171. # 'params': {
  2172. # 'force_generic_extractor': True,
  2173. # },
  2174. # }
  2175. ]
  2176. def report_following_redirect(self, new_url):
  2177. """Report information extraction."""
  2178. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2179. def _extract_rss(self, url, video_id, doc):
  2180. playlist_title = doc.find('./channel/title').text
  2181. playlist_desc_el = doc.find('./channel/description')
  2182. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2183. entries = []
  2184. for it in doc.findall('./channel/item'):
  2185. next_url = None
  2186. enclosure_nodes = it.findall('./enclosure')
  2187. for e in enclosure_nodes:
  2188. next_url = e.attrib.get('url')
  2189. if next_url:
  2190. break
  2191. if not next_url:
  2192. next_url = xpath_text(it, 'link', fatal=False)
  2193. if not next_url:
  2194. continue
  2195. entries.append({
  2196. '_type': 'url_transparent',
  2197. 'url': next_url,
  2198. 'title': it.find('title').text,
  2199. 'description': xpath_text(it, 'description', default=None),
  2200. 'timestamp': unified_timestamp(
  2201. xpath_text(it, 'pubDate', default=None)),
  2202. })
  2203. return {
  2204. '_type': 'playlist',
  2205. 'id': url,
  2206. 'title': playlist_title,
  2207. 'description': playlist_desc,
  2208. 'entries': entries,
  2209. }
  2210. def _extract_camtasia(self, url, video_id, webpage):
  2211. """ Returns None if no camtasia video can be found. """
  2212. camtasia_cfg = self._search_regex(
  2213. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2214. webpage, 'camtasia configuration file', default=None)
  2215. if camtasia_cfg is None:
  2216. return None
  2217. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2218. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2219. camtasia_cfg = self._download_xml(
  2220. camtasia_url, video_id,
  2221. note='Downloading camtasia configuration',
  2222. errnote='Failed to download camtasia configuration')
  2223. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2224. entries = []
  2225. for n in fileset_node.getchildren():
  2226. url_n = n.find('./uri')
  2227. if url_n is None:
  2228. continue
  2229. entries.append({
  2230. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2231. 'title': '%s - %s' % (title, n.tag),
  2232. 'url': compat_urlparse.urljoin(url, url_n.text),
  2233. 'duration': float_or_none(n.find('./duration').text),
  2234. })
  2235. return {
  2236. '_type': 'playlist',
  2237. 'entries': entries,
  2238. 'title': title,
  2239. }
  2240. def _real_extract(self, url):
  2241. if url.startswith('//'):
  2242. return self.url_result(self.http_scheme() + url)
  2243. parsed_url = compat_urlparse.urlparse(url)
  2244. if not parsed_url.scheme:
  2245. default_search = self._downloader.params.get('default_search')
  2246. if default_search is None:
  2247. default_search = 'fixup_error'
  2248. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2249. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2250. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2251. return self.url_result('http://' + url)
  2252. elif default_search != 'fixup_error':
  2253. if default_search == 'auto_warning':
  2254. if re.match(r'^(?:url|URL)$', url):
  2255. raise ExtractorError(
  2256. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2257. expected=True)
  2258. else:
  2259. self._downloader.report_warning(
  2260. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2261. return self.url_result('ytsearch:' + url)
  2262. if default_search in ('error', 'fixup_error'):
  2263. raise ExtractorError(
  2264. '%r is not a valid URL. '
  2265. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2266. % (url, url), expected=True)
  2267. else:
  2268. if ':' not in default_search:
  2269. default_search += ':'
  2270. return self.url_result(default_search + url)
  2271. url, smuggled_data = unsmuggle_url(url)
  2272. force_videoid = None
  2273. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2274. if smuggled_data and 'force_videoid' in smuggled_data:
  2275. force_videoid = smuggled_data['force_videoid']
  2276. video_id = force_videoid
  2277. else:
  2278. video_id = self._generic_id(url)
  2279. self.to_screen('%s: Requesting header' % video_id)
  2280. head_req = HEADRequest(url)
  2281. head_response = self._request_webpage(
  2282. head_req, video_id,
  2283. note=False, errnote='Could not send HEAD request to %s' % url,
  2284. fatal=False)
  2285. if head_response is not False:
  2286. # Check for redirect
  2287. new_url = head_response.geturl()
  2288. if url != new_url:
  2289. self.report_following_redirect(new_url)
  2290. if force_videoid:
  2291. new_url = smuggle_url(
  2292. new_url, {'force_videoid': force_videoid})
  2293. return self.url_result(new_url)
  2294. full_response = None
  2295. if head_response is False:
  2296. request = sanitized_Request(url)
  2297. request.add_header('Accept-Encoding', '*')
  2298. full_response = self._request_webpage(request, video_id)
  2299. head_response = full_response
  2300. info_dict = {
  2301. 'id': video_id,
  2302. 'title': self._generic_title(url),
  2303. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2304. }
  2305. # Check for direct link to a video
  2306. content_type = head_response.headers.get('Content-Type', '').lower()
  2307. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2308. if m:
  2309. format_id = compat_str(m.group('format_id'))
  2310. if format_id.endswith('mpegurl'):
  2311. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2312. elif format_id == 'f4m':
  2313. formats = self._extract_f4m_formats(url, video_id)
  2314. else:
  2315. formats = [{
  2316. 'format_id': format_id,
  2317. 'url': url,
  2318. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2319. }]
  2320. info_dict['direct'] = True
  2321. self._sort_formats(formats)
  2322. info_dict['formats'] = formats
  2323. return info_dict
  2324. if not self._downloader.params.get('test', False) and not is_intentional:
  2325. force = self._downloader.params.get('force_generic_extractor', False)
  2326. self._downloader.report_warning(
  2327. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2328. if not full_response:
  2329. request = sanitized_Request(url)
  2330. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2331. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2332. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2333. # that will always result in downloading the whole file that is not desirable.
  2334. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2335. # to accept raw bytes and being able to download only a chunk.
  2336. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2337. # after HEAD request finishes, but not sure if we can rely on this.
  2338. request.add_header('Accept-Encoding', '*')
  2339. full_response = self._request_webpage(request, video_id)
  2340. first_bytes = full_response.read(512)
  2341. # Is it an M3U playlist?
  2342. if first_bytes.startswith(b'#EXTM3U'):
  2343. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2344. self._sort_formats(info_dict['formats'])
  2345. return info_dict
  2346. # Maybe it's a direct link to a video?
  2347. # Be careful not to download the whole thing!
  2348. if not is_html(first_bytes):
  2349. self._downloader.report_warning(
  2350. 'URL could be a direct video link, returning it as such.')
  2351. info_dict.update({
  2352. 'direct': True,
  2353. 'url': url,
  2354. })
  2355. return info_dict
  2356. webpage = self._webpage_read_content(
  2357. full_response, url, video_id, prefix=first_bytes)
  2358. self.report_extraction(video_id)
  2359. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2360. try:
  2361. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2362. if doc.tag == 'rss':
  2363. return self._extract_rss(url, video_id, doc)
  2364. elif doc.tag == 'SmoothStreamingMedia':
  2365. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2366. self._sort_formats(info_dict['formats'])
  2367. return info_dict
  2368. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2369. smil = self._parse_smil(doc, url, video_id)
  2370. self._sort_formats(smil['formats'])
  2371. return smil
  2372. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2373. return self.playlist_result(
  2374. self._parse_xspf(
  2375. doc, video_id, xspf_url=url,
  2376. xspf_base_url=full_response.geturl()),
  2377. video_id)
  2378. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2379. info_dict['formats'] = self._parse_mpd_formats(
  2380. doc,
  2381. mpd_base_url=full_response.geturl().rpartition('/')[0],
  2382. mpd_url=url)
  2383. self._sort_formats(info_dict['formats'])
  2384. return info_dict
  2385. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2386. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2387. self._sort_formats(info_dict['formats'])
  2388. return info_dict
  2389. except compat_xml_parse_error:
  2390. pass
  2391. # Is it a Camtasia project?
  2392. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2393. if camtasia_res is not None:
  2394. return camtasia_res
  2395. # Sometimes embedded video player is hidden behind percent encoding
  2396. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2397. # Unescaping the whole page allows to handle those cases in a generic way
  2398. webpage = compat_urllib_parse_unquote(webpage)
  2399. # Unescape squarespace embeds to be detected by generic extractor,
  2400. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2401. webpage = re.sub(
  2402. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2403. lambda x: unescapeHTML(x.group(0)), webpage)
  2404. # it's tempting to parse this further, but you would
  2405. # have to take into account all the variations like
  2406. # Video Title - Site Name
  2407. # Site Name | Video Title
  2408. # Video Title - Tagline | Site Name
  2409. # and so on and so forth; it's just not practical
  2410. video_title = self._og_search_title(
  2411. webpage, default=None) or self._html_search_regex(
  2412. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2413. default='video')
  2414. # Try to detect age limit automatically
  2415. age_limit = self._rta_search(webpage)
  2416. # And then there are the jokers who advertise that they use RTA,
  2417. # but actually don't.
  2418. AGE_LIMIT_MARKERS = [
  2419. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2420. ]
  2421. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2422. age_limit = 18
  2423. # video uploader is domain name
  2424. video_uploader = self._search_regex(
  2425. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2426. video_description = self._og_search_description(webpage, default=None)
  2427. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2428. info_dict.update({
  2429. 'title': video_title,
  2430. 'description': video_description,
  2431. 'thumbnail': video_thumbnail,
  2432. 'age_limit': age_limit,
  2433. })
  2434. # Look for Brightcove Legacy Studio embeds
  2435. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2436. if bc_urls:
  2437. entries = [{
  2438. '_type': 'url',
  2439. 'url': smuggle_url(bc_url, {'Referer': url}),
  2440. 'ie_key': 'BrightcoveLegacy'
  2441. } for bc_url in bc_urls]
  2442. return {
  2443. '_type': 'playlist',
  2444. 'title': video_title,
  2445. 'id': video_id,
  2446. 'entries': entries,
  2447. }
  2448. # Look for Brightcove New Studio embeds
  2449. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2450. if bc_urls:
  2451. return self.playlist_from_matches(
  2452. bc_urls, video_id, video_title,
  2453. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2454. ie='BrightcoveNew')
  2455. # Look for Nexx embeds
  2456. nexx_urls = NexxIE._extract_urls(webpage)
  2457. if nexx_urls:
  2458. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2459. # Look for Nexx iFrame embeds
  2460. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2461. if nexx_embed_urls:
  2462. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2463. # Look for ThePlatform embeds
  2464. tp_urls = ThePlatformIE._extract_urls(webpage)
  2465. if tp_urls:
  2466. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2467. # Look for embedded rtl.nl player
  2468. matches = re.findall(
  2469. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2470. webpage)
  2471. if matches:
  2472. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2473. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2474. if vimeo_urls:
  2475. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2476. vid_me_embed_url = self._search_regex(
  2477. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2478. webpage, 'vid.me embed', default=None)
  2479. if vid_me_embed_url is not None:
  2480. return self.url_result(vid_me_embed_url, 'Vidme')
  2481. # Look for YouTube embeds
  2482. youtube_urls = YoutubeIE._extract_urls(webpage)
  2483. if youtube_urls:
  2484. return self.playlist_from_matches(
  2485. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2486. matches = DailymotionIE._extract_urls(webpage)
  2487. if matches:
  2488. return self.playlist_from_matches(matches, video_id, video_title)
  2489. # Look for embedded Dailymotion playlist player (#3822)
  2490. m = re.search(
  2491. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2492. if m:
  2493. playlists = re.findall(
  2494. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2495. if playlists:
  2496. return self.playlist_from_matches(
  2497. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2498. # Look for DailyMail embeds
  2499. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2500. if dailymail_urls:
  2501. return self.playlist_from_matches(
  2502. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2503. # Look for Teachable embeds, must be before Wistia
  2504. teachable_url = TeachableIE._extract_url(webpage, url)
  2505. if teachable_url:
  2506. return self.url_result(teachable_url)
  2507. # Look for embedded Wistia player
  2508. wistia_urls = WistiaIE._extract_urls(webpage)
  2509. if wistia_urls:
  2510. playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
  2511. for entry in playlist['entries']:
  2512. entry.update({
  2513. '_type': 'url_transparent',
  2514. 'uploader': video_uploader,
  2515. })
  2516. return playlist
  2517. # Look for SVT player
  2518. svt_url = SVTIE._extract_url(webpage)
  2519. if svt_url:
  2520. return self.url_result(svt_url, 'SVT')
  2521. # Look for Bandcamp pages with custom domain
  2522. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2523. if mobj is not None:
  2524. burl = unescapeHTML(mobj.group(1))
  2525. # Don't set the extractor because it can be a track url or an album
  2526. return self.url_result(burl)
  2527. # Look for embedded Vevo player
  2528. mobj = re.search(
  2529. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2530. if mobj is not None:
  2531. return self.url_result(mobj.group('url'))
  2532. # Look for embedded Viddler player
  2533. mobj = re.search(
  2534. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2535. webpage)
  2536. if mobj is not None:
  2537. return self.url_result(mobj.group('url'))
  2538. # Look for NYTimes player
  2539. mobj = re.search(
  2540. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2541. webpage)
  2542. if mobj is not None:
  2543. return self.url_result(mobj.group('url'))
  2544. # Look for Libsyn player
  2545. mobj = re.search(
  2546. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2547. if mobj is not None:
  2548. return self.url_result(mobj.group('url'))
  2549. # Look for Ooyala videos
  2550. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2551. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2552. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2553. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2554. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2555. if mobj is not None:
  2556. embed_token = self._search_regex(
  2557. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2558. webpage, 'ooyala embed token', default=None)
  2559. return OoyalaIE._build_url_result(smuggle_url(
  2560. mobj.group('ec'), {
  2561. 'domain': url,
  2562. 'embed_token': embed_token,
  2563. }))
  2564. # Look for multiple Ooyala embeds on SBN network websites
  2565. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2566. if mobj is not None:
  2567. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2568. if embeds:
  2569. return self.playlist_from_matches(
  2570. embeds, video_id, video_title,
  2571. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2572. # Look for Aparat videos
  2573. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2574. if mobj is not None:
  2575. return self.url_result(mobj.group(1), 'Aparat')
  2576. # Look for MPORA videos
  2577. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2578. if mobj is not None:
  2579. return self.url_result(mobj.group(1), 'Mpora')
  2580. # Look for embedded Facebook player
  2581. facebook_urls = FacebookIE._extract_urls(webpage)
  2582. if facebook_urls:
  2583. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2584. # Look for embedded VK player
  2585. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2586. if mobj is not None:
  2587. return self.url_result(mobj.group('url'), 'VK')
  2588. # Look for embedded Odnoklassniki player
  2589. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2590. if odnoklassniki_url:
  2591. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2592. # Look for embedded ivi player
  2593. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2594. if mobj is not None:
  2595. return self.url_result(mobj.group('url'), 'Ivi')
  2596. # Look for embedded Huffington Post player
  2597. mobj = re.search(
  2598. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2599. if mobj is not None:
  2600. return self.url_result(mobj.group('url'), 'HuffPost')
  2601. # Look for embed.ly
  2602. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2603. if mobj is not None:
  2604. return self.url_result(mobj.group('url'))
  2605. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2606. if mobj is not None:
  2607. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2608. # Look for funnyordie embed
  2609. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2610. if matches:
  2611. return self.playlist_from_matches(
  2612. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2613. # Look for BBC iPlayer embed
  2614. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2615. if matches:
  2616. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2617. # Look for embedded RUTV player
  2618. rutv_url = RUTVIE._extract_url(webpage)
  2619. if rutv_url:
  2620. return self.url_result(rutv_url, 'RUTV')
  2621. # Look for embedded TVC player
  2622. tvc_url = TVCIE._extract_url(webpage)
  2623. if tvc_url:
  2624. return self.url_result(tvc_url, 'TVC')
  2625. # Look for embedded SportBox player
  2626. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2627. if sportbox_urls:
  2628. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2629. # Look for embedded XHamster player
  2630. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2631. if xhamster_urls:
  2632. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2633. # Look for embedded TNAFlixNetwork player
  2634. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2635. if tnaflix_urls:
  2636. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2637. # Look for embedded PornHub player
  2638. pornhub_urls = PornHubIE._extract_urls(webpage)
  2639. if pornhub_urls:
  2640. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2641. # Look for embedded DrTuber player
  2642. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2643. if drtuber_urls:
  2644. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2645. # Look for embedded RedTube player
  2646. redtube_urls = RedTubeIE._extract_urls(webpage)
  2647. if redtube_urls:
  2648. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2649. # Look for embedded Tube8 player
  2650. tube8_urls = Tube8IE._extract_urls(webpage)
  2651. if tube8_urls:
  2652. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2653. # Look for embedded Mofosex player
  2654. mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
  2655. if mofosex_urls:
  2656. return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
  2657. # Look for embedded Spankwire player
  2658. spankwire_urls = SpankwireIE._extract_urls(webpage)
  2659. if spankwire_urls:
  2660. return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
  2661. # Look for embedded YouPorn player
  2662. youporn_urls = YouPornIE._extract_urls(webpage)
  2663. if youporn_urls:
  2664. return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
  2665. # Look for embedded Tvigle player
  2666. mobj = re.search(
  2667. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2668. if mobj is not None:
  2669. return self.url_result(mobj.group('url'), 'Tvigle')
  2670. # Look for embedded TED player
  2671. mobj = re.search(
  2672. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2673. if mobj is not None:
  2674. return self.url_result(mobj.group('url'), 'TED')
  2675. # Look for embedded Ustream videos
  2676. ustream_url = UstreamIE._extract_url(webpage)
  2677. if ustream_url:
  2678. return self.url_result(ustream_url, UstreamIE.ie_key())
  2679. # Look for embedded arte.tv player
  2680. arte_urls = ArteTVEmbedIE._extract_urls(webpage)
  2681. if arte_urls:
  2682. return self.playlist_from_matches(arte_urls, video_id, video_title)
  2683. # Look for embedded francetv player
  2684. mobj = re.search(
  2685. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2686. webpage)
  2687. if mobj is not None:
  2688. return self.url_result(mobj.group('url'))
  2689. # Look for embedded smotri.com player
  2690. smotri_url = SmotriIE._extract_url(webpage)
  2691. if smotri_url:
  2692. return self.url_result(smotri_url, 'Smotri')
  2693. # Look for embedded Myvi.ru player
  2694. myvi_url = MyviIE._extract_url(webpage)
  2695. if myvi_url:
  2696. return self.url_result(myvi_url)
  2697. # Look for embedded soundcloud player
  2698. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2699. if soundcloud_urls:
  2700. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2701. # Look for tunein player
  2702. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2703. if tunein_urls:
  2704. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2705. # Look for embedded mtvservices player
  2706. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2707. if mtvservices_url:
  2708. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2709. # Look for embedded yahoo player
  2710. mobj = re.search(
  2711. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2712. webpage)
  2713. if mobj is not None:
  2714. return self.url_result(mobj.group('url'), 'Yahoo')
  2715. # Look for embedded sbs.com.au player
  2716. mobj = re.search(
  2717. r'''(?x)
  2718. (?:
  2719. <meta\s+property="og:video"\s+content=|
  2720. <iframe[^>]+?src=
  2721. )
  2722. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2723. webpage)
  2724. if mobj is not None:
  2725. return self.url_result(mobj.group('url'), 'SBS')
  2726. # Look for embedded Cinchcast player
  2727. mobj = re.search(
  2728. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2729. webpage)
  2730. if mobj is not None:
  2731. return self.url_result(mobj.group('url'), 'Cinchcast')
  2732. mobj = re.search(
  2733. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2734. webpage)
  2735. if not mobj:
  2736. mobj = re.search(
  2737. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2738. webpage)
  2739. if mobj is not None:
  2740. return self.url_result(mobj.group('url'), 'MLB')
  2741. mobj = re.search(
  2742. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2743. webpage)
  2744. if mobj is not None:
  2745. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2746. mobj = re.search(
  2747. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2748. webpage)
  2749. if mobj is not None:
  2750. return self.url_result(mobj.group('url'), 'Livestream')
  2751. # Look for Zapiks embed
  2752. mobj = re.search(
  2753. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2754. if mobj is not None:
  2755. return self.url_result(mobj.group('url'), 'Zapiks')
  2756. # Look for Kaltura embeds
  2757. kaltura_urls = KalturaIE._extract_urls(webpage)
  2758. if kaltura_urls:
  2759. return self.playlist_from_matches(
  2760. kaltura_urls, video_id, video_title,
  2761. getter=lambda x: smuggle_url(x, {'source_url': url}),
  2762. ie=KalturaIE.ie_key())
  2763. # Look for EaglePlatform embeds
  2764. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2765. if eagleplatform_url:
  2766. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2767. # Look for ClipYou (uses EaglePlatform) embeds
  2768. mobj = re.search(
  2769. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2770. if mobj is not None:
  2771. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2772. # Look for Pladform embeds
  2773. pladform_url = PladformIE._extract_url(webpage)
  2774. if pladform_url:
  2775. return self.url_result(pladform_url)
  2776. # Look for Videomore embeds
  2777. videomore_url = VideomoreIE._extract_url(webpage)
  2778. if videomore_url:
  2779. return self.url_result(videomore_url)
  2780. # Look for Webcaster embeds
  2781. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2782. if webcaster_url:
  2783. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2784. # Look for Playwire embeds
  2785. mobj = re.search(
  2786. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2787. if mobj is not None:
  2788. return self.url_result(mobj.group('url'))
  2789. # Look for 5min embeds
  2790. mobj = re.search(
  2791. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2792. if mobj is not None:
  2793. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2794. # Look for Crooks and Liars embeds
  2795. mobj = re.search(
  2796. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2797. if mobj is not None:
  2798. return self.url_result(mobj.group('url'))
  2799. # Look for NBC Sports VPlayer embeds
  2800. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2801. if nbc_sports_url:
  2802. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2803. # Look for NBC News embeds
  2804. nbc_news_embed_url = re.search(
  2805. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2806. if nbc_news_embed_url:
  2807. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2808. # Look for Google Drive embeds
  2809. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2810. if google_drive_url:
  2811. return self.url_result(google_drive_url, 'GoogleDrive')
  2812. # Look for UDN embeds
  2813. mobj = re.search(
  2814. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2815. if mobj is not None:
  2816. return self.url_result(
  2817. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2818. # Look for Senate ISVP iframe
  2819. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2820. if senate_isvp_url:
  2821. return self.url_result(senate_isvp_url, 'SenateISVP')
  2822. # Look for Kinja embeds
  2823. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  2824. if kinja_embed_urls:
  2825. return self.playlist_from_matches(
  2826. kinja_embed_urls, video_id, video_title)
  2827. # Look for OnionStudios embeds
  2828. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2829. if onionstudios_url:
  2830. return self.url_result(onionstudios_url)
  2831. # Look for ViewLift embeds
  2832. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2833. if viewlift_url:
  2834. return self.url_result(viewlift_url)
  2835. # Look for JWPlatform embeds
  2836. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2837. if jwplatform_urls:
  2838. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2839. # Look for Digiteka embeds
  2840. digiteka_url = DigitekaIE._extract_url(webpage)
  2841. if digiteka_url:
  2842. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2843. # Look for Arkena embeds
  2844. arkena_url = ArkenaIE._extract_url(webpage)
  2845. if arkena_url:
  2846. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2847. # Look for Piksel embeds
  2848. piksel_url = PikselIE._extract_url(webpage)
  2849. if piksel_url:
  2850. return self.url_result(piksel_url, PikselIE.ie_key())
  2851. # Look for Limelight embeds
  2852. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2853. if limelight_urls:
  2854. return self.playlist_result(
  2855. limelight_urls, video_id, video_title, video_description)
  2856. # Look for Anvato embeds
  2857. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2858. if anvato_urls:
  2859. return self.playlist_result(
  2860. anvato_urls, video_id, video_title, video_description)
  2861. # Look for AdobeTVVideo embeds
  2862. mobj = re.search(
  2863. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2864. webpage)
  2865. if mobj is not None:
  2866. return self.url_result(
  2867. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2868. 'AdobeTVVideo')
  2869. # Look for Vine embeds
  2870. mobj = re.search(
  2871. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2872. webpage)
  2873. if mobj is not None:
  2874. return self.url_result(
  2875. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2876. # Look for VODPlatform embeds
  2877. mobj = re.search(
  2878. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
  2879. webpage)
  2880. if mobj is not None:
  2881. return self.url_result(
  2882. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2883. # Look for Mangomolo embeds
  2884. mobj = re.search(
  2885. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  2886. (?:
  2887. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  2888. player\.mangomolo\.com/v1
  2889. )/
  2890. (?:
  2891. video\?.*?\bid=(?P<video_id>\d+)|
  2892. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2893. ).+?)\1''', webpage)
  2894. if mobj is not None:
  2895. info = {
  2896. '_type': 'url_transparent',
  2897. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2898. 'title': video_title,
  2899. 'description': video_description,
  2900. 'thumbnail': video_thumbnail,
  2901. 'uploader': video_uploader,
  2902. }
  2903. video_id = mobj.group('video_id')
  2904. if video_id:
  2905. info.update({
  2906. 'ie_key': 'MangomoloVideo',
  2907. 'id': video_id,
  2908. })
  2909. else:
  2910. info.update({
  2911. 'ie_key': 'MangomoloLive',
  2912. 'id': mobj.group('channel_id'),
  2913. })
  2914. return info
  2915. # Look for Instagram embeds
  2916. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2917. if instagram_embed_url is not None:
  2918. return self.url_result(
  2919. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2920. # Look for LiveLeak embeds
  2921. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2922. if liveleak_urls:
  2923. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2924. # Look for 3Q SDN embeds
  2925. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2926. if threeqsdn_url:
  2927. return {
  2928. '_type': 'url_transparent',
  2929. 'ie_key': ThreeQSDNIE.ie_key(),
  2930. 'url': self._proto_relative_url(threeqsdn_url),
  2931. 'title': video_title,
  2932. 'description': video_description,
  2933. 'thumbnail': video_thumbnail,
  2934. 'uploader': video_uploader,
  2935. }
  2936. # Look for VBOX7 embeds
  2937. vbox7_url = Vbox7IE._extract_url(webpage)
  2938. if vbox7_url:
  2939. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2940. # Look for DBTV embeds
  2941. dbtv_urls = DBTVIE._extract_urls(webpage)
  2942. if dbtv_urls:
  2943. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2944. # Look for Videa embeds
  2945. videa_urls = VideaIE._extract_urls(webpage)
  2946. if videa_urls:
  2947. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2948. # Look for 20 minuten embeds
  2949. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2950. if twentymin_urls:
  2951. return self.playlist_from_matches(
  2952. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2953. # Look for VideoPress embeds
  2954. videopress_urls = VideoPressIE._extract_urls(webpage)
  2955. if videopress_urls:
  2956. return self.playlist_from_matches(
  2957. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2958. # Look for Rutube embeds
  2959. rutube_urls = RutubeIE._extract_urls(webpage)
  2960. if rutube_urls:
  2961. return self.playlist_from_matches(
  2962. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2963. # Look for WashingtonPost embeds
  2964. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2965. if wapo_urls:
  2966. return self.playlist_from_matches(
  2967. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2968. # Look for Mediaset embeds
  2969. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  2970. if mediaset_urls:
  2971. return self.playlist_from_matches(
  2972. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2973. # Look for JOJ.sk embeds
  2974. joj_urls = JojIE._extract_urls(webpage)
  2975. if joj_urls:
  2976. return self.playlist_from_matches(
  2977. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  2978. # Look for megaphone.fm embeds
  2979. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  2980. if mpfn_urls:
  2981. return self.playlist_from_matches(
  2982. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  2983. # Look for vzaar embeds
  2984. vzaar_urls = VzaarIE._extract_urls(webpage)
  2985. if vzaar_urls:
  2986. return self.playlist_from_matches(
  2987. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  2988. channel9_urls = Channel9IE._extract_urls(webpage)
  2989. if channel9_urls:
  2990. return self.playlist_from_matches(
  2991. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  2992. vshare_urls = VShareIE._extract_urls(webpage)
  2993. if vshare_urls:
  2994. return self.playlist_from_matches(
  2995. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  2996. # Look for Mediasite embeds
  2997. mediasite_urls = MediasiteIE._extract_urls(webpage)
  2998. if mediasite_urls:
  2999. entries = [
  3000. self.url_result(smuggle_url(
  3001. compat_urlparse.urljoin(url, mediasite_url),
  3002. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  3003. for mediasite_url in mediasite_urls]
  3004. return self.playlist_result(entries, video_id, video_title)
  3005. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  3006. if springboardplatform_urls:
  3007. return self.playlist_from_matches(
  3008. springboardplatform_urls, video_id, video_title,
  3009. ie=SpringboardPlatformIE.ie_key())
  3010. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  3011. if yapfiles_urls:
  3012. return self.playlist_from_matches(
  3013. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  3014. vice_urls = ViceIE._extract_urls(webpage)
  3015. if vice_urls:
  3016. return self.playlist_from_matches(
  3017. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  3018. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  3019. if xfileshare_urls:
  3020. return self.playlist_from_matches(
  3021. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  3022. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  3023. if cloudflarestream_urls:
  3024. return self.playlist_from_matches(
  3025. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  3026. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  3027. if peertube_urls:
  3028. return self.playlist_from_matches(
  3029. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  3030. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  3031. if indavideo_urls:
  3032. return self.playlist_from_matches(
  3033. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  3034. apa_urls = APAIE._extract_urls(webpage)
  3035. if apa_urls:
  3036. return self.playlist_from_matches(
  3037. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  3038. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  3039. if foxnews_urls:
  3040. return self.playlist_from_matches(
  3041. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  3042. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3043. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3044. webpage)]
  3045. if sharevideos_urls:
  3046. return self.playlist_from_matches(
  3047. sharevideos_urls, video_id, video_title)
  3048. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3049. if viqeo_urls:
  3050. return self.playlist_from_matches(
  3051. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3052. expressen_urls = ExpressenIE._extract_urls(webpage)
  3053. if expressen_urls:
  3054. return self.playlist_from_matches(
  3055. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3056. zype_urls = ZypeIE._extract_urls(webpage)
  3057. if zype_urls:
  3058. return self.playlist_from_matches(
  3059. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3060. # Look for HTML5 media
  3061. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3062. if entries:
  3063. if len(entries) == 1:
  3064. entries[0].update({
  3065. 'id': video_id,
  3066. 'title': video_title,
  3067. })
  3068. else:
  3069. for num, entry in enumerate(entries, start=1):
  3070. entry.update({
  3071. 'id': '%s-%s' % (video_id, num),
  3072. 'title': '%s (%d)' % (video_title, num),
  3073. })
  3074. for entry in entries:
  3075. self._sort_formats(entry['formats'])
  3076. return self.playlist_result(entries, video_id, video_title)
  3077. jwplayer_data = self._find_jwplayer_data(
  3078. webpage, video_id, transform_source=js_to_json)
  3079. if jwplayer_data:
  3080. try:
  3081. info = self._parse_jwplayer_data(
  3082. jwplayer_data, video_id, require_title=False, base_url=url)
  3083. return merge_dicts(info, info_dict)
  3084. except ExtractorError:
  3085. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3086. pass
  3087. # Video.js embed
  3088. mobj = re.search(
  3089. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3090. webpage)
  3091. if mobj is not None:
  3092. sources = self._parse_json(
  3093. mobj.group(1), video_id, transform_source=js_to_json,
  3094. fatal=False) or []
  3095. if not isinstance(sources, list):
  3096. sources = [sources]
  3097. formats = []
  3098. for source in sources:
  3099. src = source.get('src')
  3100. if not src or not isinstance(src, compat_str):
  3101. continue
  3102. src = compat_urlparse.urljoin(url, src)
  3103. src_type = source.get('type')
  3104. if isinstance(src_type, compat_str):
  3105. src_type = src_type.lower()
  3106. ext = determine_ext(src).lower()
  3107. if src_type == 'video/youtube':
  3108. return self.url_result(src, YoutubeIE.ie_key())
  3109. if src_type == 'application/dash+xml' or ext == 'mpd':
  3110. formats.extend(self._extract_mpd_formats(
  3111. src, video_id, mpd_id='dash', fatal=False))
  3112. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3113. formats.extend(self._extract_m3u8_formats(
  3114. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3115. m3u8_id='hls', fatal=False))
  3116. else:
  3117. formats.append({
  3118. 'url': src,
  3119. 'ext': (mimetype2ext(src_type)
  3120. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3121. })
  3122. if formats:
  3123. self._sort_formats(formats)
  3124. info_dict['formats'] = formats
  3125. return info_dict
  3126. # Looking for http://schema.org/VideoObject
  3127. json_ld = self._search_json_ld(
  3128. webpage, video_id, default={}, expected_type='VideoObject')
  3129. if json_ld.get('url'):
  3130. return merge_dicts(json_ld, info_dict)
  3131. def check_video(vurl):
  3132. if YoutubeIE.suitable(vurl):
  3133. return True
  3134. if RtmpIE.suitable(vurl):
  3135. return True
  3136. vpath = compat_urlparse.urlparse(vurl).path
  3137. vext = determine_ext(vpath)
  3138. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3139. def filter_video(urls):
  3140. return list(filter(check_video, urls))
  3141. # Start with something easy: JW Player in SWFObject
  3142. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3143. if not found:
  3144. # Look for gorilla-vid style embedding
  3145. found = filter_video(re.findall(r'''(?sx)
  3146. (?:
  3147. jw_plugins|
  3148. JWPlayerOptions|
  3149. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3150. )
  3151. .*?
  3152. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3153. if not found:
  3154. # Broaden the search a little bit
  3155. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3156. if not found:
  3157. # Broaden the findall a little bit: JWPlayer JS loader
  3158. found = filter_video(re.findall(
  3159. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3160. if not found:
  3161. # Flow player
  3162. found = filter_video(re.findall(r'''(?xs)
  3163. flowplayer\("[^"]+",\s*
  3164. \{[^}]+?\}\s*,
  3165. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3166. ["']?url["']?\s*:\s*["']([^"']+)["']
  3167. ''', webpage))
  3168. if not found:
  3169. # Cinerama player
  3170. found = re.findall(
  3171. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3172. if not found:
  3173. # Try to find twitter cards info
  3174. # twitter:player:stream should be checked before twitter:player since
  3175. # it is expected to contain a raw stream (see
  3176. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3177. found = filter_video(re.findall(
  3178. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3179. if not found:
  3180. # We look for Open Graph info:
  3181. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3182. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3183. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3184. if m_video_type is not None:
  3185. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3186. if not found:
  3187. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3188. found = re.search(
  3189. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3190. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3191. webpage)
  3192. if not found:
  3193. # Look also in Refresh HTTP header
  3194. refresh_header = head_response.headers.get('Refresh')
  3195. if refresh_header:
  3196. # In python 2 response HTTP headers are bytestrings
  3197. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3198. refresh_header = refresh_header.decode('iso-8859-1')
  3199. found = re.search(REDIRECT_REGEX, refresh_header)
  3200. if found:
  3201. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3202. if new_url != url:
  3203. self.report_following_redirect(new_url)
  3204. return {
  3205. '_type': 'url',
  3206. 'url': new_url,
  3207. }
  3208. else:
  3209. found = None
  3210. if not found:
  3211. # twitter:player is a https URL to iframe player that may or may not
  3212. # be supported by youtube-dl thus this is checked the very last (see
  3213. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3214. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3215. if embed_url and embed_url != url:
  3216. return self.url_result(embed_url)
  3217. if not found:
  3218. raise UnsupportedError(url)
  3219. entries = []
  3220. for video_url in orderedSet(found):
  3221. video_url = unescapeHTML(video_url)
  3222. video_url = video_url.replace('\\/', '/')
  3223. video_url = compat_urlparse.urljoin(url, video_url)
  3224. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3225. # Sometimes, jwplayer extraction will result in a YouTube URL
  3226. if YoutubeIE.suitable(video_url):
  3227. entries.append(self.url_result(video_url, 'Youtube'))
  3228. continue
  3229. # here's a fun little line of code for you:
  3230. video_id = os.path.splitext(video_id)[0]
  3231. entry_info_dict = {
  3232. 'id': video_id,
  3233. 'uploader': video_uploader,
  3234. 'title': video_title,
  3235. 'age_limit': age_limit,
  3236. }
  3237. if RtmpIE.suitable(video_url):
  3238. entry_info_dict.update({
  3239. '_type': 'url_transparent',
  3240. 'ie_key': RtmpIE.ie_key(),
  3241. 'url': video_url,
  3242. })
  3243. entries.append(entry_info_dict)
  3244. continue
  3245. ext = determine_ext(video_url)
  3246. if ext == 'smil':
  3247. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3248. elif ext == 'xspf':
  3249. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3250. elif ext == 'm3u8':
  3251. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3252. elif ext == 'mpd':
  3253. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3254. elif ext == 'f4m':
  3255. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3256. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3257. # Just matching .ism/manifest is not enough to be reliably sure
  3258. # whether it's actually an ISM manifest or some other streaming
  3259. # manifest since there are various streaming URL formats
  3260. # possible (see [1]) as well as some other shenanigans like
  3261. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3262. # so on.
  3263. # Thus the most reasonable way to solve this is to delegate
  3264. # to generic extractor in order to look into the contents of
  3265. # the manifest itself.
  3266. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3267. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3268. entry_info_dict = self.url_result(
  3269. smuggle_url(video_url, {'to_generic': True}),
  3270. GenericIE.ie_key())
  3271. else:
  3272. entry_info_dict['url'] = video_url
  3273. if entry_info_dict.get('formats'):
  3274. self._sort_formats(entry_info_dict['formats'])
  3275. entries.append(entry_info_dict)
  3276. if len(entries) == 1:
  3277. return entries[0]
  3278. else:
  3279. for num, e in enumerate(entries, start=1):
  3280. # 'url' results don't have a title
  3281. if e.get('title') is not None:
  3282. e['title'] = '%s (%d)' % (e['title'], num)
  3283. return {
  3284. '_type': 'playlist',
  3285. 'entries': entries,
  3286. }