generic.py 141 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502
  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. int_or_none,
  21. is_html,
  22. js_to_json,
  23. KNOWN_EXTENSIONS,
  24. merge_dicts,
  25. mimetype2ext,
  26. orderedSet,
  27. parse_duration,
  28. sanitized_Request,
  29. smuggle_url,
  30. unescapeHTML,
  31. unified_strdate,
  32. unified_timestamp,
  33. unsmuggle_url,
  34. UnsupportedError,
  35. url_or_none,
  36. xpath_text,
  37. xpath_with_ns,
  38. )
  39. from .commonprotocols import RtmpIE
  40. from .brightcove import (
  41. BrightcoveLegacyIE,
  42. BrightcoveNewIE,
  43. )
  44. from .nexx import (
  45. NexxIE,
  46. NexxEmbedIE,
  47. )
  48. from .nbc import NBCSportsVPlayerIE
  49. from .ooyala import OoyalaIE
  50. from .rutv import RUTVIE
  51. from .tvc import TVCIE
  52. from .sportbox import SportBoxIE
  53. from .smotri import SmotriIE
  54. from .myvi import MyviIE
  55. from .condenast import CondeNastIE
  56. from .udn import UDNEmbedIE
  57. from .senateisvp import SenateISVPIE
  58. from .svt import SVTIE
  59. from .pornhub import PornHubIE
  60. from .xhamster import XHamsterEmbedIE
  61. from .tnaflix import TNAFlixNetworkEmbedIE
  62. from .drtuber import DrTuberIE
  63. from .redtube import RedTubeIE
  64. from .tube8 import Tube8IE
  65. from .mofosex import MofosexEmbedIE
  66. from .spankwire import SpankwireIE
  67. from .youporn import YouPornIE
  68. from .vimeo import VimeoIE
  69. from .dailymotion import DailymotionIE
  70. from .dailymail import DailyMailIE
  71. from .onionstudios import OnionStudiosIE
  72. from .viewlift import ViewLiftEmbedIE
  73. from .mtv import MTVServicesEmbeddedIE
  74. from .pladform import PladformIE
  75. from .videomore import VideomoreIE
  76. from .webcaster import WebcasterFeedIE
  77. from .googledrive import GoogleDriveIE
  78. from .jwplatform import JWPlatformIE
  79. from .digiteka import DigitekaIE
  80. from .arkena import ArkenaIE
  81. from .instagram import InstagramIE
  82. from .liveleak import LiveLeakIE
  83. from .threeqsdn import ThreeQSDNIE
  84. from .theplatform import ThePlatformIE
  85. from .kaltura import KalturaIE
  86. from .eagleplatform import EaglePlatformIE
  87. from .facebook import FacebookIE
  88. from .soundcloud import SoundcloudEmbedIE
  89. from .tunein import TuneInBaseIE
  90. from .vbox7 import Vbox7IE
  91. from .dbtv import DBTVIE
  92. from .piksel import PikselIE
  93. from .videa import VideaIE
  94. from .twentymin import TwentyMinutenIE
  95. from .ustream import UstreamIE
  96. from .arte import ArteTVEmbedIE
  97. from .videopress import VideoPressIE
  98. from .rutube import RutubeIE
  99. from .limelight import LimelightBaseIE
  100. from .anvato import AnvatoIE
  101. from .washingtonpost import WashingtonPostIE
  102. from .wistia import WistiaIE
  103. from .mediaset import MediasetIE
  104. from .joj import JojIE
  105. from .megaphone import MegaphoneIE
  106. from .vzaar import VzaarIE
  107. from .channel9 import Channel9IE
  108. from .vshare import VShareIE
  109. from .mediasite import MediasiteIE
  110. from .springboardplatform import SpringboardPlatformIE
  111. from .yapfiles import YapFilesIE
  112. from .vice import ViceIE
  113. from .xfileshare import XFileShareIE
  114. from .cloudflarestream import CloudflareStreamIE
  115. from .peertube import PeerTubeIE
  116. from .teachable import TeachableIE
  117. from .indavideo import IndavideoEmbedIE
  118. from .apa import APAIE
  119. from .foxnews import FoxNewsIE
  120. from .viqeo import ViqeoIE
  121. from .expressen import ExpressenIE
  122. from .zype import ZypeIE
  123. from .odnoklassniki import OdnoklassnikiIE
  124. from .kinja import KinjaEmbedIE
  125. class GenericIE(InfoExtractor):
  126. IE_DESC = 'Generic downloader that works on some sites'
  127. _VALID_URL = r'.*'
  128. IE_NAME = 'generic'
  129. _TESTS = [
  130. # Direct link to a video
  131. {
  132. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  133. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  134. 'info_dict': {
  135. 'id': 'trailer',
  136. 'ext': 'mp4',
  137. 'title': 'trailer',
  138. 'upload_date': '20100513',
  139. }
  140. },
  141. # Direct link to media delivered compressed (until Accept-Encoding is *)
  142. {
  143. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  144. 'md5': '128c42e68b13950268b648275386fc74',
  145. 'info_dict': {
  146. 'id': 'FictionJunction-Parallel_Hearts',
  147. 'ext': 'flac',
  148. 'title': 'FictionJunction-Parallel_Hearts',
  149. 'upload_date': '20140522',
  150. },
  151. 'expected_warnings': [
  152. 'URL could be a direct video link, returning it as such.'
  153. ],
  154. 'skip': 'URL invalid',
  155. },
  156. # Direct download with broken HEAD
  157. {
  158. 'url': 'http://ai-radio.org:8000/radio.opus',
  159. 'info_dict': {
  160. 'id': 'radio',
  161. 'ext': 'opus',
  162. 'title': 'radio',
  163. },
  164. 'params': {
  165. 'skip_download': True, # infinite live stream
  166. },
  167. 'expected_warnings': [
  168. r'501.*Not Implemented',
  169. r'400.*Bad Request',
  170. ],
  171. },
  172. # Direct link with incorrect MIME type
  173. {
  174. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  175. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  176. 'info_dict': {
  177. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  178. 'id': '5_Lennart_Poettering_-_Systemd',
  179. 'ext': 'webm',
  180. 'title': '5_Lennart_Poettering_-_Systemd',
  181. 'upload_date': '20141120',
  182. },
  183. 'expected_warnings': [
  184. 'URL could be a direct video link, returning it as such.'
  185. ]
  186. },
  187. # RSS feed
  188. {
  189. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  190. 'info_dict': {
  191. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  192. 'title': 'Zero Punctuation',
  193. 'description': 're:.*groundbreaking video review series.*'
  194. },
  195. 'playlist_mincount': 11,
  196. },
  197. # RSS feed with enclosure
  198. {
  199. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  200. 'info_dict': {
  201. 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  202. 'title': 'MSNBC Rachel Maddow (video)',
  203. 'description': 're:.*her unique approach to storytelling.*',
  204. },
  205. 'playlist': [{
  206. 'info_dict': {
  207. 'ext': 'mov',
  208. 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
  209. 'title': 're:MSNBC Rachel Maddow',
  210. 'description': 're:.*her unique approach to storytelling.*',
  211. 'timestamp': int,
  212. 'upload_date': compat_str,
  213. 'duration': float,
  214. },
  215. }],
  216. },
  217. # RSS feed with enclosures and unsupported link URLs
  218. {
  219. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  220. 'info_dict': {
  221. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  222. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  223. 'title': 'Hello Internet',
  224. },
  225. 'playlist_mincount': 100,
  226. },
  227. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  228. {
  229. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  230. 'info_dict': {
  231. 'id': 'smil',
  232. 'ext': 'mp4',
  233. 'title': 'Automatics, robotics and biocybernetics',
  234. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  235. 'upload_date': '20130627',
  236. 'formats': 'mincount:16',
  237. 'subtitles': 'mincount:1',
  238. },
  239. 'params': {
  240. 'force_generic_extractor': True,
  241. 'skip_download': True,
  242. },
  243. },
  244. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  245. {
  246. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  247. 'info_dict': {
  248. 'id': 'hds',
  249. 'ext': 'flv',
  250. 'title': 'hds',
  251. 'formats': 'mincount:1',
  252. },
  253. 'params': {
  254. 'skip_download': True,
  255. },
  256. },
  257. # SMIL from https://www.restudy.dk/video/play/id/1637
  258. {
  259. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  260. 'info_dict': {
  261. 'id': 'video_1637',
  262. 'ext': 'flv',
  263. 'title': 'video_1637',
  264. 'formats': 'mincount:3',
  265. },
  266. 'params': {
  267. 'skip_download': True,
  268. },
  269. },
  270. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  271. {
  272. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  273. 'info_dict': {
  274. 'id': 'smil-service',
  275. 'ext': 'flv',
  276. 'title': 'smil-service',
  277. 'formats': 'mincount:1',
  278. },
  279. 'params': {
  280. 'skip_download': True,
  281. },
  282. },
  283. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  284. {
  285. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  286. 'info_dict': {
  287. 'id': '4719370',
  288. 'ext': 'mp4',
  289. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  290. 'formats': 'mincount:3',
  291. },
  292. 'params': {
  293. 'skip_download': True,
  294. },
  295. },
  296. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  297. {
  298. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  299. 'info_dict': {
  300. 'id': 'mZlp2ctYIUEB',
  301. 'ext': 'mp4',
  302. 'title': 'Tikibad ontruimd wegens brand',
  303. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  304. 'thumbnail': r're:^https?://.*\.jpg$',
  305. 'duration': 33,
  306. },
  307. 'params': {
  308. 'skip_download': True,
  309. },
  310. },
  311. # MPD from http://dash-mse-test.appspot.com/media.html
  312. {
  313. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  314. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  315. 'info_dict': {
  316. 'id': 'car-20120827-manifest',
  317. 'ext': 'mp4',
  318. 'title': 'car-20120827-manifest',
  319. 'formats': 'mincount:9',
  320. 'upload_date': '20130904',
  321. },
  322. 'params': {
  323. 'format': 'bestvideo',
  324. },
  325. },
  326. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  327. {
  328. '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',
  329. 'info_dict': {
  330. 'id': 'content',
  331. 'ext': 'mp4',
  332. 'title': 'content',
  333. 'formats': 'mincount:8',
  334. },
  335. 'params': {
  336. # m3u8 downloads
  337. 'skip_download': True,
  338. },
  339. 'skip': 'video gone',
  340. },
  341. # m3u8 served with Content-Type: text/plain
  342. {
  343. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  344. 'info_dict': {
  345. 'id': 'index',
  346. 'ext': 'mp4',
  347. 'title': 'index',
  348. 'upload_date': '20140720',
  349. 'formats': 'mincount:11',
  350. },
  351. 'params': {
  352. # m3u8 downloads
  353. 'skip_download': True,
  354. },
  355. 'skip': 'video gone',
  356. },
  357. # google redirect
  358. {
  359. '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',
  360. 'info_dict': {
  361. 'id': 'cmQHVoWB5FY',
  362. 'ext': 'mp4',
  363. 'upload_date': '20130224',
  364. 'uploader_id': 'TheVerge',
  365. 'description': r're:^Chris Ziegler takes a look at the\.*',
  366. 'uploader': 'The Verge',
  367. 'title': 'First Firefox OS phones side-by-side',
  368. },
  369. 'params': {
  370. 'skip_download': False,
  371. }
  372. },
  373. {
  374. # redirect in Refresh HTTP header
  375. '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',
  376. 'info_dict': {
  377. 'id': 'pO8h3EaFRdo',
  378. 'ext': 'mp4',
  379. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  380. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  381. 'upload_date': '20150917',
  382. 'uploader_id': 'brtvofficial',
  383. 'uploader': 'Boiler Room',
  384. },
  385. 'params': {
  386. 'skip_download': False,
  387. },
  388. },
  389. {
  390. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  391. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  392. 'info_dict': {
  393. 'id': '13601338388002',
  394. 'ext': 'mp4',
  395. 'uploader': 'www.hodiho.fr',
  396. 'title': 'R\u00e9gis plante sa Jeep',
  397. }
  398. },
  399. # bandcamp page with custom domain
  400. {
  401. 'add_ie': ['Bandcamp'],
  402. 'url': 'http://bronyrock.com/track/the-pony-mash',
  403. 'info_dict': {
  404. 'id': '3235767654',
  405. 'ext': 'mp3',
  406. 'title': 'The Pony Mash',
  407. 'uploader': 'M_Pallante',
  408. },
  409. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  410. },
  411. {
  412. # embedded brightcove video
  413. # it also tests brightcove videos that need to set the 'Referer'
  414. # in the http requests
  415. 'add_ie': ['BrightcoveLegacy'],
  416. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  417. 'info_dict': {
  418. 'id': '2765128793001',
  419. 'ext': 'mp4',
  420. 'title': 'Le cours de bourse : l’analyse technique',
  421. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  422. 'uploader': 'BFM BUSINESS',
  423. },
  424. 'params': {
  425. 'skip_download': True,
  426. },
  427. },
  428. {
  429. # embedded with itemprop embedURL and video id spelled as `idVideo`
  430. 'add_id': ['BrightcoveLegacy'],
  431. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  432. 'info_dict': {
  433. 'id': '5255628253001',
  434. 'ext': 'mp4',
  435. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  436. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  437. 'uploader': 'BFM BUSINESS',
  438. 'uploader_id': '876450612001',
  439. 'timestamp': 1482255315,
  440. 'upload_date': '20161220',
  441. },
  442. 'params': {
  443. 'skip_download': True,
  444. },
  445. },
  446. {
  447. # https://github.com/ytdl-org/youtube-dl/issues/2253
  448. 'url': 'http://bcove.me/i6nfkrc3',
  449. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  450. 'info_dict': {
  451. 'id': '3101154703001',
  452. 'ext': 'mp4',
  453. 'title': 'Still no power',
  454. 'uploader': 'thestar.com',
  455. '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.',
  456. },
  457. 'add_ie': ['BrightcoveLegacy'],
  458. 'skip': 'video gone',
  459. },
  460. {
  461. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  462. 'md5': 'fb973ecf6e4a78a67453647444222983',
  463. 'info_dict': {
  464. 'id': '3414141473001',
  465. 'ext': 'mp4',
  466. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  467. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  468. 'uploader': 'Championat',
  469. },
  470. },
  471. {
  472. # https://github.com/ytdl-org/youtube-dl/issues/3541
  473. 'add_ie': ['BrightcoveLegacy'],
  474. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  475. 'info_dict': {
  476. 'id': '3866516442001',
  477. 'ext': 'mp4',
  478. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  479. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  480. 'uploader': 'SBS Broadcasting',
  481. },
  482. 'skip': 'Restricted to Netherlands',
  483. 'params': {
  484. 'skip_download': True, # m3u8 download
  485. },
  486. },
  487. {
  488. # Brightcove video in <iframe>
  489. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  490. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  491. 'info_dict': {
  492. 'id': '5360463607001',
  493. 'ext': 'mp4',
  494. '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',
  495. '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。',
  496. 'uploader': 'United Nations',
  497. 'uploader_id': '1362235914001',
  498. 'timestamp': 1489593889,
  499. 'upload_date': '20170315',
  500. },
  501. 'add_ie': ['BrightcoveLegacy'],
  502. },
  503. {
  504. # Brightcove with alternative playerID key
  505. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  506. 'info_dict': {
  507. 'id': 'nmeth.2062_SV1',
  508. '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',
  509. },
  510. 'playlist': [{
  511. 'info_dict': {
  512. 'id': '2228375078001',
  513. 'ext': 'mp4',
  514. 'title': 'nmeth.2062-sv1',
  515. 'description': 'nmeth.2062-sv1',
  516. 'timestamp': 1363357591,
  517. 'upload_date': '20130315',
  518. 'uploader': 'Nature Publishing Group',
  519. 'uploader_id': '1964492299001',
  520. },
  521. }],
  522. },
  523. {
  524. # Brightcove with UUID in videoPlayer
  525. 'url': 'http://www8.hp.com/cn/zh/home.html',
  526. 'info_dict': {
  527. 'id': '5255815316001',
  528. 'ext': 'mp4',
  529. 'title': 'Sprocket Video - China',
  530. 'description': 'Sprocket Video - China',
  531. 'uploader': 'HP-Video Gallery',
  532. 'timestamp': 1482263210,
  533. 'upload_date': '20161220',
  534. 'uploader_id': '1107601872001',
  535. },
  536. 'params': {
  537. 'skip_download': True, # m3u8 download
  538. },
  539. 'skip': 'video rotates...weekly?',
  540. },
  541. {
  542. # Brightcove:new type [2].
  543. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  544. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  545. 'info_dict': {
  546. 'id': '5348741021001',
  547. 'ext': 'mp4',
  548. 'upload_date': '20170306',
  549. 'uploader_id': '4191638492001',
  550. 'timestamp': 1488769918,
  551. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  552. },
  553. },
  554. {
  555. # Alternative brightcove <video> attributes
  556. '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/',
  557. 'info_dict': {
  558. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  559. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  560. },
  561. 'playlist': [{
  562. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  563. 'info_dict': {
  564. 'id': '5311302538001',
  565. 'ext': 'mp4',
  566. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  567. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  568. 'timestamp': 1486321708,
  569. 'upload_date': '20170205',
  570. 'uploader_id': '800000640001',
  571. },
  572. 'only_matching': True,
  573. }],
  574. },
  575. {
  576. # Brightcove with UUID in videoPlayer
  577. 'url': 'http://www8.hp.com/cn/zh/home.html',
  578. 'info_dict': {
  579. 'id': '5255815316001',
  580. 'ext': 'mp4',
  581. 'title': 'Sprocket Video - China',
  582. 'description': 'Sprocket Video - China',
  583. 'uploader': 'HP-Video Gallery',
  584. 'timestamp': 1482263210,
  585. 'upload_date': '20161220',
  586. 'uploader_id': '1107601872001',
  587. },
  588. 'params': {
  589. 'skip_download': True, # m3u8 download
  590. },
  591. },
  592. # ooyala video
  593. {
  594. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  595. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  596. 'info_dict': {
  597. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  598. 'ext': 'mp4',
  599. 'title': '2cc213299525360.mov', # that's what we get
  600. 'duration': 238.231,
  601. },
  602. 'add_ie': ['Ooyala'],
  603. },
  604. {
  605. # ooyala video embedded with http://player.ooyala.com/iframe.js
  606. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  607. 'info_dict': {
  608. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  609. 'ext': 'mp4',
  610. 'title': '"Steve Jobs: Man in the Machine" trailer',
  611. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  612. 'duration': 135.427,
  613. },
  614. 'params': {
  615. 'skip_download': True,
  616. },
  617. 'skip': 'movie expired',
  618. },
  619. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  620. {
  621. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  622. 'info_dict': {
  623. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  624. 'ext': 'mp4',
  625. 'title': 'Steampunk Fest Comes to Honesdale',
  626. 'duration': 43.276,
  627. },
  628. 'params': {
  629. 'skip_download': True,
  630. }
  631. },
  632. # embed.ly video
  633. {
  634. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  635. 'info_dict': {
  636. 'id': '9ODmcdjQcHQ',
  637. 'ext': 'mp4',
  638. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  639. 'upload_date': '20140225',
  640. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  641. 'uploader': 'Tested',
  642. 'uploader_id': 'testedcom',
  643. },
  644. # No need to test YoutubeIE here
  645. 'params': {
  646. 'skip_download': True,
  647. },
  648. },
  649. # funnyordie embed
  650. {
  651. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  652. 'info_dict': {
  653. 'id': '18e820ec3f',
  654. 'ext': 'mp4',
  655. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  656. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  657. },
  658. # HEAD requests lead to endless 301, while GET is OK
  659. 'expected_warnings': ['301'],
  660. },
  661. # RUTV embed
  662. {
  663. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  664. 'info_dict': {
  665. 'id': '776940',
  666. 'ext': 'mp4',
  667. 'title': 'Охотское море стало целиком российским',
  668. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  669. },
  670. 'params': {
  671. # m3u8 download
  672. 'skip_download': True,
  673. },
  674. },
  675. # TVC embed
  676. {
  677. '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/',
  678. 'info_dict': {
  679. 'id': '55304',
  680. 'ext': 'mp4',
  681. 'title': 'Дошкольное воспитание',
  682. },
  683. },
  684. # SportBox embed
  685. {
  686. 'url': 'http://www.vestifinance.ru/articles/25753',
  687. 'info_dict': {
  688. 'id': '25753',
  689. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  690. },
  691. 'playlist': [{
  692. 'info_dict': {
  693. 'id': '370908',
  694. 'title': 'Госзаказ. День 3',
  695. 'ext': 'mp4',
  696. }
  697. }, {
  698. 'info_dict': {
  699. 'id': '370905',
  700. 'title': 'Госзаказ. День 2',
  701. 'ext': 'mp4',
  702. }
  703. }, {
  704. 'info_dict': {
  705. 'id': '370902',
  706. 'title': 'Госзаказ. День 1',
  707. 'ext': 'mp4',
  708. }
  709. }],
  710. 'params': {
  711. # m3u8 download
  712. 'skip_download': True,
  713. },
  714. },
  715. # Myvi.ru embed
  716. {
  717. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  718. 'info_dict': {
  719. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  720. 'ext': 'mp4',
  721. 'title': 'Ужастики, русский трейлер (2015)',
  722. 'thumbnail': r're:^https?://.*\.jpg$',
  723. 'duration': 153,
  724. }
  725. },
  726. # XHamster embed
  727. {
  728. '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',
  729. 'info_dict': {
  730. 'id': 'showthread',
  731. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  732. },
  733. 'playlist_mincount': 7,
  734. # This forum does not allow <iframe> syntaxes anymore
  735. # Now HTML tags are displayed as-is
  736. 'skip': 'No videos on this page',
  737. },
  738. # Embedded TED video
  739. {
  740. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  741. 'md5': '65fdff94098e4a607385a60c5177c638',
  742. 'info_dict': {
  743. 'id': '1969',
  744. 'ext': 'mp4',
  745. 'title': 'Hidden miracles of the natural world',
  746. 'uploader': 'Louie Schwartzberg',
  747. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  748. }
  749. },
  750. # nowvideo embed hidden behind percent encoding
  751. {
  752. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  753. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  754. 'info_dict': {
  755. 'id': '06e53103ca9aa',
  756. 'ext': 'flv',
  757. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  758. 'description': 'No description',
  759. },
  760. },
  761. # arte embed
  762. {
  763. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  764. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  765. 'info_dict': {
  766. 'id': '048195-004_PLUS7-F',
  767. 'ext': 'flv',
  768. 'title': 'X:enius',
  769. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  770. 'upload_date': '20140320',
  771. },
  772. 'params': {
  773. 'skip_download': 'Requires rtmpdump'
  774. },
  775. 'skip': 'video gone',
  776. },
  777. # francetv embed
  778. {
  779. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  780. 'info_dict': {
  781. 'id': 'EV_30231',
  782. 'ext': 'mp4',
  783. 'title': 'Alcaline, le concert avec Calogero',
  784. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  785. 'upload_date': '20150226',
  786. 'timestamp': 1424989860,
  787. 'duration': 5400,
  788. },
  789. 'params': {
  790. # m3u8 downloads
  791. 'skip_download': True,
  792. },
  793. 'expected_warnings': [
  794. 'Forbidden'
  795. ]
  796. },
  797. # Condé Nast embed
  798. {
  799. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  800. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  801. 'info_dict': {
  802. 'id': '53501be369702d3275860000',
  803. 'ext': 'mp4',
  804. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  805. }
  806. },
  807. # Dailymotion embed
  808. {
  809. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  810. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  811. 'info_dict': {
  812. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  813. 'ext': 'mp4',
  814. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  815. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  816. 'uploader': 'Spi0n',
  817. 'uploader_id': 'xgditw',
  818. 'upload_date': '20140425',
  819. 'timestamp': 1398441542,
  820. },
  821. 'add_ie': ['Dailymotion'],
  822. },
  823. # DailyMail embed
  824. {
  825. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  826. 'info_dict': {
  827. 'id': '1495629',
  828. 'ext': 'mp4',
  829. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  830. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  831. },
  832. 'add_ie': ['DailyMail'],
  833. 'params': {
  834. 'skip_download': True,
  835. },
  836. },
  837. # YouTube embed
  838. {
  839. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  840. 'info_dict': {
  841. 'id': 'FXRb4ykk4S0',
  842. 'ext': 'mp4',
  843. 'title': 'The NBL Auction 2014',
  844. 'uploader': 'BADMINTON England',
  845. 'uploader_id': 'BADMINTONEvents',
  846. 'upload_date': '20140603',
  847. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  848. },
  849. 'add_ie': ['Youtube'],
  850. 'params': {
  851. 'skip_download': True,
  852. }
  853. },
  854. # MTVServices embed
  855. {
  856. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  857. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  858. 'info_dict': {
  859. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  860. 'ext': 'mp4',
  861. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  862. 'description': 'Two valets share their love for movie star Liam Neesons.',
  863. 'timestamp': 1349922600,
  864. 'upload_date': '20121011',
  865. },
  866. },
  867. # YouTube embed via <data-embed-url="">
  868. {
  869. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  870. 'info_dict': {
  871. 'id': '4vAffPZIT44',
  872. 'ext': 'mp4',
  873. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  874. 'uploader': 'Gameloft',
  875. 'uploader_id': 'gameloft',
  876. 'upload_date': '20140828',
  877. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  878. },
  879. 'params': {
  880. 'skip_download': True,
  881. }
  882. },
  883. # YouTube <object> embed
  884. {
  885. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  886. 'md5': '516718101ec834f74318df76259fb3cc',
  887. 'info_dict': {
  888. 'id': 'msN87y-iEx0',
  889. 'ext': 'webm',
  890. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  891. 'upload_date': '20080526',
  892. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  893. 'uploader': 'Christopher Sykes',
  894. 'uploader_id': 'ChristopherJSykes',
  895. },
  896. 'add_ie': ['Youtube'],
  897. },
  898. # Camtasia studio
  899. {
  900. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  901. 'playlist': [{
  902. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  903. 'info_dict': {
  904. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  905. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  906. 'ext': 'flv',
  907. 'duration': 2235.90,
  908. }
  909. }, {
  910. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  911. 'info_dict': {
  912. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  913. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  914. 'ext': 'flv',
  915. 'duration': 2235.93,
  916. }
  917. }],
  918. 'info_dict': {
  919. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  920. }
  921. },
  922. # Flowplayer
  923. {
  924. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  925. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  926. 'info_dict': {
  927. 'id': '5123ea6d5e5a7',
  928. 'ext': 'mp4',
  929. 'age_limit': 18,
  930. 'uploader': 'www.handjobhub.com',
  931. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  932. }
  933. },
  934. # Multiple brightcove videos
  935. # https://github.com/ytdl-org/youtube-dl/issues/2283
  936. {
  937. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  938. 'info_dict': {
  939. 'id': 'always-never',
  940. 'title': 'Always / Never - The New Yorker',
  941. },
  942. 'playlist_count': 3,
  943. 'params': {
  944. 'extract_flat': False,
  945. 'skip_download': True,
  946. }
  947. },
  948. # MLB embed
  949. {
  950. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  951. 'md5': '96f09a37e44da40dd083e12d9a683327',
  952. 'info_dict': {
  953. 'id': '33322633',
  954. 'ext': 'mp4',
  955. 'title': 'Ump changes call to ball',
  956. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  957. 'duration': 48,
  958. 'timestamp': 1401537900,
  959. 'upload_date': '20140531',
  960. 'thumbnail': r're:^https?://.*\.jpg$',
  961. },
  962. },
  963. # Wistia embed
  964. {
  965. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  966. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  967. 'info_dict': {
  968. 'id': '6e2wtrbdaf',
  969. 'ext': 'mov',
  970. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  971. 'description': 'a Paywall Videos video from Remilon',
  972. 'duration': 644.072,
  973. 'uploader': 'study.com',
  974. 'timestamp': 1459678540,
  975. 'upload_date': '20160403',
  976. 'filesize': 24687186,
  977. },
  978. },
  979. {
  980. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  981. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  982. 'info_dict': {
  983. 'id': 'uxjb0lwrcz',
  984. 'ext': 'mp4',
  985. 'title': 'Conversation about Hexagonal Rails Part 1',
  986. 'description': 'a Martin Fowler video from ThoughtWorks',
  987. 'duration': 1715.0,
  988. 'uploader': 'thoughtworks.wistia.com',
  989. 'timestamp': 1401832161,
  990. 'upload_date': '20140603',
  991. },
  992. },
  993. # Wistia standard embed (async)
  994. {
  995. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  996. 'info_dict': {
  997. 'id': '807fafadvk',
  998. 'ext': 'mp4',
  999. 'title': 'Drip Brennan Dunn Workshop',
  1000. 'description': 'a JV Webinars video from getdrip-1',
  1001. 'duration': 4986.95,
  1002. 'timestamp': 1463607249,
  1003. 'upload_date': '20160518',
  1004. },
  1005. 'params': {
  1006. 'skip_download': True,
  1007. }
  1008. },
  1009. # Soundcloud embed
  1010. {
  1011. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  1012. 'info_dict': {
  1013. 'id': '174391317',
  1014. 'ext': 'mp3',
  1015. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  1016. 'uploader': 'Sophos Security',
  1017. 'title': 'Chet Chat 171 - Oct 29, 2014',
  1018. 'upload_date': '20141029',
  1019. }
  1020. },
  1021. # Soundcloud multiple embeds
  1022. {
  1023. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1024. 'info_dict': {
  1025. 'id': '52809',
  1026. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1027. },
  1028. 'playlist_mincount': 7,
  1029. },
  1030. # TuneIn station embed
  1031. {
  1032. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1033. 'info_dict': {
  1034. 'id': '204146',
  1035. 'ext': 'mp3',
  1036. 'title': 'CNRV',
  1037. 'location': 'Paris, France',
  1038. 'is_live': True,
  1039. },
  1040. 'params': {
  1041. # Live stream
  1042. 'skip_download': True,
  1043. },
  1044. },
  1045. # Livestream embed
  1046. {
  1047. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1048. 'info_dict': {
  1049. 'id': '67864563',
  1050. 'ext': 'flv',
  1051. 'upload_date': '20141112',
  1052. 'title': 'Rosetta #CometLanding webcast HL 10',
  1053. }
  1054. },
  1055. # Another Livestream embed, without 'new.' in URL
  1056. {
  1057. 'url': 'https://www.freespeech.org/',
  1058. 'info_dict': {
  1059. 'id': '123537347',
  1060. 'ext': 'mp4',
  1061. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1062. },
  1063. 'params': {
  1064. # Live stream
  1065. 'skip_download': True,
  1066. },
  1067. },
  1068. # LazyYT
  1069. {
  1070. 'url': 'https://skiplagged.com/',
  1071. 'info_dict': {
  1072. 'id': 'skiplagged',
  1073. 'title': 'Skiplagged: The smart way to find cheap flights',
  1074. },
  1075. 'playlist_mincount': 1,
  1076. 'add_ie': ['Youtube'],
  1077. },
  1078. # Cinchcast embed
  1079. {
  1080. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1081. 'info_dict': {
  1082. 'id': '7141703',
  1083. 'ext': 'mp3',
  1084. 'upload_date': '20141126',
  1085. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1086. }
  1087. },
  1088. # Cinerama player
  1089. {
  1090. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1091. 'info_dict': {
  1092. 'id': '730m_DandD_1901_512k',
  1093. 'ext': 'mp4',
  1094. 'uploader': 'www.abc.net.au',
  1095. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1096. }
  1097. },
  1098. # embedded viddler video
  1099. {
  1100. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1101. 'info_dict': {
  1102. 'id': '4d03aad9',
  1103. 'ext': 'mp4',
  1104. 'uploader': 'deadspin',
  1105. 'title': 'WALL-TO-GORTAT',
  1106. 'timestamp': 1422285291,
  1107. 'upload_date': '20150126',
  1108. },
  1109. 'add_ie': ['Viddler'],
  1110. },
  1111. # Libsyn embed
  1112. {
  1113. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1114. 'info_dict': {
  1115. 'id': '3377616',
  1116. 'ext': 'mp3',
  1117. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1118. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1119. 'upload_date': '20150220',
  1120. },
  1121. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1122. },
  1123. # jwplayer YouTube
  1124. {
  1125. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1126. 'info_dict': {
  1127. 'id': 'Mrj4DVp2zeA',
  1128. 'ext': 'mp4',
  1129. 'upload_date': '20150212',
  1130. 'uploader': 'The National Archives UK',
  1131. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1132. 'uploader_id': 'NationalArchives08',
  1133. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1134. },
  1135. },
  1136. # jwplayer rtmp
  1137. {
  1138. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1139. 'info_dict': {
  1140. 'id': 'live',
  1141. 'ext': 'flv',
  1142. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1143. 'uploader': 'www.suffolk.edu',
  1144. },
  1145. 'params': {
  1146. 'skip_download': True,
  1147. },
  1148. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1149. },
  1150. # Complex jwplayer
  1151. {
  1152. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1153. 'info_dict': {
  1154. 'id': 'videos',
  1155. 'ext': 'mp4',
  1156. 'title': 'king machine trailer 1',
  1157. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1158. 'thumbnail': r're:^https?://.*\.jpg$',
  1159. },
  1160. },
  1161. {
  1162. # JWPlayer config passed as variable
  1163. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1164. 'info_dict': {
  1165. 'id': '3326530_hq',
  1166. 'ext': 'mp4',
  1167. 'title': 'ARIELE | Tube Cup',
  1168. 'uploader': 'www.txxx.com',
  1169. 'age_limit': 18,
  1170. },
  1171. 'params': {
  1172. 'skip_download': True,
  1173. }
  1174. },
  1175. {
  1176. # JWPlatform iframe
  1177. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1178. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1179. 'info_dict': {
  1180. 'id': 'O0c5JcKT',
  1181. 'ext': 'mp4',
  1182. 'upload_date': '20171122',
  1183. 'timestamp': 1511366290,
  1184. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1185. },
  1186. 'add_ie': [JWPlatformIE.ie_key()],
  1187. },
  1188. {
  1189. # Video.js embed, multiple formats
  1190. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1191. 'info_dict': {
  1192. 'id': 'yygqldloqIk',
  1193. 'ext': 'mp4',
  1194. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1195. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1196. 'upload_date': '20130314',
  1197. 'uploader': 'PROстое3D',
  1198. 'uploader_id': 'PROstoe3D',
  1199. },
  1200. 'params': {
  1201. 'skip_download': True,
  1202. },
  1203. },
  1204. {
  1205. # Video.js embed, single format
  1206. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1207. 'info_dict': {
  1208. 'id': 'watch',
  1209. 'ext': 'mp4',
  1210. 'title': 'Step 1 - Good Foundation',
  1211. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1212. },
  1213. 'params': {
  1214. 'skip_download': True,
  1215. },
  1216. },
  1217. # rtl.nl embed
  1218. {
  1219. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1220. 'playlist_mincount': 5,
  1221. 'info_dict': {
  1222. 'id': 'aanslagen-kopenhagen',
  1223. 'title': 'Aanslagen Kopenhagen',
  1224. }
  1225. },
  1226. # Zapiks embed
  1227. {
  1228. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1229. 'info_dict': {
  1230. 'id': '118046',
  1231. 'ext': 'mp4',
  1232. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1233. }
  1234. },
  1235. # Kaltura embed (different embed code)
  1236. {
  1237. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1238. 'info_dict': {
  1239. 'id': '1_a52wc67y',
  1240. 'ext': 'flv',
  1241. 'upload_date': '20150127',
  1242. 'uploader_id': 'PremierMedia',
  1243. 'timestamp': int,
  1244. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1245. },
  1246. },
  1247. # Kaltura embed with single quotes
  1248. {
  1249. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1250. 'info_dict': {
  1251. 'id': '0_izeg5utt',
  1252. 'ext': 'mp4',
  1253. 'title': '35871',
  1254. 'timestamp': 1355743100,
  1255. 'upload_date': '20121217',
  1256. 'uploader_id': 'cplapp@learn360.com',
  1257. },
  1258. 'add_ie': ['Kaltura'],
  1259. },
  1260. {
  1261. # Kaltura embedded via quoted entry_id
  1262. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1263. 'info_dict': {
  1264. 'id': '0_utuok90b',
  1265. 'ext': 'mp4',
  1266. 'title': '06_matthew_brender_raj_dutt',
  1267. 'timestamp': 1466638791,
  1268. 'upload_date': '20160622',
  1269. },
  1270. 'add_ie': ['Kaltura'],
  1271. 'expected_warnings': [
  1272. 'Could not send HEAD request'
  1273. ],
  1274. 'params': {
  1275. 'skip_download': True,
  1276. }
  1277. },
  1278. {
  1279. # Kaltura embedded, some fileExt broken (#11480)
  1280. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1281. 'info_dict': {
  1282. 'id': '1_sgtvehim',
  1283. 'ext': 'mp4',
  1284. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1285. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1286. 'timestamp': 1321158993,
  1287. 'upload_date': '20111113',
  1288. 'uploader_id': 'kps1',
  1289. },
  1290. 'add_ie': ['Kaltura'],
  1291. },
  1292. {
  1293. # Kaltura iframe embed
  1294. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1295. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1296. 'info_dict': {
  1297. 'id': '0_f2cfbpwy',
  1298. 'ext': 'mp4',
  1299. 'title': 'I. M. Pei: A Centennial Celebration',
  1300. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1301. 'upload_date': '20170403',
  1302. 'uploader_id': 'batchUser',
  1303. 'timestamp': 1491232186,
  1304. },
  1305. 'add_ie': ['Kaltura'],
  1306. },
  1307. {
  1308. # Kaltura iframe embed, more sophisticated
  1309. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1310. 'info_dict': {
  1311. 'id': '1_9gzouybz',
  1312. 'ext': 'mp4',
  1313. 'title': 'lecture-05sep2017',
  1314. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1315. 'upload_date': '20170913',
  1316. 'uploader_id': 'eps2',
  1317. 'timestamp': 1505340777,
  1318. },
  1319. 'params': {
  1320. 'skip_download': True,
  1321. },
  1322. 'add_ie': ['Kaltura'],
  1323. },
  1324. {
  1325. # meta twitter:player
  1326. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1327. 'info_dict': {
  1328. 'id': '0_01b42zps',
  1329. 'ext': 'mp4',
  1330. 'title': 'Main Twerk (Video)',
  1331. 'upload_date': '20171208',
  1332. 'uploader_id': 'sebastian.salinas@thechive.com',
  1333. 'timestamp': 1512713057,
  1334. },
  1335. 'params': {
  1336. 'skip_download': True,
  1337. },
  1338. 'add_ie': ['Kaltura'],
  1339. },
  1340. # referrer protected EaglePlatform embed
  1341. {
  1342. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1343. 'info_dict': {
  1344. 'id': '582306',
  1345. 'ext': 'mp4',
  1346. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1347. 'thumbnail': r're:^https?://.*\.jpg$',
  1348. 'duration': 3382,
  1349. 'view_count': int,
  1350. },
  1351. 'params': {
  1352. 'skip_download': True,
  1353. },
  1354. },
  1355. # ClipYou (EaglePlatform) embed (custom URL)
  1356. {
  1357. 'url': 'http://muz-tv.ru/play/7129/',
  1358. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1359. 'info_dict': {
  1360. 'id': '12820',
  1361. 'ext': 'mp4',
  1362. 'title': "'O Sole Mio",
  1363. 'thumbnail': r're:^https?://.*\.jpg$',
  1364. 'duration': 216,
  1365. 'view_count': int,
  1366. },
  1367. 'params': {
  1368. 'skip_download': True,
  1369. },
  1370. 'skip': 'This video is unavailable.',
  1371. },
  1372. # Pladform embed
  1373. {
  1374. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1375. 'info_dict': {
  1376. 'id': '100183293',
  1377. 'ext': 'mp4',
  1378. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1379. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1380. 'thumbnail': r're:^https?://.*\.jpg$',
  1381. 'duration': 694,
  1382. 'age_limit': 0,
  1383. },
  1384. 'skip': 'HTTP Error 404: Not Found',
  1385. },
  1386. # Playwire embed
  1387. {
  1388. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1389. 'info_dict': {
  1390. 'id': '3519514',
  1391. 'ext': 'mp4',
  1392. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1393. 'thumbnail': r're:^https?://.*\.png$',
  1394. 'duration': 45.115,
  1395. },
  1396. },
  1397. # 5min embed
  1398. {
  1399. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1400. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1401. 'info_dict': {
  1402. 'id': '518726732',
  1403. 'ext': 'mp4',
  1404. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1405. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1406. 'timestamp': 1427237531,
  1407. 'uploader': 'Crunch Report',
  1408. 'upload_date': '20150324',
  1409. },
  1410. 'params': {
  1411. # m3u8 download
  1412. 'skip_download': True,
  1413. },
  1414. },
  1415. # Crooks and Liars embed
  1416. {
  1417. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1418. 'info_dict': {
  1419. 'id': '8RUoRhRi',
  1420. 'ext': 'mp4',
  1421. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1422. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1423. 'timestamp': 1428207000,
  1424. 'upload_date': '20150405',
  1425. 'uploader': 'Heather',
  1426. },
  1427. },
  1428. # Crooks and Liars external embed
  1429. {
  1430. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1431. 'info_dict': {
  1432. 'id': 'MTE3MjUtMzQ2MzA',
  1433. 'ext': 'mp4',
  1434. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1435. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1436. 'timestamp': 1265032391,
  1437. 'upload_date': '20100201',
  1438. 'uploader': 'Heather',
  1439. },
  1440. },
  1441. # NBC Sports vplayer embed
  1442. {
  1443. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1444. 'info_dict': {
  1445. 'id': 'ln7x1qSThw4k',
  1446. 'ext': 'flv',
  1447. 'title': "PFT Live: New leader in the 'new-look' defense",
  1448. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1449. 'uploader': 'NBCU-SPORTS',
  1450. 'upload_date': '20140107',
  1451. 'timestamp': 1389118457,
  1452. },
  1453. 'skip': 'Invalid Page URL',
  1454. },
  1455. # NBC News embed
  1456. {
  1457. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1458. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1459. 'info_dict': {
  1460. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1461. 'ext': 'mp4',
  1462. 'title': 'David Letterman: A Preview',
  1463. '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.',
  1464. 'upload_date': '20160609',
  1465. 'timestamp': 1465431544,
  1466. 'uploader': 'NBCU-NEWS',
  1467. },
  1468. },
  1469. # UDN embed
  1470. {
  1471. 'url': 'https://video.udn.com/news/300346',
  1472. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1473. 'info_dict': {
  1474. 'id': '300346',
  1475. 'ext': 'mp4',
  1476. 'title': '中一中男師變性 全校師生力挺',
  1477. 'thumbnail': r're:^https?://.*\.jpg$',
  1478. },
  1479. 'params': {
  1480. # m3u8 download
  1481. 'skip_download': True,
  1482. },
  1483. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1484. },
  1485. # Brightcove URL in single quotes
  1486. {
  1487. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1488. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1489. 'info_dict': {
  1490. 'id': '4255764656001',
  1491. 'ext': 'mp4',
  1492. 'title': 'SN Presents: Russell Martin, World Citizen',
  1493. '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.',
  1494. 'uploader': 'Rogers Sportsnet',
  1495. 'uploader_id': '1704050871',
  1496. 'upload_date': '20150525',
  1497. 'timestamp': 1432570283,
  1498. },
  1499. },
  1500. # Kinja embed
  1501. {
  1502. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1503. 'info_dict': {
  1504. 'id': '106351',
  1505. 'ext': 'mp4',
  1506. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1507. 'description': 'Migrated from OnionStudios',
  1508. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1509. 'uploader': 'clickhole',
  1510. 'upload_date': '20150527',
  1511. 'timestamp': 1432744860,
  1512. }
  1513. },
  1514. # SnagFilms embed
  1515. {
  1516. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1517. 'info_dict': {
  1518. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1519. 'ext': 'mp4',
  1520. 'title': '#whilewewatch',
  1521. }
  1522. },
  1523. # AdobeTVVideo embed
  1524. {
  1525. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1526. 'md5': '43662b577c018ad707a63766462b1e87',
  1527. 'info_dict': {
  1528. 'id': '2456',
  1529. 'ext': 'mp4',
  1530. 'title': 'New experience with Acrobat DC',
  1531. 'description': 'New experience with Acrobat DC',
  1532. 'duration': 248.667,
  1533. },
  1534. },
  1535. # BrightcoveInPageEmbed embed
  1536. {
  1537. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1538. 'info_dict': {
  1539. 'id': '4238694884001',
  1540. 'ext': 'flv',
  1541. 'title': 'Tabletop: Dread, Last Thoughts',
  1542. 'description': 'Tabletop: Dread, Last Thoughts',
  1543. 'duration': 51690,
  1544. },
  1545. },
  1546. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1547. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1548. {
  1549. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1550. 'info_dict': {
  1551. 'id': '4785848093001',
  1552. 'ext': 'mp4',
  1553. 'title': 'The Cardinal Pell Interview',
  1554. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1555. 'uploader': 'GlobeCast Australia - GlobeStream',
  1556. 'uploader_id': '2733773828001',
  1557. 'upload_date': '20160304',
  1558. 'timestamp': 1457083087,
  1559. },
  1560. 'params': {
  1561. # m3u8 downloads
  1562. 'skip_download': True,
  1563. },
  1564. },
  1565. {
  1566. # Brightcove embed with whitespace around attribute names
  1567. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1568. 'info_dict': {
  1569. 'id': '3167554373001',
  1570. 'ext': 'mp4',
  1571. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1572. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1573. 'uploader_id': '1079349493',
  1574. 'upload_date': '20140207',
  1575. 'timestamp': 1391810548,
  1576. },
  1577. 'params': {
  1578. 'skip_download': True,
  1579. },
  1580. },
  1581. # Another form of arte.tv embed
  1582. {
  1583. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1584. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1585. 'info_dict': {
  1586. 'id': '030273-562_PLUS7-F',
  1587. 'ext': 'mp4',
  1588. 'title': 'ARTE Reportage - Nulle part, en France',
  1589. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1590. 'upload_date': '20160409',
  1591. },
  1592. },
  1593. # LiveLeak embed
  1594. {
  1595. 'url': 'http://www.wykop.pl/link/3088787/',
  1596. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1597. 'info_dict': {
  1598. 'id': '874_1459135191',
  1599. 'ext': 'mp4',
  1600. 'title': 'Man shows poor quality of new apartment building',
  1601. 'description': 'The wall is like a sand pile.',
  1602. 'uploader': 'Lake8737',
  1603. },
  1604. 'add_ie': [LiveLeakIE.ie_key()],
  1605. },
  1606. # Another LiveLeak embed pattern (#13336)
  1607. {
  1608. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1609. 'info_dict': {
  1610. 'id': '2eb_1496309988',
  1611. 'ext': 'mp4',
  1612. 'title': 'Thief robs place where everyone was armed',
  1613. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1614. 'uploader': 'brazilwtf',
  1615. },
  1616. 'add_ie': [LiveLeakIE.ie_key()],
  1617. },
  1618. # Duplicated embedded video URLs
  1619. {
  1620. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1621. 'info_dict': {
  1622. 'id': '149298443_480_16c25b74_2',
  1623. 'ext': 'mp4',
  1624. 'title': 'vs. Blue Orange Spring Game',
  1625. 'uploader': 'www.hudl.com',
  1626. },
  1627. },
  1628. # twitter:player:stream embed
  1629. {
  1630. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1631. 'info_dict': {
  1632. 'id': 'master',
  1633. 'ext': 'mp4',
  1634. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1635. 'uploader': 'www.rtl.be',
  1636. },
  1637. 'params': {
  1638. # m3u8 downloads
  1639. 'skip_download': True,
  1640. },
  1641. },
  1642. # twitter:player embed
  1643. {
  1644. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1645. 'md5': 'a3e0df96369831de324f0778e126653c',
  1646. 'info_dict': {
  1647. 'id': '4909620399001',
  1648. 'ext': 'mp4',
  1649. 'title': 'What Do Black Holes Sound Like?',
  1650. 'description': 'what do black holes sound like',
  1651. 'upload_date': '20160524',
  1652. 'uploader_id': '29913724001',
  1653. 'timestamp': 1464107587,
  1654. 'uploader': 'TheAtlantic',
  1655. },
  1656. 'add_ie': ['BrightcoveLegacy'],
  1657. },
  1658. # Facebook <iframe> embed
  1659. {
  1660. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1661. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1662. 'info_dict': {
  1663. 'id': '599637780109885',
  1664. 'ext': 'mp4',
  1665. 'title': 'Facebook video #599637780109885',
  1666. },
  1667. },
  1668. # Facebook <iframe> embed, plugin video
  1669. {
  1670. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1671. 'info_dict': {
  1672. 'id': '1754168231264132',
  1673. 'ext': 'mp4',
  1674. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1675. 'uploader': 'Tariq Ramadan (official)',
  1676. 'timestamp': 1496758379,
  1677. 'upload_date': '20170606',
  1678. },
  1679. 'params': {
  1680. 'skip_download': True,
  1681. },
  1682. },
  1683. # Facebook API embed
  1684. {
  1685. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1686. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1687. 'info_dict': {
  1688. 'id': '10153467542406923',
  1689. 'ext': 'mp4',
  1690. 'title': 'Facebook video #10153467542406923',
  1691. },
  1692. },
  1693. # Wordpress "YouTube Video Importer" plugin
  1694. {
  1695. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1696. 'md5': 'd16797741b560b485194eddda8121b48',
  1697. 'info_dict': {
  1698. 'id': 'HNTXWDXV9Is',
  1699. 'ext': 'mp4',
  1700. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1701. 'upload_date': '20160627',
  1702. 'uploader_id': 'GENOCIDE8GENERAL10',
  1703. 'uploader': 'cylus cyrus',
  1704. },
  1705. },
  1706. {
  1707. # video stored on custom kaltura server
  1708. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1709. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1710. 'info_dict': {
  1711. 'id': '0_1iotm5bh',
  1712. 'ext': 'mp4',
  1713. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1714. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1715. 'uploader_id': 'videos.expansion@el-mundo.net',
  1716. 'upload_date': '20150429',
  1717. 'timestamp': 1430303472,
  1718. },
  1719. 'add_ie': ['Kaltura'],
  1720. },
  1721. {
  1722. # multiple kaltura embeds, nsfw
  1723. 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
  1724. 'info_dict': {
  1725. 'id': 'kamila-avec-video-jaime-sadomie',
  1726. 'title': "Kamila avec vídeo “J'aime sadomie”",
  1727. },
  1728. 'playlist_count': 8,
  1729. },
  1730. {
  1731. # Non-standard Vimeo embed
  1732. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1733. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1734. 'info_dict': {
  1735. 'id': '148867247',
  1736. 'ext': 'mp4',
  1737. 'title': 'Understanding the web - Teaser',
  1738. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1739. 'upload_date': '20151214',
  1740. 'uploader': 'OpenClassrooms',
  1741. 'uploader_id': 'openclassrooms',
  1742. },
  1743. 'add_ie': ['Vimeo'],
  1744. },
  1745. {
  1746. # generic vimeo embed that requires original URL passed as Referer
  1747. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1748. 'only_matching': True,
  1749. },
  1750. {
  1751. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1752. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1753. 'info_dict': {
  1754. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1755. 'ext': 'mp4',
  1756. 'title': 'Big Buck Bunny',
  1757. 'description': 'Royalty free test video',
  1758. 'timestamp': 1432816365,
  1759. 'upload_date': '20150528',
  1760. 'is_live': False,
  1761. },
  1762. 'params': {
  1763. 'skip_download': True,
  1764. },
  1765. 'add_ie': [ArkenaIE.ie_key()],
  1766. },
  1767. {
  1768. '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/',
  1769. 'info_dict': {
  1770. 'id': '1c7141f46c',
  1771. 'ext': 'mp4',
  1772. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1773. },
  1774. 'params': {
  1775. 'skip_download': True,
  1776. },
  1777. 'add_ie': [Vbox7IE.ie_key()],
  1778. },
  1779. {
  1780. # DBTV embeds
  1781. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1782. 'info_dict': {
  1783. 'id': '43254897',
  1784. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1785. },
  1786. 'playlist_mincount': 3,
  1787. },
  1788. {
  1789. # Videa embeds
  1790. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1791. 'info_dict': {
  1792. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1793. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1794. },
  1795. 'playlist_mincount': 2,
  1796. },
  1797. {
  1798. # 20 minuten embed
  1799. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1800. 'info_dict': {
  1801. 'id': '523629',
  1802. 'ext': 'mp4',
  1803. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1804. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1805. },
  1806. 'params': {
  1807. 'skip_download': True,
  1808. },
  1809. 'add_ie': [TwentyMinutenIE.ie_key()],
  1810. },
  1811. {
  1812. # VideoPress embed
  1813. 'url': 'https://en.support.wordpress.com/videopress/',
  1814. 'info_dict': {
  1815. 'id': 'OcobLTqC',
  1816. 'ext': 'm4v',
  1817. 'title': 'IMG_5786',
  1818. 'timestamp': 1435711927,
  1819. 'upload_date': '20150701',
  1820. },
  1821. 'params': {
  1822. 'skip_download': True,
  1823. },
  1824. 'add_ie': [VideoPressIE.ie_key()],
  1825. },
  1826. {
  1827. # Rutube embed
  1828. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1829. 'info_dict': {
  1830. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1831. 'ext': 'flv',
  1832. 'title': 'Магаззино: Казань 2',
  1833. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1834. 'uploader': 'Магаззино',
  1835. 'upload_date': '20170228',
  1836. 'uploader_id': '996642',
  1837. },
  1838. 'params': {
  1839. 'skip_download': True,
  1840. },
  1841. 'add_ie': [RutubeIE.ie_key()],
  1842. },
  1843. {
  1844. # ThePlatform embedded with whitespaces in URLs
  1845. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1846. 'only_matching': True,
  1847. },
  1848. {
  1849. # Senate ISVP iframe https
  1850. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1851. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1852. 'info_dict': {
  1853. 'id': 'govtaff020316',
  1854. 'ext': 'mp4',
  1855. 'title': 'Integrated Senate Video Player',
  1856. },
  1857. 'add_ie': [SenateISVPIE.ie_key()],
  1858. },
  1859. {
  1860. # Limelight embeds (1 channel embed + 4 media embeds)
  1861. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1862. 'info_dict': {
  1863. 'id': 'FacilitatorTraining2017',
  1864. 'title': 'Facilitator Training 2017',
  1865. },
  1866. 'playlist_mincount': 5,
  1867. },
  1868. {
  1869. # Limelight embed (LimelightPlayerUtil.embed)
  1870. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1871. 'info_dict': {
  1872. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1873. 'ext': 'mp4',
  1874. 'title': '07448641',
  1875. 'timestamp': 1499890639,
  1876. 'upload_date': '20170712',
  1877. },
  1878. 'params': {
  1879. 'skip_download': True,
  1880. },
  1881. 'add_ie': ['LimelightMedia'],
  1882. },
  1883. {
  1884. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1885. 'info_dict': {
  1886. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1887. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1888. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1889. },
  1890. 'playlist_mincount': 4,
  1891. },
  1892. {
  1893. # WashingtonPost embed
  1894. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1895. 'info_dict': {
  1896. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1897. 'ext': 'mp4',
  1898. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1899. '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.',
  1900. 'timestamp': 1455216756,
  1901. 'uploader': 'The Washington Post',
  1902. 'upload_date': '20160211',
  1903. },
  1904. 'add_ie': [WashingtonPostIE.ie_key()],
  1905. },
  1906. {
  1907. # Mediaset embed
  1908. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1909. 'info_dict': {
  1910. 'id': '720642',
  1911. 'ext': 'mp4',
  1912. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1913. },
  1914. 'params': {
  1915. 'skip_download': True,
  1916. },
  1917. 'add_ie': [MediasetIE.ie_key()],
  1918. },
  1919. {
  1920. # JOJ.sk embeds
  1921. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1922. 'info_dict': {
  1923. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1924. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1925. },
  1926. 'playlist_mincount': 5,
  1927. 'add_ie': [JojIE.ie_key()],
  1928. },
  1929. {
  1930. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1931. 'url': 'https://tvrain.ru/amp/418921/',
  1932. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1933. 'info_dict': {
  1934. 'id': '418921',
  1935. 'ext': 'mp4',
  1936. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1937. },
  1938. },
  1939. {
  1940. # vzaar embed
  1941. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1942. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1943. 'info_dict': {
  1944. 'id': '8707641',
  1945. 'ext': 'mp4',
  1946. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1947. },
  1948. },
  1949. {
  1950. # multiple HTML5 videos on one page
  1951. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1952. 'info_dict': {
  1953. 'id': 'keyscenarios',
  1954. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1955. },
  1956. 'playlist_count': 4,
  1957. },
  1958. {
  1959. # vshare embed
  1960. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1961. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1962. 'info_dict': {
  1963. 'id': '0f64ce6',
  1964. 'title': 'vl14062007715967',
  1965. 'ext': 'mp4',
  1966. }
  1967. },
  1968. {
  1969. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1970. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1971. 'info_dict': {
  1972. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1973. 'ext': 'mp4',
  1974. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1975. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1976. 'timestamp': 1474354800,
  1977. 'upload_date': '20160920',
  1978. }
  1979. },
  1980. {
  1981. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1982. 'info_dict': {
  1983. 'id': '1731611',
  1984. 'ext': 'mp4',
  1985. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1986. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1987. 'timestamp': 1516100691,
  1988. 'upload_date': '20180116',
  1989. },
  1990. 'params': {
  1991. 'skip_download': True,
  1992. },
  1993. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1994. },
  1995. {
  1996. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1997. 'info_dict': {
  1998. 'id': 'uPDB5I9wfp8',
  1999. 'ext': 'webm',
  2000. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  2001. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  2002. 'upload_date': '20160219',
  2003. 'uploader': 'Pocoyo - Português (BR)',
  2004. 'uploader_id': 'PocoyoBrazil',
  2005. },
  2006. 'add_ie': [YoutubeIE.ie_key()],
  2007. 'params': {
  2008. 'skip_download': True,
  2009. },
  2010. },
  2011. {
  2012. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  2013. 'info_dict': {
  2014. 'id': 'vMDE4NzI1Mjgt690b',
  2015. 'ext': 'mp4',
  2016. 'title': 'Котята',
  2017. },
  2018. 'add_ie': [YapFilesIE.ie_key()],
  2019. 'params': {
  2020. 'skip_download': True,
  2021. },
  2022. },
  2023. {
  2024. # CloudflareStream embed
  2025. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  2026. 'info_dict': {
  2027. 'id': '31c9291ab41fac05471db4e73aa11717',
  2028. 'ext': 'mp4',
  2029. 'title': '31c9291ab41fac05471db4e73aa11717',
  2030. },
  2031. 'add_ie': [CloudflareStreamIE.ie_key()],
  2032. 'params': {
  2033. 'skip_download': True,
  2034. },
  2035. },
  2036. {
  2037. # PeerTube embed
  2038. 'url': 'https://joinpeertube.org/fr/home/',
  2039. 'info_dict': {
  2040. 'id': 'home',
  2041. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2042. },
  2043. 'playlist_count': 2,
  2044. },
  2045. {
  2046. # Indavideo embed
  2047. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2048. 'info_dict': {
  2049. 'id': '1693903',
  2050. 'ext': 'mp4',
  2051. 'title': 'Így kell otthon hamburgert sütni',
  2052. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2053. 'timestamp': 1426330212,
  2054. 'upload_date': '20150314',
  2055. 'uploader': 'StreetKitchen',
  2056. 'uploader_id': '546363',
  2057. },
  2058. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2059. 'params': {
  2060. 'skip_download': True,
  2061. },
  2062. },
  2063. {
  2064. # APA embed via JWPlatform embed
  2065. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2066. 'info_dict': {
  2067. 'id': 'jjv85FdZ',
  2068. 'ext': 'mp4',
  2069. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2070. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2071. 'thumbnail': r're:^https?://.*\.jpg$',
  2072. 'duration': 254,
  2073. 'timestamp': 1519211149,
  2074. 'upload_date': '20180221',
  2075. },
  2076. 'params': {
  2077. 'skip_download': True,
  2078. },
  2079. },
  2080. {
  2081. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2082. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2083. 'info_dict': {
  2084. 'id': '83645793',
  2085. 'title': 'Lock up and get excited',
  2086. 'ext': 'mp4'
  2087. },
  2088. 'skip': 'TODO: fix nested playlists processing in tests',
  2089. },
  2090. {
  2091. # Viqeo embeds
  2092. 'url': 'https://viqeo.tv/',
  2093. 'info_dict': {
  2094. 'id': 'viqeo',
  2095. 'title': 'All-new video platform',
  2096. },
  2097. 'playlist_count': 6,
  2098. },
  2099. {
  2100. # Squarespace video embed, 2019-08-28
  2101. 'url': 'http://ootboxford.com',
  2102. 'info_dict': {
  2103. 'id': 'Tc7b_JGdZfw',
  2104. 'title': 'Out of the Blue, at Childish Things 10',
  2105. 'ext': 'mp4',
  2106. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2107. 'uploader_id': 'helendouglashouse',
  2108. 'uploader': 'Helen & Douglas House',
  2109. 'upload_date': '20140328',
  2110. },
  2111. 'params': {
  2112. 'skip_download': True,
  2113. },
  2114. },
  2115. {
  2116. # Zype embed
  2117. 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2118. 'info_dict': {
  2119. 'id': '5b400b834b32992a310622b9',
  2120. 'ext': 'mp4',
  2121. 'title': 'Smoky Barbecue Favorites',
  2122. 'thumbnail': r're:^https?://.*\.jpe?g',
  2123. 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  2124. 'upload_date': '20170909',
  2125. 'timestamp': 1504915200,
  2126. },
  2127. 'add_ie': [ZypeIE.ie_key()],
  2128. 'params': {
  2129. 'skip_download': True,
  2130. },
  2131. },
  2132. {
  2133. # videojs embed
  2134. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2135. 'info_dict': {
  2136. 'id': 'shell',
  2137. 'ext': 'mp4',
  2138. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2139. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2140. 'thumbnail': r're:^https?://.*\.jpg$',
  2141. },
  2142. 'params': {
  2143. 'skip_download': True,
  2144. },
  2145. 'expected_warnings': ['Failed to download MPD manifest'],
  2146. },
  2147. {
  2148. # DailyMotion embed with DM.player
  2149. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2150. 'info_dict': {
  2151. 'id': 'k6aKkGHd9FJs4mtJN39',
  2152. 'ext': 'mp4',
  2153. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2154. 'description': 'This video is private.',
  2155. 'uploader_id': 'x1jf30l',
  2156. 'uploader': 'beIN SPORTS USA',
  2157. 'upload_date': '20190528',
  2158. 'timestamp': 1559062971,
  2159. },
  2160. 'params': {
  2161. 'skip_download': True,
  2162. },
  2163. },
  2164. # {
  2165. # # TODO: find another test
  2166. # # http://schema.org/VideoObject
  2167. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2168. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2169. # 'info_dict': {
  2170. # 'id': 'nyvTSJMKId',
  2171. # 'ext': 'mp4',
  2172. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2173. # 'description': '#love for cats.',
  2174. # 'timestamp': 1461244995,
  2175. # 'upload_date': '20160421',
  2176. # },
  2177. # 'params': {
  2178. # 'force_generic_extractor': True,
  2179. # },
  2180. # }
  2181. ]
  2182. def report_following_redirect(self, new_url):
  2183. """Report information extraction."""
  2184. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2185. def _extract_rss(self, url, video_id, doc):
  2186. playlist_title = doc.find('./channel/title').text
  2187. playlist_desc_el = doc.find('./channel/description')
  2188. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2189. NS_MAP = {
  2190. 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
  2191. }
  2192. entries = []
  2193. for it in doc.findall('./channel/item'):
  2194. next_url = None
  2195. enclosure_nodes = it.findall('./enclosure')
  2196. for e in enclosure_nodes:
  2197. next_url = e.attrib.get('url')
  2198. if next_url:
  2199. break
  2200. if not next_url:
  2201. next_url = xpath_text(it, 'link', fatal=False)
  2202. if not next_url:
  2203. continue
  2204. def itunes(key):
  2205. return xpath_text(
  2206. it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
  2207. default=None)
  2208. duration = itunes('duration')
  2209. explicit = itunes('explicit')
  2210. if explicit == 'true':
  2211. age_limit = 18
  2212. elif explicit == 'false':
  2213. age_limit = 0
  2214. else:
  2215. age_limit = None
  2216. entries.append({
  2217. '_type': 'url_transparent',
  2218. 'url': next_url,
  2219. 'title': it.find('title').text,
  2220. 'description': xpath_text(it, 'description', default=None),
  2221. 'timestamp': unified_timestamp(
  2222. xpath_text(it, 'pubDate', default=None)),
  2223. 'duration': int_or_none(duration) or parse_duration(duration),
  2224. 'thumbnail': url_or_none(itunes('image')),
  2225. 'episode': itunes('title'),
  2226. 'episode_number': int_or_none(itunes('episode')),
  2227. 'season_number': int_or_none(itunes('season')),
  2228. 'age_limit': age_limit,
  2229. })
  2230. return {
  2231. '_type': 'playlist',
  2232. 'id': url,
  2233. 'title': playlist_title,
  2234. 'description': playlist_desc,
  2235. 'entries': entries,
  2236. }
  2237. def _extract_camtasia(self, url, video_id, webpage):
  2238. """ Returns None if no camtasia video can be found. """
  2239. camtasia_cfg = self._search_regex(
  2240. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2241. webpage, 'camtasia configuration file', default=None)
  2242. if camtasia_cfg is None:
  2243. return None
  2244. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2245. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2246. camtasia_cfg = self._download_xml(
  2247. camtasia_url, video_id,
  2248. note='Downloading camtasia configuration',
  2249. errnote='Failed to download camtasia configuration')
  2250. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2251. entries = []
  2252. for n in fileset_node.getchildren():
  2253. url_n = n.find('./uri')
  2254. if url_n is None:
  2255. continue
  2256. entries.append({
  2257. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2258. 'title': '%s - %s' % (title, n.tag),
  2259. 'url': compat_urlparse.urljoin(url, url_n.text),
  2260. 'duration': float_or_none(n.find('./duration').text),
  2261. })
  2262. return {
  2263. '_type': 'playlist',
  2264. 'entries': entries,
  2265. 'title': title,
  2266. }
  2267. def _real_extract(self, url):
  2268. if url.startswith('//'):
  2269. return self.url_result(self.http_scheme() + url)
  2270. parsed_url = compat_urlparse.urlparse(url)
  2271. if not parsed_url.scheme:
  2272. default_search = self._downloader.params.get('default_search')
  2273. if default_search is None:
  2274. default_search = 'fixup_error'
  2275. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2276. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2277. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2278. return self.url_result('http://' + url)
  2279. elif default_search != 'fixup_error':
  2280. if default_search == 'auto_warning':
  2281. if re.match(r'^(?:url|URL)$', url):
  2282. raise ExtractorError(
  2283. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2284. expected=True)
  2285. else:
  2286. self._downloader.report_warning(
  2287. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2288. return self.url_result('ytsearch:' + url)
  2289. if default_search in ('error', 'fixup_error'):
  2290. raise ExtractorError(
  2291. '%r is not a valid URL. '
  2292. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2293. % (url, url), expected=True)
  2294. else:
  2295. if ':' not in default_search:
  2296. default_search += ':'
  2297. return self.url_result(default_search + url)
  2298. url, smuggled_data = unsmuggle_url(url)
  2299. force_videoid = None
  2300. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2301. if smuggled_data and 'force_videoid' in smuggled_data:
  2302. force_videoid = smuggled_data['force_videoid']
  2303. video_id = force_videoid
  2304. else:
  2305. video_id = self._generic_id(url)
  2306. self.to_screen('%s: Requesting header' % video_id)
  2307. head_req = HEADRequest(url)
  2308. head_response = self._request_webpage(
  2309. head_req, video_id,
  2310. note=False, errnote='Could not send HEAD request to %s' % url,
  2311. fatal=False)
  2312. if head_response is not False:
  2313. # Check for redirect
  2314. new_url = head_response.geturl()
  2315. if url != new_url:
  2316. self.report_following_redirect(new_url)
  2317. if force_videoid:
  2318. new_url = smuggle_url(
  2319. new_url, {'force_videoid': force_videoid})
  2320. return self.url_result(new_url)
  2321. full_response = None
  2322. if head_response is False:
  2323. request = sanitized_Request(url)
  2324. request.add_header('Accept-Encoding', '*')
  2325. full_response = self._request_webpage(request, video_id)
  2326. head_response = full_response
  2327. info_dict = {
  2328. 'id': video_id,
  2329. 'title': self._generic_title(url),
  2330. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2331. }
  2332. # Check for direct link to a video
  2333. content_type = head_response.headers.get('Content-Type', '').lower()
  2334. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2335. if m:
  2336. format_id = compat_str(m.group('format_id'))
  2337. if format_id.endswith('mpegurl'):
  2338. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2339. elif format_id == 'f4m':
  2340. formats = self._extract_f4m_formats(url, video_id)
  2341. else:
  2342. formats = [{
  2343. 'format_id': format_id,
  2344. 'url': url,
  2345. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2346. }]
  2347. info_dict['direct'] = True
  2348. self._sort_formats(formats)
  2349. info_dict['formats'] = formats
  2350. return info_dict
  2351. if not self._downloader.params.get('test', False) and not is_intentional:
  2352. force = self._downloader.params.get('force_generic_extractor', False)
  2353. self._downloader.report_warning(
  2354. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2355. if not full_response:
  2356. request = sanitized_Request(url)
  2357. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2358. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2359. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2360. # that will always result in downloading the whole file that is not desirable.
  2361. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2362. # to accept raw bytes and being able to download only a chunk.
  2363. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2364. # after HEAD request finishes, but not sure if we can rely on this.
  2365. request.add_header('Accept-Encoding', '*')
  2366. full_response = self._request_webpage(request, video_id)
  2367. first_bytes = full_response.read(512)
  2368. # Is it an M3U playlist?
  2369. if first_bytes.startswith(b'#EXTM3U'):
  2370. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2371. self._sort_formats(info_dict['formats'])
  2372. return info_dict
  2373. # Maybe it's a direct link to a video?
  2374. # Be careful not to download the whole thing!
  2375. if not is_html(first_bytes):
  2376. self._downloader.report_warning(
  2377. 'URL could be a direct video link, returning it as such.')
  2378. info_dict.update({
  2379. 'direct': True,
  2380. 'url': url,
  2381. })
  2382. return info_dict
  2383. webpage = self._webpage_read_content(
  2384. full_response, url, video_id, prefix=first_bytes)
  2385. self.report_extraction(video_id)
  2386. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2387. try:
  2388. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2389. if doc.tag == 'rss':
  2390. return self._extract_rss(url, video_id, doc)
  2391. elif doc.tag == 'SmoothStreamingMedia':
  2392. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2393. self._sort_formats(info_dict['formats'])
  2394. return info_dict
  2395. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2396. smil = self._parse_smil(doc, url, video_id)
  2397. self._sort_formats(smil['formats'])
  2398. return smil
  2399. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2400. return self.playlist_result(
  2401. self._parse_xspf(
  2402. doc, video_id, xspf_url=url,
  2403. xspf_base_url=full_response.geturl()),
  2404. video_id)
  2405. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2406. info_dict['formats'] = self._parse_mpd_formats(
  2407. doc,
  2408. mpd_base_url=full_response.geturl().rpartition('/')[0],
  2409. mpd_url=url)
  2410. self._sort_formats(info_dict['formats'])
  2411. return info_dict
  2412. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2413. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2414. self._sort_formats(info_dict['formats'])
  2415. return info_dict
  2416. except compat_xml_parse_error:
  2417. pass
  2418. # Is it a Camtasia project?
  2419. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2420. if camtasia_res is not None:
  2421. return camtasia_res
  2422. # Sometimes embedded video player is hidden behind percent encoding
  2423. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2424. # Unescaping the whole page allows to handle those cases in a generic way
  2425. # FIXME: unescaping the whole page may break URLs, commenting out for now.
  2426. # There probably should be a second run of generic extractor on unescaped webpage.
  2427. # webpage = compat_urllib_parse_unquote(webpage)
  2428. # Unescape squarespace embeds to be detected by generic extractor,
  2429. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2430. webpage = re.sub(
  2431. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2432. lambda x: unescapeHTML(x.group(0)), webpage)
  2433. # it's tempting to parse this further, but you would
  2434. # have to take into account all the variations like
  2435. # Video Title - Site Name
  2436. # Site Name | Video Title
  2437. # Video Title - Tagline | Site Name
  2438. # and so on and so forth; it's just not practical
  2439. video_title = self._og_search_title(
  2440. webpage, default=None) or self._html_search_regex(
  2441. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2442. default='video')
  2443. # Try to detect age limit automatically
  2444. age_limit = self._rta_search(webpage)
  2445. # And then there are the jokers who advertise that they use RTA,
  2446. # but actually don't.
  2447. AGE_LIMIT_MARKERS = [
  2448. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2449. ]
  2450. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2451. age_limit = 18
  2452. # video uploader is domain name
  2453. video_uploader = self._search_regex(
  2454. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2455. video_description = self._og_search_description(webpage, default=None)
  2456. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2457. info_dict.update({
  2458. 'title': video_title,
  2459. 'description': video_description,
  2460. 'thumbnail': video_thumbnail,
  2461. 'age_limit': age_limit,
  2462. })
  2463. # Look for Brightcove Legacy Studio embeds
  2464. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2465. if bc_urls:
  2466. entries = [{
  2467. '_type': 'url',
  2468. 'url': smuggle_url(bc_url, {'Referer': url}),
  2469. 'ie_key': 'BrightcoveLegacy'
  2470. } for bc_url in bc_urls]
  2471. return {
  2472. '_type': 'playlist',
  2473. 'title': video_title,
  2474. 'id': video_id,
  2475. 'entries': entries,
  2476. }
  2477. # Look for Brightcove New Studio embeds
  2478. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2479. if bc_urls:
  2480. return self.playlist_from_matches(
  2481. bc_urls, video_id, video_title,
  2482. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2483. ie='BrightcoveNew')
  2484. # Look for Nexx embeds
  2485. nexx_urls = NexxIE._extract_urls(webpage)
  2486. if nexx_urls:
  2487. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2488. # Look for Nexx iFrame embeds
  2489. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2490. if nexx_embed_urls:
  2491. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2492. # Look for ThePlatform embeds
  2493. tp_urls = ThePlatformIE._extract_urls(webpage)
  2494. if tp_urls:
  2495. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2496. # Look for embedded rtl.nl player
  2497. matches = re.findall(
  2498. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2499. webpage)
  2500. if matches:
  2501. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2502. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2503. if vimeo_urls:
  2504. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2505. vid_me_embed_url = self._search_regex(
  2506. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2507. webpage, 'vid.me embed', default=None)
  2508. if vid_me_embed_url is not None:
  2509. return self.url_result(vid_me_embed_url, 'Vidme')
  2510. # Look for YouTube embeds
  2511. youtube_urls = YoutubeIE._extract_urls(webpage)
  2512. if youtube_urls:
  2513. return self.playlist_from_matches(
  2514. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2515. matches = DailymotionIE._extract_urls(webpage)
  2516. if matches:
  2517. return self.playlist_from_matches(matches, video_id, video_title)
  2518. # Look for embedded Dailymotion playlist player (#3822)
  2519. m = re.search(
  2520. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2521. if m:
  2522. playlists = re.findall(
  2523. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2524. if playlists:
  2525. return self.playlist_from_matches(
  2526. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2527. # Look for DailyMail embeds
  2528. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2529. if dailymail_urls:
  2530. return self.playlist_from_matches(
  2531. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2532. # Look for Teachable embeds, must be before Wistia
  2533. teachable_url = TeachableIE._extract_url(webpage, url)
  2534. if teachable_url:
  2535. return self.url_result(teachable_url)
  2536. # Look for embedded Wistia player
  2537. wistia_urls = WistiaIE._extract_urls(webpage)
  2538. if wistia_urls:
  2539. playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
  2540. for entry in playlist['entries']:
  2541. entry.update({
  2542. '_type': 'url_transparent',
  2543. 'uploader': video_uploader,
  2544. })
  2545. return playlist
  2546. # Look for SVT player
  2547. svt_url = SVTIE._extract_url(webpage)
  2548. if svt_url:
  2549. return self.url_result(svt_url, 'SVT')
  2550. # Look for Bandcamp pages with custom domain
  2551. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2552. if mobj is not None:
  2553. burl = unescapeHTML(mobj.group(1))
  2554. # Don't set the extractor because it can be a track url or an album
  2555. return self.url_result(burl)
  2556. # Look for embedded Vevo player
  2557. mobj = re.search(
  2558. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2559. if mobj is not None:
  2560. return self.url_result(mobj.group('url'))
  2561. # Look for embedded Viddler player
  2562. mobj = re.search(
  2563. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2564. webpage)
  2565. if mobj is not None:
  2566. return self.url_result(mobj.group('url'))
  2567. # Look for NYTimes player
  2568. mobj = re.search(
  2569. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2570. webpage)
  2571. if mobj is not None:
  2572. return self.url_result(mobj.group('url'))
  2573. # Look for Libsyn player
  2574. mobj = re.search(
  2575. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2576. if mobj is not None:
  2577. return self.url_result(mobj.group('url'))
  2578. # Look for Ooyala videos
  2579. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2580. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2581. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2582. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2583. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2584. if mobj is not None:
  2585. embed_token = self._search_regex(
  2586. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2587. webpage, 'ooyala embed token', default=None)
  2588. return OoyalaIE._build_url_result(smuggle_url(
  2589. mobj.group('ec'), {
  2590. 'domain': url,
  2591. 'embed_token': embed_token,
  2592. }))
  2593. # Look for multiple Ooyala embeds on SBN network websites
  2594. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2595. if mobj is not None:
  2596. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2597. if embeds:
  2598. return self.playlist_from_matches(
  2599. embeds, video_id, video_title,
  2600. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2601. # Look for Aparat videos
  2602. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2603. if mobj is not None:
  2604. return self.url_result(mobj.group(1), 'Aparat')
  2605. # Look for MPORA videos
  2606. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2607. if mobj is not None:
  2608. return self.url_result(mobj.group(1), 'Mpora')
  2609. # Look for embedded Facebook player
  2610. facebook_urls = FacebookIE._extract_urls(webpage)
  2611. if facebook_urls:
  2612. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2613. # Look for embedded VK player
  2614. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2615. if mobj is not None:
  2616. return self.url_result(mobj.group('url'), 'VK')
  2617. # Look for embedded Odnoklassniki player
  2618. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2619. if odnoklassniki_url:
  2620. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2621. # Look for embedded ivi player
  2622. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2623. if mobj is not None:
  2624. return self.url_result(mobj.group('url'), 'Ivi')
  2625. # Look for embedded Huffington Post player
  2626. mobj = re.search(
  2627. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2628. if mobj is not None:
  2629. return self.url_result(mobj.group('url'), 'HuffPost')
  2630. # Look for embed.ly
  2631. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2632. if mobj is not None:
  2633. return self.url_result(mobj.group('url'))
  2634. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2635. if mobj is not None:
  2636. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2637. # Look for funnyordie embed
  2638. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2639. if matches:
  2640. return self.playlist_from_matches(
  2641. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2642. # Look for BBC iPlayer embed
  2643. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2644. if matches:
  2645. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2646. # Look for embedded RUTV player
  2647. rutv_url = RUTVIE._extract_url(webpage)
  2648. if rutv_url:
  2649. return self.url_result(rutv_url, 'RUTV')
  2650. # Look for embedded TVC player
  2651. tvc_url = TVCIE._extract_url(webpage)
  2652. if tvc_url:
  2653. return self.url_result(tvc_url, 'TVC')
  2654. # Look for embedded SportBox player
  2655. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2656. if sportbox_urls:
  2657. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2658. # Look for embedded XHamster player
  2659. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2660. if xhamster_urls:
  2661. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2662. # Look for embedded TNAFlixNetwork player
  2663. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2664. if tnaflix_urls:
  2665. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2666. # Look for embedded PornHub player
  2667. pornhub_urls = PornHubIE._extract_urls(webpage)
  2668. if pornhub_urls:
  2669. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2670. # Look for embedded DrTuber player
  2671. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2672. if drtuber_urls:
  2673. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2674. # Look for embedded RedTube player
  2675. redtube_urls = RedTubeIE._extract_urls(webpage)
  2676. if redtube_urls:
  2677. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2678. # Look for embedded Tube8 player
  2679. tube8_urls = Tube8IE._extract_urls(webpage)
  2680. if tube8_urls:
  2681. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2682. # Look for embedded Mofosex player
  2683. mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
  2684. if mofosex_urls:
  2685. return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
  2686. # Look for embedded Spankwire player
  2687. spankwire_urls = SpankwireIE._extract_urls(webpage)
  2688. if spankwire_urls:
  2689. return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
  2690. # Look for embedded YouPorn player
  2691. youporn_urls = YouPornIE._extract_urls(webpage)
  2692. if youporn_urls:
  2693. return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
  2694. # Look for embedded Tvigle player
  2695. mobj = re.search(
  2696. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2697. if mobj is not None:
  2698. return self.url_result(mobj.group('url'), 'Tvigle')
  2699. # Look for embedded TED player
  2700. mobj = re.search(
  2701. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2702. if mobj is not None:
  2703. return self.url_result(mobj.group('url'), 'TED')
  2704. # Look for embedded Ustream videos
  2705. ustream_url = UstreamIE._extract_url(webpage)
  2706. if ustream_url:
  2707. return self.url_result(ustream_url, UstreamIE.ie_key())
  2708. # Look for embedded arte.tv player
  2709. arte_urls = ArteTVEmbedIE._extract_urls(webpage)
  2710. if arte_urls:
  2711. return self.playlist_from_matches(arte_urls, video_id, video_title)
  2712. # Look for embedded francetv player
  2713. mobj = re.search(
  2714. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2715. webpage)
  2716. if mobj is not None:
  2717. return self.url_result(mobj.group('url'))
  2718. # Look for embedded smotri.com player
  2719. smotri_url = SmotriIE._extract_url(webpage)
  2720. if smotri_url:
  2721. return self.url_result(smotri_url, 'Smotri')
  2722. # Look for embedded Myvi.ru player
  2723. myvi_url = MyviIE._extract_url(webpage)
  2724. if myvi_url:
  2725. return self.url_result(myvi_url)
  2726. # Look for embedded soundcloud player
  2727. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2728. if soundcloud_urls:
  2729. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2730. # Look for tunein player
  2731. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2732. if tunein_urls:
  2733. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2734. # Look for embedded mtvservices player
  2735. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2736. if mtvservices_url:
  2737. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2738. # Look for embedded yahoo player
  2739. mobj = re.search(
  2740. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2741. webpage)
  2742. if mobj is not None:
  2743. return self.url_result(mobj.group('url'), 'Yahoo')
  2744. # Look for embedded sbs.com.au player
  2745. mobj = re.search(
  2746. r'''(?x)
  2747. (?:
  2748. <meta\s+property="og:video"\s+content=|
  2749. <iframe[^>]+?src=
  2750. )
  2751. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2752. webpage)
  2753. if mobj is not None:
  2754. return self.url_result(mobj.group('url'), 'SBS')
  2755. # Look for embedded Cinchcast player
  2756. mobj = re.search(
  2757. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2758. webpage)
  2759. if mobj is not None:
  2760. return self.url_result(mobj.group('url'), 'Cinchcast')
  2761. mobj = re.search(
  2762. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2763. webpage)
  2764. if not mobj:
  2765. mobj = re.search(
  2766. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2767. webpage)
  2768. if mobj is not None:
  2769. return self.url_result(mobj.group('url'), 'MLB')
  2770. mobj = re.search(
  2771. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2772. webpage)
  2773. if mobj is not None:
  2774. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2775. mobj = re.search(
  2776. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2777. webpage)
  2778. if mobj is not None:
  2779. return self.url_result(mobj.group('url'), 'Livestream')
  2780. # Look for Zapiks embed
  2781. mobj = re.search(
  2782. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2783. if mobj is not None:
  2784. return self.url_result(mobj.group('url'), 'Zapiks')
  2785. # Look for Kaltura embeds
  2786. kaltura_urls = KalturaIE._extract_urls(webpage)
  2787. if kaltura_urls:
  2788. return self.playlist_from_matches(
  2789. kaltura_urls, video_id, video_title,
  2790. getter=lambda x: smuggle_url(x, {'source_url': url}),
  2791. ie=KalturaIE.ie_key())
  2792. # Look for EaglePlatform embeds
  2793. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2794. if eagleplatform_url:
  2795. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2796. # Look for ClipYou (uses EaglePlatform) embeds
  2797. mobj = re.search(
  2798. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2799. if mobj is not None:
  2800. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2801. # Look for Pladform embeds
  2802. pladform_url = PladformIE._extract_url(webpage)
  2803. if pladform_url:
  2804. return self.url_result(pladform_url)
  2805. # Look for Videomore embeds
  2806. videomore_url = VideomoreIE._extract_url(webpage)
  2807. if videomore_url:
  2808. return self.url_result(videomore_url)
  2809. # Look for Webcaster embeds
  2810. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2811. if webcaster_url:
  2812. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2813. # Look for Playwire embeds
  2814. mobj = re.search(
  2815. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2816. if mobj is not None:
  2817. return self.url_result(mobj.group('url'))
  2818. # Look for 5min embeds
  2819. mobj = re.search(
  2820. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2821. if mobj is not None:
  2822. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2823. # Look for Crooks and Liars embeds
  2824. mobj = re.search(
  2825. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2826. if mobj is not None:
  2827. return self.url_result(mobj.group('url'))
  2828. # Look for NBC Sports VPlayer embeds
  2829. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2830. if nbc_sports_url:
  2831. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2832. # Look for NBC News embeds
  2833. nbc_news_embed_url = re.search(
  2834. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2835. if nbc_news_embed_url:
  2836. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2837. # Look for Google Drive embeds
  2838. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2839. if google_drive_url:
  2840. return self.url_result(google_drive_url, 'GoogleDrive')
  2841. # Look for UDN embeds
  2842. mobj = re.search(
  2843. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2844. if mobj is not None:
  2845. return self.url_result(
  2846. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2847. # Look for Senate ISVP iframe
  2848. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2849. if senate_isvp_url:
  2850. return self.url_result(senate_isvp_url, 'SenateISVP')
  2851. # Look for Kinja embeds
  2852. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  2853. if kinja_embed_urls:
  2854. return self.playlist_from_matches(
  2855. kinja_embed_urls, video_id, video_title)
  2856. # Look for OnionStudios embeds
  2857. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2858. if onionstudios_url:
  2859. return self.url_result(onionstudios_url)
  2860. # Look for ViewLift embeds
  2861. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2862. if viewlift_url:
  2863. return self.url_result(viewlift_url)
  2864. # Look for JWPlatform embeds
  2865. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2866. if jwplatform_urls:
  2867. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2868. # Look for Digiteka embeds
  2869. digiteka_url = DigitekaIE._extract_url(webpage)
  2870. if digiteka_url:
  2871. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2872. # Look for Arkena embeds
  2873. arkena_url = ArkenaIE._extract_url(webpage)
  2874. if arkena_url:
  2875. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2876. # Look for Piksel embeds
  2877. piksel_url = PikselIE._extract_url(webpage)
  2878. if piksel_url:
  2879. return self.url_result(piksel_url, PikselIE.ie_key())
  2880. # Look for Limelight embeds
  2881. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2882. if limelight_urls:
  2883. return self.playlist_result(
  2884. limelight_urls, video_id, video_title, video_description)
  2885. # Look for Anvato embeds
  2886. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2887. if anvato_urls:
  2888. return self.playlist_result(
  2889. anvato_urls, video_id, video_title, video_description)
  2890. # Look for AdobeTVVideo embeds
  2891. mobj = re.search(
  2892. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2893. webpage)
  2894. if mobj is not None:
  2895. return self.url_result(
  2896. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2897. 'AdobeTVVideo')
  2898. # Look for Vine embeds
  2899. mobj = re.search(
  2900. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2901. webpage)
  2902. if mobj is not None:
  2903. return self.url_result(
  2904. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2905. # Look for VODPlatform embeds
  2906. mobj = re.search(
  2907. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
  2908. webpage)
  2909. if mobj is not None:
  2910. return self.url_result(
  2911. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2912. # Look for Mangomolo embeds
  2913. mobj = re.search(
  2914. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  2915. (?:
  2916. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  2917. player\.mangomolo\.com/v1
  2918. )/
  2919. (?:
  2920. video\?.*?\bid=(?P<video_id>\d+)|
  2921. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2922. ).+?)\1''', webpage)
  2923. if mobj is not None:
  2924. info = {
  2925. '_type': 'url_transparent',
  2926. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2927. 'title': video_title,
  2928. 'description': video_description,
  2929. 'thumbnail': video_thumbnail,
  2930. 'uploader': video_uploader,
  2931. }
  2932. video_id = mobj.group('video_id')
  2933. if video_id:
  2934. info.update({
  2935. 'ie_key': 'MangomoloVideo',
  2936. 'id': video_id,
  2937. })
  2938. else:
  2939. info.update({
  2940. 'ie_key': 'MangomoloLive',
  2941. 'id': mobj.group('channel_id'),
  2942. })
  2943. return info
  2944. # Look for Instagram embeds
  2945. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2946. if instagram_embed_url is not None:
  2947. return self.url_result(
  2948. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2949. # Look for LiveLeak embeds
  2950. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2951. if liveleak_urls:
  2952. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2953. # Look for 3Q SDN embeds
  2954. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2955. if threeqsdn_url:
  2956. return {
  2957. '_type': 'url_transparent',
  2958. 'ie_key': ThreeQSDNIE.ie_key(),
  2959. 'url': self._proto_relative_url(threeqsdn_url),
  2960. 'title': video_title,
  2961. 'description': video_description,
  2962. 'thumbnail': video_thumbnail,
  2963. 'uploader': video_uploader,
  2964. }
  2965. # Look for VBOX7 embeds
  2966. vbox7_url = Vbox7IE._extract_url(webpage)
  2967. if vbox7_url:
  2968. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2969. # Look for DBTV embeds
  2970. dbtv_urls = DBTVIE._extract_urls(webpage)
  2971. if dbtv_urls:
  2972. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2973. # Look for Videa embeds
  2974. videa_urls = VideaIE._extract_urls(webpage)
  2975. if videa_urls:
  2976. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2977. # Look for 20 minuten embeds
  2978. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2979. if twentymin_urls:
  2980. return self.playlist_from_matches(
  2981. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2982. # Look for VideoPress embeds
  2983. videopress_urls = VideoPressIE._extract_urls(webpage)
  2984. if videopress_urls:
  2985. return self.playlist_from_matches(
  2986. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2987. # Look for Rutube embeds
  2988. rutube_urls = RutubeIE._extract_urls(webpage)
  2989. if rutube_urls:
  2990. return self.playlist_from_matches(
  2991. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2992. # Look for WashingtonPost embeds
  2993. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2994. if wapo_urls:
  2995. return self.playlist_from_matches(
  2996. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2997. # Look for Mediaset embeds
  2998. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  2999. if mediaset_urls:
  3000. return self.playlist_from_matches(
  3001. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  3002. # Look for JOJ.sk embeds
  3003. joj_urls = JojIE._extract_urls(webpage)
  3004. if joj_urls:
  3005. return self.playlist_from_matches(
  3006. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  3007. # Look for megaphone.fm embeds
  3008. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  3009. if mpfn_urls:
  3010. return self.playlist_from_matches(
  3011. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  3012. # Look for vzaar embeds
  3013. vzaar_urls = VzaarIE._extract_urls(webpage)
  3014. if vzaar_urls:
  3015. return self.playlist_from_matches(
  3016. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  3017. channel9_urls = Channel9IE._extract_urls(webpage)
  3018. if channel9_urls:
  3019. return self.playlist_from_matches(
  3020. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  3021. vshare_urls = VShareIE._extract_urls(webpage)
  3022. if vshare_urls:
  3023. return self.playlist_from_matches(
  3024. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  3025. # Look for Mediasite embeds
  3026. mediasite_urls = MediasiteIE._extract_urls(webpage)
  3027. if mediasite_urls:
  3028. entries = [
  3029. self.url_result(smuggle_url(
  3030. compat_urlparse.urljoin(url, mediasite_url),
  3031. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  3032. for mediasite_url in mediasite_urls]
  3033. return self.playlist_result(entries, video_id, video_title)
  3034. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  3035. if springboardplatform_urls:
  3036. return self.playlist_from_matches(
  3037. springboardplatform_urls, video_id, video_title,
  3038. ie=SpringboardPlatformIE.ie_key())
  3039. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  3040. if yapfiles_urls:
  3041. return self.playlist_from_matches(
  3042. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  3043. vice_urls = ViceIE._extract_urls(webpage)
  3044. if vice_urls:
  3045. return self.playlist_from_matches(
  3046. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  3047. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  3048. if xfileshare_urls:
  3049. return self.playlist_from_matches(
  3050. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  3051. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  3052. if cloudflarestream_urls:
  3053. return self.playlist_from_matches(
  3054. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  3055. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  3056. if peertube_urls:
  3057. return self.playlist_from_matches(
  3058. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  3059. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  3060. if indavideo_urls:
  3061. return self.playlist_from_matches(
  3062. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  3063. apa_urls = APAIE._extract_urls(webpage)
  3064. if apa_urls:
  3065. return self.playlist_from_matches(
  3066. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  3067. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  3068. if foxnews_urls:
  3069. return self.playlist_from_matches(
  3070. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  3071. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3072. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3073. webpage)]
  3074. if sharevideos_urls:
  3075. return self.playlist_from_matches(
  3076. sharevideos_urls, video_id, video_title)
  3077. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3078. if viqeo_urls:
  3079. return self.playlist_from_matches(
  3080. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3081. expressen_urls = ExpressenIE._extract_urls(webpage)
  3082. if expressen_urls:
  3083. return self.playlist_from_matches(
  3084. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3085. zype_urls = ZypeIE._extract_urls(webpage)
  3086. if zype_urls:
  3087. return self.playlist_from_matches(
  3088. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3089. # Look for HTML5 media
  3090. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3091. if entries:
  3092. if len(entries) == 1:
  3093. entries[0].update({
  3094. 'id': video_id,
  3095. 'title': video_title,
  3096. })
  3097. else:
  3098. for num, entry in enumerate(entries, start=1):
  3099. entry.update({
  3100. 'id': '%s-%s' % (video_id, num),
  3101. 'title': '%s (%d)' % (video_title, num),
  3102. })
  3103. for entry in entries:
  3104. self._sort_formats(entry['formats'])
  3105. return self.playlist_result(entries, video_id, video_title)
  3106. jwplayer_data = self._find_jwplayer_data(
  3107. webpage, video_id, transform_source=js_to_json)
  3108. if jwplayer_data:
  3109. try:
  3110. info = self._parse_jwplayer_data(
  3111. jwplayer_data, video_id, require_title=False, base_url=url)
  3112. return merge_dicts(info, info_dict)
  3113. except ExtractorError:
  3114. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3115. pass
  3116. # Video.js embed
  3117. mobj = re.search(
  3118. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3119. webpage)
  3120. if mobj is not None:
  3121. sources = self._parse_json(
  3122. mobj.group(1), video_id, transform_source=js_to_json,
  3123. fatal=False) or []
  3124. if not isinstance(sources, list):
  3125. sources = [sources]
  3126. formats = []
  3127. for source in sources:
  3128. src = source.get('src')
  3129. if not src or not isinstance(src, compat_str):
  3130. continue
  3131. src = compat_urlparse.urljoin(url, src)
  3132. src_type = source.get('type')
  3133. if isinstance(src_type, compat_str):
  3134. src_type = src_type.lower()
  3135. ext = determine_ext(src).lower()
  3136. if src_type == 'video/youtube':
  3137. return self.url_result(src, YoutubeIE.ie_key())
  3138. if src_type == 'application/dash+xml' or ext == 'mpd':
  3139. formats.extend(self._extract_mpd_formats(
  3140. src, video_id, mpd_id='dash', fatal=False))
  3141. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3142. formats.extend(self._extract_m3u8_formats(
  3143. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3144. m3u8_id='hls', fatal=False))
  3145. else:
  3146. formats.append({
  3147. 'url': src,
  3148. 'ext': (mimetype2ext(src_type)
  3149. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3150. })
  3151. if formats:
  3152. self._sort_formats(formats)
  3153. info_dict['formats'] = formats
  3154. return info_dict
  3155. # Looking for http://schema.org/VideoObject
  3156. json_ld = self._search_json_ld(
  3157. webpage, video_id, default={}, expected_type='VideoObject')
  3158. if json_ld.get('url'):
  3159. return merge_dicts(json_ld, info_dict)
  3160. def check_video(vurl):
  3161. if YoutubeIE.suitable(vurl):
  3162. return True
  3163. if RtmpIE.suitable(vurl):
  3164. return True
  3165. vpath = compat_urlparse.urlparse(vurl).path
  3166. vext = determine_ext(vpath)
  3167. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3168. def filter_video(urls):
  3169. return list(filter(check_video, urls))
  3170. # Start with something easy: JW Player in SWFObject
  3171. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3172. if not found:
  3173. # Look for gorilla-vid style embedding
  3174. found = filter_video(re.findall(r'''(?sx)
  3175. (?:
  3176. jw_plugins|
  3177. JWPlayerOptions|
  3178. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3179. )
  3180. .*?
  3181. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3182. if not found:
  3183. # Broaden the search a little bit
  3184. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3185. if not found:
  3186. # Broaden the findall a little bit: JWPlayer JS loader
  3187. found = filter_video(re.findall(
  3188. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3189. if not found:
  3190. # Flow player
  3191. found = filter_video(re.findall(r'''(?xs)
  3192. flowplayer\("[^"]+",\s*
  3193. \{[^}]+?\}\s*,
  3194. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3195. ["']?url["']?\s*:\s*["']([^"']+)["']
  3196. ''', webpage))
  3197. if not found:
  3198. # Cinerama player
  3199. found = re.findall(
  3200. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3201. if not found:
  3202. # Try to find twitter cards info
  3203. # twitter:player:stream should be checked before twitter:player since
  3204. # it is expected to contain a raw stream (see
  3205. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3206. found = filter_video(re.findall(
  3207. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3208. if not found:
  3209. # We look for Open Graph info:
  3210. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3211. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3212. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3213. if m_video_type is not None:
  3214. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3215. if not found:
  3216. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3217. found = re.search(
  3218. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3219. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3220. webpage)
  3221. if not found:
  3222. # Look also in Refresh HTTP header
  3223. refresh_header = head_response.headers.get('Refresh')
  3224. if refresh_header:
  3225. # In python 2 response HTTP headers are bytestrings
  3226. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3227. refresh_header = refresh_header.decode('iso-8859-1')
  3228. found = re.search(REDIRECT_REGEX, refresh_header)
  3229. if found:
  3230. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3231. if new_url != url:
  3232. self.report_following_redirect(new_url)
  3233. return {
  3234. '_type': 'url',
  3235. 'url': new_url,
  3236. }
  3237. else:
  3238. found = None
  3239. if not found:
  3240. # twitter:player is a https URL to iframe player that may or may not
  3241. # be supported by youtube-dl thus this is checked the very last (see
  3242. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3243. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3244. if embed_url and embed_url != url:
  3245. return self.url_result(embed_url)
  3246. if not found:
  3247. raise UnsupportedError(url)
  3248. entries = []
  3249. for video_url in orderedSet(found):
  3250. video_url = unescapeHTML(video_url)
  3251. video_url = video_url.replace('\\/', '/')
  3252. video_url = compat_urlparse.urljoin(url, video_url)
  3253. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3254. # Sometimes, jwplayer extraction will result in a YouTube URL
  3255. if YoutubeIE.suitable(video_url):
  3256. entries.append(self.url_result(video_url, 'Youtube'))
  3257. continue
  3258. # here's a fun little line of code for you:
  3259. video_id = os.path.splitext(video_id)[0]
  3260. entry_info_dict = {
  3261. 'id': video_id,
  3262. 'uploader': video_uploader,
  3263. 'title': video_title,
  3264. 'age_limit': age_limit,
  3265. }
  3266. if RtmpIE.suitable(video_url):
  3267. entry_info_dict.update({
  3268. '_type': 'url_transparent',
  3269. 'ie_key': RtmpIE.ie_key(),
  3270. 'url': video_url,
  3271. })
  3272. entries.append(entry_info_dict)
  3273. continue
  3274. ext = determine_ext(video_url)
  3275. if ext == 'smil':
  3276. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3277. elif ext == 'xspf':
  3278. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3279. elif ext == 'm3u8':
  3280. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3281. elif ext == 'mpd':
  3282. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3283. elif ext == 'f4m':
  3284. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3285. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3286. # Just matching .ism/manifest is not enough to be reliably sure
  3287. # whether it's actually an ISM manifest or some other streaming
  3288. # manifest since there are various streaming URL formats
  3289. # possible (see [1]) as well as some other shenanigans like
  3290. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3291. # so on.
  3292. # Thus the most reasonable way to solve this is to delegate
  3293. # to generic extractor in order to look into the contents of
  3294. # the manifest itself.
  3295. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3296. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3297. entry_info_dict = self.url_result(
  3298. smuggle_url(video_url, {'to_generic': True}),
  3299. GenericIE.ie_key())
  3300. else:
  3301. entry_info_dict['url'] = video_url
  3302. if entry_info_dict.get('formats'):
  3303. self._sort_formats(entry_info_dict['formats'])
  3304. entries.append(entry_info_dict)
  3305. if len(entries) == 1:
  3306. return entries[0]
  3307. else:
  3308. for num, e in enumerate(entries, start=1):
  3309. # 'url' results don't have a title
  3310. if e.get('title') is not None:
  3311. e['title'] = '%s (%d)' % (e['title'], num)
  3312. return {
  3313. '_type': 'playlist',
  3314. 'entries': entries,
  3315. }