X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9f2b33881274af98a9145c533a1d295fad71521a..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/generic.py?ds=sidebyside diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index c6bf8d2..355067a 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1,4 +1,4 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals @@ -10,6 +10,7 @@ from .common import InfoExtractor from .youtube import YoutubeIE from ..compat import ( compat_etree_fromstring, + compat_str, compat_urllib_parse_unquote, compat_urlparse, compat_xml_parse_error, @@ -20,6 +21,10 @@ from ..utils import ( float_or_none, HEADRequest, is_html, + js_to_json, + KNOWN_EXTENSIONS, + merge_dicts, + mimetype2ext, orderedSet, sanitized_Request, smuggle_url, @@ -27,18 +32,22 @@ from ..utils import ( unified_strdate, unsmuggle_url, UnsupportedError, - url_basename, xpath_text, ) +from .commonprotocols import RtmpIE from .brightcove import ( BrightcoveLegacyIE, BrightcoveNewIE, ) +from .nexx import ( + NexxIE, + NexxEmbedIE, +) from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .tvc import TVCIE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .smotri import SmotriIE from .myvi import MyviIE from .condenast import CondeNastIE @@ -47,17 +56,69 @@ from .senateisvp import SenateISVPIE from .svt import SVTIE from .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE +from .tnaflix import TNAFlixNetworkEmbedIE +from .drtuber import DrTuberIE +from .redtube import RedTubeIE +from .tube8 import Tube8IE +from .mofosex import MofosexEmbedIE +from .spankwire import SpankwireIE +from .youporn import YouPornIE from .vimeo import VimeoIE -from .dailymotion import DailymotionCloudIE +from .dailymotion import DailymotionIE +from .dailymail import DailyMailIE from .onionstudios import OnionStudiosIE -from .snagfilms import SnagFilmsEmbedIE -from .screenwavemedia import ScreenwaveMediaIE +from .viewlift import ViewLiftEmbedIE from .mtv import MTVServicesEmbeddedIE from .pladform import PladformIE from .videomore import VideomoreIE +from .webcaster import WebcasterFeedIE from .googledrive import GoogleDriveIE from .jwplatform import JWPlatformIE from .digiteka import DigitekaIE +from .arkena import ArkenaIE +from .instagram import InstagramIE +from .liveleak import LiveLeakIE +from .threeqsdn import ThreeQSDNIE +from .theplatform import ThePlatformIE +from .kaltura import KalturaIE +from .eagleplatform import EaglePlatformIE +from .facebook import FacebookIE +from .soundcloud import SoundcloudEmbedIE +from .tunein import TuneInBaseIE +from .vbox7 import Vbox7IE +from .dbtv import DBTVIE +from .piksel import PikselIE +from .videa import VideaIE +from .twentymin import TwentyMinutenIE +from .ustream import UstreamIE +from .videopress import VideoPressIE +from .rutube import RutubeIE +from .limelight import LimelightBaseIE +from .anvato import AnvatoIE +from .washingtonpost import WashingtonPostIE +from .wistia import WistiaIE +from .mediaset import MediasetIE +from .joj import JojIE +from .megaphone import MegaphoneIE +from .vzaar import VzaarIE +from .channel9 import Channel9IE +from .vshare import VShareIE +from .mediasite import MediasiteIE +from .springboardplatform import SpringboardPlatformIE +from .yapfiles import YapFilesIE +from .vice import ViceIE +from .xfileshare import XFileShareIE +from .cloudflarestream import CloudflareStreamIE +from .peertube import PeerTubeIE +from .teachable import TeachableIE +from .indavideo import IndavideoEmbedIE +from .apa import APAIE +from .foxnews import FoxNewsIE +from .viqeo import ViqeoIE +from .expressen import ExpressenIE +from .zype import ZypeIE +from .odnoklassniki import OdnoklassnikiIE +from .kinja import KinjaEmbedIE class GenericIE(InfoExtractor): @@ -88,7 +149,8 @@ class GenericIE(InfoExtractor): }, 'expected_warnings': [ 'URL could be a direct video link, returning it as such.' - ] + ], + 'skip': 'URL invalid', }, # Direct download with broken HEAD { @@ -102,7 +164,8 @@ class GenericIE(InfoExtractor): 'skip_download': True, # infinite live stream }, 'expected_warnings': [ - r'501.*Not Implemented' + r'501.*Not Implemented', + r'400.*Bad Request', ], }, # Direct link with incorrect MIME type @@ -140,6 +203,16 @@ class GenericIE(InfoExtractor): 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624', } }, + # RSS feed with enclosures and unsupported link URLs + { + 'url': 'http://www.hellointernet.fm/podcast?format=rss', + 'info_dict': { + 'id': 'http://www.hellointernet.fm/podcast?format=rss', + 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.', + 'title': 'Hello Internet', + }, + 'playlist_mincount': 100, + }, # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng { 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml', @@ -217,7 +290,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'Tikibad ontruimd wegens brand', 'description': 'md5:05ca046ff47b931f9b04855015e163a4', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 33, }, 'params': { @@ -233,11 +306,43 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'car-20120827-manifest', 'formats': 'mincount:9', + 'upload_date': '20130904', }, 'params': { 'format': 'bestvideo', }, }, + # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8 + { + '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', + 'info_dict': { + 'id': 'content', + 'ext': 'mp4', + 'title': 'content', + 'formats': 'mincount:8', + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + }, + 'skip': 'video gone', + }, + # m3u8 served with Content-Type: text/plain + { + 'url': 'http://www.nacentapps.com/m3u8/index.m3u8', + 'info_dict': { + 'id': 'index', + 'ext': 'mp4', + 'title': 'index', + 'upload_date': '20140720', + 'formats': 'mincount:11', + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + }, + 'skip': 'video gone', + }, # google redirect { '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', @@ -246,7 +351,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20130224', 'uploader_id': 'TheVerge', - 'description': 're:^Chris Ziegler takes a look at the\.*', + 'description': r're:^Chris Ziegler takes a look at the\.*', 'uploader': 'The Verge', 'title': 'First Firefox OS phones side-by-side', }, @@ -292,10 +397,10 @@ class GenericIE(InfoExtractor): }, 'skip': 'There is a limit of 200 free downloads / month for the test song', }, - # embedded brightcove video - # it also tests brightcove videos that need to set the 'Referer' in the - # http requests { + # embedded brightcove video + # it also tests brightcove videos that need to set the 'Referer' + # in the http requests 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', 'info_dict': { @@ -310,7 +415,25 @@ class GenericIE(InfoExtractor): }, }, { - # https://github.com/rg3/youtube-dl/issues/2253 + # embedded with itemprop embedURL and video id spelled as `idVideo` + 'add_id': ['BrightcoveLegacy'], + 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/', + 'info_dict': { + 'id': '5255628253001', + 'ext': 'mp4', + 'title': 'md5:37c519b1128915607601e75a87995fc0', + 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26', + 'uploader': 'BFM BUSINESS', + 'uploader_id': '876450612001', + 'timestamp': 1482255315, + 'upload_date': '20161220', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # https://github.com/ytdl-org/youtube-dl/issues/2253 'url': 'http://bcove.me/i6nfkrc3', 'md5': '0ba9446db037002366bab3b3eb30c88c', 'info_dict': { @@ -321,6 +444,7 @@ class GenericIE(InfoExtractor): '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.', }, 'add_ie': ['BrightcoveLegacy'], + 'skip': 'video gone', }, { 'url': 'http://www.championat.com/video/football/v/87/87499.html', @@ -334,7 +458,7 @@ class GenericIE(InfoExtractor): }, }, { - # https://github.com/rg3/youtube-dl/issues/3541 + # https://github.com/ytdl-org/youtube-dl/issues/3541 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', 'info_dict': { @@ -349,6 +473,112 @@ class GenericIE(InfoExtractor): 'skip_download': True, # m3u8 download }, }, + { + # Brightcove video in <iframe> + 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724', + 'md5': '36d74ef5e37c8b4a2ce92880d208b968', + 'info_dict': { + 'id': '5360463607001', + 'ext': 'mp4', + 'title': 'åå©äºå¤±æå¿ç«¥å¨åºå¢ä¸æ¼å±ãå¿è·³ã å¼åè·å¾æ£å¸¸ç«¥å¹´çæ´»', + 'description': 'èåå½å¿ç«¥åºéä¼ä¸ä¸ååéåºå大使ãä½æ²å®¶æ德·迪æå°¼ï¼Zade Diraniï¼å¨3æ15æ¥åå©äºå²çªçå7å¨å¹´çºªå¿µæ¥ä¹é åå¸äºä¸ºåå©äºè°±åçææ²ãå¿è·³ãï¼HEARTBEATï¼ï¼ä¸ºåå°å å¹´å²çªå½±åçåå©äºå¿ç«¥ååºå¼ºçååï¼å¼åä¸çååºå ±ååªåï¼ä½¿åå©äºå¿ç«¥éæ°è·å¾äº«ææ£å¸¸ç«¥å¹´çæ´»çæå©ã', + 'uploader': 'United Nations', + 'uploader_id': '1362235914001', + 'timestamp': 1489593889, + 'upload_date': '20170315', + }, + 'add_ie': ['BrightcoveLegacy'], + }, + { + # Brightcove with alternative playerID key + 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html', + 'info_dict': { + 'id': 'nmeth.2062_SV1', + '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', + }, + 'playlist': [{ + 'info_dict': { + 'id': '2228375078001', + 'ext': 'mp4', + 'title': 'nmeth.2062-sv1', + 'description': 'nmeth.2062-sv1', + 'timestamp': 1363357591, + 'upload_date': '20130315', + 'uploader': 'Nature Publishing Group', + 'uploader_id': '1964492299001', + }, + }], + }, + { + # Brightcove with UUID in videoPlayer + 'url': 'http://www8.hp.com/cn/zh/home.html', + 'info_dict': { + 'id': '5255815316001', + 'ext': 'mp4', + 'title': 'Sprocket Video - China', + 'description': 'Sprocket Video - China', + 'uploader': 'HP-Video Gallery', + 'timestamp': 1482263210, + 'upload_date': '20161220', + 'uploader_id': '1107601872001', + }, + 'params': { + 'skip_download': True, # m3u8 download + }, + 'skip': 'video rotates...weekly?', + }, + { + # Brightcove:new type [2]. + 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis', + 'md5': '2b35148fcf48da41c9fb4591650784f3', + 'info_dict': { + 'id': '5348741021001', + 'ext': 'mp4', + 'upload_date': '20170306', + 'uploader_id': '4191638492001', + 'timestamp': 1488769918, + 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis', + + }, + }, + { + # Alternative brightcove <video> attributes + '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/', + 'info_dict': { + 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche', + 'title': "Guillaume Canet eÌvoque les rumeurs d'infideÌliteÌ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs", + }, + 'playlist': [{ + 'md5': '732d22ba3d33f2f3fc253c39f8f36523', + 'info_dict': { + 'id': '5311302538001', + 'ext': 'mp4', + 'title': "Guillaume Canet eÌvoque les rumeurs d'infideÌliteÌ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche", + 'description': "Guillaume Canet eÌvoque les rumeurs d'infideÌliteÌ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)", + 'timestamp': 1486321708, + 'upload_date': '20170205', + 'uploader_id': '800000640001', + }, + 'only_matching': True, + }], + }, + { + # Brightcove with UUID in videoPlayer + 'url': 'http://www8.hp.com/cn/zh/home.html', + 'info_dict': { + 'id': '5255815316001', + 'ext': 'mp4', + 'title': 'Sprocket Video - China', + 'description': 'Sprocket Video - China', + 'uploader': 'HP-Video Gallery', + 'timestamp': 1482263210, + 'upload_date': '20161220', + 'uploader_id': '1107601872001', + }, + 'params': { + 'skip_download': True, # m3u8 download + }, + }, # ooyala video { 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', @@ -374,19 +604,20 @@ class GenericIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'movie expired', }, - # multiple ooyala embeds on SBN network websites + # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js { - 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok', + 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/', 'info_dict': { - 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok', - 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com', + 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2', + 'ext': 'mp4', + 'title': 'Steampunk Fest Comes to Honesdale', + 'duration': 43.276, }, - 'playlist_mincount': 3, 'params': { 'skip_download': True, - }, - 'add_ie': ['Ooyala'], + } }, # embed.ly video { @@ -414,6 +645,8 @@ class GenericIE(InfoExtractor): 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama', 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', }, + # HEAD requests lead to endless 301, while GET is OK + 'expected_warnings': ['301'], }, # RUTV embed { @@ -443,7 +676,7 @@ class GenericIE(InfoExtractor): 'url': 'http://www.vestifinance.ru/articles/25753', 'info_dict': { 'id': '25753', - 'title': 'ÐеÑÑи Ðкономика â ÐÑÑмÑе ÑÑанÑлÑÑии Ñ Ð¤Ð¾ÑÑма-вÑÑÑавки "ÐоÑзаказ-2013"', + 'title': 'ÐÑÑмÑе ÑÑанÑлÑÑии Ñ Ð¤Ð¾ÑÑма-вÑÑÑавки "ÐоÑзаказ-2013"', }, 'playlist': [{ 'info_dict': { @@ -476,7 +709,7 @@ class GenericIE(InfoExtractor): 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e', 'ext': 'mp4', 'title': 'УжаÑÑики, ÑÑÑÑкий ÑÑÐµÐ¹Ð»ÐµÑ (2015)', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 153, } }, @@ -488,6 +721,9 @@ class GenericIE(InfoExtractor): 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )', }, 'playlist_mincount': 7, + # This forum does not allow <iframe> syntaxes anymore + # Now HTML tags are displayed as-is + 'skip': 'No videos on this page', }, # Embedded TED video { @@ -501,17 +737,6 @@ class GenericIE(InfoExtractor): 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', } }, - # Embedded Ustream video - { - 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm', - 'md5': '27b99cdb639c9b12a79bca876a073417', - 'info_dict': { - 'id': '45734260', - 'ext': 'flv', - 'uploader': 'AU SPA: The NSA and Privacy', - 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman' - } - }, # nowvideo embed hidden behind percent encoding { 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/', @@ -536,7 +761,8 @@ class GenericIE(InfoExtractor): }, 'params': { 'skip_download': 'Requires rtmpdump' - } + }, + 'skip': 'video gone', }, # francetv embed { @@ -576,10 +802,28 @@ class GenericIE(InfoExtractor): 'id': 'k2mm4bCdJ6CQ2i7c8o2', 'ext': 'mp4', 'title': 'Le Zap de Spi0n n°216 - Zapping du Web', + 'description': 'md5:faf028e48a461b8b7fad38f1e104b119', 'uploader': 'Spi0n', + 'uploader_id': 'xgditw', + 'upload_date': '20140425', + 'timestamp': 1398441542, }, 'add_ie': ['Dailymotion'], }, + # DailyMail embed + { + 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot', + 'info_dict': { + 'id': '1495629', + 'ext': 'mp4', + 'title': 'Care worker punches elderly dementia patient in head 11 times', + 'description': 'md5:3a743dee84e57e48ec68bf67113199a5', + }, + 'add_ie': ['DailyMail'], + 'params': { + 'skip_download': True, + }, + }, # YouTube embed { 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html', @@ -599,13 +843,15 @@ class GenericIE(InfoExtractor): }, # MTVSercices embed { - 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too', - 'md5': '35727f82f58c76d996fc188f9755b0d5', + 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html', + 'md5': 'ca1aef97695ef2c1d6973256a57e5252', 'info_dict': { - 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9', + 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1', 'ext': 'mp4', - 'title': 'Review', - 'description': 'Mario\'s life in the fast lane has never looked so good.', + 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored', + 'description': 'Two valets share their love for movie star Liam Neesons.', + 'timestamp': 1349922600, + 'upload_date': '20121011', }, }, # YouTube embed via <data-embed-url=""> @@ -624,6 +870,21 @@ class GenericIE(InfoExtractor): 'skip_download': True, } }, + # YouTube <object> embed + { + 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/', + 'md5': '516718101ec834f74318df76259fb3cc', + 'info_dict': { + 'id': 'msN87y-iEx0', + 'ext': 'webm', + 'title': 'Feynman: Mirrors FUN TO IMAGINE 6', + 'upload_date': '20080526', + 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d', + 'uploader': 'Christopher Sykes', + 'uploader_id': 'ChristopherJSykes', + }, + 'add_ie': ['Youtube'], + }, # Camtasia studio { 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/', @@ -661,7 +922,7 @@ class GenericIE(InfoExtractor): } }, # Multiple brightcove videos - # https://github.com/rg3/youtube-dl/issues/2283 + # https://github.com/ytdl-org/youtube-dl/issues/2283 { 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', 'info_dict': { @@ -686,20 +947,23 @@ class GenericIE(InfoExtractor): 'duration': 48, 'timestamp': 1401537900, 'upload_date': '20140531', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, }, # Wistia embed { - 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', - 'md5': '8788b683c777a5cf25621eaf286d0c23', + 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', + 'md5': '1953f3a698ab51cfc948ed3992a0b7ff', 'info_dict': { - 'id': '1cfaf6b7ea', + 'id': '6e2wtrbdaf', 'ext': 'mov', - 'title': 'md5:51364a8d3d009997ba99656004b5e20d', - 'duration': 643.0, - 'filesize': 182808282, - 'uploader': 'education-portal.com', + 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england', + 'description': 'a Paywall Videos video from Remilon', + 'duration': 644.072, + 'uploader': 'study.com', + 'timestamp': 1459678540, + 'upload_date': '20160403', + 'filesize': 24687186, }, }, { @@ -708,10 +972,29 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': 'uxjb0lwrcz', 'ext': 'mp4', - 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', + 'title': 'Conversation about Hexagonal Rails Part 1', + 'description': 'a Martin Fowler video from ThoughtWorks', 'duration': 1715.0, 'uploader': 'thoughtworks.wistia.com', + 'timestamp': 1401832161, + 'upload_date': '20140603', + }, + }, + # Wistia standard embed (async) + { + 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/', + 'info_dict': { + 'id': '807fafadvk', + 'ext': 'mp4', + 'title': 'Drip Brennan Dunn Workshop', + 'description': 'a JV Webinars video from getdrip-1', + 'duration': 4986.95, + 'timestamp': 1463607249, + 'upload_date': '20160518', }, + 'params': { + 'skip_download': True, + } }, # Soundcloud embed { @@ -725,6 +1008,30 @@ class GenericIE(InfoExtractor): 'upload_date': '20141029', } }, + # Soundcloud multiple embeds + { + 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809', + 'info_dict': { + 'id': '52809', + 'title': 'Guitar Essentials: Legato WorkoutâOne-Hour to Fluid Performance | TAB + AUDIO', + }, + 'playlist_mincount': 7, + }, + # TuneIn station embed + { + 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/', + 'info_dict': { + 'id': '204146', + 'ext': 'mp3', + 'title': 'CNRV', + 'location': 'Paris, France', + 'is_live': True, + }, + 'params': { + # Live stream + 'skip_download': True, + }, + }, # Livestream embed { 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast', @@ -735,14 +1042,28 @@ class GenericIE(InfoExtractor): 'title': 'Rosetta #CometLanding webcast HL 10', } }, + # Another Livestream embed, without 'new.' in URL + { + 'url': 'https://www.freespeech.org/', + 'info_dict': { + 'id': '123537347', + 'ext': 'mp4', + 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + }, + 'params': { + # Live stream + 'skip_download': True, + }, + }, # LazyYT { - 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986', + 'url': 'https://skiplagged.com/', 'info_dict': { - 'id': '1986', - 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse', + 'id': 'skiplagged', + 'title': 'Skiplagged: The smart way to find cheap flights', }, - 'playlist_mincount': 2, + 'playlist_mincount': 1, + 'add_ie': ['Youtube'], }, # Cinchcast embed { @@ -787,6 +1108,7 @@ class GenericIE(InfoExtractor): 'description': 'md5:601cb790edd05908957dae8aaa866465', 'upload_date': '20150220', }, + 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/', }, # jwplayer YouTube { @@ -796,18 +1118,99 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20150212', 'uploader': 'The National Archives UK', - 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6', + 'description': 'md5:8078af856dca76edc42910b61273dbbf', 'uploader_id': 'NationalArchives08', 'title': 'Webinar: Using Discovery, The National Archivesâ online catalogue', }, }, + # jwplayer rtmp + { + 'url': 'http://www.suffolk.edu/sjc/live.php', + 'info_dict': { + 'id': 'live', + 'ext': 'flv', + 'title': 'Massachusetts Supreme Judicial Court Oral Arguments', + 'uploader': 'www.suffolk.edu', + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/', + }, + # Complex jwplayer + { + 'url': 'http://www.indiedb.com/games/king-machine/videos', + 'info_dict': { + 'id': 'videos', + 'ext': 'mp4', + 'title': 'king machine trailer 1', + 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + }, + { + # JWPlayer config passed as variable + 'url': 'http://www.txxx.com/videos/3326530/ariele/', + 'info_dict': { + 'id': '3326530_hq', + 'ext': 'mp4', + 'title': 'ARIELE | Tube Cup', + 'uploader': 'www.txxx.com', + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + } + }, + { + # JWPlatform iframe + 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/', + 'md5': 'ca00a040364b5b439230e7ebfd02c4e9', + 'info_dict': { + 'id': 'O0c5JcKT', + 'ext': 'mp4', + 'upload_date': '20171122', + 'timestamp': 1511366290, + 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone', + }, + 'add_ie': [JWPlatformIE.ie_key()], + }, + { + # Video.js embed, multiple formats + 'url': 'http://ortcam.com/solidworks-ÑÑок-6-наÑÑÑойка-ÑеÑÑежа_33f9b7351.html', + 'info_dict': { + 'id': 'yygqldloqIk', + 'ext': 'mp4', + 'title': 'SolidWorks. УÑок 6 ÐаÑÑÑойка ÑеÑÑежа', + 'description': 'md5:baf95267792646afdbf030e4d06b2ab3', + 'upload_date': '20130314', + 'uploader': 'PROÑÑое3D', + 'uploader_id': 'PROstoe3D', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # Video.js embed, single format + 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=', + 'info_dict': { + 'id': 'watch', + 'ext': 'mp4', + 'title': 'Step 1 - Good Foundation', + 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4', + }, + 'params': { + 'skip_download': True, + }, + }, # rtl.nl embed { 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen', 'playlist_mincount': 5, 'info_dict': { 'id': 'aanslagen-kopenhagen', - 'title': 'Aanslagen Kopenhagen | RTL Nieuws', + 'title': 'Aanslagen Kopenhagen', } }, # Zapiks embed @@ -819,18 +1222,6 @@ class GenericIE(InfoExtractor): 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !', } }, - # Kaltura embed - { - 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15', - 'info_dict': { - 'id': '1_eergr3h1', - 'ext': 'mp4', - 'upload_date': '20150226', - 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com', - 'timestamp': int, - 'title': 'John Carlson Postgame 2/25/15', - }, - }, # Kaltura embed (different embed code) { 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014', @@ -843,44 +1234,130 @@ class GenericIE(InfoExtractor): 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', }, }, - # Kaltura embed protected with referrer + # Kaltura embed with single quotes + { + 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY', + 'info_dict': { + 'id': '0_izeg5utt', + 'ext': 'mp4', + 'title': '35871', + 'timestamp': 1355743100, + 'upload_date': '20121217', + 'uploader_id': 'cplapp@learn360.com', + }, + 'add_ie': ['Kaltura'], + }, + { + # Kaltura embedded via quoted entry_id + 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures', + 'info_dict': { + 'id': '0_utuok90b', + 'ext': 'mp4', + 'title': '06_matthew_brender_raj_dutt', + 'timestamp': 1466638791, + 'upload_date': '20160622', + }, + 'add_ie': ['Kaltura'], + 'expected_warnings': [ + 'Could not send HEAD request' + ], + 'params': { + 'skip_download': True, + } + }, + { + # Kaltura embedded, some fileExt broken (#11480) + 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics', + 'info_dict': { + 'id': '1_sgtvehim', + 'ext': 'mp4', + 'title': 'Our "Standard Models" of particle physics and cosmology', + 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861', + 'timestamp': 1321158993, + 'upload_date': '20111113', + 'uploader_id': 'kps1', + }, + 'add_ie': ['Kaltura'], + }, + { + # Kaltura iframe embed + 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/', + 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44', + 'info_dict': { + 'id': '0_f2cfbpwy', + 'ext': 'mp4', + 'title': 'I. M. Pei: A Centennial Celebration', + 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c', + 'upload_date': '20170403', + 'uploader_id': 'batchUser', + 'timestamp': 1491232186, + }, + 'add_ie': ['Kaltura'], + }, + { + # Kaltura iframe embed, more sophisticated + 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html', + 'info_dict': { + 'id': '1_9gzouybz', + 'ext': 'mp4', + 'title': 'lecture-05sep2017', + 'description': 'md5:40f347d91fd4ba047e511c5321064b49', + 'upload_date': '20170913', + 'uploader_id': 'eps2', + 'timestamp': 1505340777, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Kaltura'], + }, { - 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero', + # meta twitter:player + 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/', 'info_dict': { - 'id': '1_g4fbemnq', + 'id': '0_01b42zps', 'ext': 'mp4', - 'title': 'Violetta - Achter De Schermen - Ruggero', - 'description': 'Achter de schermen met Ruggero', - 'timestamp': 1435133761, - 'upload_date': '20150624', - 'uploader_id': 'echojecka', + 'title': 'Main Twerk (Video)', + 'upload_date': '20171208', + 'uploader_id': 'sebastian.salinas@thechive.com', + 'timestamp': 1512713057, + }, + 'params': { + 'skip_download': True, }, + 'add_ie': ['Kaltura'], }, - # Eagle.Platform embed (generic URL) + # referrer protected EaglePlatform embed { - 'url': 'http://lenta.ru/news/2015/03/06/navalny/', + 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/', 'info_dict': { - 'id': '227304', + 'id': '582306', 'ext': 'mp4', - 'title': 'ÐавалÑнÑй вÑÑел на ÑвободÑ', - 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', - 'thumbnail': 're:^https?://.*\.jpg$', - 'duration': 87, + 'title': 'СÑÐ°Ñ Ðамин: «ÐÑ Ð½Ð°ÑÑÑили девÑÑвенноÑÑÑ ÐÑемлÑ»', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 3382, 'view_count': int, - 'age_limit': 0, + }, + 'params': { + 'skip_download': True, }, }, - # ClipYou (Eagle.Platform) embed (custom URL) + # ClipYou (EaglePlatform) embed (custom URL) { 'url': 'http://muz-tv.ru/play/7129/', + # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used 'info_dict': { 'id': '12820', 'ext': 'mp4', 'title': "'O Sole Mio", - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 216, 'view_count': int, }, + 'params': { + 'skip_download': True, + }, + 'skip': 'This video is unavailable.', }, # Pladform embed { @@ -890,10 +1367,11 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'Ð¢Ð°Ð¹Ð½Ñ Ð¿ÐµÑевала ÐÑÑлова ⢠1 ÑеÑÐ¸Ñ 2 ÑаÑÑÑ', 'description': 'ÐокÑменÑалÑнÑй ÑеÑиал-ÑаÑÑледование одной из ÑамÑÑ Ð¶ÑÑÐºÐ¸Ñ Ñайн ХХ века', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 694, 'age_limit': 0, }, + 'skip': 'HTTP Error 404: Not Found', }, # Playwire embed { @@ -902,7 +1380,7 @@ class GenericIE(InfoExtractor): 'id': '3519514', 'ext': 'mp4', 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer', - 'thumbnail': 're:^https?://.*\.png$', + 'thumbnail': r're:^https?://.*\.png$', 'duration': 45.115, }, }, @@ -914,17 +1392,14 @@ class GenericIE(InfoExtractor): 'id': '518726732', 'ext': 'mp4', 'title': 'Facebook Creates "On This Day" | Crunch Report', + 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild', + 'timestamp': 1427237531, + 'uploader': 'Crunch Report', + 'upload_date': '20150324', }, - }, - # SVT embed - { - 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', - 'info_dict': { - 'id': '2900353', - 'ext': 'flv', - 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', - 'duration': 27, - 'age_limit': 0, + 'params': { + # m3u8 download + 'skip_download': True, }, }, # Crooks and Liars embed @@ -961,81 +1436,69 @@ class GenericIE(InfoExtractor): 'ext': 'flv', 'title': "PFT Live: New leader in the 'new-look' defense", 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e', + 'uploader': 'NBCU-SPORTS', + 'upload_date': '20140107', + 'timestamp': 1389118457, }, + 'skip': 'Invalid Page URL', }, - # UDN embed + # NBC News embed { - 'url': 'http://www.udn.com/news/story/7314/822787', - 'md5': 'fd2060e988c326991037b9aff9df21a6', + 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html', + 'md5': '1aa589c675898ae6d37a17913cf68d66', 'info_dict': { - 'id': '300346', + 'id': 'x_dtl_oa_LettermanliftPR_160608', 'ext': 'mp4', - 'title': 'ä¸ä¸ä¸ç·å¸«è®æ§ å ¨æ ¡å¸«çåæº', - 'thumbnail': 're:^https?://.*\.jpg$', - } + 'title': 'David Letterman: A Preview', + 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.', + 'upload_date': '20160609', + 'timestamp': 1465431544, + 'uploader': 'NBCU-NEWS', + }, }, - # Ooyala embed + # UDN embed { - 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T', + 'url': 'https://video.udn.com/news/300346', + 'md5': 'fd2060e988c326991037b9aff9df21a6', 'info_dict': { - 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', + 'id': '300346', 'ext': 'mp4', - 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.', - 'title': 'This is what separates the Excel masters from the wannabes', - 'duration': 191.933, + 'title': 'ä¸ä¸ä¸ç·å¸«è®æ§ å ¨æ ¡å¸«çåæº', + 'thumbnail': r're:^https?://.*\.jpg$', }, 'params': { - # m3u8 downloads + # m3u8 download 'skip_download': True, - } + }, + 'expected_warnings': ['Failed to parse JSON Expecting value'], }, - # Contains a SMIL manifest + # Brightcove URL in single quotes { - 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html', - 'info_dict': { - 'id': 'file', - 'ext': 'flv', - 'title': '+ Football: Lottery Champions League Europe', - 'uploader': 'www.telewebion.com', - }, - 'params': { - # rtmpe downloads - 'skip_download': True, - } - }, - # Brightcove URL in single quotes - { - 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', - 'md5': '4ae374f1f8b91c889c4b9203c8c752af', + 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', + 'md5': '4ae374f1f8b91c889c4b9203c8c752af', 'info_dict': { 'id': '4255764656001', 'ext': 'mp4', 'title': 'SN Presents: Russell Martin, World Citizen', 'description': 'To understand why he was the Toronto Blue Jaysâ 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.', 'uploader': 'Rogers Sportsnet', + 'uploader_id': '1704050871', + 'upload_date': '20150525', + 'timestamp': 1432570283, }, }, - # Dailymotion Cloud video - { - 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', - 'md5': '49444254273501a64675a7e68c502681', - 'info_dict': { - 'id': '5585de919473990de4bee11b', - 'ext': 'mp4', - 'title': 'Le débat', - 'thumbnail': 're:^https?://.*\.jpe?g$', - } - }, - # OnionStudios embed + # Kinja embed { 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', 'info_dict': { - 'id': '2855', + 'id': '106351', 'ext': 'mp4', 'title': 'Donât Understand Bitcoin? This Man Will Mumble An Explanation At You', - 'thumbnail': 're:^https?://.*\.jpe?g$', - 'uploader': 'ClickHole', - 'uploader_id': 'clickhole', + 'description': 'Migrated from OnionStudios', + 'thumbnail': r're:^https?://.*\.jpe?g$', + 'uploader': 'clickhole', + 'upload_date': '20150527', + 'timestamp': 1432744860, } }, # SnagFilms embed @@ -1059,16 +1522,6 @@ class GenericIE(InfoExtractor): 'duration': 248.667, }, }, - # ScreenwaveMedia embed - { - 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1', - 'md5': '24ace5baba0d35d55c6810b51f34e9e0', - 'info_dict': { - 'id': 'cinemasnob-55d26273809dd', - 'ext': 'mp4', - 'title': 'cinemasnob', - }, - }, # BrightcoveInPageEmbed embed { 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/', @@ -1080,20 +1533,641 @@ class GenericIE(InfoExtractor): 'duration': 51690, }, }, - # JWPlayer with M3U8 + # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions' + # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm + { + 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html', + 'info_dict': { + 'id': '4785848093001', + 'ext': 'mp4', + 'title': 'The Cardinal Pell Interview', + 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ', + 'uploader': 'GlobeCast Australia - GlobeStream', + 'uploader_id': '2733773828001', + 'upload_date': '20160304', + 'timestamp': 1457083087, + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + }, + }, + { + # Brightcove embed with whitespace around attribute names + 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill', + 'info_dict': { + 'id': '3167554373001', + 'ext': 'mp4', + 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill", + 'description': 'md5:57bacb0e0f29349de4972bfda3191713', + 'uploader_id': '1079349493', + 'upload_date': '20140207', + 'timestamp': 1391810548, + }, + 'params': { + 'skip_download': True, + }, + }, + # Another form of arte.tv embed + { + 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html', + 'md5': '850bfe45417ddf221288c88a0cffe2e2', + 'info_dict': { + 'id': '030273-562_PLUS7-F', + 'ext': 'mp4', + 'title': 'ARTE Reportage - Nulle part, en France', + 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d', + 'upload_date': '20160409', + }, + }, + # LiveLeak embed + { + 'url': 'http://www.wykop.pl/link/3088787/', + 'md5': '7619da8c820e835bef21a1efa2a0fc71', + 'info_dict': { + 'id': '874_1459135191', + 'ext': 'mp4', + 'title': 'Man shows poor quality of new apartment building', + 'description': 'The wall is like a sand pile.', + 'uploader': 'Lake8737', + }, + 'add_ie': [LiveLeakIE.ie_key()], + }, + # Another LiveLeak embed pattern (#13336) + { + 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/', + 'info_dict': { + 'id': '2eb_1496309988', + 'ext': 'mp4', + 'title': 'Thief robs place where everyone was armed', + 'description': 'md5:694d73ee79e535953cf2488562288eee', + 'uploader': 'brazilwtf', + }, + 'add_ie': [LiveLeakIE.ie_key()], + }, + # Duplicated embedded video URLs + { + 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443', + 'info_dict': { + 'id': '149298443_480_16c25b74_2', + 'ext': 'mp4', + 'title': 'vs. Blue Orange Spring Game', + 'uploader': 'www.hudl.com', + }, + }, + # twitter:player:stream embed { - 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video', + 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288', 'info_dict': { - 'id': 'playlist', + 'id': 'master', 'ext': 'mp4', - 'title': 'СлÑÑайнÑй пÑÐ¾Ñ Ð¾Ð¶Ð¸Ð¹ поймал авÑоÑгонÑика в ÐÑÑманÑке. ÐÐÐÐÐ | Ð ÐРТÐ', - 'uploader': 'ren.tv', + 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine', + 'uploader': 'www.rtl.be', }, 'params': { # m3u8 downloads 'skip_download': True, + }, + }, + # twitter:player embed + { + 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/', + 'md5': 'a3e0df96369831de324f0778e126653c', + 'info_dict': { + 'id': '4909620399001', + 'ext': 'mp4', + 'title': 'What Do Black Holes Sound Like?', + 'description': 'what do black holes sound like', + 'upload_date': '20160524', + 'uploader_id': '29913724001', + 'timestamp': 1464107587, + 'uploader': 'TheAtlantic', + }, + 'add_ie': ['BrightcoveLegacy'], + }, + # Facebook <iframe> embed + { + 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html', + 'md5': 'fbcde74f534176ecb015849146dd3aee', + 'info_dict': { + 'id': '599637780109885', + 'ext': 'mp4', + 'title': 'Facebook video #599637780109885', + }, + }, + # Facebook <iframe> embed, plugin video + { + 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/', + 'info_dict': { + 'id': '1754168231264132', + 'ext': 'mp4', + 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...', + 'uploader': 'Tariq Ramadan (official)', + 'timestamp': 1496758379, + 'upload_date': '20170606', + }, + 'params': { + 'skip_download': True, + }, + }, + # Facebook API embed + { + 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/', + 'md5': 'a47372ee61b39a7b90287094d447d94e', + 'info_dict': { + 'id': '10153467542406923', + 'ext': 'mp4', + 'title': 'Facebook video #10153467542406923', + }, + }, + # Wordpress "YouTube Video Importer" plugin + { + 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/', + 'md5': 'd16797741b560b485194eddda8121b48', + 'info_dict': { + 'id': 'HNTXWDXV9Is', + 'ext': 'mp4', + 'title': 'Blue Devils Drumline Stanford lot 2016', + 'upload_date': '20160627', + 'uploader_id': 'GENOCIDE8GENERAL10', + 'uploader': 'cylus cyrus', + }, + }, + { + # video stored on custom kaltura server + 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv', + 'md5': '537617d06e64dfed891fa1593c4b30cc', + 'info_dict': { + 'id': '0_1iotm5bh', + 'ext': 'mp4', + 'title': 'Elecciones británicas: 5 lecciones para Rajoy', + 'description': 'md5:435a89d68b9760b92ce67ed227055f16', + 'uploader_id': 'videos.expansion@el-mundo.net', + 'upload_date': '20150429', + 'timestamp': 1430303472, + }, + 'add_ie': ['Kaltura'], + }, + { + # multiple kaltura embeds, nsfw + 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html', + 'info_dict': { + 'id': 'kamila-avec-video-jaime-sadomie', + 'title': "Kamila avec vÃdeo âJ'aime sadomieâ", + }, + 'playlist_count': 8, + }, + { + # Non-standard Vimeo embed + 'url': 'https://openclassrooms.com/courses/understanding-the-web', + 'md5': '64d86f1c7d369afd9a78b38cbb88d80a', + 'info_dict': { + 'id': '148867247', + 'ext': 'mp4', + 'title': 'Understanding the web - Teaser', + 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.', + 'upload_date': '20151214', + 'uploader': 'OpenClassrooms', + 'uploader_id': 'openclassrooms', + }, + 'add_ie': ['Vimeo'], + }, + { + # generic vimeo embed that requires original URL passed as Referer + 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/', + 'only_matching': True, + }, + { + 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video', + 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365', + 'info_dict': { + 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'description': 'Royalty free test video', + 'timestamp': 1432816365, + 'upload_date': '20150528', + 'is_live': False, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [ArkenaIE.ie_key()], + }, + { + '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/', + 'info_dict': { + 'id': '1c7141f46c', + 'ext': 'mp4', + 'title': 'ÐÐ ÐÐСЪРÐТ ÐÐÐ ÐÐ: ÐзÑиÑане на газ на бензиноÑÑанÑÐ¸Ñ Ð² Ðловдив', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [Vbox7IE.ie_key()], + }, + { + # DBTV embeds + 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/', + 'info_dict': { + 'id': '43254897', + 'title': 'Etter ett Ã¥rs planlegging, klaffet endelig alt: - Jeg mÃ¥tte ta en liten dans', + }, + 'playlist_mincount': 3, + }, + { + # Videa embeds + 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html', + 'info_dict': { + 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style', + 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum', + }, + 'playlist_mincount': 2, + }, + { + # 20 minuten embed + 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552', + 'info_dict': { + 'id': '523629', + 'ext': 'mp4', + 'title': 'So kommen Sie bei Eis und Schnee sicher an', + 'description': 'md5:117c212f64b25e3d95747e5276863f7d', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [TwentyMinutenIE.ie_key()], + }, + { + # VideoPress embed + 'url': 'https://en.support.wordpress.com/videopress/', + 'info_dict': { + 'id': 'OcobLTqC', + 'ext': 'm4v', + 'title': 'IMG_5786', + 'timestamp': 1435711927, + 'upload_date': '20150701', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [VideoPressIE.ie_key()], + }, + { + # Rutube embed + 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2', + 'info_dict': { + 'id': '9b3d5bee0a8740bf70dfd29d3ea43541', + 'ext': 'flv', + 'title': 'Ðагаззино: ÐÐ°Ð·Ð°Ð½Ñ 2', + 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a', + 'uploader': 'Ðагаззино', + 'upload_date': '20170228', + 'uploader_id': '996642', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [RutubeIE.ie_key()], + }, + { + # ThePlatform embedded with whitespaces in URLs + 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm', + 'only_matching': True, + }, + { + # Senate ISVP iframe https + 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security', + 'md5': 'fb8c70b0b515e5037981a2492099aab8', + 'info_dict': { + 'id': 'govtaff020316', + 'ext': 'mp4', + 'title': 'Integrated Senate Video Player', + }, + 'add_ie': [SenateISVPIE.ie_key()], + }, + { + # Limelight embeds (1 channel embed + 4 media embeds) + 'url': 'http://www.sedona.com/FacilitatorTraining2017', + 'info_dict': { + 'id': 'FacilitatorTraining2017', + 'title': 'Facilitator Training 2017', + }, + 'playlist_mincount': 5, + }, + { + # Limelight embed (LimelightPlayerUtil.embed) + 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri', + 'info_dict': { + 'id': '95d035dc5c8a401588e9c0e6bd1e9c92', + 'ext': 'mp4', + 'title': '07448641', + 'timestamp': 1499890639, + 'upload_date': '20170712', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['LimelightMedia'], + }, + { + 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/', + 'info_dict': { + 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest', + 'title': 'Standoff with Walnut Creek murder suspect ends', + 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788', + }, + 'playlist_mincount': 4, + }, + { + # WashingtonPost embed + 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches', + 'info_dict': { + 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac', + 'ext': 'mp4', + 'title': "No one has seen the drama series based on Trump's life \u2014 until now", + '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 â and enlisted actors.', + 'timestamp': 1455216756, + 'uploader': 'The Washington Post', + 'upload_date': '20160211', + }, + 'add_ie': [WashingtonPostIE.ie_key()], + }, + { + # Mediaset embed + 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml', + 'info_dict': { + 'id': '720642', + 'ext': 'mp4', + 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [MediasetIE.ie_key()], + }, + { + # JOJ.sk embeds + 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok', + 'info_dict': { + 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok', + 'title': 'Slovenskom sa prehnala vlna silných búrok', + }, + 'playlist_mincount': 5, + 'add_ie': [JojIE.ie_key()], + }, + { + # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video) + 'url': 'https://tvrain.ru/amp/418921/', + 'md5': 'cc00413936695987e8de148b67d14f1d', + 'info_dict': { + 'id': '418921', + 'ext': 'mp4', + 'title': 'СÑÐ°Ñ Ðамин: «ÐÑ Ð½Ð°ÑÑÑили девÑÑвенноÑÑÑ ÐÑемлÑ»', + }, + }, + { + # vzaar embed + 'url': 'http://help.vzaar.com/article/165-embedding-video', + 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4', + 'info_dict': { + 'id': '8707641', + 'ext': 'mp4', + 'title': 'Building A Business Online: Principal Chairs Q & A', + }, + }, + { + # multiple HTML5 videos on one page + 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html', + 'info_dict': { + 'id': 'keyscenarios', + 'title': 'Rescue Kit 14 Free Edition - Getting started', + }, + 'playlist_count': 4, + }, + { + # vshare embed + 'url': 'https://youtube-dl-demo.neocities.org/vshare.html', + 'md5': '17b39f55b5497ae8b59f5fbce8e35886', + 'info_dict': { + 'id': '0f64ce6', + 'title': 'vl14062007715967', + 'ext': 'mp4', } - } + }, + { + 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/', + 'md5': 'aecd089f55b1cb5a59032cb049d3a356', + 'info_dict': { + 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d', + 'ext': 'mp4', + 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare', + 'description': 'md5:5a51db84a62def7b7054df2ade403c6c', + 'timestamp': 1474354800, + 'upload_date': '20160920', + } + }, + { + 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton', + 'info_dict': { + 'id': '1731611', + 'ext': 'mp4', + 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!', + 'description': 'md5:eb5f23826a027ba95277d105f248b825', + 'timestamp': 1516100691, + 'upload_date': '20180116', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [SpringboardPlatformIE.ie_key()], + }, + { + 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU', + 'info_dict': { + 'id': 'uPDB5I9wfp8', + 'ext': 'webm', + 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3', + 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d', + 'upload_date': '20160219', + 'uploader': 'Pocoyo - Português (BR)', + 'uploader_id': 'PocoyoBrazil', + }, + 'add_ie': [YoutubeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html', + 'info_dict': { + 'id': 'vMDE4NzI1Mjgt690b', + 'ext': 'mp4', + 'title': 'ÐоÑÑÑа', + }, + 'add_ie': [YapFilesIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # CloudflareStream embed + 'url': 'https://www.cloudflare.com/products/cloudflare-stream/', + 'info_dict': { + 'id': '31c9291ab41fac05471db4e73aa11717', + 'ext': 'mp4', + 'title': '31c9291ab41fac05471db4e73aa11717', + }, + 'add_ie': [CloudflareStreamIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # PeerTube embed + 'url': 'https://joinpeertube.org/fr/home/', + 'info_dict': { + 'id': 'home', + 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube', + }, + 'playlist_count': 2, + }, + { + # Indavideo embed + 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/', + 'info_dict': { + 'id': '1693903', + 'ext': 'mp4', + 'title': 'Ãgy kell otthon hamburgert sütni', + 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7', + 'timestamp': 1426330212, + 'upload_date': '20150314', + 'uploader': 'StreetKitchen', + 'uploader_id': '546363', + }, + 'add_ie': [IndavideoEmbedIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # APA embed via JWPlatform embed + 'url': 'http://www.vol.at/blue-man-group/5593454', + 'info_dict': { + 'id': 'jjv85FdZ', + 'ext': 'mp4', + 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 254, + 'timestamp': 1519211149, + 'upload_date': '20180221', + }, + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'http://share-videos.se/auto/video/83645793?uid=13', + 'md5': 'b68d276de422ab07ee1d49388103f457', + 'info_dict': { + 'id': '83645793', + 'title': 'Lock up and get excited', + 'ext': 'mp4' + }, + 'skip': 'TODO: fix nested playlists processing in tests', + }, + { + # Viqeo embeds + 'url': 'https://viqeo.tv/', + 'info_dict': { + 'id': 'viqeo', + 'title': 'All-new video platform', + }, + 'playlist_count': 6, + }, + { + # Squarespace video embed, 2019-08-28 + 'url': 'http://ootboxford.com', + 'info_dict': { + 'id': 'Tc7b_JGdZfw', + 'title': 'Out of the Blue, at Childish Things 10', + 'ext': 'mp4', + 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f', + 'uploader_id': 'helendouglashouse', + 'uploader': 'Helen & Douglas House', + 'upload_date': '20140328', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # Zype embed + 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + 'description': 'md5:5ff01e76316bd8d46508af26dc86023b', + 'upload_date': '20170909', + 'timestamp': 1504915200, + }, + 'add_ie': [ZypeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # videojs embed + 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', + 'info_dict': { + 'id': 'shell', + 'ext': 'mp4', + 'title': 'ÐоÑÑавÑик пиÑÑÑ ÑпÑоÑил ÑазÑеÑÐµÐ½Ð¸Ñ ÑÑгÑаÑÑ Ð½Ð° ÑоÑÑепиано', + 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Failed to download MPD manifest'], + }, + { + # DailyMotion embed with DM.player + 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804', + 'info_dict': { + 'id': 'k6aKkGHd9FJs4mtJN39', + 'ext': 'mp4', + 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final', + 'description': 'This video is private.', + 'uploader_id': 'x1jf30l', + 'uploader': 'beIN SPORTS USA', + 'upload_date': '20190528', + 'timestamp': 1559062971, + }, + 'params': { + 'skip_download': True, + }, + }, + # { + # # TODO: find another test + # # http://schema.org/VideoObject + # 'url': 'https://flipagram.com/f/nyvTSJMKId', + # 'md5': '888dcf08b7ea671381f00fab74692755', + # 'info_dict': { + # 'id': 'nyvTSJMKId', + # 'ext': 'mp4', + # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', + # 'description': '#love for cats.', + # 'timestamp': 1461244995, + # 'upload_date': '20160421', + # }, + # 'params': { + # 'force_generic_extractor': True, + # }, + # } ] def report_following_redirect(self, new_url): @@ -1107,19 +2181,21 @@ class GenericIE(InfoExtractor): entries = [] for it in doc.findall('./channel/item'): - next_url = xpath_text(it, 'link', fatal=False) + next_url = None + enclosure_nodes = it.findall('./enclosure') + for e in enclosure_nodes: + next_url = e.attrib.get('url') + if next_url: + break + if not next_url: - enclosure_nodes = it.findall('./enclosure') - for e in enclosure_nodes: - next_url = e.attrib.get('url') - if next_url: - break + next_url = xpath_text(it, 'link', fatal=False) if not next_url: continue entries.append({ - '_type': 'url', + '_type': 'url_transparent', 'url': next_url, 'title': it.find('title').text, }) @@ -1171,10 +2247,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: @@ -1183,7 +2256,7 @@ class GenericIE(InfoExtractor): default_search = 'fixup_error' if default_search in ('auto', 'auto_warning', 'fixup_error'): - if '/' in url: + if re.match(r'^[^\s/]+\.[^\s/]+/', url): self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) elif default_search != 'fixup_error': @@ -1214,7 +2287,7 @@ class GenericIE(InfoExtractor): force_videoid = smuggled_data['force_videoid'] video_id = force_videoid else: - video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0]) + video_id = self._generic_id(url) self.to_screen('%s: Requesting header' % video_id) @@ -1241,28 +2314,31 @@ class GenericIE(InfoExtractor): full_response = self._request_webpage(request, video_id) head_response = full_response + info_dict = { + 'id': video_id, + 'title': self._generic_title(url), + 'upload_date': unified_strdate(head_response.headers.get('Last-Modified')) + } + # Check for direct link to a video - content_type = head_response.headers.get('Content-Type', '') - m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type) + content_type = head_response.headers.get('Content-Type', '').lower() + m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type) if m: - upload_date = unified_strdate( - head_response.headers.get('Last-Modified')) - formats = [] - if m.group('format_id').endswith('mpegurl'): + format_id = compat_str(m.group('format_id')) + if format_id.endswith('mpegurl'): formats = self._extract_m3u8_formats(url, video_id, 'mp4') + elif format_id == 'f4m': + formats = self._extract_f4m_formats(url, video_id) else: formats = [{ - 'format_id': m.group('format_id'), + 'format_id': format_id, 'url': url, 'vcodec': 'none' if m.group('type') == 'audio' else None }] - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), - 'direct': True, - 'formats': formats, - 'upload_date': upload_date, - } + info_dict['direct'] = True + self._sort_formats(formats) + info_dict['formats'] = formats + return info_dict if not self._downloader.params.get('test', False) and not is_intentional: force = self._downloader.params.get('force_generic_extractor', False) @@ -1282,21 +2358,24 @@ class GenericIE(InfoExtractor): request.add_header('Accept-Encoding', '*') full_response = self._request_webpage(request, video_id) + first_bytes = full_response.read(512) + + # Is it an M3U playlist? + if first_bytes.startswith(b'#EXTM3U'): + info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4') + self._sort_formats(info_dict['formats']) + return info_dict + # Maybe it's a direct link to a video? # Be careful not to download the whole thing! - first_bytes = full_response.read(512) if not is_html(first_bytes): self._downloader.report_warning( 'URL could be a direct video link, returning it as such.') - upload_date = unified_strdate( - head_response.headers.get('Last-Modified')) - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'url': url, - 'upload_date': upload_date, - } + }) + return info_dict webpage = self._webpage_read_content( full_response, url, video_id, prefix=first_bytes) @@ -1308,17 +2387,31 @@ class GenericIE(InfoExtractor): doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return self._extract_rss(url, video_id, doc) + elif doc.tag == 'SmoothStreamingMedia': + info_dict['formats'] = self._parse_ism_formats(doc, url) + self._sort_formats(info_dict['formats']) + return info_dict elif re.match(r'^(?:{[^}]+})?smil$', doc.tag): - return self._parse_smil(doc, url, video_id) + smil = self._parse_smil(doc, url, video_id) + self._sort_formats(smil['formats']) + return smil elif doc.tag == '{http://xspf.org/ns/0/}playlist': - return self.playlist_result(self._parse_xspf(doc, video_id), video_id) + return self.playlist_result( + self._parse_xspf( + doc, video_id, xspf_url=url, + xspf_base_url=full_response.geturl()), + video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), - 'formats': self._parse_mpd_formats( - doc, video_id, mpd_base_url=url.rpartition('/')[0]), - } + info_dict['formats'] = self._parse_mpd_formats( + doc, + mpd_base_url=full_response.geturl().rpartition('/')[0], + mpd_url=url) + self._sort_formats(info_dict['formats']) + return info_dict + elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag): + info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id) + self._sort_formats(info_dict['formats']) + return info_dict except compat_xml_parse_error: pass @@ -1328,17 +2421,24 @@ class GenericIE(InfoExtractor): return camtasia_res # Sometimes embedded video player is hidden behind percent encoding - # (e.g. https://github.com/rg3/youtube-dl/issues/2448) + # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way webpage = compat_urllib_parse_unquote(webpage) + # Unescape squarespace embeds to be detected by generic extractor, + # see https://github.com/ytdl-org/youtube-dl/issues/21294 + webpage = re.sub( + r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>', + lambda x: unescapeHTML(x.group(0)), webpage) + # it's tempting to parse this further, but you would # have to take into account all the variations like # Video Title - Site Name # Site Name | Video Title # Video Title - Tagline | Site Name # and so on and so forth; it's just not practical - video_title = self._html_search_regex( + video_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( r'(?s)<title>(.*?)</title>', webpage, 'video title', default='video') @@ -1347,7 +2447,7 @@ class GenericIE(InfoExtractor): # And then there are the jokers who advertise that they use RTA, # but actually don't. AGE_LIMIT_MARKERS = [ - r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>', + r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>', ] if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): age_limit = 18 @@ -1356,18 +2456,19 @@ class GenericIE(InfoExtractor): video_uploader = self._search_regex( r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') - # Helper method - def _playlist_from_matches(matches, getter=None, ie=None): - urlrs = orderedSet( - self.url_result(self._proto_relative_url(getter(m) if getter else m), ie) - for m in matches) - return self.playlist_result( - urlrs, playlist_id=video_id, playlist_title=video_title) + video_description = self._og_search_description(webpage, default=None) + video_thumbnail = self._og_search_thumbnail(webpage, default=None) + + info_dict.update({ + 'title': video_title, + 'description': video_description, + 'thumbnail': video_thumbnail, + 'age_limit': age_limit, + }) # Look for Brightcove Legacy Studio embeds bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage) if bc_urls: - self.to_screen('Brightcove video detected.') entries = [{ '_type': 'url', 'url': smuggle_url(bc_url, {'Referer': url}), @@ -1382,20 +2483,38 @@ class GenericIE(InfoExtractor): } # Look for Brightcove New Studio embeds - bc_urls = BrightcoveNewIE._extract_urls(webpage) + bc_urls = BrightcoveNewIE._extract_urls(self, webpage) if bc_urls: - return _playlist_from_matches(bc_urls, ie='BrightcoveNew') + return self.playlist_from_matches( + bc_urls, video_id, video_title, + getter=lambda x: smuggle_url(x, {'referrer': url}), + ie='BrightcoveNew') + + # Look for Nexx embeds + nexx_urls = NexxIE._extract_urls(webpage) + if nexx_urls: + return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key()) + + # Look for Nexx iFrame embeds + nexx_embed_urls = NexxEmbedIE._extract_urls(webpage) + if nexx_embed_urls: + return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key()) + + # Look for ThePlatform embeds + tp_urls = ThePlatformIE._extract_urls(webpage) + if tp_urls: + return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform') # Look for embedded rtl.nl player matches = re.findall( - r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"', + r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"', webpage) if matches: - return _playlist_from_matches(matches, ie='RtlNl') + return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl') - vimeo_url = VimeoIE._extract_vimeo_url(url, webpage) - if vimeo_url is not None: - return self.url_result(vimeo_url) + vimeo_urls = VimeoIE._extract_urls(url, webpage) + if vimeo_urls: + return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key()) vid_me_embed_url = self._search_regex( r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]', @@ -1403,35 +2522,15 @@ class GenericIE(InfoExtractor): if vid_me_embed_url is not None: return self.url_result(vid_me_embed_url, 'Vidme') - # Look for embedded YouTube player - matches = re.findall(r'''(?x) - (?: - <iframe[^>]+?src=| - data-video-url=| - <embed[^>]+?src=| - embedSWF\(?:\s*| - new\s+SWFObject\( - ) - (["\']) - (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ - (?:embed|v|p)/.+?) - \1''', webpage) - if matches: - return _playlist_from_matches( - matches, lambda m: unescapeHTML(m[1])) + # Look for YouTube embeds + youtube_urls = YoutubeIE._extract_urls(webpage) + if youtube_urls: + return self.playlist_from_matches( + youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key()) - # Look for lazyYT YouTube embed - matches = re.findall( - r'class="lazyYT" data-youtube-id="([^"]+)"', webpage) - if matches: - return _playlist_from_matches(matches, lambda m: unescapeHTML(m)) - - # Look for embedded Dailymotion player - matches = re.findall( - r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) + matches = DailymotionIE._extract_urls(webpage) if matches: - return _playlist_from_matches( - matches, lambda m: unescapeHTML(m[1])) + return self.playlist_from_matches(matches, video_id, video_title) # Look for embedded Dailymotion playlist player (#3822) m = re.search( @@ -1440,56 +2539,36 @@ class GenericIE(InfoExtractor): playlists = re.findall( r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url'))) if playlists: - return _playlist_from_matches( - playlists, lambda p: '//dailymotion.com/playlist/%s' % p) + return self.playlist_from_matches( + playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p) - # Look for embedded Wistia player - match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) - if match: - embed_url = self._proto_relative_url( - unescapeHTML(match.group('url'))) - return { - '_type': 'url_transparent', - 'url': embed_url, - 'ie_key': 'Wistia', - 'uploader': video_uploader, - 'title': video_title, - 'id': video_id, - } + # Look for DailyMail embeds + dailymail_urls = DailyMailIE._extract_urls(webpage) + if dailymail_urls: + return self.playlist_from_matches( + dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) - match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) - if match: - return { - '_type': 'url_transparent', - 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), - 'ie_key': 'Wistia', - 'uploader': video_uploader, - 'title': video_title, - 'id': match.group('id') - } + # Look for Teachable embeds, must be before Wistia + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + + # Look for embedded Wistia player + wistia_urls = WistiaIE._extract_urls(webpage) + if wistia_urls: + playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key()) + for entry in playlist['entries']: + entry.update({ + '_type': 'url_transparent', + 'uploader': video_uploader, + }) + return playlist # Look for SVT player svt_url = SVTIE._extract_url(webpage) if svt_url: return self.url_result(svt_url, 'SVT') - # Look for embedded condenast player - matches = re.findall( - r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")', - webpage) - if matches: - return { - '_type': 'playlist', - 'entries': [{ - '_type': 'url', - 'ie_key': 'CondeNast', - 'url': ma, - } for ma in matches], - 'title': video_title, - 'id': video_id, - } - # Look for Bandcamp pages with custom domain mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) if mobj is not None: @@ -1524,20 +2603,29 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url')) # Look for Ooyala videos - mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or - re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or - re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or - re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage)) + mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) + or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) + or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) + or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) + or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage)) if mobj is not None: - return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url})) + embed_token = self._search_regex( + r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)', + webpage, 'ooyala embed token', default=None) + return OoyalaIE._build_url_result(smuggle_url( + mobj.group('ec'), { + 'domain': url, + 'embed_token': embed_token, + })) # Look for multiple Ooyala embeds on SBN network websites mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage) if mobj is not None: embeds = self._parse_json(mobj.group(1), video_id, fatal=False) if embeds: - return _playlist_from_matches( - embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') + return self.playlist_from_matches( + embeds, video_id, video_title, + getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') # Look for Aparat videos mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage) @@ -1549,24 +2637,10 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group(1), 'Mpora') - # Look for embedded NovaMov-based player - mobj = re.search( - r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\']) - (?P<url>http://(?:(?:embed|www)\.)? - (?:novamov\.com| - nowvideo\.(?:ch|sx|eu|at|ag|co)| - videoweed\.(?:es|com)| - movshare\.(?:net|sx|ag)| - divxstage\.(?:eu|net|ch|co|at|ag)) - /embed\.php.+?)\1''', webpage) - if mobj is not None: - return self.url_result(mobj.group('url')) - # Look for embedded Facebook player - mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Facebook') + facebook_urls = FacebookIE._extract_urls(webpage) + if facebook_urls: + return self.playlist_from_matches(facebook_urls, video_id, video_title) # Look for embedded VK player mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage) @@ -1574,9 +2648,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'VK') # Look for embedded Odnoklassniki player - mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Odnoklassniki') + odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) # Look for embedded ivi player mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) @@ -1600,13 +2674,13 @@ class GenericIE(InfoExtractor): # Look for funnyordie embed matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) if matches: - return _playlist_from_matches( - matches, getter=unescapeHTML, ie='FunnyOrDie') + return self.playlist_from_matches( + matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie') # Look for BBC iPlayer embed matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage) if matches: - return _playlist_from_matches(matches, ie='BBCCoUk') + return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk') # Look for embedded RUTV player rutv_url = RUTVIE._extract_url(webpage) @@ -1619,19 +2693,54 @@ class GenericIE(InfoExtractor): return self.url_result(tvc_url, 'TVC') # Look for embedded SportBox player - sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + sportbox_urls = SportBoxIE._extract_urls(webpage) if sportbox_urls: - return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed') - - # Look for embedded PornHub player - pornhub_url = PornHubIE._extract_url(webpage) - if pornhub_url: - return self.url_result(pornhub_url, 'PornHub') + return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key()) # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) if xhamster_urls: - return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed') + return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed') + + # Look for embedded TNAFlixNetwork player + tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage) + if tnaflix_urls: + return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key()) + + # Look for embedded PornHub player + pornhub_urls = PornHubIE._extract_urls(webpage) + if pornhub_urls: + return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key()) + + # Look for embedded DrTuber player + drtuber_urls = DrTuberIE._extract_urls(webpage) + if drtuber_urls: + return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key()) + + # Look for embedded RedTube player + redtube_urls = RedTubeIE._extract_urls(webpage) + if redtube_urls: + return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key()) + + # Look for embedded Tube8 player + tube8_urls = Tube8IE._extract_urls(webpage) + if tube8_urls: + return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key()) + + # Look for embedded Mofosex player + mofosex_urls = MofosexEmbedIE._extract_urls(webpage) + if mofosex_urls: + return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key()) + + # Look for embedded Spankwire player + spankwire_urls = SpankwireIE._extract_urls(webpage) + if spankwire_urls: + return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key()) + + # Look for embedded YouPorn player + youporn_urls = YouPornIE._extract_urls(webpage) + if youporn_urls: + return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key()) # Look for embedded Tvigle player mobj = re.search( @@ -1646,14 +2755,13 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'TED') # Look for embedded Ustream videos - mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Ustream') + ustream_url = UstreamIE._extract_url(webpage) + if ustream_url: + return self.url_result(ustream_url, UstreamIE.ie_key()) # Look for embedded arte.tv player mobj = re.search( - r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"', + r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"', webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'ArteTVEmbed') @@ -1676,20 +2784,14 @@ class GenericIE(InfoExtractor): return self.url_result(myvi_url) # Look for embedded soundcloud player - mobj = re.search( - r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', - webpage) - if mobj is not None: - url = unescapeHTML(mobj.group('url')) - return self.url_result(url) + soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage) + if soundcloud_urls: + return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML) - # Look for embedded vulture.com player - mobj = re.search( - r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"', - webpage) - if mobj is not None: - url = unescapeHTML(mobj.group('url')) - return self.url_result(url, ie='Vulture') + # Look for tunein player + tunein_urls = TuneInBaseIE._extract_urls(webpage) + if tunein_urls: + return self.playlist_from_matches(tunein_urls, video_id, video_title) # Look for embedded mtvservices player mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage) @@ -1739,7 +2841,7 @@ class GenericIE(InfoExtractor): return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast') mobj = re.search( - r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"', + r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"', webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'Livestream') @@ -1751,20 +2853,19 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'Zapiks') # Look for Kaltura embeds - mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or - re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage)) - if mobj is not None: - return self.url_result(smuggle_url( - 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), - {'source_url': url}), 'Kaltura') - - # Look for Eagle.Platform embeds - mobj = re.search( - r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'EaglePlatform') - - # Look for ClipYou (uses Eagle.Platform) embeds + kaltura_urls = KalturaIE._extract_urls(webpage) + if kaltura_urls: + return self.playlist_from_matches( + kaltura_urls, video_id, video_title, + getter=lambda x: smuggle_url(x, {'source_url': url}), + ie=KalturaIE.ie_key()) + + # Look for EaglePlatform embeds + eagleplatform_url = EaglePlatformIE._extract_url(webpage) + if eagleplatform_url: + return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key()) + + # Look for ClipYou (uses EaglePlatform) embeds mobj = re.search( r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage) if mobj is not None: @@ -1780,6 +2881,11 @@ class GenericIE(InfoExtractor): if videomore_url: return self.url_result(videomore_url) + # Look for Webcaster embeds + webcaster_url = WebcasterFeedIE._extract_url(self, webpage) + if webcaster_url: + return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key()) + # Look for Playwire embeds mobj = re.search( r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage) @@ -1803,6 +2909,12 @@ class GenericIE(InfoExtractor): if nbc_sports_url: return self.url_result(nbc_sports_url, 'NBCSportsVPlayer') + # Look for NBC News embeds + nbc_news_embed_url = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage) + if nbc_news_embed_url: + return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews') + # Look for Google Drive embeds google_drive_url = GoogleDriveIE._extract_url(webpage) if google_drive_url: @@ -1810,7 +2922,7 @@ class GenericIE(InfoExtractor): # Look for UDN embeds mobj = re.search( - r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage) + r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage) if mobj is not None: return self.url_result( compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed') @@ -1820,46 +2932,53 @@ class GenericIE(InfoExtractor): if senate_isvp_url: return self.url_result(senate_isvp_url, 'SenateISVP') - # Look for Dailymotion Cloud videos - dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) - if dmcloud_url: - return self.url_result(dmcloud_url, 'DailymotionCloud') + # Look for Kinja embeds + kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url) + if kinja_embed_urls: + return self.playlist_from_matches( + kinja_embed_urls, video_id, video_title) # Look for OnionStudios embeds onionstudios_url = OnionStudiosIE._extract_url(webpage) if onionstudios_url: return self.url_result(onionstudios_url) - # Look for SnagFilms embeds - snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage) - if snagfilms_url: - return self.url_result(snagfilms_url) + # Look for ViewLift embeds + viewlift_url = ViewLiftEmbedIE._extract_url(webpage) + if viewlift_url: + return self.url_result(viewlift_url) # Look for JWPlatform embeds - jwplatform_url = JWPlatformIE._extract_url(webpage) - if jwplatform_url: - return self.url_result(jwplatform_url, 'JWPlatform') - - # Look for ScreenwaveMedia embeds - mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage) - if mobj is not None: - return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia') + jwplatform_urls = JWPlatformIE._extract_urls(webpage) + if jwplatform_urls: + return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key()) # Look for Digiteka embeds digiteka_url = DigitekaIE._extract_url(webpage) if digiteka_url: return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key()) + # Look for Arkena embeds + arkena_url = ArkenaIE._extract_url(webpage) + if arkena_url: + return self.url_result(arkena_url, ArkenaIE.ie_key()) + + # Look for Piksel embeds + piksel_url = PikselIE._extract_url(webpage) + if piksel_url: + return self.url_result(piksel_url, PikselIE.ie_key()) + # Look for Limelight embeds - mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage) - if mobj: - lm = { - 'Media': 'media', - 'Channel': 'channel', - 'ChannelList': 'channel_list', - } - return self.url_result('limelight:%s:%s' % ( - lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) + limelight_urls = LimelightBaseIE._extract_urls(webpage, url) + if limelight_urls: + return self.playlist_result( + limelight_urls, video_id, video_title, video_description) + + # Look for Anvato embeds + anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id) + if anvato_urls: + return self.playlist_result( + anvato_urls, video_id, video_title, video_description) # Look for AdobeTVVideo embeds mobj = re.search( @@ -1870,12 +2989,313 @@ class GenericIE(InfoExtractor): self._proto_relative_url(unescapeHTML(mobj.group(1))), 'AdobeTVVideo') + # Look for Vine embeds + mobj = re.search( + r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))', + webpage) + if mobj is not None: + return self.url_result( + self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine') + + # Look for VODPlatform embeds + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1', + webpage) + if mobj is not None: + return self.url_result( + self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform') + + # Look for Mangomolo embeds + mobj = re.search( + r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?// + (?: + admin\.mangomolo\.com/analytics/index\.php/customers/embed| + player\.mangomolo\.com/v1 + )/ + (?: + video\?.*?\bid=(?P<video_id>\d+)| + (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) + ).+?)\1''', webpage) + if mobj is not None: + info = { + '_type': 'url_transparent', + 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))), + 'title': video_title, + 'description': video_description, + 'thumbnail': video_thumbnail, + 'uploader': video_uploader, + } + video_id = mobj.group('video_id') + if video_id: + info.update({ + 'ie_key': 'MangomoloVideo', + 'id': video_id, + }) + else: + info.update({ + 'ie_key': 'MangomoloLive', + 'id': mobj.group('channel_id'), + }) + return info + + # Look for Instagram embeds + instagram_embed_url = InstagramIE._extract_embed_url(webpage) + if instagram_embed_url is not None: + return self.url_result( + self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key()) + + # Look for LiveLeak embeds + liveleak_urls = LiveLeakIE._extract_urls(webpage) + if liveleak_urls: + return self.playlist_from_matches(liveleak_urls, video_id, video_title) + + # Look for 3Q SDN embeds + threeqsdn_url = ThreeQSDNIE._extract_url(webpage) + if threeqsdn_url: + return { + '_type': 'url_transparent', + 'ie_key': ThreeQSDNIE.ie_key(), + 'url': self._proto_relative_url(threeqsdn_url), + 'title': video_title, + 'description': video_description, + 'thumbnail': video_thumbnail, + 'uploader': video_uploader, + } + + # Look for VBOX7 embeds + vbox7_url = Vbox7IE._extract_url(webpage) + if vbox7_url: + return self.url_result(vbox7_url, Vbox7IE.ie_key()) + + # Look for DBTV embeds + dbtv_urls = DBTVIE._extract_urls(webpage) + if dbtv_urls: + return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key()) + + # Look for Videa embeds + videa_urls = VideaIE._extract_urls(webpage) + if videa_urls: + return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key()) + + # Look for 20 minuten embeds + twentymin_urls = TwentyMinutenIE._extract_urls(webpage) + if twentymin_urls: + return self.playlist_from_matches( + twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key()) + + # Look for VideoPress embeds + videopress_urls = VideoPressIE._extract_urls(webpage) + if videopress_urls: + return self.playlist_from_matches( + videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key()) + + # Look for Rutube embeds + rutube_urls = RutubeIE._extract_urls(webpage) + if rutube_urls: + return self.playlist_from_matches( + rutube_urls, video_id, video_title, ie=RutubeIE.ie_key()) + + # Look for WashingtonPost embeds + wapo_urls = WashingtonPostIE._extract_urls(webpage) + if wapo_urls: + return self.playlist_from_matches( + wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key()) + + # Look for Mediaset embeds + mediaset_urls = MediasetIE._extract_urls(self, webpage) + if mediaset_urls: + return self.playlist_from_matches( + mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key()) + + # Look for JOJ.sk embeds + joj_urls = JojIE._extract_urls(webpage) + if joj_urls: + return self.playlist_from_matches( + joj_urls, video_id, video_title, ie=JojIE.ie_key()) + + # Look for megaphone.fm embeds + mpfn_urls = MegaphoneIE._extract_urls(webpage) + if mpfn_urls: + return self.playlist_from_matches( + mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key()) + + # Look for vzaar embeds + vzaar_urls = VzaarIE._extract_urls(webpage) + if vzaar_urls: + return self.playlist_from_matches( + vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key()) + + channel9_urls = Channel9IE._extract_urls(webpage) + if channel9_urls: + return self.playlist_from_matches( + channel9_urls, video_id, video_title, ie=Channel9IE.ie_key()) + + vshare_urls = VShareIE._extract_urls(webpage) + if vshare_urls: + return self.playlist_from_matches( + vshare_urls, video_id, video_title, ie=VShareIE.ie_key()) + + # Look for Mediasite embeds + mediasite_urls = MediasiteIE._extract_urls(webpage) + if mediasite_urls: + entries = [ + self.url_result(smuggle_url( + compat_urlparse.urljoin(url, mediasite_url), + {'UrlReferrer': url}), ie=MediasiteIE.ie_key()) + for mediasite_url in mediasite_urls] + return self.playlist_result(entries, video_id, video_title) + + springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage) + if springboardplatform_urls: + return self.playlist_from_matches( + springboardplatform_urls, video_id, video_title, + ie=SpringboardPlatformIE.ie_key()) + + yapfiles_urls = YapFilesIE._extract_urls(webpage) + if yapfiles_urls: + return self.playlist_from_matches( + yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key()) + + vice_urls = ViceIE._extract_urls(webpage) + if vice_urls: + return self.playlist_from_matches( + vice_urls, video_id, video_title, ie=ViceIE.ie_key()) + + xfileshare_urls = XFileShareIE._extract_urls(webpage) + if xfileshare_urls: + return self.playlist_from_matches( + xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key()) + + cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage) + if cloudflarestream_urls: + return self.playlist_from_matches( + cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key()) + + peertube_urls = PeerTubeIE._extract_urls(webpage, url) + if peertube_urls: + return self.playlist_from_matches( + peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) + if indavideo_urls: + return self.playlist_from_matches( + indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key()) + + apa_urls = APAIE._extract_urls(webpage) + if apa_urls: + return self.playlist_from_matches( + apa_urls, video_id, video_title, ie=APAIE.ie_key()) + + foxnews_urls = FoxNewsIE._extract_urls(webpage) + if foxnews_urls: + return self.playlist_from_matches( + foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key()) + + sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer( + r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', + webpage)] + if sharevideos_urls: + return self.playlist_from_matches( + sharevideos_urls, video_id, video_title) + + viqeo_urls = ViqeoIE._extract_urls(webpage) + if viqeo_urls: + return self.playlist_from_matches( + viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + + expressen_urls = ExpressenIE._extract_urls(webpage) + if expressen_urls: + return self.playlist_from_matches( + expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + + zype_urls = ZypeIE._extract_urls(webpage) + if zype_urls: + return self.playlist_from_matches( + zype_urls, video_id, video_title, ie=ZypeIE.ie_key()) + + # Look for HTML5 media + entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') + if entries: + if len(entries) == 1: + entries[0].update({ + 'id': video_id, + 'title': video_title, + }) + else: + for num, entry in enumerate(entries, start=1): + entry.update({ + 'id': '%s-%s' % (video_id, num), + 'title': '%s (%d)' % (video_title, num), + }) + for entry in entries: + self._sort_formats(entry['formats']) + return self.playlist_result(entries, video_id, video_title) + + jwplayer_data = self._find_jwplayer_data( + webpage, video_id, transform_source=js_to_json) + if jwplayer_data: + try: + info = self._parse_jwplayer_data( + jwplayer_data, video_id, require_title=False, base_url=url) + return merge_dicts(info, info_dict) + except ExtractorError: + # See https://github.com/ytdl-org/youtube-dl/pull/16735 + pass + + # Video.js embed + mobj = re.search( + r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;', + webpage) + if mobj is not None: + sources = self._parse_json( + mobj.group(1), video_id, transform_source=js_to_json, + fatal=False) or [] + if not isinstance(sources, list): + sources = [sources] + formats = [] + for source in sources: + src = source.get('src') + if not src or not isinstance(src, compat_str): + continue + src = compat_urlparse.urljoin(url, src) + src_type = source.get('type') + if isinstance(src_type, compat_str): + src_type = src_type.lower() + ext = determine_ext(src).lower() + if src_type == 'video/youtube': + return self.url_result(src, YoutubeIE.ie_key()) + if src_type == 'application/dash+xml' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + src, video_id, mpd_id='dash', fatal=False)) + elif src_type == 'application/x-mpegurl' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + src, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'url': src, + 'ext': (mimetype2ext(src_type) + or ext if ext in KNOWN_EXTENSIONS else 'mp4'), + }) + if formats: + self._sort_formats(formats) + info_dict['formats'] = formats + return info_dict + + # Looking for http://schema.org/VideoObject + json_ld = self._search_json_ld( + webpage, video_id, default={}, expected_type='VideoObject') + if json_ld.get('url'): + return merge_dicts(json_ld, info_dict) + def check_video(vurl): if YoutubeIE.suitable(vurl): return True + if RtmpIE.suitable(vurl): + return True vpath = compat_urlparse.urlparse(vurl).path vext = determine_ext(vpath) - return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') + return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml') def filter_video(urls): return list(filter(check_video, urls)) @@ -1913,6 +3333,9 @@ class GenericIE(InfoExtractor): r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage) if not found: # Try to find twitter cards info + # twitter:player:stream should be checked before twitter:player since + # it is expected to contain a raw stream (see + # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser) found = filter_video(re.findall( r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)) if not found: @@ -1922,9 +3345,6 @@ class GenericIE(InfoExtractor): # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: if m_video_type is not None: found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)) - if not found: - # HTML5 video - found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage) if not found: REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)' found = re.search( @@ -1941,16 +3361,29 @@ class GenericIE(InfoExtractor): found = re.search(REDIRECT_REGEX, refresh_header) if found: new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1))) - self.report_following_redirect(new_url) - return { - '_type': 'url', - 'url': new_url, - } + if new_url != url: + self.report_following_redirect(new_url) + return { + '_type': 'url', + 'url': new_url, + } + else: + found = None + + if not found: + # twitter:player is a https URL to iframe player that may or may not + # be supported by youtube-dl thus this is checked the very last (see + # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser) + embed_url = self._html_search_meta('twitter:player', webpage, default=None) + if embed_url and embed_url != url: + return self.url_result(embed_url) + if not found: raise UnsupportedError(url) entries = [] - for video_url in found: + for video_url in orderedSet(found): + video_url = unescapeHTML(video_url) video_url = video_url.replace('\\/', '/') video_url = compat_urlparse.urljoin(url, video_url) video_id = compat_urllib_parse_unquote(os.path.basename(video_url)) @@ -1970,6 +3403,15 @@ class GenericIE(InfoExtractor): 'age_limit': age_limit, } + if RtmpIE.suitable(video_url): + entry_info_dict.update({ + '_type': 'url_transparent', + 'ie_key': RtmpIE.ie_key(), + 'url': video_url, + }) + entries.append(entry_info_dict) + continue + ext = determine_ext(video_url) if ext == 'smil': entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id) @@ -1979,9 +3421,29 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') elif ext == 'mpd': entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) + elif ext == 'f4m': + entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) + elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url: + # Just matching .ism/manifest is not enough to be reliably sure + # whether it's actually an ISM manifest or some other streaming + # manifest since there are various streaming URL formats + # possible (see [1]) as well as some other shenanigans like + # .smil/manifest URLs that actually serve an ISM (see [2]) and + # so on. + # Thus the most reasonable way to solve this is to delegate + # to generic extractor in order to look into the contents of + # the manifest itself. + # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats + # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest + entry_info_dict = self.url_result( + smuggle_url(video_url, {'to_generic': True}), + GenericIE.ie_key()) else: entry_info_dict['url'] = video_url + if entry_info_dict.get('formats'): + self._sort_formats(entry_info_dict['formats']) + entries.append(entry_info_dict) if len(entries) == 1: