itdominator/SolarFM
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

restructured manifest and plugins loading; updated plugins

Browse Source
This commit is contained in:
itdominator
2025-12-29 22:50:05 -06:00
parent c74f97aca7
commit 21120cd61e
324 changed files with 18088 additions and 15974 deletions
Download Patch File Download Diff File Expand all files Collapse all files
plugins/youtube_download/yt_dlp/extractor/_extractors.py
+53 -85
View File
@@ -58,13 +58,7 @@ from .adn import (
ADNSeasonIE,
)
from .adobeconnect import AdobeConnectIE
from .adobetv import (
AdobeTVChannelIE,
AdobeTVEmbedIE,
AdobeTVIE,
AdobeTVShowIE,
AdobeTVVideoIE,
)
from .adobetv import AdobeTVVideoIE
from .adultswim import AdultSwimIE
from .aenetworks import (
AENetworksCollectionIE,
@@ -152,7 +146,6 @@ from .ard import (
ARDBetaMediathekIE,
ARDMediathekCollectionIE,
)
from .arkena import ArkenaIE
from .arnes import ArnesIE
from .art19 import (
Art19IE,
@@ -201,7 +194,6 @@ from .banbye import (
BanByeChannelIE,
BanByeIE,
)
from .bandaichannel import BandaiChannelIE
from .bandcamp import (
BandcampAlbumIE,
BandcampIE,
@@ -229,7 +221,6 @@ from .beatbump import (
from .beatport import BeatportIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bellmedia import BellMediaIE
from .berufetv import BerufeTVIE
from .bet import BetIE
from .bfi import BFIPlayerIE
@@ -275,7 +266,10 @@ from .bitchute import (
BitChuteChannelIE,
BitChuteIE,
)
from .blackboardcollaborate import BlackboardCollaborateIE
from .blackboardcollaborate import (
BlackboardCollaborateIE,
BlackboardCollaborateLaunchIE,
)
from .bleacherreport import (
BleacherReportCMSIE,
BleacherReportIE,
@@ -300,7 +294,6 @@ from .brainpop import (
BrainPOPIlIE,
BrainPOPJrIE,
)
from .bravotv import BravoTVIE
from .breitbart import BreitBartIE
from .brightcove import (
BrightcoveLegacyIE,
@@ -310,6 +303,7 @@ from .brilliantpala import (
BrilliantpalaClassesIE,
BrilliantpalaElearnIE,
)
from .btvplus import BTVPlusIE
from .bundesliga import BundesligaIE
from .bundestag import BundestagIE
from .bunnycdn import BunnyCdnIE
@@ -338,12 +332,12 @@ from .canalc2 import Canalc2IE
from .canalplus import CanalplusIE
from .canalsurmas import CanalsurmasIE
from .caracoltv import CaracolTvPlayIE
from .cartoonnetwork import CartoonNetworkIE
from .cbc import (
CBCIE,
CBCGemIE,
CBCGemLiveIE,
CBCGemPlaylistIE,
CBCListenIE,
CBCPlayerIE,
CBCPlayerPlaylistIE,
)
@@ -405,16 +399,12 @@ from .cloudflarestream import CloudflareStreamIE
from .cloudycdn import CloudyCDNIE
from .clubic import ClubicIE
from .clyp import ClypIE
from .cmt import CMTIE
from .cnbc import CNBCVideoIE
from .cnn import (
CNNIE,
CNNIndonesiaIE,
)
from .comedycentral import (
ComedyCentralIE,
ComedyCentralTVIE,
)
from .comedycentral import ComedyCentralIE
from .commonmistakes import (
BlobIE,
CommonMistakesIE,
@@ -435,7 +425,6 @@ from .cpac import (
CPACPlaylistIE,
)
from .cracked import CrackedIE
from .crackle import CrackleIE
from .craftsy import CraftsyIE
from .crooksandliars import CrooksAndLiarsIE
from .crowdbunker import (
@@ -448,7 +437,6 @@ from .cspan import (
CSpanIE,
)
from .ctsnews import CtsNewsIE
from .ctv import CTVIE
from .ctvnews import CTVNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .curiositystream import (
@@ -456,10 +444,6 @@ from .curiositystream import (
CuriosityStreamIE,
CuriosityStreamSeriesIE,
)
from .cwtv import (
CWTVIE,
CWTVMovieIE,
)
from .cybrary import (
CybraryCourseIE,
CybraryIE,
@@ -572,10 +556,6 @@ from .dw import (
DWIE,
DWArticleIE,
)
from .eagleplatform import (
ClipYouEmbedIE,
EaglePlatformIE,
)
from .ebaumsworld import EbaumsWorldIE
from .ebay import EbayIE
from .egghead import (
@@ -641,6 +621,10 @@ from .fancode import (
FancodeVodIE,
)
from .fathom import FathomIE
from .faulio import (
FaulioIE,
FaulioLiveIE,
)
from .faz import FazIE
from .fc2 import (
FC2IE,
@@ -807,9 +791,7 @@ from .holodex import HolodexIE
from .hotnewhiphop import HotNewHipHopIE
from .hotstar import (
HotStarIE,
HotStarPlaylistIE,
HotStarPrefixIE,
HotStarSeasonIE,
HotStarSeriesIE,
)
from .hrefli import HrefLiRedirectIE
@@ -842,6 +824,13 @@ from .ichinanalive import (
IchinanaLiveIE,
IchinanaLiveVODIE,
)
from .idagio import (
IdagioAlbumIE,
IdagioPersonalPlaylistIE,
IdagioPlaylistIE,
IdagioRecordingIE,
IdagioTrackIE,
)
from .idolplus import IdolPlusIE
from .ign import (
IGNIE,
@@ -923,17 +912,15 @@ from .japandiet import (
ShugiinItvVodIE,
)
from .jeuxvideo import JeuxVideoIE
from .jiocinema import (
JioCinemaIE,
JioCinemaSeriesIE,
)
from .jiosaavn import (
JioSaavnAlbumIE,
JioSaavnArtistIE,
JioSaavnPlaylistIE,
JioSaavnShowIE,
JioSaavnShowPlaylistIE,
JioSaavnSongIE,
)
from .joj import JojIE
from .joqrag import JoqrAgIE
from .jove import JoveIE
from .jstream import JStreamIE
from .jtbc import (
@@ -1036,11 +1023,6 @@ from .likee import (
LikeeIE,
LikeeUserIE,
)
from .limelight import (
LimelightChannelIE,
LimelightChannelListIE,
LimelightMediaIE,
)
from .linkedin import (
LinkedInEventsIE,
LinkedInIE,
@@ -1106,6 +1088,7 @@ from .markiza import (
from .massengeschmacktv import MassengeschmackTVIE
from .masters import MastersIE
from .matchtv import MatchTVIE
from .mave import MaveIE
from .mbn import MBNIE
from .mdr import MDRIE
from .medaltv import MedalTVIE
@@ -1151,6 +1134,7 @@ from .minds import (
MindsIE,
)
from .minoto import MinotoIE
from .mir24tv import Mir24TvIE
from .mirrativ import (
MirrativIE,
MirrativUserIE,
@@ -1160,7 +1144,6 @@ from .mit import (
OCWMITIE,
TechTVMITIE,
)
from .mitele import MiTeleIE
from .mixch import (
MixchArchiveIE,
MixchIE,
@@ -1171,6 +1154,10 @@ from .mixcloud import (
MixcloudPlaylistIE,
MixcloudUserIE,
)
from .mixlr import (
MixlrIE,
MixlrRecoringIE,
)
from .mlb import (
MLBIE,
MLBTVIE,
@@ -1194,15 +1181,7 @@ from .moview import MoviewPlayIE
from .moviezine import MoviezineIE
from .movingimage import MovingImageIE
from .msn import MSNIE
from .mtv import (
MTVDEIE,
MTVIE,
MTVItaliaIE,
MTVItaliaProgrammaIE,
MTVJapanIE,
MTVServicesEmbeddedIE,
MTVVideoIE,
)
from .mtv import MTVIE
from .muenchentv import MuenchenTVIE
from .murrtube import (
MurrtubeIE,
@@ -1260,6 +1239,7 @@ from .nba import (
)
from .nbc import (
NBCIE,
BravoTVIE,
NBCNewsIE,
NBCOlympicsIE,
NBCOlympicsStreamIE,
@@ -1267,6 +1247,7 @@ from .nbc import (
NBCSportsStreamIE,
NBCSportsVPlayerIE,
NBCStationsIE,
SyfyIE,
)
from .ndr import (
NDRIE,
@@ -1342,12 +1323,7 @@ from .nhk import (
NhkVodProgramIE,
)
from .nhl import NHLIE
from .nick import (
NickBrIE,
NickDeIE,
NickIE,
NickRuIE,
)
from .nick import NickIE
from .niconico import (
NiconicoHistoryIE,
NiconicoIE,
@@ -1379,7 +1355,6 @@ from .nobelprize import NobelPrizeIE
from .noice import NoicePodcastIE
from .nonktube import NonkTubeIE
from .noodlemagazine import NoodleMagazineIE
from .noovo import NoovoIE
from .nosnl import NOSNLArticleIE
from .nova import (
NovaEmbedIE,
@@ -1460,6 +1435,7 @@ from .onet import (
OnetPlIE,
)
from .onionstudios import OnionStudiosIE
from .onsen import OnsenIE
from .opencast import (
OpencastIE,
OpencastPlaylistIE,
@@ -1493,10 +1469,6 @@ from .panopto import (
PanoptoListIE,
PanoptoPlaylistIE,
)
from .paramountplus import (
ParamountPlusIE,
ParamountPlusSeriesIE,
)
from .parler import ParlerIE
from .parlview import ParlviewIE
from .parti import (
@@ -1550,16 +1522,12 @@ from .piramidetv import (
PiramideTVChannelIE,
PiramideTVIE,
)
from .pixivsketch import (
PixivSketchIE,
PixivSketchUserIE,
)
from .pladform import PladformIE
from .planetmarathi import PlanetMarathiIE
from .platzi import (
PlatziCourseIE,
PlatziIE,
)
from .playerfm import PlayerFmIE
from .playplustv import PlayPlusTVIE
from .playsuisse import PlaySuisseIE
from .playtvak import PlaytvakIE
@@ -1570,6 +1538,7 @@ from .pluralsight import (
)
from .plutotv import PlutoTVIE
from .plvideo import PlVideoIE
from .plyr import PlyrEmbedIE
from .podbayfm import (
PodbayFMChannelIE,
PodbayFMIE,
@@ -1785,6 +1754,7 @@ from .rtve import (
RTVEALaCartaIE,
RTVEAudioIE,
RTVELiveIE,
RTVEProgramIE,
RTVETelevisionIE,
)
from .rtvs import RTVSIE
@@ -1808,7 +1778,6 @@ from .rutube import (
RutubePlaylistIE,
RutubeTagsIE,
)
from .rutv import RUTVIE
from .ruutu import RuutuIE
from .ruv import (
RuvIE,
@@ -1826,6 +1795,7 @@ from .safari import (
from .saitosan import SaitosanIE
from .samplefocus import SampleFocusIE
from .sapo import SapoIE
from .sauceplus import SaucePlusIE
from .sbs import SBSIE
from .sbscokr import (
SBSCoKrAllvodProgramIE,
@@ -1868,6 +1838,7 @@ from .shahid import (
from .sharepoint import SharePointIE
from .sharevideos import ShareVideosEmbedIE
from .shemaroome import ShemarooMeIE
from .shiey import ShieyIE
from .showroomlive import ShowRoomLiveIE
from .sibnet import SibnetEmbedIE
from .simplecast import (
@@ -1876,7 +1847,6 @@ from .simplecast import (
SimplecastPodcastIE,
)
from .sina import SinaIE
from .sixplay import SixPlayIE
from .skeb import SkebIE
from .sky import (
SkyNewsIE,
@@ -1904,7 +1874,12 @@ from .skynewsau import SkyNewsAUIE
from .slideshare import SlideshareIE
from .slideslive import SlidesLiveIE
from .slutload import SlutloadIE
from .smotrim import SmotrimIE
from .smotrim import (
SmotrimAudioIE,
SmotrimIE,
SmotrimLiveIE,
SmotrimPlaylistIE,
)
from .snapchat import SnapchatSpotlightIE
from .snotr import SnotrIE
from .softwhiteunderbelly import SoftWhiteUnderbellyIE
@@ -1932,12 +1907,13 @@ from .soundgasm import (
SoundgasmProfileIE,
)
from .southpark import (
SouthParkComBrIE,
SouthParkCoUkIE,
SouthParkDeIE,
SouthParkDkIE,
SouthParkEsIE,
SouthParkIE,
SouthParkLatIE,
SouthParkNlIE,
)
from .sovietscloset import (
SovietsClosetIE,
@@ -1948,23 +1924,14 @@ from .spankbang import (
SpankBangPlaylistIE,
)
from .spiegel import SpiegelIE
from .spike import (
BellatorIE,
ParamountNetworkIE,
)
from .sport5 import Sport5IE
from .sportbox import SportBoxIE
from .sportdeutschland import SportDeutschlandIE
from .spotify import (
SpotifyIE,
SpotifyShowIE,
)
from .spreaker import (
SpreakerIE,
SpreakerShowIE,
)
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE
from .sproutvideo import (
SproutVideoIE,
VidsIoIE,
@@ -1986,6 +1953,7 @@ from .startrek import StarTrekIE
from .startv import StarTVIE
from .steam import (
SteamCommunityBroadcastIE,
SteamCommunityIE,
SteamIE,
)
from .stitcher import (
@@ -2015,13 +1983,11 @@ from .sverigesradio import (
SverigesRadioPublicationIE,
)
from .svt import (
SVTIE,
SVTPageIE,
SVTPlayIE,
SVTSeriesIE,
)
from .swearnet import SwearnetEpisodeIE
from .syfy import SyfyIE
from .syvdk import SYVDKIE
from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE
@@ -2100,6 +2066,7 @@ from .theguardian import (
TheGuardianPodcastIE,
TheGuardianPodcastPlaylistIE,
)
from .thehighwire import TheHighWireIE
from .theholetv import TheHoleTvIE
from .theintercept import TheInterceptIE
from .theplatform import (
@@ -2146,6 +2113,7 @@ from .toggle import (
from .toggo import ToggoIE
from .tonline import TOnlineIE
from .toongoggles import ToonGogglesIE
from .toutiao import ToutiaoIE
from .toutv import TouTvIE
from .toypics import (
ToypicsIE,
@@ -2168,7 +2136,6 @@ from .trtworld import TrtWorldIE
from .trueid import TrueIDIE
from .trunews import TruNewsIE
from .truth import TruthIE
from .trutv import TruTVIE
from .tube8 import Tube8IE
from .tubetugraz import (
TubeTuGrazIE,
@@ -2180,6 +2147,7 @@ from .tubitv import (
)
from .tumblr import TumblrIE
from .tunein import (
TuneInEmbedIE,
TuneInPodcastEpisodeIE,
TuneInPodcastIE,
TuneInShortenerIE,
@@ -2218,7 +2186,6 @@ from .tvc import (
from .tver import TVerIE
from .tvigle import TvigleIE
from .tviplayer import TVIPlayerIE
from .tvland import TVLandIE
from .tvn24 import TVN24IE
from .tvnoe import TVNoeIE
from .tvopengr import (
@@ -2239,6 +2206,7 @@ from .tvplay import (
from .tvplayer import TVPlayerIE
from .tvw import (
TvwIE,
TvwNewsIE,
TvwTvChannelsIE,
)
from .tweakers import TweakersIE
@@ -2287,6 +2255,7 @@ from .uliza import (
)
from .umg import UMGDeIE
from .unistra import UnistraIE
from .unitednations import UnitedNationsWebTvIE
from .unity import UnityIE
from .unsupported import (
KnownDRMIE,
@@ -2313,7 +2282,6 @@ from .utreon import UtreonIE
from .varzesh3 import Varzesh3IE
from .vbox7 import Vbox7IE
from .veo import VeoIE
from .vesti import VestiIE
from .vevo import (
VevoIE,
VevoPlaylistIE,
@@ -2368,6 +2336,7 @@ from .vimeo import (
VHXEmbedIE,
VimeoAlbumIE,
VimeoChannelIE,
VimeoEventIE,
VimeoGroupsIE,
VimeoIE,
VimeoLikesIE,
@@ -2501,7 +2470,6 @@ from .wykop import (
WykopPostCommentIE,
WykopPostIE,
)
from .xanimu import XanimuIE
from .xboxclips import XboxClipsIE
from .xhamster import (
XHamsterEmbedIE,
plugins/youtube_download/yt_dlp/extractor/abc.py
+18 -6
View File
@@ -21,7 +21,7 @@ from ..utils import (
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/(?:news|btn)/(?:[^/]+/){1,4}(?P<id>\d{5,})'
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/(?:news|btn|listen)/(?:[^/?#]+/){1,4}(?P<id>\d{5,})'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -53,8 +53,9 @@ class ABCIE(InfoExtractor):
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'title': 'NAB lifts interest rates, following Westpac and CBA - ABC listen',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
'thumbnail': r're:https://live-production\.wcms\.abc-cdn\.net\.au/2193d7437c84b25eafd6360c82b5fa21',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
@@ -64,8 +65,9 @@ class ABCIE(InfoExtractor):
'info_dict': {
'id': '10527914',
'ext': 'mp4',
'title': 'WWI Centenary',
'description': 'md5:c2379ec0ca84072e86b446e536954546',
'title': 'WWI Centenary - Behind The News',
'description': 'md5:fa4405939ff750fade46ff0cd4c66a52',
'thumbnail': r're:https://live-production\.wcms\.abc-cdn\.net\.au/bcc3433c97bf992dff32ec5a768713c9',
},
}, {
'url': 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074',
@@ -73,7 +75,8 @@ class ABCIE(InfoExtractor):
'id': '12342074',
'ext': 'mp4',
'title': 'Black Lives Matter protests spawn support for Papuans in Indonesia',
'description': 'md5:2961a17dc53abc558589ccd0fb8edd6f',
'description': 'md5:625257209f2d14ce23cb4e3785da9beb',
'thumbnail': r're:https://live-production\.wcms\.abc-cdn\.net\.au/7ee6f190de6d7dbb04203e514bfae9ec',
},
}, {
'url': 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476',
@@ -93,7 +96,16 @@ class ABCIE(InfoExtractor):
'title': 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus',
'ext': 'mp4',
'description': 'Wagner troops leave Rostov-on-Don and\xa0Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.',
'thumbnail': 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485',
'thumbnail': r're:https://live-production\.wcm\.abc-cdn\.net\.au/0c170f5b57f0105c432f366c0e8e267b',
},
}, {
'url': 'https://www.abc.net.au/listen/programs/the-followers-madness-of-two/presents-followers-madness-of-two/105697646',
'info_dict': {
'id': '105697646',
'title': 'INTRODUCING — The Followers: Madness of Two - ABC listen',
'ext': 'mp3',
'description': 'md5:2310cd0d440a4e01656abea15db8d1f3',
'thumbnail': r're:https://live-production\.wcms\.abc-cdn\.net\.au/90d7078214e5d66553ffb7fcf0da0cda',
},
}]
plugins/youtube_download/yt_dlp/extractor/adobepass.py
+143 -48
View File
@@ -3,6 +3,7 @@ import json
import re
import time
import urllib.parse
import uuid
import xml.etree.ElementTree as etree
from .common import InfoExtractor
@@ -10,6 +11,7 @@ from ..networking.exceptions import HTTPError
from ..utils import (
NO_DEFAULT,
ExtractorError,
parse_qs,
unescapeHTML,
unified_timestamp,
urlencode_postdata,
@@ -45,6 +47,7 @@ MSO_INFO = {
'name': 'Comcast XFINITY',
'username_field': 'user',
'password_field': 'passwd',
'login_hostname': 'login.xfinity.com',
},
'TWC': {
'name': 'Time Warner Cable | Spectrum',
@@ -74,6 +77,12 @@ MSO_INFO = {
'name': 'Verizon FiOS',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
'login_hostname': 'ssoauth.verizon.com',
},
'Fubo': {
'name': 'Fubo',
'username_field': 'username',
'password_field': 'password',
},
'Cablevision': {
'name': 'Optimum/Cablevision',
@@ -1338,6 +1347,7 @@ MSO_INFO = {
'name': 'Sling TV',
'username_field': 'username',
'password_field': 'password',
'login_hostname': 'identity.sling.com',
},
'Suddenlink': {
'name': 'Suddenlink',
@@ -1355,7 +1365,6 @@ MSO_INFO = {
class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MODERN_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0'
_MVPD_CACHE = 'ap-mvpd'
_DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
@@ -1367,6 +1376,11 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
return super()._download_webpage_handle(
*args, **kwargs)
@staticmethod
def _get_mso_headers(mso_info):
# Not needed currently
return {}
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')
@@ -1382,7 +1396,13 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
resource_rating.text = rating
return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource, software_statement):
mso_id = self.get_param('ap_mso')
if mso_id:
mso_info = MSO_INFO[mso_id]
else:
mso_info = {}
def xml_text(xml_str, tag):
return self._search_regex(
f'<{tag}>(.+?)</{tag}>', xml_str, tag)
@@ -1391,15 +1411,27 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
return token_expires and token_expires <= int(time.time())
def post_form(form_page_res, note, data={}):
def post_form(form_page_res, note, data={}, validate_url=False):
form_page, urlh = form_page_res
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url):
post_url = urllib.parse.urljoin(urlh.url, post_url)
if validate_url:
# This request is submitting credentials so we should validate it when possible
url_parsed = urllib.parse.urlparse(post_url)
expected_hostname = mso_info.get('login_hostname')
if expected_hostname and expected_hostname != url_parsed.hostname:
raise ExtractorError(
f'Unexpected login URL hostname; expected "{expected_hostname}" but got '
f'"{url_parsed.hostname}". Aborting before submitting credentials')
if url_parsed.scheme != 'https':
self.write_debug('Upgrading login URL scheme to https')
post_url = urllib.parse.urlunparse(url_parsed._replace(scheme='https'))
form_data = self._hidden_inputs(form_page)
form_data.update(data)
return self._download_webpage_handle(
post_url, video_id, note, data=urlencode_postdata(form_data), headers={
**self._get_mso_headers(mso_info),
'Content-Type': 'application/x-www-form-urlencoded',
})
@@ -1432,40 +1464,72 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}
guid = xml_text(resource, 'guid') if '<' in resource else resource
count = 0
while count < 2:
for _ in range(2):
requestor_info = self.cache.load(self._MVPD_CACHE, requestor_id) or {}
authn_token = requestor_info.get('authn_token')
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
authn_token = None
if not authn_token:
mso_id = self.get_param('ap_mso')
if mso_id:
username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
if not username or not password:
raise_mvpd_required()
mso_info = MSO_INFO[mso_id]
provider_redirect_page_res = self._download_webpage_handle(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
'Downloading Provider Redirect Page', query={
'noflash': 'true',
'mso_id': mso_id,
'requestor_id': requestor_id,
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
}, headers={
# yt-dlp's default user-agent is usually too old for Comcast_SSO
# See: https://github.com/yt-dlp/yt-dlp/issues/10848
'User-Agent': self._MODERN_USER_AGENT,
} if mso_id == 'Comcast_SSO' else None)
elif not self._cookies_passed:
if not mso_id:
raise_mvpd_required()
username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
if not username or not password:
raise_mvpd_required()
if not mso_id:
pass
elif mso_id == 'Comcast_SSO':
device_info, urlh = self._download_json_handle(
'https://sp.auth.adobe.com/indiv/devices',
video_id, 'Registering device with Adobe',
data=json.dumps({'fingerprint': uuid.uuid4().hex}).encode(),
headers={'Content-Type': 'application/json; charset=UTF-8'})
device_id = device_info['deviceId']
mvpd_headers['pass_sfp'] = urlh.get_header('pass_sfp')
mvpd_headers['Ap_21'] = device_id
registration = self._download_json(
'https://sp.auth.adobe.com/o/client/register',
video_id, 'Registering client with Adobe',
data=json.dumps({'software_statement': software_statement}).encode(),
headers={'Content-Type': 'application/json; charset=UTF-8'})
access_token = self._download_json(
'https://sp.auth.adobe.com/o/client/token', video_id,
'Obtaining access token', data=urlencode_postdata({
'grant_type': 'client_credentials',
'client_id': registration['client_id'],
'client_secret': registration['client_secret'],
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
})['access_token']
mvpd_headers['Authorization'] = f'Bearer {access_token}'
reg_code = self._download_json(
f'https://sp.auth.adobe.com/reggie/v1/{requestor_id}/regcode',
video_id, 'Obtaining registration code',
data=urlencode_postdata({
'requestor': requestor_id,
'deviceId': device_id,
'format': 'json',
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Authorization': f'Bearer {access_token}',
})['code']
provider_redirect_page_res = self._download_webpage_handle(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
'Downloading Provider Redirect Page', query={
'noflash': 'true',
'mso_id': mso_id,
'requestor_id': requestor_id,
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
'reg_code': reg_code,
}, headers=self._get_mso_headers(mso_info))
if mso_id == 'Comcast_SSO':
# Comcast page flow varies by video site and whether you
# are on Comcast's network.
provider_redirect_page, urlh = provider_redirect_page_res
@@ -1489,8 +1553,8 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
oauth_redirect_url = extract_redirect_url(
provider_redirect_page, fatal=True)
provider_login_page_res = self._download_webpage_handle(
oauth_redirect_url, video_id,
self._DOWNLOADING_LOGIN_PAGE)
oauth_redirect_url, video_id, self._DOWNLOADING_LOGIN_PAGE,
headers=self._get_mso_headers(mso_info))
else:
provider_login_page_res = post_form(
provider_redirect_page_res,
@@ -1500,24 +1564,35 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
mvpd_confirm_page, urlh = mvpd_confirm_page_res
if '<button class="submit" value="Resume">Resume</button>' in mvpd_confirm_page:
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Philo':
# Philo has very unique authentication method
self._download_webpage(
'https://idp.philo.com/auth/init/login_code', video_id, 'Requesting auth code', data=urlencode_postdata({
self._request_webpage(
'https://idp.philo.com/auth/init/login_code', video_id,
'Requesting Philo auth code', data=json.dumps({
'ident': username,
'device': 'web',
'send_confirm_link': False,
'send_token': True,
}))
'device_ident': f'web-{uuid.uuid4().hex}',
'include_login_link': True,
}).encode(), headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
})
philo_code = getpass.getpass('Type auth code you have received [Return]: ')
self._download_webpage(
'https://idp.philo.com/auth/update/login_code', video_id, 'Submitting token', data=urlencode_postdata({
'token': philo_code,
}))
self._request_webpage(
'https://idp.philo.com/auth/update/login_code', video_id,
'Submitting token', data=json.dumps({'token': philo_code}).encode(),
headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
})
mvpd_confirm_page_res = self._download_webpage_handle('https://idp.philo.com/idp/submit', video_id, 'Confirming Philo Login')
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Verizon':
@@ -1539,7 +1614,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_redirect_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
saml_login_page, urlh = saml_login_page_res
if 'Please try again.' in saml_login_page:
raise ExtractorError(
@@ -1560,7 +1635,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
[saml_login_page, saml_redirect_url], 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
if 'Please try again.' in saml_login_page:
raise ExtractorError(
'Failed to login, incorrect User ID or Password.')
@@ -1631,7 +1706,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@@ -1682,7 +1757,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@@ -1699,6 +1774,27 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Fubo':
_, urlh = provider_redirect_page_res
fubo_response = self._download_json(
'https://api.fubo.tv/partners/tve/connect', video_id,
'Authenticating with Fubo', 'Unable to authenticate with Fubo',
query=parse_qs(urlh.url), data=json.dumps({
'username': username,
'password': password,
}).encode(), headers={
'Accept': 'application/json',
'Content-Type': 'application/json',
})
self._request_webpage(
'https://sp.auth.adobe.com/adobe-services/oauth2', video_id,
'Authenticating with Adobe', 'Failed to authenticate with Adobe',
query={
'code': fubo_response['code'],
'state': fubo_response['state'],
})
else:
# Some providers (e.g. DIRECTV NOW) have another meta refresh
# based redirect that should be followed.
@@ -1717,7 +1813,8 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}
if mso_id in ('Cablevision', 'AlticeOne'):
form_data['_eventId_proceed'] = ''
mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', form_data)
mvpd_confirm_page_res = post_form(
provider_login_page_res, 'Logging in', form_data, validate_url=True)
if mso_id != 'Rogers':
post_form(mvpd_confirm_page_res, 'Confirming Login')
@@ -1727,6 +1824,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
'Retrieving Session', data=urlencode_postdata({
'_method': 'GET',
'requestor_id': requestor_id,
'reg_code': reg_code,
}), headers=mvpd_headers)
except ExtractorError as e:
if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
@@ -1734,7 +1832,6 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
raise
if '<pendingLogout' in session:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
requestor_info['authn_token'] = authn_token
@@ -1755,7 +1852,6 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}), headers=mvpd_headers)
if '<pendingLogout' in authorize:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
if '<error' in authorize:
raise ExtractorError(xml_text(authorize, 'details'), expected=True)
@@ -1778,6 +1874,5 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}), headers=mvpd_headers)
if '<pendingLogout' in short_authorize:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
return short_authorize
plugins/youtube_download/yt_dlp/extractor/adobetv.py
+70 -255
View File
@@ -1,285 +1,100 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
ISO639Utils,
OnDemandPagedList,
clean_html,
determine_ext,
float_or_none,
int_or_none,
join_nonempty,
parse_duration,
str_or_none,
str_to_int,
unified_strdate,
url_or_none,
)
from ..utils.traversal import traverse_obj
class AdobeTVBaseIE(InfoExtractor):
def _call_api(self, path, video_id, query, note=None):
return self._download_json(
'http://tv.adobe.com/api/v4/' + path,
video_id, note, query=query)['data']
def _parse_subtitles(self, video_data, url_key):
subtitles = {}
for translation in video_data.get('translations', []):
vtt_path = translation.get(url_key)
if not vtt_path:
continue
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
subtitles.setdefault(lang, []).append({
'ext': 'vtt',
'url': vtt_path,
})
return subtitles
def _parse_video_data(self, video_data):
video_id = str(video_data['id'])
title = video_data['title']
s3_extracted = False
formats = []
for source in video_data.get('videos', []):
source_url = source.get('url')
if not source_url:
continue
f = {
'format_id': source.get('quality_level'),
'fps': int_or_none(source.get('frame_rate')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('video_data_rate')),
'width': int_or_none(source.get('width')),
'url': source_url,
}
original_filename = source.get('original_filename')
if original_filename:
if not (f.get('height') and f.get('width')):
mobj = re.search(r'_(\d+)x(\d+)', original_filename)
if mobj:
f.update({
'height': int(mobj.group(2)),
'width': int(mobj.group(1)),
})
if original_filename.startswith('s3://') and not s3_extracted:
formats.append({
'format_id': 'original',
'quality': 1,
'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
})
s3_extracted = True
formats.append(f)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'upload_date': unified_strdate(video_data.get('start_date')),
'duration': parse_duration(video_data.get('duration')),
'view_count': str_to_int(video_data.get('playcount')),
'formats': formats,
'subtitles': self._parse_subtitles(video_data, 'vtt'),
}
class AdobeTVEmbedIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:embed'
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
_TEST = {
'url': 'https://tv.adobe.com/embed/22/4153',
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
'info_dict': {
'id': '4153',
'ext': 'flv',
'title': 'Creating Graphics Optimized for BlackBerry',
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20091109',
'duration': 377,
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._call_api(
'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
return self._parse_video_data(video_data)
class AdobeTVIE(AdobeTVBaseIE):
class AdobeTVVideoIE(InfoExtractor):
IE_NAME = 'adobetv'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
'id': '10981',
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20110914',
'duration': 60,
'view_count': int,
},
}
def _real_extract(self, url):
language, show_urlname, urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
video_data = self._call_api(
'episode/get', urlname, {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
'urlname': urlname,
})[0]
return self._parse_video_data(video_data)
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
_PAGE_SIZE = 25
def _fetch_page(self, display_id, query, page):
page += 1
query['page'] = page
for element_data in self._call_api(
self._RESOURCE, display_id, query, f'Download Page {page}'):
yield self._process_data(element_data)
def _extract_playlist_entries(self, display_id, query):
return OnDemandPagedList(functools.partial(
self._fetch_page, display_id, query), self._PAGE_SIZE)
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:show'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
'info_dict': {
'id': '36',
'title': 'The Complete Picture with Julieanne Kost',
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
},
'playlist_mincount': 136,
}
_RESOURCE = 'episode'
_process_data = AdobeTVBaseIE._parse_video_data
def _real_extract(self, url):
language, show_urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
query = {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
}
show_data = self._call_api(
'show/get', show_urlname, query)[0]
return self.playlist_result(
self._extract_playlist_entries(show_urlname, query),
str_or_none(show_data.get('id')),
show_data.get('show_name'),
show_data.get('show_description'))
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:channel'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
_TEST = {
'url': 'http://tv.adobe.com/channel/development',
'info_dict': {
'id': 'development',
},
'playlist_mincount': 96,
}
_RESOURCE = 'show'
def _process_data(self, show_data):
return self.url_result(
show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
def _real_extract(self, url):
language, channel_urlname, category_urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
query = {
'channel_urlname': channel_urlname,
'language': language,
}
if category_urlname:
query['category_urlname'] = category_urlname
return self.playlist_result(
self._extract_playlist_entries(channel_urlname, query),
channel_urlname)
class AdobeTVVideoIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:video'
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
_EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
_TEST = {
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
'url': 'https://video.tv.adobe.com/v/2456/',
_EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+)']
_TESTS = [{
'url': 'https://video.tv.adobe.com/v/2456',
'md5': '43662b577c018ad707a63766462b1e87',
'info_dict': {
'id': '2456',
'ext': 'mp4',
'title': 'New experience with Acrobat DC',
'description': 'New experience with Acrobat DC',
'duration': 248.667,
'duration': 248.522,
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
},
}
}, {
'url': 'https://video.tv.adobe.com/v/3463980/adobe-acrobat',
'info_dict': {
'id': '3463980',
'ext': 'mp4',
'title': 'Adobe Acrobat: How to Customize the Toolbar for Faster PDF Editing',
'description': 'md5:94368ab95ae24f9c1bee0cb346e03dc3',
'duration': 97.514,
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
},
}]
_WEBPAGE_TESTS = [{
# https://video.tv.adobe.com/v/3442499
'url': 'https://business.adobe.com/dx-fragments/summit/2025/marquees/S335/ondemand.live.html',
'info_dict': {
'id': '3442499',
'ext': 'mp4',
'title': 'S335 - Beyond Personalization: Creating Intent-Based Experiences at Scale',
'description': 'Beyond Personalization: Creating Intent-Based Experiences at Scale',
'duration': 2906.8,
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex(
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
title = video_data['title']
video_data = self._search_json(
r'var\s+bridge\s*=', webpage, 'bridged data', video_id)
formats = []
sources = video_data.get('sources') or []
for source in sources:
source_src = source.get('src')
if not source_src:
continue
formats.append({
'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
'format_id': join_nonempty(source.get('format'), source.get('label')),
'height': int_or_none(source.get('height') or None),
'tbr': int_or_none(source.get('bitrate') or None),
'width': int_or_none(source.get('width') or None),
'url': source_src,
})
for source in traverse_obj(video_data, (
'sources', lambda _, v: v['format'] != 'playlist' and url_or_none(v['src']),
)):
source_url = self._proto_relative_url(source['src'])
if determine_ext(source_url) == 'm3u8':
fmts = self._extract_m3u8_formats(
source_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
else:
fmts = [{'url': source_url}]
# For both metadata and downloaded files the duration varies among
# formats. I just pick the max one
duration = max(filter(None, [
float_or_none(source.get('duration'), scale=1000)
for source in sources]))
for fmt in fmts:
fmt.update(traverse_obj(source, {
'duration': ('duration', {float_or_none(scale=1000)}),
'filesize': ('kilobytes', {float_or_none(invscale=1000)}),
'format_id': (('format', 'label'), {str}, all, {lambda x: join_nonempty(*x)}),
'height': ('height', {int_or_none}),
'tbr': ('bitrate', {int_or_none}),
'width': ('width', {int_or_none}),
}))
formats.extend(fmts)
subtitles = {}
for translation in traverse_obj(video_data, (
'translations', lambda _, v: url_or_none(v['vttPath']),
)):
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation.get('language_medium')) or 'und'
subtitles.setdefault(lang, []).append({
'ext': 'vtt',
'url': self._proto_relative_url(translation['vttPath']),
})
return {
'id': video_id,
'formats': formats,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('video', {}).get('poster'),
'duration': duration,
'subtitles': self._parse_subtitles(video_data, 'vttPath'),
'subtitles': subtitles,
**traverse_obj(video_data, {
'title': ('title', {clean_html}),
'description': ('description', {clean_html}, filter),
'thumbnail': ('video', 'poster', {self._proto_relative_url}, {url_or_none}),
}),
}
plugins/youtube_download/yt_dlp/extractor/adultswim.py
+3 -1
View File
@@ -84,6 +84,8 @@ class AdultSwimIE(TurnerBaseIE):
'skip': '404 Not Found',
}]
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwNjg5ZmU2My00OTc5LTQxZmQtYWYxNC1hYjVlNmJjNWVkZWIiLCJuYmYiOjE1MzcxOTA2NzQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwNjc0fQ.Xl3AEduM0s1TxDQ6-XssdKIiLm261hhsEv1C1yo_nitIajZThSI9rXILqtIzO0aujoHhdzUnu_dUCq9ffiSBzEG632tTa1la-5tegHtce80cMhewBN4n2t8n9O5tiaPx8MPY8ALdm5wS7QzWE6DO_LTJKgE8Bl7Yv-CWJT4q4SywtNiQWLVOuhBRnDyfsRezxRwptw8qTn9dv5ZzUrVJaby5fDZ_nOncMKvegOgaKd5KEuCAGQ-mg-PSuValMjGuf6FwDguGaK7IyI5Y2oOrzXmD4Dj7q4WBg8w9QoZhtLeAU56mcsGILolku2R5FHlVLO9xhjResyt-pfmegOkpSw'
def _real_extract(self, url):
show_path, episode_path = self._match_valid_url(url).groups()
display_id = episode_path or show_path
@@ -152,7 +154,7 @@ class AdultSwimIE(TurnerBaseIE):
# CDN_TOKEN_APP_ID from:
# https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
}, {
}, self._SOFTWARE_STATEMENT, {
'url': url,
'site_name': 'AdultSwim',
'auth_required': auth,
plugins/youtube_download/yt_dlp/extractor/aenetworks.py
+76 -33
View File
@@ -1,3 +1,5 @@
import json
from .theplatform import ThePlatformIE
from ..utils import (
ExtractorError,
@@ -6,7 +8,6 @@ from ..utils import (
remove_start,
traverse_obj,
update_url_query,
urlencode_postdata,
)
@@ -20,13 +21,13 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
'biography.com': (None, 'biography'),
'history.com': ('HISTORY', 'history', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzZlMTQ3ZS0zMzFhLTQxY2YtYTMwNC01MDA2NzNlOGYwYjYiLCJuYmYiOjE1Mzg2NjMzMDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM4NjYzMzA5fQ.n24-FVHLGXJe2D4atIQZ700aiXKIajKh5PWFoHJ40Az4itjtwwSFHnvufnoal3T8lYkwNLxce7H-IEGxIykRkZEdwq09pMKMT-ft9ASzE4vQ8fAWbf5ZgDME86x4Jq_YaxkRc9Ne0eShGhl8fgTJHvk07sfWcol61HJ7kU7K8FzzcHR0ucFQgA5VNd8RyjoGWY7c6VxnXR214LOpXsywmit04-vGJC102b_WA2EQfqI93UzG6M6l0EeV4n0_ijP3s8_i8WMJZ_uwnTafCIY6G_731i01dKXDLSFzG1vYglAwDa8DTcdrAAuIFFDF6QNGItCCmwbhjufjmoeVb7R1Gg'),
'aetv.com': ('AETV', 'aetv', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI5Y2IwNjg2Yy03ODUxLTRiZDUtODcyMC00MjNlZTg1YTQ1NzMiLCJuYmYiOjE1Mzg2NjMyOTAsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM4NjYzMjkwfQ.T5Elf0X4TndO4NEgqBas1gDxNHGPVk_daO2Ha5FBzVO6xi3zM7eavdAKfYMCN7gpWYJx03iADaVPtczO_t_aGZczDjpwJHgTUzDgvcLZAVsVDqtDIAMy3S846rPgT6UDbVoxurA7B2VTPm9phjrSXhejvd0LBO8MQL4AZ3sy2VmiPJ2noT1ily5PuHCYlkrT1fheO064duR__Cd9DQ5VTMnKjzY3Cx345CEwKDkUk5gwgxhXM-aY0eblehrq8VD81_aRM_O3tvh7nbTydHOnUpV-k_iKVi49gqz7Sf8zb6Zh5z2Uftn3vYCfE5NQuesitoRMnsH17nW7o_D59hkRgg'),
'mylifetime.com': ('LIFETIME', 'lifetime', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJmODg0MDM1ZC1mZGRmLTRmYjgtYmRkMC05MzRhZDdiYTAwYTciLCJuYmYiOjE1NDkzOTI2NDQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQ5MzkyNjQ0fQ.vkTIaCpheKdKQd__2-3ec4qkcpbAhyCTvwe5iTl922ItSQfVhpEJG4wseVSNmBTrpBi0hvLedcw6Hj1_UuzBMVuVcCqLprU-pI8recEwL0u7G-eVkylsxe1OTUm1o3V6OykXQ9KlA-QQLL1neUhdhR1n5B1LZ4cmtBmiEpfgf4rFwXD1ScFylIcaWKLBqHoRBNUmxyTmoXXvn_A-GGSj9eCizFzY8W5uBwUcsoiw2Cr1skx7PbB2RSP1I5DsoIJKG-8XV1KS7MWl-fNLjE-hVAsI9znqfEEFcPBiv3LhCP4Nf4OIs7xAselMn0M0c8igRUZhURWX_hdygUAxkbKFtQ'),
'fyi.tv': ('FYI', 'fyi', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxOGZiOWM3Ny1mYmMzLTQxYTktYmE1Yi1lMzM0ZmUzNzU4NjEiLCJuYmYiOjE1ODc1ODAzNzcsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NTgwMzc3fQ.AYDuipKswmIfLBfOjHRsfc5fMV5NmJUmiJnkpiep4VEw9QiXkygFj4bN06Si5tFc5Mee5TDrGzDpV6iuKbVpLT5kuqXhAn-Wozf5zKPsg_IpdEKO7gsiCq4calt72ct44KTqtKD_hVcoxQU24_HaJsRgXzu3B-6Ff6UrmsXkyvYifYVC9v2DSkdCuA02_IrlllzVT2kRuefUXgL4vQRtTFf77uYa0RKSTG7uVkiQ_AU41eXevKlO2qgtc14Hk5cZ7-ZNrDyMCXYA5ngdIHP7Gs9PWaFXT36PFHI_rC4EfxUABPzjQFxjpP75aX5qn8SH__HbM9q3hoPWgaEaf76qIQ'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc', None),
'historyvault.com': (None, 'historyvault', None),
'biography.com': (None, 'biography', None),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
@@ -71,7 +72,7 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
}
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
requestor_id, brand, software_statement = self._DOMAIN_MAP[domain]
result = self._download_json(
f'https://feeds.video.aetnd.com/api/v2/{brand}/videos',
filter_value, query={f'filter[{filter_key}]': filter_value})
@@ -95,7 +96,7 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
traverse_obj(theplatform_metadata, ('ratings', 0, 'rating')))
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
url, video_id, requestor_id, resource, software_statement)
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
@@ -110,11 +111,9 @@ class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
shows/[^/]+/season-\d+/episode-\d+|
(?:
(?:movie|special)s/[^/]+|
(?:shows/[^/]+/)?videos
)/[^/?#&]+
shows/[^/?#]+/season-\d+/episode-\d+|
(?P<type>movie|special)s/[^/?#]+(?P<extra>/[^/?#]+)?|
(?:shows/[^/?#]+/)?videos/[^/?#]+
)'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
@@ -127,20 +126,18 @@ class AENetworksIE(AENetworksBaseIE):
'upload_date': '20120529',
'uploader': 'AENE-NEW',
'duration': 2592.0,
'thumbnail': r're:^https?://.*\.jpe?g$',
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:5',
'tags': 'count:14',
'categories': ['Mountain Men'],
'episode_number': 1,
'episode': 'Episode 1',
'episode': 'Winter Is Coming',
'season': 'Season 1',
'season_number': 1,
'series': 'Mountain Men',
'age_limit': 0,
},
'params': {
# m3u8 download
'skip_download': True,
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
'skip': 'Geo-restricted - This content is not available in your location.',
}, {
@@ -154,21 +151,64 @@ class AENetworksIE(AENetworksBaseIE):
'upload_date': '20160112',
'uploader': 'AENE-NEW',
'duration': 1277.695,
'thumbnail': r're:^https?://.*\.jpe?g$',
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:4',
'tags': 'count:23',
'episode': 'Episode 1',
'episode': 'Inlawful Entry',
'episode_number': 1,
'season': 'Season 9',
'season_number': 9,
'series': 'Duck Dynasty',
'age_limit': 0,
},
'params': {
# m3u8 download
'skip_download': True,
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
}, {
'url': 'https://play.mylifetime.com/movies/v-c-andrews-web-of-dreams',
'info_dict': {
'id': '1590627395981',
'ext': 'mp4',
'title': 'VC Andrews\' Web of Dreams',
'description': 'md5:2a8ba13ae64271c79eb65c0577d312ce',
'uploader': 'AENE-NEW',
'age_limit': 14,
'duration': 5253.665,
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:8',
'tags': ['lifetime', 'mylifetime', 'lifetime channel', "VC Andrews' Web of Dreams"],
'series': '',
'season': 'Season 0',
'season_number': 0,
'episode': 'VC Andrews\' Web of Dreams',
'episode_number': 0,
'timestamp': 1566489703.0,
'upload_date': '20190822',
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story',
'info_dict': {
'id': '1488235587551',
'ext': 'mp4',
'title': 'Hunting JonBenet\'s Killer: The Untold Story',
'description': 'md5:209869425ee392d74fe29201821e48b4',
'uploader': 'AENE-NEW',
'age_limit': 14,
'duration': 5003.903,
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:10',
'tags': 'count:11',
'series': '',
'season': 'Season 0',
'season_number': 0,
'episode': 'Hunting JonBenet\'s Killer: The Untold Story',
'episode_number': 0,
'timestamp': 1554987697.0,
'upload_date': '20190411',
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True,
@@ -196,25 +236,28 @@ class AENetworksIE(AENetworksBaseIE):
}]
def _real_extract(self, url):
domain, canonical = self._match_valid_url(url).groups()
domain, canonical, url_type, extra = self._match_valid_url(url).group('domain', 'id', 'type', 'extra')
if url_type in ('movie', 'special') and not extra:
canonical += f'/full-{url_type}'
return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'https://yoga.appsvcs.aetnd.com/graphql', slug,
query={'brand': brand}, headers={'Content-Type': 'application/json'},
data=json.dumps({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields), # noqa: UP031
}))['data'][resource]
}).encode())['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
_, brand, _ = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = f'http://watch.{domain}'
plugins/youtube_download/yt_dlp/extractor/amcnetworks.py
+27 -113
View File
@@ -1,32 +1,24 @@
import re
from .theplatform import ThePlatformIE
from ..utils import (
int_or_none,
parse_age_limit,
try_get,
update_url_query,
)
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils.traversal import traverse_obj
class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
class AMCNetworksIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/?#]+)+)/[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
'url': 'https://www.amc.com/shows/dark-winds/videos/dark-winds-a-look-at-season-3--1072027',
'info_dict': {
'id': '4Lq1dzOnZGt0',
'id': '6369261343112',
'ext': 'mp4',
'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
'upload_date': '20201120',
'timestamp': 1605904350,
'uploader': 'AMCN',
'title': 'Dark Winds: A Look at Season 3',
'uploader_id': '6240731308001',
'duration': 176.427,
'thumbnail': r're:https://[^/]+\.boltdns\.net/.+/image\.jpg',
'tags': [],
'timestamp': 1740414792,
'upload_date': '20250224',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
@@ -52,96 +44,18 @@ class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
'only_matching': True,
}]
_REQUESTOR_ID_MAP = {
'amc': 'AMC',
'bbcamerica': 'BBCA',
'ifc': 'IFC',
'sundancetv': 'SUNDANCE',
'wetv': 'WETV',
}
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
requestor_id = self._REQUESTOR_ID_MAP[site]
page_data = self._download_json(
f'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/{requestor_id.lower()}/url/{display_id}',
display_id)['data']
properties = page_data.get('properties') or {}
query = {
'mbr': 'true',
'manifest': 'm3u',
}
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
initial_data = self._search_json(
r'window\.initialData\s*=\s*JSON\.parse\(String\.raw`', webpage, 'initial data', display_id)
video_id = traverse_obj(initial_data, ('initialData', 'properties', 'videoId', {str}))
if not video_id: # All locked videos are now DRM-protected
self.report_drm(display_id)
account_id = initial_data['config']['brightcove']['accountId']
player_id = initial_data['config']['brightcove']['playerId']
video_player_count = 0
try:
for v in page_data['children']:
if v.get('type') == 'video-player':
release_pid = v['properties']['currentVideo']['meta']['releasePid']
tp_path = 'M_UwQC/' + release_pid
media_url = 'https://link.theplatform.com/s/' + tp_path
video_player_count += 1
except KeyError:
pass
if video_player_count > 1:
self.report_warning(
f'The JSON data has {video_player_count} video players. Only one will be extracted')
# Fall back to videoPid if releasePid not found.
# TODO: Fall back to videoPid if releasePid manifest uses DRM.
if not video_player_count:
tp_path = 'M_UwQC/media/' + properties['videoPid']
media_url = 'https://link.theplatform.com/s/' + tp_path
theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = try_get(
theplatform_metadata, lambda x: x['ratings'][0]['rating'])
video_category = properties.get('videoCategory')
if video_category and video_category.endswith('-Auth'):
resource = self._get_mvpd_resource(
requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
media_url = update_url_query(media_url, query)
formats, subtitles = self._extract_theplatform_smil(
media_url, video_id)
thumbnails = []
thumbnail_urls = [properties.get('imageDesktop')]
if 'thumbnail' in info:
thumbnail_urls.append(info.pop('thumbnail'))
for thumbnail_url in thumbnail_urls:
if not thumbnail_url:
continue
mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
thumbnails.append({
'url': thumbnail_url,
'width': int(mobj.group(1)) if mobj else None,
'height': int(mobj.group(2)) if mobj else None,
})
info.update({
'age_limit': parse_age_limit(rating),
'formats': formats,
'id': video_id,
'subtitles': subtitles,
'thumbnails': thumbnails,
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = next(iter(ns_keys))
episode = theplatform_metadata.get(ns + '$episodeTitle') or None
episode_number = int_or_none(
theplatform_metadata.get(ns + '$episode'))
season_number = int_or_none(
theplatform_metadata.get(ns + '$season'))
series = theplatform_metadata.get(ns + '$show') or None
info.update({
'episode': episode,
'episode_number': episode_number,
'season_number': season_number,
'series': series,
})
return info
return self.url_result(
f'https://players.brightcove.net/{account_id}/{player_id}_default/index.html?videoId={video_id}',
BrightcoveNewIE, video_id)
plugins/youtube_download/yt_dlp/extractor/apa.py
+10 -2
View File
@@ -11,12 +11,11 @@ class APAIE(InfoExtractor):
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://kf-vn\.sf\.apa\.at/vn/.+\.jpg',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
@@ -28,6 +27,15 @@ class APAIE(InfoExtractor):
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.vol.at/blue-man-group/5593454',
'info_dict': {
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:https?://kf-vn\.sf\.apa\.at/vn/.+\.jpg',
},
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
plugins/youtube_download/yt_dlp/extractor/appleconnect.py
+103 -25
View File
@@ -1,47 +1,125 @@
import time
from .common import InfoExtractor
from ..utils import ExtractorError, str_to_int
from ..utils import (
ExtractorError,
extract_attributes,
float_or_none,
jwt_decode_hs256,
jwt_encode,
parse_resolution,
qualities,
unified_strdate,
update_url,
url_or_none,
urljoin,
)
from ..utils.traversal import (
find_element,
require,
traverse_obj,
)
class AppleConnectIE(InfoExtractor):
_VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
IE_NAME = 'apple:music:connect'
IE_DESC = 'Apple Music Connect'
_BASE_URL = 'https://music.apple.com'
_QUALITIES = {
'provisionalUploadVideo': None,
'sdVideo': 480,
'sdVideoWithPlusAudio': 480,
'sd480pVideo': 480,
'720pHdVideo': 720,
'1080pHdVideo': 1080,
}
_VALID_URL = r'https?://music\.apple\.com/[\w-]+/post/(?P<id>\d+)'
_TESTS = [{
'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'md5': 'c1d41f72c8bcaf222e089434619316e4',
'url': 'https://music.apple.com/us/post/1018290019',
'info_dict': {
'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'id': '1018290019',
'ext': 'm4v',
'title': 'Energy',
'uploader': 'Drake',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 177.911,
'thumbnail': r're:https?://.+\.png',
'upload_date': '20150710',
'timestamp': 1436545535,
'uploader': 'Drake',
},
}, {
'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
'only_matching': True,
'url': 'https://music.apple.com/us/post/1016746627',
'info_dict': {
'id': '1016746627',
'ext': 'm4v',
'title': 'Body Shop (Madonna) - Chellous Lima (Acoustic Cover)',
'duration': 210.278,
'thumbnail': r're:https?://.+\.png',
'upload_date': '20150706',
'uploader': 'Chellous Lima',
},
}]
_jwt = None
@staticmethod
def _jwt_is_expired(token):
return jwt_decode_hs256(token)['exp'] - time.time() < 120
def _get_token(self, webpage, video_id):
if self._jwt and not self._jwt_is_expired(self._jwt):
return self._jwt
js_url = traverse_obj(webpage, (
{find_element(tag='script', attr='crossorigin', value='', html=True)},
{extract_attributes}, 'src', {urljoin(self._BASE_URL)}, {require('JS URL')}))
js = self._download_webpage(
js_url, video_id, 'Downloading token JS', 'Unable to download token JS')
header = jwt_encode({}, '', headers={'alg': 'ES256', 'kid': 'WebPlayKid'}).split('.')[0]
self._jwt = self._search_regex(
fr'(["\'])(?P<jwt>{header}(?:\.[\w-]+){{2}})\1', js, 'JSON Web Token', group='jwt')
if self._jwt_is_expired(self._jwt):
raise ExtractorError('The fetched token is already expired')
return self._jwt
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
try:
video_json = self._html_search_regex(
r'class="auc-video-data">(\{.*?\})', webpage, 'json')
except ExtractorError:
raise ExtractorError('This post doesn\'t contain a video', expected=True)
videos = self._download_json(
'https://amp-api.music.apple.com/v1/catalog/us/uploaded-videos',
video_id, headers={
'Authorization': f'Bearer {self._get_token(webpage, video_id)}',
'Origin': self._BASE_URL,
}, query={'ids': video_id, 'l': 'en-US'})
attributes = traverse_obj(videos, (
'data', ..., 'attributes', any, {require('video information')}))
video_data = self._parse_json(video_json, video_id)
timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
formats = []
quality = qualities(list(self._QUALITIES.keys()))
for format_id, src_url in traverse_obj(attributes, (
'assetTokens', {dict.items}, lambda _, v: url_or_none(v[1]),
)):
formats.append({
'ext': 'm4v',
'format_id': format_id,
'height': self._QUALITIES.get(format_id),
'quality': quality(format_id),
'url': src_url,
**parse_resolution(update_url(src_url, query=None), lenient=True),
})
return {
'id': video_id,
'url': video_data['sslSrc'],
'title': video_data['title'],
'description': video_data['description'],
'uploader': video_data['artistName'],
'thumbnail': video_data['artworkUrl'],
'timestamp': timestamp,
'like_count': like_count,
'formats': formats,
'thumbnail': self._html_search_meta(
['og:image', 'og:image:secure_url', 'twitter:image'], webpage),
**traverse_obj(attributes, {
'title': ('name', {str}),
'duration': ('durationInMilliseconds', {float_or_none(scale=1000)}),
'upload_date': ('uploadDate', {unified_strdate}),
'uploader': (('artistName', 'uploadingArtistName'), {str}, any),
'webpage_url': ('postUrl', {url_or_none}),
}),
}
plugins/youtube_download/yt_dlp/extractor/applepodcasts.py
+5 -3
View File
@@ -1,5 +1,6 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
int_or_none,
parse_iso8601,
@@ -17,7 +18,7 @@ class ApplePodcastsIE(InfoExtractor):
'ext': 'mp3',
'title': 'Ferreck Dawn - To The Break of Dawn 117',
'episode': 'Ferreck Dawn - To The Break of Dawn 117',
'description': 'md5:1fc571102f79dbd0a77bfd71ffda23bc',
'description': 'md5:8c4f5c2c30af17ed6a98b0b9daf15b76',
'upload_date': '20240812',
'timestamp': 1723449600,
'duration': 3596,
@@ -58,7 +59,7 @@ class ApplePodcastsIE(InfoExtractor):
r'<script [^>]*\bid=["\']serialized-server-data["\'][^>]*>', webpage,
'server data', episode_id, contains_pattern=r'\[{(?s:.+)}\]')[0]['data']
model_data = traverse_obj(server_data, (
'headerButtonItems', lambda _, v: v['$kind'] == 'bookmark' and v['modelType'] == 'EpisodeOffer',
'headerButtonItems', lambda _, v: v['$kind'] == 'share' and v['modelType'] == 'EpisodeLockup',
'model', {dict}, any))
return {
@@ -68,7 +69,8 @@ class ApplePodcastsIE(InfoExtractor):
or self._yield_json_ld(webpage, episode_id, fatal=False), episode_id, fatal=False),
**traverse_obj(model_data, {
'title': ('title', {str}),
'url': ('streamUrl', {clean_podcast_url}),
'description': ('summary', {clean_html}),
'url': ('playAction', 'episodeOffer', 'streamUrl', {clean_podcast_url}),
'timestamp': ('releaseDate', {parse_iso8601}),
'duration': ('duration', {int_or_none}),
}),
plugins/youtube_download/yt_dlp/extractor/archiveorg.py
+53 -31
View File
@@ -16,6 +16,7 @@ from ..utils import (
dict_get,
extract_attributes,
get_element_by_id,
get_element_text_and_html_by_tag,
int_or_none,
join_nonempty,
js_to_json,
@@ -32,7 +33,6 @@ from ..utils import (
unified_timestamp,
url_or_none,
urlhandle_detect_ext,
variadic,
)
@@ -72,6 +72,7 @@ class ArchiveOrgIE(InfoExtractor):
'display_id': 'Cops-v2.mp4',
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'duration': 1091.96,
'track': 'Cops-v2',
},
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
@@ -86,6 +87,7 @@ class ArchiveOrgIE(InfoExtractor):
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'duration': 59.77,
'display_id': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
'track': 'Commercial-JFK1960ElectionAdCampaignJingle',
},
}, {
'url': 'https://archive.org/details/Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
@@ -102,6 +104,7 @@ class ArchiveOrgIE(InfoExtractor):
'duration': 59.51,
'license': 'http://creativecommons.org/licenses/publicdomain/',
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'track': 'Commercial-Nixon1960ElectionAdToughonDefense',
},
}, {
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16',
@@ -182,6 +185,7 @@ class ArchiveOrgIE(InfoExtractor):
'duration': 130.46,
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_01_000117.jpg',
'display_id': 'irelandthemakingofarepublicreel1_01.mov',
'track': 'irelandthemakingofarepublicreel1 01',
},
}, {
'md5': '67335ee3b23a0da930841981c1e79b02',
@@ -192,6 +196,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': 'irelandthemakingofarepublicreel1_02.mov',
'display_id': 'irelandthemakingofarepublicreel1_02.mov',
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_02_001374.jpg',
'track': 'irelandthemakingofarepublicreel1 02',
},
}, {
'md5': 'e470e86787893603f4a341a16c281eb5',
@@ -202,6 +207,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': 'irelandthemakingofarepublicreel2.mov',
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel2_001554.jpg',
'display_id': 'irelandthemakingofarepublicreel2.mov',
'track': 'irelandthemakingofarepublicreel2',
},
},
],
@@ -225,19 +231,29 @@ class ArchiveOrgIE(InfoExtractor):
'release_date': '19950402',
'timestamp': 1084927901,
},
}, {
# metadata['metadata']['description'] is a list of strings instead of str
'url': 'https://archive.org/details/pra-KZ1908.02',
'info_dict': {
'id': 'pra-KZ1908.02',
'ext': 'mp3',
'display_id': 'KZ1908.02_01.wav',
'title': 'Crips and Bloods speak about gang life',
'description': 'md5:2b56b35ff021311e3554b47a285e70b3',
'uploader': '[email protected]',
'duration': 1733.74,
'track': 'KZ1908.02 01',
'track_number': 1,
'timestamp': 1336026026,
'upload_date': '20120503',
'release_year': 1992,
},
}]
@staticmethod
def _playlist_data(webpage):
element = re.findall(r'''(?xs)
<input
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s+class=['"]?js-play8-playlist['"]?
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s*/>
''', webpage)[0]
return json.loads(extract_attributes(element)['value'])
element = get_element_text_and_html_by_tag('play-av', webpage)[1]
return json.loads(extract_attributes(element)['playlist'])
def _real_extract(self, url):
video_id = urllib.parse.unquote_plus(self._match_id(url))
@@ -274,34 +290,40 @@ class ArchiveOrgIE(InfoExtractor):
m = metadata['metadata']
identifier = m['identifier']
info = {
info = traverse_obj(m, {
'title': ('title', {str}),
'description': ('description', ({str}, (..., all, {' '.join})), {clean_html}, filter, any),
'uploader': (('uploader', 'adder'), {str}, any),
'creators': ('creator', (None, ...), {str}, filter, all, filter),
'license': ('licenseurl', {url_or_none}),
'release_date': ('date', {unified_strdate}),
'timestamp': (('publicdate', 'addeddate'), {unified_timestamp}, any),
'location': ('venue', {str}),
'release_year': ('year', {int_or_none}),
})
info.update({
'id': identifier,
'title': m['title'],
'description': clean_html(m.get('description')),
'uploader': dict_get(m, ['uploader', 'adder']),
'creators': traverse_obj(m, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
'license': m.get('licenseurl'),
'release_date': unified_strdate(m.get('date')),
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
'webpage_url': f'https://archive.org/details/{identifier}',
'location': m.get('venue'),
'release_year': int_or_none(m.get('year'))}
})
for f in metadata['files']:
if f['name'] in entries:
entries[f['name']] = merge_dicts(entries[f['name']], {
'id': identifier + '/' + f['name'],
'title': f.get('title') or f['name'],
'display_id': f['name'],
'description': clean_html(f.get('description')),
'creators': traverse_obj(f, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
'duration': parse_duration(f.get('length')),
'track_number': int_or_none(f.get('track')),
'album': f.get('album'),
'discnumber': int_or_none(f.get('disc')),
'release_year': int_or_none(f.get('year'))})
**traverse_obj(f, {
'title': (('title', 'name'), {str}, any),
'display_id': ('name', {str}),
'description': ('description', ({str}, (..., all, {' '.join})), {clean_html}, filter, any),
'creators': ('creator', (None, ...), {str}, filter, all, filter),
'duration': ('length', {parse_duration}),
'track_number': ('track', {int_or_none}),
'album': ('album', {str}),
'discnumber': ('disc', {int_or_none}),
'release_year': ('year', {int_or_none}),
}),
})
entry = entries[f['name']]
elif traverse_obj(f, 'original', expected_type=str) in entries:
elif traverse_obj(f, ('original', {str})) in entries:
entry = entries[f['original']]
else:
continue
@@ -718,7 +740,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
note or 'Downloading CDX API JSON', query=query, fatal=fatal)
if isinstance(res, list) and len(res) >= 2:
# format response to make it easier to use
return [dict(zip(res[0], v)) for v in res[1:]]
return [dict(zip(res[0], v)) for v in res[1:]] # noqa: B905
elif not isinstance(res, list) or len(res) != 0:
self.report_warning('Error while parsing CDX API response' + bug_reports_message())
plugins/youtube_download/yt_dlp/extractor/arcpublishing.py
+14
View File
@@ -62,6 +62,20 @@ class ArcPublishingIE(InfoExtractor):
'url': 'arcpublishing:tronc:460f2931-8130-4719-8ea1-ffcb2d7cb685',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.uppermichiganssource.com/2025/07/18/scattered-showers-storms-bring-heavy-rain-potential/',
'info_dict': {
'id': '508116f7-e999-48db-b7c2-60a04842679b',
'ext': 'mp4',
'title': 'Scattered showers & storms bring heavy rain potential',
'description': 'Scattered showers & storms bring heavy rain potential',
'duration': 2016,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1752881287,
'upload_date': '20250718',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
}]
_POWA_DEFAULTS = [
(['cmg', 'prisa'], '%s-config-prod.api.cdn.arcpublishing.com/video'),
([
plugins/youtube_download/yt_dlp/extractor/arkena.py
-150
View File
@@ -1,150 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
parse_iso8601,
parse_qs,
try_get,
)
class ArkenaIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
)
'''
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
_TESTS = [{
'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
'md5': '97f117754e5f3c020f5f26da4a44ebaf',
'info_dict': {
'id': 'd8ab4607-00090107-aab86310',
'ext': 'mp4',
'title': 'EM_HT20_117_roslund_v2.mp4',
'timestamp': 1608285912,
'upload_date': '20201218',
'duration': 1429.162667,
'subtitles': {
'sv': 'count:3',
},
},
}, {
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
'only_matching': True,
}, {
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
'only_matching': True,
}, {
'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
account_id = mobj.group('account_id')
# Handle http://video.arkena.com/play2/embed/player URL
if not video_id:
qs = parse_qs(url)
video_id = qs.get('mediaId', [None])[0]
account_id = qs.get('accountId', [None])[0]
if not video_id or not account_id:
raise ExtractorError('Invalid URL', expected=True)
media = self._download_json(
f'https://video.qbrick.com/api/v1/public/accounts/{account_id}/medias/{video_id}',
video_id, query={
# https://video.qbrick.com/docs/api/examples/library-api.html
'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
})
metadata = media.get('metadata') or {}
title = metadata['title']
duration = None
formats = []
thumbnails = []
subtitles = {}
for resource in media['asset']['resources']:
for rendition in (resource.get('renditions') or []):
rendition_type = rendition.get('type')
for i, link in enumerate(rendition.get('links') or []):
href = link.get('href')
if not href:
continue
if rendition_type == 'image':
thumbnails.append({
'filesize': int_or_none(rendition.get('size')),
'height': int_or_none(rendition.get('height')),
'id': rendition.get('id'),
'url': href,
'width': int_or_none(rendition.get('width')),
})
elif rendition_type == 'subtitle':
subtitles.setdefault(rendition.get('language') or 'en', []).append({
'url': href,
})
elif rendition_type == 'video':
f = {
'filesize': int_or_none(rendition.get('size')),
'format_id': rendition.get('id'),
'url': href,
}
video = try_get(rendition, lambda x: x['videos'][i], dict)
if video:
if not duration:
duration = float_or_none(video.get('duration'))
f.update({
'height': int_or_none(video.get('height')),
'tbr': int_or_none(video.get('bitrate'), 1000),
'vcodec': video.get('codec'),
'width': int_or_none(video.get('width')),
})
audio = try_get(video, lambda x: x['audios'][0], dict)
if audio:
f.update({
'acodec': audio.get('codec'),
'asr': int_or_none(audio.get('sampleRate')),
})
formats.append(f)
elif rendition_type == 'index':
mime_type = link.get('mimeType')
if mime_type == 'application/smil+xml':
formats.extend(self._extract_smil_formats(
href, video_id, fatal=False))
elif mime_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif mime_type == 'application/hds+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/dash+xml':
formats.extend(self._extract_mpd_formats(
href, video_id, mpd_id='dash', fatal=False))
elif mime_type == 'application/vnd.ms-sstr+xml':
formats.extend(self._extract_ism_formats(
href, video_id, ism_id='mss', fatal=False))
return {
'id': video_id,
'title': title,
'description': metadata.get('description'),
'timestamp': parse_iso8601(media.get('created')),
'thumbnails': thumbnails,
'subtitles': subtitles,
'duration': duration,
'tags': media.get('tags'),
'formats': formats,
}
plugins/youtube_download/yt_dlp/extractor/arte.py
+29 -4
View File
@@ -51,8 +51,8 @@ class ArteTVIE(ArteTVBaseIE):
'id': '109067-000-A',
'ext': 'mp4',
'description': 'md5:d2ca367b8ecee028dddaa8bd1aebc739',
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
'timestamp': 1713927600,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/3rR6PLzfbigSkkeHtkCZNF/940x530',
'duration': 7599,
'title': 'La loi de Téhéran',
'upload_date': '20240424',
@@ -62,6 +62,7 @@ class ArteTVIE(ArteTVBaseIE):
'fr-forced': 'mincount:1',
},
},
'skip': 'Invalid URL',
}, {
'note': 'age-restricted',
'url': 'https://www.arte.tv/de/videos/006785-000-A/the-element-of-crime/',
@@ -69,9 +70,9 @@ class ArteTVIE(ArteTVBaseIE):
'id': '006785-000-A',
'description': 'md5:c2f94fdfefc8a280e4dab68ab96ab0ba',
'title': 'The Element of Crime',
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
'timestamp': 1696111200,
'duration': 5849,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/q82dTTfyuCXupPsGxXsd7B/940x530',
'upload_date': '20230930',
'ext': 'mp4',
},
@@ -252,6 +253,30 @@ class ArteTVEmbedIE(InfoExtractor):
'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://timesofmalta.com/article/watch-sunken-warships-north-sea-arte.1108358',
'info_dict': {
'id': '110288-000-A',
'ext': 'mp4',
'title': 'Danger on the Seabed',
'alt_title': 'Sunken Warships in the North Sea',
'description': 'md5:a2c84cbad37d280bddb6484087120add',
'duration': 3148,
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
'timestamp': 1741686820,
'upload_date': '20250311',
},
'params': {'skip_download': 'm3u8'},
}, {
# FIXME: Embed detection
'url': 'https://www.eurockeennes.fr/en-live/',
'info_dict': {
'id': 'en-live',
'title': 'Les Eurocks en live | Les Eurockéennes de Belfort – 3-4-5-6 juillet 2025 sur la Presqu&#039;Île du Malsaucy',
},
'playlist_count': 4,
}]
def _real_extract(self, url):
qs = parse_qs(url)
@@ -304,9 +329,9 @@ class ArteTVCategoryIE(ArteTVBaseIE):
'info_dict': {
'id': 'politics-and-society',
'title': 'Politics and society',
'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
'description': 'Watch documentaries and reportage about politics, society and current affairs.',
},
'playlist_mincount': 13,
'playlist_mincount': 3,
}]
@classmethod
plugins/youtube_download/yt_dlp/extractor/atvat.py
+2 -3
View File
@@ -4,7 +4,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
jwt_encode_hs256,
jwt_encode,
try_get,
)
@@ -83,11 +83,10 @@ class ATVAtIE(InfoExtractor):
'nbf': int(not_before.timestamp()),
'exp': int(expire.timestamp()),
}
jwt_token = jwt_encode_hs256(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID})
videos = self._download_json(
'https://vas-v4.p7s1video.net/4.0/getsources',
content_id, 'Downloading videos JSON', query={
'token': jwt_token.decode('utf-8'),
'token': jwt_encode(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID}),
})
video_id, videos_data = next(iter(videos['data'].items()))
plugins/youtube_download/yt_dlp/extractor/bandaichannel.py
-33
View File
@@ -1,33 +0,0 @@
from .brightcove import BrightcoveNewBaseIE
from ..utils import extract_attributes
class BandaiChannelIE(BrightcoveNewBaseIE):
IE_NAME = 'bandaichannel'
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
_TESTS = [{
'url': 'https://www.b-ch.com/titles/514/001',
'md5': 'a0f2d787baa5729bed71108257f613a4',
'info_dict': {
'id': '6128044564001',
'ext': 'mp4',
'title': 'メタルファイターMIKU 第1話',
'timestamp': 1580354056,
'uploader_id': '5797077852001',
'upload_date': '20200130',
'duration': 1387.733,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(self._search_regex(
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
bc = self._download_json(
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
return self._parse_brightcove_metadata(bc, bc['id'])
plugins/youtube_download/yt_dlp/extractor/bandcamp.py
+42 -16
View File
@@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
clean_html,
extract_attributes,
float_or_none,
int_or_none,
@@ -19,7 +20,7 @@ from ..utils import (
url_or_none,
urljoin,
)
from ..utils.traversal import find_element, traverse_obj
from ..utils.traversal import find_element, find_elements, traverse_obj
class BandcampIE(InfoExtractor):
@@ -35,14 +36,12 @@ class BandcampIE(InfoExtractor):
'duration': 9.8485,
'uploader': 'youtube-dl "\'/\\ä↭',
'upload_date': '20121129',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1354224127,
'track': 'youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
'album_artist': 'youtube-dl "\'/\\ä↭',
'track_id': '1812978515',
'artist': 'youtube-dl "\'/\\ä↭',
'uploader_url': 'https://youtube-dl.bandcamp.com',
'uploader_id': 'youtube-dl',
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
'artists': ['youtube-dl "\'/\\ä↭'],
'album_artists': ['youtube-dl "\'/\\ä↭'],
},
@@ -53,10 +52,9 @@ class BandcampIE(InfoExtractor):
'info_dict': {
'id': '2650410135',
'ext': 'm4a',
'acodec': r're:[fa]lac',
'title': 'Ben Prunty - Lanius (Battle)',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ben Prunty',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1396508491,
'upload_date': '20140403',
'release_timestamp': 1396483200,
@@ -65,11 +63,12 @@ class BandcampIE(InfoExtractor):
'track': 'Lanius (Battle)',
'track_number': 1,
'track_id': '2650410135',
'artist': 'Ben Prunty',
'album_artist': 'Ben Prunty',
'album': 'FTL: Advanced Edition Soundtrack',
'uploader_url': 'https://benprunty.bandcamp.com',
'uploader_id': 'benprunty',
'tags': ['soundtrack', 'chiptunes', 'cinematic', 'electronic', 'video game music', 'California'],
'artists': ['Ben Prunty'],
'album_artists': ['Ben Prunty'],
},
}, {
# no free download, mp3 128
@@ -79,8 +78,8 @@ class BandcampIE(InfoExtractor):
'id': '2584466013',
'ext': 'mp3',
'title': 'Mastodon - Hail to Fire',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mastodon',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1322005399,
'upload_date': '20111122',
'release_timestamp': 1076112000,
@@ -89,11 +88,12 @@ class BandcampIE(InfoExtractor):
'track': 'Hail to Fire',
'track_number': 5,
'track_id': '2584466013',
'artist': 'Mastodon',
'album_artist': 'Mastodon',
'album': 'Call of the Mastodon',
'uploader_url': 'https://relapsealumni.bandcamp.com',
'uploader_id': 'relapsealumni',
'tags': ['Philadelphia'],
'artists': ['Mastodon'],
'album_artists': ['Mastodon'],
},
}, {
# track from compilation album (artist/album_artist difference)
@@ -103,8 +103,8 @@ class BandcampIE(InfoExtractor):
'id': '1978174799',
'ext': 'mp3',
'title': 'submerse - submerse - Safehouse',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'submerse',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1480779297,
'upload_date': '20161203',
'release_timestamp': 1481068800,
@@ -113,11 +113,36 @@ class BandcampIE(InfoExtractor):
'track': 'submerse - Safehouse',
'track_number': 3,
'track_id': '1978174799',
'artist': 'submerse',
'album_artist': 'Diskotopia',
'album': 'DSK F/W 2016-2017 Free Compilation',
'uploader_url': 'https://diskotopia.bandcamp.com',
'uploader_id': 'diskotopia',
'tags': ['Japan'],
'artists': ['submerse'],
'album_artists': ['Diskotopia'],
},
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://www.punknews.org/article/85809/stay-inside-super-sonic',
'info_dict': {
'id': '2475540375',
'ext': 'mp3',
'title': 'Stay Inside - Super Sonic',
'album': 'Lunger',
'album_artists': ['Stay Inside'],
'artists': ['Stay Inside'],
'duration': 166.157,
'release_date': '20251003',
'release_timestamp': 1759449600.0,
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1749473029.0,
'track': 'Super Sonic',
'track_id': '2475540375',
'track_number': 3,
'upload_date': '20250609',
'uploader': 'Stay Inside',
'uploader_id': 'stayinside',
'uploader_url': 'https://stayinside.bandcamp.com',
},
}]
@@ -252,6 +277,7 @@ class BandcampIE(InfoExtractor):
'album': embed.get('album_title'),
'album_artist': album_artist,
'formats': formats,
'tags': traverse_obj(webpage, ({find_elements(cls='tag')}, ..., {clean_html})),
}
@@ -268,10 +294,10 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'id': '1353101989',
'ext': 'mp3',
'title': 'Blazo - Intro',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1311756226,
'upload_date': '20110727',
'uploader': 'Blazo',
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
'album_artists': ['Blazo'],
'uploader_url': 'https://blazo.bandcamp.com',
'release_date': '20110727',
@@ -291,6 +317,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'id': '38097443',
'ext': 'mp3',
'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1311757238,
'upload_date': '20110727',
'uploader': 'Blazo',
@@ -304,7 +331,6 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'uploader_id': 'blazo',
'album_artists': ['Blazo'],
'artists': ['Blazo'],
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
'release_timestamp': 1311724800.0,
},
},
plugins/youtube_download/yt_dlp/extractor/bellmedia.py
-91
View File
@@ -1,91 +0,0 @@
from .common import InfoExtractor
class BellMediaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?
(?P<domain>
(?:
ctv|
tsn|
bnn(?:bloomberg)?|
thecomedynetwork|
discovery|
discoveryvelocity|
sciencechannel|
investigationdiscovery|
animalplanet|
bravo|
mtv|
space|
etalk|
marilyn
)\.ca|
(?:much|cp24)\.com
)/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
_TESTS = [{
'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
'md5': '3e5b8e38370741d5089da79161646635',
'info_dict': {
'id': '1403070',
'ext': 'flv',
'title': 'David Cockfield\'s Top Picks',
'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3',
'upload_date': '20180525',
'timestamp': 1527288600,
'season_id': '73997',
'season': '2018',
'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg',
'tags': [],
'categories': ['ETFs'],
'season_number': 8,
'duration': 272.038,
'series': 'Market Call Tonight',
},
}, {
'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
'only_matching': True,
}, {
'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549',
'only_matching': True,
}, {
'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
'only_matching': True,
}, {
'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
'only_matching': True,
}, {
'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
'only_matching': True,
}, {
'url': 'http://www.etalk.ca/video?videoid=663455',
'only_matching': True,
}, {
'url': 'https://www.cp24.com/video?clipId=1982548',
'only_matching': True,
}]
_DOMAINS = {
'thecomedynetwork': 'comedy',
'discoveryvelocity': 'discvel',
'sciencechannel': 'discsci',
'investigationdiscovery': 'invdisc',
'animalplanet': 'aniplan',
'etalk': 'ctv',
'bnnbloomberg': 'bnn',
'marilyn': 'ctv_marilyn',
}
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
domain = domain.split('.')[0]
return {
'_type': 'url_transparent',
'id': video_id,
'url': f'9c9media:{self._DOMAINS.get(domain, domain)}_web:{video_id}',
'ie_key': 'NineCNineMedia',
}
plugins/youtube_download/yt_dlp/extractor/bet.py
+43 -75
View File
@@ -1,79 +1,47 @@
from .mtv import MTVServicesInfoExtractor
from ..utils import unified_strdate
from .mtv import MTVServicesBaseIE
class BetIE(MTVServicesInfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
_TESTS = [
{
'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
'info_dict': {
'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
'ext': 'flv',
'title': 'A Conversation With President Obama',
'description': 'President Obama urges persistence in confronting racism and bias.',
'duration': 1534,
'upload_date': '20141208',
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
},
},
'params': {
# rtmp download
'skip_download': True,
},
class BetIE(MTVServicesBaseIE):
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:video-clips|episodes)/(?P<id>[\da-z]{6})'
_TESTS = [{
'url': 'https://www.bet.com/video-clips/w9mk7v',
'info_dict': {
'id': '3022d121-d191-43fd-b5fb-b2c26f335497',
'ext': 'mp4',
'display_id': 'w9mk7v',
'title': 'New Normal',
'description': 'md5:d7898c124713b4646cecad9d16ff01f3',
'duration': 30.08,
'series': 'Tyler Perry\'s Sistas',
'season': 'Season 0',
'season_number': 0,
'episode': 'Episode 0',
'episode_number': 0,
'timestamp': 1755269073,
'upload_date': '20250815',
},
{
'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
'info_dict': {
'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
'display_id': 'justice-for-ferguson-a-community-reacts',
'ext': 'flv',
'title': 'Justice for Ferguson: A Community Reacts',
'description': 'A BET News special.',
'duration': 1696,
'upload_date': '20141125',
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
},
},
'params': {
# rtmp download
'skip_download': True,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bet.com/episodes/nmce72/tyler-perry-s-sistas-heavy-is-the-crown-season-9-ep-5',
'info_dict': {
'id': '6427562b-3029-11f0-b405-16fff45bc035',
'ext': 'mp4',
'display_id': 'nmce72',
'title': 'Heavy Is the Crown',
'description': 'md5:1ed345d3157a50572d2464afcc7a652a',
'channel': 'BET',
'duration': 2550.0,
'thumbnail': r're:https://images\.paramount\.tech/uri/mgid:arc:imageassetref',
'series': 'Tyler Perry\'s Sistas',
'season': 'Season 9',
'season_number': 9,
'episode': 'Episode 5',
'episode_number': 5,
'timestamp': 1755165600,
'upload_date': '20250814',
'release_timestamp': 1755129600,
'release_date': '20250814',
},
]
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/bet-mrss-player'
def _get_feed_query(self, uri):
return {
'uuid': uri,
}
def _extract_mgid(self, webpage):
return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
mgid = self._extract_mgid(webpage)
videos_info = self._get_videos_info(mgid)
info_dict = videos_info['entries'][0]
upload_date = unified_strdate(self._html_search_meta('date', webpage))
description = self._html_search_meta('description', webpage)
info_dict.update({
'display_id': display_id,
'description': description,
'upload_date': upload_date,
})
return info_dict
'params': {'skip_download': 'm3u8'},
'skip': 'Requires provider sign-in',
}]
plugins/youtube_download/yt_dlp/extractor/bilibili.py
+134 -19
View File
@@ -304,7 +304,7 @@ class BilibiliBaseIE(InfoExtractor):
class BiliBiliIE(BilibiliBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)(?P<prefix>[aAbB][vV])(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bilibili.com/video/BV13x41117TL',
@@ -353,7 +353,7 @@ class BiliBiliIE(BilibiliBaseIE):
'id': 'BV1bK411W797',
'title': '物语中的人物是如何吐槽自己的OP的',
},
'playlist_count': 18,
'playlist_count': 23,
'playlist': [{
'info_dict': {
'id': 'BV1bK411W797_p1',
@@ -373,6 +373,7 @@ class BiliBiliIE(BilibiliBaseIE):
'_old_archive_ids': ['bilibili 498159642_part1'],
},
}],
'params': {'playlist_items': '2'},
}, {
'note': 'Specific page of Anthology',
'url': 'https://www.bilibili.com/video/BV1bK411W797?p=1',
@@ -562,7 +563,7 @@ class BiliBiliIE(BilibiliBaseIE):
},
}],
}, {
'note': '301 redirect to bangumi link',
'note': 'redirect from bvid to bangumi link via redirect_url',
'url': 'https://www.bilibili.com/video/BV1TE411f7f1',
'info_dict': {
'id': '288525',
@@ -579,7 +580,27 @@ class BiliBiliIE(BilibiliBaseIE):
'duration': 1183.957,
'timestamp': 1571648124,
'upload_date': '20191021',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'thumbnail': r're:https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'redirect from aid to bangumi link via redirect_url',
'url': 'https://www.bilibili.com/video/av114868162141203',
'info_dict': {
'id': '1933368',
'title': 'PV 引爆变革的起点',
'ext': 'mp4',
'duration': 63.139,
'series': '时光代理人',
'series_id': '5183',
'season': '第三季',
'season_number': 4,
'season_id': '105212',
'episode': '引爆变革的起点',
'episode_number': 1,
'episode_id': '1933368',
'timestamp': 1752849001,
'upload_date': '20250718',
'thumbnail': r're:https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'video has subtitles, which requires login',
@@ -635,7 +656,7 @@ class BiliBiliIE(BilibiliBaseIE):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_id, prefix = self._match_valid_url(url).group('id', 'prefix')
headers = self.geo_verification_headers()
webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers)
if not self._match_valid_url(urlh.url):
@@ -643,7 +664,24 @@ class BiliBiliIE(BilibiliBaseIE):
headers['Referer'] = url
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id, default=None)
if not initial_state:
if self._search_json(r'\bwindow\._riskdata_\s*=', webpage, 'risk', video_id, default={}).get('v_voucher'):
raise ExtractorError('You have exceeded the rate limit. Try again later', expected=True)
query = {'platform': 'web'}
prefix = prefix.upper()
if prefix == 'BV':
query['bvid'] = prefix + video_id
elif prefix == 'AV':
query['aid'] = video_id
detail = self._download_json(
'https://api.bilibili.com/x/web-interface/wbi/view/detail', video_id,
note='Downloading redirection URL', errnote='Failed to download redirection URL',
query=self._sign_wbi(query, video_id), headers=headers)
new_url = traverse_obj(detail, ('data', 'View', 'redirect_url', {url_or_none}))
if new_url and BiliBiliBangumiIE.suitable(new_url):
return self.url_result(new_url, BiliBiliBangumiIE)
raise ExtractorError('Unable to extract initial state')
if traverse_obj(initial_state, ('error', 'trueCode')) == -403:
self.raise_login_required()
@@ -816,6 +854,26 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'upload_date': '20111104',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'new playurlSSRData scheme',
'url': 'https://www.bilibili.com/bangumi/play/ep678060',
'info_dict': {
'id': '678060',
'ext': 'mp4',
'series': '去你家吃饭好吗',
'series_id': '6198',
'season': '第二季',
'season_id': '42542',
'season_number': 2,
'episode': '吴老二：你家大公鸡养不熟，能煮熟吗…',
'episode_id': '678060',
'episode_number': 61,
'title': '一只小九九丫 吴老二：你家大公鸡养不熟，能煮熟吗…',
'duration': 266.123,
'timestamp': 1663315904,
'upload_date': '20220916',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'url': 'https://www.bilibili.com/bangumi/play/ep267851',
'info_dict': {
@@ -879,12 +937,41 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'Extracting episode', query={'fnval': 12240, 'ep_id': episode_id},
headers=headers))
premium_only = play_info.get('code') == -10403
play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
# play_info can be structured in at least three different ways, e.g.:
# 1.) play_info['result']['video_info'] and play_info['code']
# 2.) play_info['raw']['data']['video_info'] and play_info['code']
# 3.) play_info['data']['result']['video_info'] and play_info['data']['code']
# So we need to transform any of the above into a common structure
status_code = play_info.get('code')
if 'raw' in play_info:
play_info = play_info['raw']
if 'data' in play_info:
play_info = play_info['data']
if status_code is None:
status_code = play_info.get('code')
if 'result' in play_info:
play_info = play_info['result']
formats = self.extract_formats(play_info)
if not formats and (premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage):
self.raise_login_required('This video is for premium members only')
geo_blocked = traverse_obj(play_info, (
'plugins', lambda _, v: v['name'] == 'AreaLimitPanel', 'config', 'is_block', {bool}, any))
premium_only = status_code == -10403
video_info = traverse_obj(play_info, ('video_info', {dict})) or {}
formats = self.extract_formats(video_info)
if not formats:
if geo_blocked:
self.raise_geo_restricted()
elif premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage:
self.raise_login_required('This video is for premium members only')
if traverse_obj(play_info, ((
('play_check', 'play_detail'), # 'PLAY_PREVIEW' vs 'PLAY_WHOLE' vs 'PLAY_NONE'
'play_video_type', # 'preview' vs 'whole' vs 'none'
), any, {lambda x: x in ('PLAY_PREVIEW', 'preview')})):
self.report_warning(
'Only preview format is available, '
f'you have to become a premium member to access full video. {self._login_hint()}')
bangumi_info = self._download_json(
'https://api.bilibili.com/pgc/view/web/season', episode_id, 'Get episode details',
@@ -922,7 +1009,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'season': str_or_none(season_title),
'season_id': str_or_none(season_id),
'season_number': season_number,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'duration': float_or_none(video_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
'__post_extractor': self.extract_comments(aid),
'http_headers': {'Referer': url},
@@ -966,6 +1053,7 @@ class BiliBiliBangumiMediaIE(BilibiliBaseIE):
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
'params': {'playlist_items': '2'},
}]
def _real_extract(self, url):
@@ -1021,6 +1109,7 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
'params': {'playlist_items': '2'},
}]
def _real_extract(self, url):
@@ -1192,6 +1281,26 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
'id': '313580179',
},
'playlist_mincount': 92,
}, {
# Hidden-mode collection
'url': 'https://space.bilibili.com/3669403/video',
'info_dict': {
'id': '3669403',
},
'playlist': [{
'info_dict': {
'_type': 'playlist',
'id': '3669403_3958082',
'title': '合集·直播回放',
'description': '',
'uploader': '月路Yuel',
'uploader_id': '3669403',
'timestamp': int,
'upload_date': str,
'thumbnail': str,
},
}],
'params': {'playlist_items': '7'},
}]
def _real_extract(self, url):
@@ -1248,10 +1357,16 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
}
def get_entries(page_data):
for entry in traverse_obj(page_data, ('list', 'vlist')) or []:
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
for entry in traverse_obj(page_data, ('list', 'vlist', ..., {dict})):
if traverse_obj(entry, ('meta', 'attribute')) == 156:
# hidden-mode collection doesn't show its videos in uploads; extract as playlist instead
yield self.url_result(
f'https://space.bilibili.com/{entry["mid"]}/lists/{entry["meta"]["id"]}?type=season',
BilibiliCollectionListIE, f'{entry["mid"]}_{entry["meta"]["id"]}')
else:
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
_, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
return self.playlist_result(paged_list, playlist_id)
@@ -1285,7 +1400,7 @@ class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE):
for entry in page_data.get('data') or []:
yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id'])
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
_, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
return self.playlist_result(paged_list, playlist_id)
@@ -1785,7 +1900,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
'thumbnail': r're:^https?://.+\.jpg',
'timestamp': 1564836614,
'upload_date': '20190803',
'uploader': 'tsukimi-つきみぐー',
'uploader': '十六夜tsukimiつきみぐ',
'view_count': int,
},
}
@@ -1840,10 +1955,10 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
'url': 'https://www.bilibili.com/audio/am10624',
'info_dict': {
'id': '10624',
'title': '每日新曲推荐（每日11:00更新）',
'title': '新曲推荐',
'description': '每天11:00更新，为你推送最新音乐',
},
'playlist_count': 19,
'playlist_count': 16,
}
def _real_extract(self, url):
plugins/youtube_download/yt_dlp/extractor/bitchute.py
+95 -61
View File
@@ -1,30 +1,32 @@
import functools
import json
import re
from .common import InfoExtractor
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
clean_html,
extract_attributes,
determine_ext,
format_field,
get_element_by_class,
get_element_by_id,
get_element_html_by_class,
get_elements_html_by_class,
int_or_none,
orderedSet,
parse_count,
parse_duration,
traverse_obj,
unified_strdate,
parse_iso8601,
url_or_none,
urlencode_postdata,
urljoin,
)
from ..utils.traversal import traverse_obj
class BitChuteIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/?#]+)/(?P<id>[^/?#&]+)'
_EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
@@ -34,12 +36,17 @@ class BitChuteIE(InfoExtractor):
'ext': 'mp4',
'title': 'This is the first video on #BitChute !',
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://.+/.+\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
'uploader_id': 'I5NgtHZn9vPj',
'channel_id': '1VBwRfyNcKdX',
'view_count': int,
'duration': 16.0,
'timestamp': 1483425443,
},
}, {
# test case: video with different channel and uploader
@@ -49,13 +56,18 @@ class BitChuteIE(InfoExtractor):
'id': 'Yti_j9A-UZ4',
'ext': 'mp4',
'title': 'Israel at War | Full Measure',
'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:e60198b89971966d6030d22b3268f08f',
'thumbnail': r're:https?://.+/.+\.jpg$',
'uploader': 'sharylattkisson',
'upload_date': '20231106',
'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
'channel': 'Full Measure with Sharyl Attkisson',
'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/',
'uploader_id': '9K0kUWA9zmd9',
'channel_id': 'NpdxoCRv3ZLb',
'view_count': int,
'duration': 554.0,
'timestamp': 1699296106,
},
}, {
# video not downloadable in browser, but we can recover it
@@ -66,25 +78,21 @@ class BitChuteIE(InfoExtractor):
'ext': 'mp4',
'filesize': 71537926,
'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control',
'description': 'md5:228ee93bd840a24938f536aeac9cf749',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:2029c7c212ccd4b040f52bb2d036ef4e',
'thumbnail': r're:https?://.+/.+\.jpg$',
'uploader': 'BitChute',
'upload_date': '20181113',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
'uploader_id': 'I5NgtHZn9vPj',
'channel_id': '1VBwRfyNcKdX',
'view_count': int,
'duration': 1701.0,
'tags': ['bitchute'],
'timestamp': 1542130287,
},
'params': {'check_formats': None},
}, {
# restricted video
'url': 'https://www.bitchute.com/video/WEnQU7XGcTdl/',
'info_dict': {
'id': 'WEnQU7XGcTdl',
'ext': 'mp4',
'title': 'Impartial Truth - Ein Letzter Appell an die Vernunft',
},
'params': {'skip_download': True},
'skip': 'Georestricted in DE',
}, {
'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
'only_matching': True,
@@ -96,11 +104,8 @@ class BitChuteIE(InfoExtractor):
'only_matching': True,
}]
_GEO_BYPASS = False
_HEADERS = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
'Referer': 'https://www.bitchute.com/',
}
_UPLOADER_URL_TMPL = 'https://www.bitchute.com/profile/%s/'
_CHANNEL_URL_TMPL = 'https://www.bitchute.com/channel/%s/'
def _check_format(self, video_url, video_id):
urls = orderedSet(
@@ -112,7 +117,7 @@ class BitChuteIE(InfoExtractor):
for url in urls:
try:
response = self._request_webpage(
HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS)
HEADRequest(url), video_id=video_id, note=f'Checking {url}')
except ExtractorError as e:
self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}')
continue
@@ -121,54 +126,79 @@ class BitChuteIE(InfoExtractor):
'filesize': int_or_none(response.headers.get('Content-Length')),
}
def _raise_if_restricted(self, webpage):
page_title = clean_html(get_element_by_class('page-title', webpage)) or ''
if re.fullmatch(r'(?:Channel|Video) Restricted', page_title):
reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
self.raise_geo_restricted(reason)
@staticmethod
def _make_url(html):
path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
return urljoin('https://www.bitchute.com', path)
def _call_api(self, endpoint, data, display_id, fatal=True):
note = endpoint.rpartition('/')[2]
try:
return self._download_json(
f'https://api.bitchute.com/api/beta/{endpoint}', display_id,
f'Downloading {note} API JSON', f'Unable to download {note} API JSON',
data=json.dumps(data).encode(),
headers={
'Accept': 'application/json',
'Content-Type': 'application/json',
})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
errors = '. '.join(traverse_obj(e.cause.response.read().decode(), (
{json.loads}, 'errors', lambda _, v: v['context'] == 'reason', 'message', {str})))
if errors and 'location' in errors:
# Can always be fatal since the video/media call will reach this code first
self.raise_geo_restricted(errors)
if fatal:
raise
self.report_warning(e.msg)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
self._raise_if_restricted(webpage)
publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
entries = self._parse_html5_media_entries(url, webpage, video_id)
data = {'video_id': video_id}
media_url = self._call_api('video/media', data, video_id)['media_url']
formats = []
for format_ in traverse_obj(entries, (0, 'formats', ...)):
if determine_ext(media_url) == 'm3u8':
formats.extend(
self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls', live=True))
else:
if self.get_param('check_formats') is not False:
format_.update(self._check_format(format_.pop('url'), video_id) or {})
if 'url' not in format_:
continue
formats.append(format_)
if fmt := self._check_format(media_url, video_id):
formats.append(fmt)
else:
formats.append({'url': media_url})
if not formats:
self.raise_no_formats(
'Video is unavailable. Please make sure this video is playable in the browser '
'before reporting this issue.', expected=True, video_id=video_id)
details = get_element_by_class('details', webpage) or ''
uploader_html = get_element_html_by_class('creator', details) or ''
channel_html = get_element_html_by_class('name', details) or ''
video = self._call_api('video', data, video_id, fatal=False)
channel = None
if channel_id := traverse_obj(video, ('channel', 'channel_id', {str})):
channel = self._call_api('channel', {'channel_id': channel_id}, video_id, fatal=False)
return {
**traverse_obj(video, {
'title': ('video_name', {str}),
'description': ('description', {str}),
'thumbnail': ('thumbnail_url', {url_or_none}),
'channel': ('channel', 'channel_name', {str}),
'channel_id': ('channel', 'channel_id', {str}),
'channel_url': ('channel', 'channel_url', {urljoin('https://www.bitchute.com/')}),
'uploader_id': ('profile_id', {str}),
'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
'timestamp': ('date_published', {parse_iso8601}),
'duration': ('duration', {parse_duration}),
'tags': ('hashtags', ..., {str}, filter, all, filter),
'view_count': ('view_count', {int_or_none}),
'is_live': ('state_id', {lambda x: x == 'live'}),
}),
**traverse_obj(channel, {
'channel': ('channel_name', {str}),
'channel_id': ('channel_id', {str}),
'channel_url': ('url_slug', {format_field(template=self._CHANNEL_URL_TMPL)}, filter),
'uploader': ('profile_name', {str}),
'uploader_id': ('profile_id', {str}),
'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
}),
'id': video_id,
'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'uploader': clean_html(uploader_html),
'uploader_url': self._make_url(uploader_html),
'channel': clean_html(channel_html),
'channel_url': self._make_url(channel_html),
'upload_date': unified_strdate(self._search_regex(
r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
'formats': formats,
}
@@ -190,7 +220,7 @@ class BitChuteChannelIE(InfoExtractor):
'ext': 'mp4',
'title': 'This is the first video on #BitChute !',
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://.+/.+\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
@@ -198,6 +228,9 @@ class BitChuteChannelIE(InfoExtractor):
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
'duration': 16,
'view_count': int,
'uploader_id': 'I5NgtHZn9vPj',
'channel_id': '1VBwRfyNcKdX',
'timestamp': 1483425443,
},
},
],
@@ -213,6 +246,7 @@ class BitChuteChannelIE(InfoExtractor):
'title': 'Bruce MacDonald and "The Light of Darkness"',
'description': 'md5:747724ef404eebdfc04277714f81863e',
},
'skip': '404 Not Found',
}, {
'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
'only_matching': True,
plugins/youtube_download/yt_dlp/extractor/blackboardcollaborate.py
+131 -15
View File
@@ -1,16 +1,27 @@
from .common import InfoExtractor
from ..utils import parse_iso8601
from ..utils import (
UnsupportedError,
float_or_none,
int_or_none,
join_nonempty,
jwt_decode_hs256,
mimetype2ext,
parse_iso8601,
parse_qs,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BlackboardCollaborateIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?P<region>[a-z-]+)\.bbcollab\.com/
(?P<region>[a-z]+)(?:-lti)?\.bbcollab\.com/
(?:
collab/ui/session/playback/load|
recording
)/
(?P<id>[^/]+)'''
(?P<id>[^/?#]+)'''
_TESTS = [
{
'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
@@ -19,9 +30,55 @@ class BlackboardCollaborateIE(InfoExtractor):
'id': '0a633b6a88824deb8c918f470b22b256',
'title': 'HESI A2 Information Session - Thursday, May 6, 2021 - recording_1',
'ext': 'mp4',
'duration': 1896000,
'timestamp': 1620331399,
'duration': 1896,
'timestamp': 1620333295,
'upload_date': '20210506',
'subtitles': {
'live_chat': 'mincount:1',
},
},
},
{
'url': 'https://eu.bbcollab.com/collab/ui/session/playback/load/4bde2dee104f40289a10f8e554270600',
'md5': '108db6a8f83dcb0c2a07793649581865',
'info_dict': {
'id': '4bde2dee104f40289a10f8e554270600',
'title': 'Meeting - Azerbaycanca erize formasi',
'ext': 'mp4',
'duration': 880,
'timestamp': 1671176868,
'upload_date': '20221216',
},
},
{
'url': 'https://eu.bbcollab.com/recording/f83be390ecff46c0bf7dccb9dddcf5f6',
'md5': 'e3b0b88ddf7847eae4b4c0e2d40b83a5',
'info_dict': {
'id': 'f83be390ecff46c0bf7dccb9dddcf5f6',
'title': 'Keynote lecture by Laura Carvalho - recording_1',
'ext': 'mp4',
'duration': 5506,
'timestamp': 1662721705,
'upload_date': '20220909',
'subtitles': {
'live_chat': 'mincount:1',
},
},
},
{
'url': 'https://eu.bbcollab.com/recording/c3e1e7c9e83d4cd9981c93c74888d496',
'md5': 'fdb2d8c43d66fbc0b0b74ef5e604eb1f',
'info_dict': {
'id': 'c3e1e7c9e83d4cd9981c93c74888d496',
'title': 'International Ally User Group - recording_18',
'ext': 'mp4',
'duration': 3479,
'timestamp': 1721919621,
'upload_date': '20240725',
'subtitles': {
'en': 'mincount:1',
'live_chat': 'mincount:1',
},
},
},
{
@@ -42,22 +99,81 @@ class BlackboardCollaborateIE(InfoExtractor):
},
]
def _call_api(self, region, video_id, path=None, token=None, note=None, fatal=False):
# Ref: https://github.com/blackboard/BBDN-Collab-Postman-REST
return self._download_json(
join_nonempty(f'https://{region}.bbcollab.com/collab/api/csa/recordings', video_id, path, delim='/'),
video_id, note or 'Downloading JSON metadata', fatal=fatal,
headers={'Authorization': f'Bearer {token}'} if token else None)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
region = mobj.group('region')
video_id = mobj.group('id')
info = self._download_json(
f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
duration = info.get('duration')
title = info['name']
upload_date = info.get('created')
streams = info['streams']
formats = [{'format_id': k, 'url': url} for k, url in streams.items()]
token = parse_qs(url).get('authToken', [None])[-1]
video_info = self._call_api(region, video_id, path='data/secure', token=token, note='Trying auth token')
if video_info:
video_extra = self._call_api(region, video_id, token=token, note='Retrieving extra attributes')
else:
video_info = self._call_api(region, video_id, path='data', note='Trying fallback', fatal=True)
video_extra = {}
formats = traverse_obj(video_info, ('extStreams', lambda _, v: url_or_none(v['streamUrl']), {
'url': 'streamUrl',
'ext': ('contentType', {mimetype2ext}),
'aspect_ratio': ('aspectRatio', {float_or_none}),
}))
if filesize := traverse_obj(video_extra, ('storageSize', {int_or_none})):
for fmt in formats:
fmt['filesize'] = filesize
subtitles = {}
for subs in traverse_obj(video_info, ('subtitles', lambda _, v: url_or_none(v['url']))):
subtitles.setdefault(subs.get('lang') or 'und', []).append({
'name': traverse_obj(subs, ('label', {str})),
'url': subs['url'],
})
for live_chat_url in traverse_obj(video_info, ('chats', ..., 'url', {url_or_none})):
subtitles.setdefault('live_chat', []).append({'url': live_chat_url})
return {
'duration': duration,
**traverse_obj(video_info, {
'title': ('name', {str}),
'timestamp': ('created', {parse_iso8601}),
'duration': ('duration', {int_or_none(scale=1000)}),
}),
'formats': formats,
'id': video_id,
'timestamp': parse_iso8601(upload_date),
'title': title,
'subtitles': subtitles,
}
class BlackboardCollaborateLaunchIE(InfoExtractor):
_VALID_URL = r'https?://[a-z]+\.bbcollab\.com/launch/(?P<id>[^/?#]+)'
_TESTS = [
{
'url': 'https://au.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.xuELw4EafEwUMoYcCHidGn4Tw9O1QCbYHzYGJUl0kKk',
'only_matching': True,
},
{
'url': 'https://us.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.yOhRZNaIjXYoMYMpcTzgjZJCnIFaYf2cAzbco8OAxlY',
'only_matching': True,
},
{
'url': 'https://eu.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.Xj4ymojYLwZ1vKPKZ-KxjpqQvFXoJekjRaG0npngwWs',
'only_matching': True,
},
]
def _real_extract(self, url):
token = self._match_id(url)
video_id = jwt_decode_hs256(token)['resourceAccessTicket']['resourceId']
redirect_url = self._request_webpage(url, video_id).url
if self.suitable(redirect_url):
raise UnsupportedError(redirect_url)
return self.url_result(redirect_url, BlackboardCollaborateIE, video_id)
plugins/youtube_download/yt_dlp/extractor/blogger.py
+12 -1
View File
@@ -19,8 +19,19 @@ class BloggerIE(InfoExtractor):
'id': 'BLOGGER-video-3c740e3a49197e16-796',
'title': 'BLOGGER-video-3c740e3a49197e16-796',
'ext': 'mp4',
'thumbnail': r're:^https?://.*',
'duration': 76.068,
'thumbnail': r're:https?://i9\.ytimg\.com/vi_blogger/.+',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://blog.tomeuvizoso.net/2019/01/a-panfrost-milestone.html',
'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
'info_dict': {
'id': 'BLOGGER-video-3c740e3a49197e16-12203',
'ext': 'mp4',
'title': 'BLOGGER-video-3c740e3a49197e16-12203',
'duration': 76.068,
'thumbnail': r're:https?://i9\.ytimg\.com/vi_blogger/.+',
},
}]
plugins/youtube_download/yt_dlp/extractor/brainpop.py
+1 -1
View File
@@ -174,7 +174,7 @@ class BrainPOPLegacyBaseIE(BrainPOPBaseIE):
}
def _real_extract(self, url):
slug, display_id = self._match_valid_url(url).group('slug', 'id')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
topic_data = self._search_json(
r'var\s+content\s*=\s*', webpage, 'content data',
plugins/youtube_download/yt_dlp/extractor/bravotv.py
-188
View File
@@ -1,188 +0,0 @@
from .adobepass import AdobePassIE
from ..networking import HEADRequest
from ..utils import (
extract_attributes,
float_or_none,
get_element_html_by_class,
int_or_none,
merge_dicts,
parse_age_limit,
remove_end,
str_or_none,
traverse_obj,
unescapeHTML,
unified_timestamp,
update_url_query,
url_or_none,
)
class BravoTVIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
'info_dict': {
'id': '3923059',
'ext': 'mp4',
'title': 'The Top Chef Season 16 Winner Is...',
'description': 'Find out who takes the title of Top Chef!',
'upload_date': '20190314',
'timestamp': 1552591860,
'season_number': 16,
'episode_number': 15,
'series': 'Top Chef',
'episode': 'The Top Chef Season 16 Winner Is...',
'duration': 190.357,
'season': 'Season 16',
'thumbnail': r're:^https://.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
'info_dict': {
'id': '9000234570',
'ext': 'mp4',
'title': 'London Calling',
'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
'upload_date': '20230310',
'timestamp': 1678410000,
'season_number': 20,
'episode_number': 1,
'series': 'Top Chef',
'episode': 'London Calling',
'duration': 3266.03,
'season': 'Season 20',
'chapters': 'count:7',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
'info_dict': {
'id': '3692045',
'ext': 'mp4',
'title': 'Closing Night',
'description': 'md5:3170065c5c2f19548d72a4cbc254af63',
'upload_date': '20180401',
'timestamp': 1522623600,
'season_number': 1,
'episode_number': 1,
'series': 'In Ice Cold Blood',
'episode': 'Closing Night',
'duration': 2629.051,
'season': 'Season 1',
'chapters': 'count:6',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
'info_dict': {
'id': '3974019',
'ext': 'mp4',
'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
'upload_date': '20190617',
'timestamp': 1560790800,
'season_number': 2,
'episode_number': 16,
'series': 'In Ice Cold Blood',
'episode': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'duration': 68.235,
'season': 'Season 2',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}]
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
settings = self._search_json(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>', webpage, 'settings', display_id)
tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
query = {
'manifest': 'm3u',
'formats': 'm3u,mpeg4',
}
if tve:
account_pid = tve.get('data-mpx-media-account-pid') or 'HNK2IC'
account_id = tve['data-mpx-media-account-id']
metadata = self._parse_json(
tve.get('data-normalized-video', ''), display_id, fatal=False, transform_source=unescapeHTML)
video_id = tve.get('data-guid') or metadata['guid']
if tve.get('data-entitlement') == 'auth':
auth = traverse_obj(settings, ('tve_adobe_auth', {dict})) or {}
site = remove_end(site, 'tv')
release_pid = tve['data-release-pid']
resource = self._get_mvpd_resource(
tve.get('data-adobe-pass-resource-id') or auth.get('adobePassResourceId') or site,
tve['data-title'], release_pid, tve.get('data-rating'))
query.update({
'switch': 'HLSServiceSecure',
'auth': self._extract_mvpd_auth(
url, release_pid, auth.get('adobePassRequestorId') or site, resource),
})
else:
ls_playlist = traverse_obj(settings, ('ls_playlist', ..., {dict}), get_all=False) or {}
account_pid = ls_playlist.get('mpxMediaAccountPid') or 'PHSl-B'
account_id = ls_playlist['mpxMediaAccountId']
video_id = ls_playlist['defaultGuid']
metadata = traverse_obj(
ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, {dict}), get_all=False)
tp_url = f'https://link.theplatform.com/s/{account_pid}/media/guid/{account_id}/{video_id}'
tp_metadata = self._download_json(
update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
chapters = traverse_obj(tp_metadata, ('chapters', ..., {
'start_time': ('startTime', {float_or_none(scale=1000)}),
'end_time': ('endTime', {float_or_none(scale=1000)}),
}))
# prune pointless single chapters that span the entire duration from short videos
if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
chapters = None
m3u8_url = self._request_webpage(HEADRequest(
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
if 'mpeg_cenc' in m3u8_url:
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'chapters': chapters,
**merge_dicts(traverse_obj(tp_metadata, {
'title': 'title',
'description': 'description',
'duration': ('duration', {float_or_none(scale=1000)}),
'timestamp': ('pubDate', {float_or_none(scale=1000)}),
'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),
'episode': (('title', 'pl1$episodeNumber', 'nbcu$episodeNumber'), {str_or_none}),
'age_limit': ('ratings', ..., 'rating', {parse_age_limit}),
}, get_all=False), traverse_obj(metadata, {
'title': 'title',
'description': 'description',
'duration': ('durationInSeconds', {int_or_none}),
'timestamp': ('airDate', {unified_timestamp}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode': 'episodeTitle',
'series': 'show',
})),
}
plugins/youtube_download/yt_dlp/extractor/brightcove.py
+17 -14
View File
@@ -495,8 +495,6 @@ class BrightcoveLegacyIE(InfoExtractor):
class BrightcoveNewBaseIE(AdobePassIE):
def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
title = json_data['name'].strip()
formats, subtitles = [], {}
sources = json_data.get('sources') or []
for source in sources:
@@ -600,16 +598,18 @@ class BrightcoveNewBaseIE(AdobePassIE):
return {
'id': video_id,
'title': title,
'description': clean_html(json_data.get('description')),
'thumbnails': thumbnails,
'duration': duration,
'timestamp': parse_iso8601(json_data.get('published_at')),
'uploader_id': json_data.get('account_id'),
'formats': formats,
'subtitles': subtitles,
'tags': json_data.get('tags', []),
'is_live': is_live,
**traverse_obj(json_data, {
'title': ('name', {clean_html}),
'description': ('description', {clean_html}),
'tags': ('tags', ..., {str}, filter, all, filter),
'timestamp': ('published_at', {parse_iso8601}),
'uploader_id': ('account_id', {str}),
}),
}
@@ -645,10 +645,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'uploader_id': '4036320279001',
'formats': 'mincount:39',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
# playlist stream
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
@@ -709,7 +706,6 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'ext': 'mp4',
'title': 'TGD_01-032_5',
'thumbnail': r're:^https?://.*\.jpg$',
'tags': [],
'timestamp': 1646078943,
'uploader_id': '1569565978001',
'upload_date': '20220228',
@@ -721,7 +717,6 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'ext': 'mp4',
'title': 'TGD 01-087 (Airs 05.25.22)_Segment 5',
'thumbnail': r're:^https?://.*\.jpg$',
'tags': [],
'timestamp': 1651604591,
'uploader_id': '1569565978001',
'upload_date': '20220503',
@@ -923,10 +918,18 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
missing_fields = ', '.join(
key for key in ('source_url', 'software_statement') if not smuggled_data.get(key))
if missing_fields:
raise ExtractorError(
f'Missing fields in smuggled data: {missing_fields}. '
f'This video can be only extracted from the webpage where it is embedded. '
f'Pass the URL of the embedding webpage instead of the Brightcove URL', expected=True)
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
custom_fields['bcadobepassresourceid'],
smuggled_data['software_statement'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': f'application/json;pk={policy_key}',
plugins/youtube_download/yt_dlp/extractor/btvplus.py
+73
View File
@@ -0,0 +1,73 @@
from .common import InfoExtractor
from ..utils import (
bug_reports_message,
clean_html,
get_element_by_class,
js_to_json,
mimetype2ext,
strip_or_none,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class BTVPlusIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?btvplus\.bg/produkt/(?:predavaniya|seriali|novini)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://btvplus.bg/produkt/predavaniya/67271/btv-reporterite/btv-reporterite-12-07-2025-g',
'info_dict': {
'ext': 'mp4',
'id': '67271',
'title': 'bTV Репортерите - 12.07.2025 г.',
'thumbnail': 'https://cdn.btv.bg/media/images/940x529/Jul2025/2113606319.jpg',
},
}, {
'url': 'https://btvplus.bg/produkt/seriali/66942/sezon-2/plen-sezon-2-epizod-55',
'info_dict': {
'ext': 'mp4',
'id': '66942',
'title': 'Плен - сезон 2, епизод 55',
'thumbnail': 'https://cdn.btv.bg/media/images/940x529/Jun2025/2113595104.jpg',
},
}, {
'url': 'https://btvplus.bg/produkt/novini/67270/btv-novinite-centralna-emisija-12-07-2025',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'var\s+videoUrl\s*=\s*[\'"]([^\'"]+)[\'"]',
webpage, 'player URL')
player_config = self._download_json(
urljoin('https://btvplus.bg', player_url), video_id)['config']
videojs_data = self._search_json(
r'videojs\(["\'][^"\']+["\'],', player_config, 'videojs data',
video_id, transform_source=js_to_json)
formats = []
subtitles = {}
for src in traverse_obj(videojs_data, ('sources', lambda _, v: url_or_none(v['src']))):
ext = mimetype2ext(src.get('type'))
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
self.report_warning(f'Unknown format type {ext}{bug_reports_message()}')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'title': (
strip_or_none(self._og_search_title(webpage, default=None))
or clean_html(get_element_by_class('product-title', webpage))),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
}
plugins/youtube_download/yt_dlp/extractor/cartoonnetwork.py
-59
View File
@@ -1,59 +0,0 @@
from .turner import TurnerBaseIE
from ..utils import int_or_none
class CartoonNetworkIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
_TEST = {
'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html',
'info_dict': {
'id': '6e3375097f63874ebccec7ef677c1c3845fa850e',
'ext': 'mp4',
'title': 'How to Draw Upgrade',
'description': 'md5:2061d83776db7e8be4879684eefe8c0f',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False):
metadata_re = ''
if content_re:
metadata_re = r'|video_metadata\.content_' + content_re
return self._search_regex(
rf'(?:_cnglobal\.currentVideo\.{global_re}{metadata_re})\s*=\s*"({value_re})";',
webpage, name, fatal=fatal)
media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True)
title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True)
info = self._extract_ngtv_info(
media_id, {'networkId': 'cartoonnetwork'}, {
'url': url,
'site_name': 'CartoonNetwork',
'auth_required': find_field('authType', 'auth type') != 'unauth',
})
series = find_field(
'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage)
info.update({
'id': media_id,
'display_id': display_id,
'title': title,
'description': self._html_search_meta('description', webpage),
'series': series,
'episode': title,
})
for field in ('season', 'episode'):
field_name = field + 'Number'
info[field + '_number'] = int_or_none(find_field(
field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage))
return info
plugins/youtube_download/yt_dlp/extractor/cbc.py
+61 -5
View File
@@ -31,7 +31,7 @@ from ..utils.traversal import require, traverse_obj, trim_str
class CBCIE(InfoExtractor):
IE_NAME = 'cbc.ca'
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/|listen/|i/caffeine/syndicate/)(?:[^/?#]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# with mediaId
'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs',
@@ -112,10 +112,6 @@ class CBCIE(InfoExtractor):
'playlist_mincount': 6,
}]
@classmethod
def suitable(cls, url):
return False if CBCPlayerIE.suitable(url) else super().suitable(url)
def _extract_player_init(self, player_init, display_id):
player_info = self._parse_json(player_init, display_id, js_to_json)
media_id = player_info.get('mediaId')
@@ -913,3 +909,63 @@ class CBCGemLiveIE(InfoExtractor):
'thumbnail': ('images', 'card', 'url'),
}),
}
class CBCListenIE(InfoExtractor):
IE_NAME = 'cbc.ca:listen'
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/listen/(?:cbc-podcasts|live-radio)/[\w-]+/[\w-]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.cbc.ca/listen/cbc-podcasts/1353-the-naked-emperor/episode/16142603-introducing-understood-who-broke-the-internet',
'info_dict': {
'id': '16142603',
'title': 'Introducing Understood: Who Broke the Internet?',
'ext': 'mp3',
'description': 'md5:c605117500084e43f08a950adc6a708c',
'duration': 229,
'timestamp': 1745812800,
'release_timestamp': 1745827200,
'release_date': '20250428',
'upload_date': '20250428',
},
}, {
'url': 'https://www.cbc.ca/listen/live-radio/1-64-the-house/clip/16170773-should-canada-suck-stand-donald-trump',
'info_dict': {
'id': '16170773',
'title': 'Should Canada suck up or stand up to Donald Trump?',
'ext': 'mp3',
'description': 'md5:7385194f1cdda8df27ba3764b35e7976',
'duration': 3159,
'timestamp': 1758340800,
'release_timestamp': 1758254400,
'release_date': '20250919',
'upload_date': '20250920',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
response = self._download_json(
f'https://www.cbc.ca/listen/api/v1/clips/{video_id}', video_id, fatal=False)
data = traverse_obj(response, ('data', {dict}))
if not data:
self.report_warning('API failed to return data. Falling back to webpage parsing')
webpage = self._download_webpage(url, video_id)
preloaded_state = self._search_json(
r'window\.__PRELOADED_STATE__\s*=', webpage, 'preloaded state',
video_id, transform_source=js_to_json)
data = traverse_obj(preloaded_state, (
('podcastDetailData', 'showDetailData'), ..., 'episodes',
lambda _, v: str(v['clipID']) == video_id, any, {require('episode data')}))
return {
'id': video_id,
**traverse_obj(data, {
'url': (('src', 'url'), {url_or_none}, any),
'title': ('title', {str}),
'description': ('description', {str}),
'release_timestamp': ('releasedAt', {int_or_none(scale=1000)}),
'timestamp': ('airdate', {int_or_none(scale=1000)}),
'duration': ('duration', {int_or_none}),
}),
}
plugins/youtube_download/yt_dlp/extractor/cbsnews.py
+1 -9
View File
@@ -5,8 +5,6 @@ import zlib
from .anvato import AnvatoIE
from .common import InfoExtractor
from .paramountplus import ParamountPlusIE
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
UserNotLive,
@@ -132,13 +130,7 @@ class CBSNewsEmbedIE(CBSNewsBaseIE):
video_id = item['mpxRefId']
video_url = self._get_video_url(item)
if not video_url:
# Old embeds redirect user to ParamountPlus but most links are 404
pplus_url = f'https://www.paramountplus.com/shows/video/{video_id}'
try:
self._request_webpage(HEADRequest(pplus_url), video_id)
return self.url_result(pplus_url, ParamountPlusIE)
except ExtractorError:
self.raise_no_formats('This video is no longer available', True, video_id)
raise ExtractorError('This video is no longer available', expected=True)
return self._extract_video(item, video_url, video_id)
plugins/youtube_download/yt_dlp/extractor/cellebrite.py
-12
View File
@@ -5,18 +5,6 @@ from ..utils import ExtractorError, make_archive_id, url_basename
class CellebriteIE(VidyardBaseIE):
_VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/',
'info_dict': {
'id': 'ZqmUss3dQfEMGpauambPuH',
'display_id': '16025876',
'ext': 'mp4',
'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
'description': 'md5:dee48fe12bbae5c01fe6a053f7676da4',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
'duration': 455.979,
'_old_archive_ids': ['cellebrite 16025876'],
},
}, {
'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
'info_dict': {
'id': 'QV1U8a2yzcxigw7VFnqKyg',
plugins/youtube_download/yt_dlp/extractor/charlierose.py
+5 -1
View File
@@ -6,7 +6,7 @@ class CharlieRoseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?charlierose\.com/(?:video|episode)(?:s|/player)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://charlierose.com/videos/27996',
'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
'md5': '4405b662f557f94aa256fa6a7baf7426',
'info_dict': {
'id': '27996',
'ext': 'mp4',
@@ -39,12 +39,16 @@ class CharlieRoseIE(InfoExtractor):
self._PLAYER_BASE % video_id, webpage, video_id,
m3u8_entry_protocol='m3u8_native')[0]
self._remove_duplicate_formats(info_dict['formats'])
for fmt in info_dict['formats']:
if fmt.get('protocol') == 'm3u8_native':
fmt['__needs_testing'] = True
info_dict.update({
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'_format_sort_fields': ('proto',),
})
return info_dict
plugins/youtube_download/yt_dlp/extractor/cloudflarestream.py
+14 -6
View File
@@ -19,18 +19,16 @@ class CloudflareStreamIE(InfoExtractor):
'id': '31c9291ab41fac05471db4e73aa11717',
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
},
'params': {
'skip_download': 'm3u8',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://watch.cloudflarestream.com/embed/sdk-iframe-integration.fla9.latest.js?video=0e8e040aec776862e1d632a699edf59e',
'info_dict': {
'id': '0e8e040aec776862e1d632a699edf59e',
'ext': 'mp4',
'title': '0e8e040aec776862e1d632a699edf59e',
'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
}, {
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@@ -54,11 +52,21 @@ class CloudflareStreamIE(InfoExtractor):
'id': 'eaef9dea5159cf968be84241b5cedfe7',
'ext': 'mp4',
'title': 'eaef9dea5159cf968be84241b5cedfe7',
'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
'params': {
'extractor_args': {'generic': {'impersonate': ['chrome']}},
'skip_download': 'm3u8',
},
}, {
# FIXME: Embed detection
'url': 'https://www.cloudflare.com/developer-platform/products/cloudflare-stream/',
'info_dict': {
'id': 'e7bd2dd67e0f8860b4ae81e33a966049',
'ext': 'mp4',
'title': 'e7bd2dd67e0f8860b4ae81e33a966049',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
}]
def _real_extract(self, url):
plugins/youtube_download/yt_dlp/extractor/cloudycdn.py
+19 -7
View File
@@ -11,7 +11,7 @@ from ..utils.traversal import traverse_obj
class CloudyCDNIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//embed\.cloudycdn\.services/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_VALID_URL = r'(?:https?:)?//embed\.(?P<domain>cloudycdn\.services|backscreen\.com)/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://embed.cloudycdn.services/ltv/media/46k_d23-6000-105?',
@@ -23,7 +23,7 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1442,
'upload_date': '20231121',
'title': 'D23-6000-105_cetstud',
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
},
}, {
'url': 'https://embed.cloudycdn.services/izm/media/26e_lv-8-5-1',
@@ -33,7 +33,7 @@ class CloudyCDNIE(InfoExtractor):
'ext': 'mp4',
'title': 'LV-8-5-1',
'timestamp': 1669767167,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'duration': 1205,
'upload_date': '20221130',
},
@@ -48,9 +48,21 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1673,
'title': 'D24-6000-074-cetstud',
'timestamp': 1718902233,
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
},
'params': {'format': 'bv'},
}, {
'url': 'https://embed.backscreen.com/ltv/media/32j_z25-0600-127?',
'md5': '9b6fa09ac1a4de53d4f42b94affc3b42',
'info_dict': {
'id': '32j_z25-0600-127',
'ext': 'mp4',
'title': 'Z25-0600-127-DZ',
'duration': 1906,
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/977427/placeholder1746633646.jpg',
'timestamp': 1746632402,
'upload_date': '20250507',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.tavaklase.lv/video/es-esmu-mina-um-2/',
@@ -60,17 +72,17 @@ class CloudyCDNIE(InfoExtractor):
'ext': 'mp4',
'upload_date': '20230223',
'duration': 629,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'timestamp': 1677181513,
'title': 'LIB-2',
},
}]
def _real_extract(self, url):
site_id, video_id = self._match_valid_url(url).group('site_id', 'id')
domain, site_id, video_id = self._match_valid_url(url).group('domain', 'site_id', 'id')
data = self._download_json(
f'https://player.cloudycdn.services/player/{site_id}/media/{video_id}/',
f'https://player.{domain}/player/{site_id}/media/{video_id}/',
video_id, data=urlencode_postdata({
'version': '6.4.0',
'referer': url,
plugins/youtube_download/yt_dlp/extractor/cmt.py
-55
View File
@@ -1,55 +0,0 @@
from .mtv import MTVIE
# TODO: Remove - Reason: Outdated Site
class CMTIE(MTVIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_NAME = 'cmt.com'
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|(?:full-)?episodes|video-clips)/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
'md5': 'e6b7ef3c4c45bbfae88061799bbba6c2',
'info_dict': {
'id': '989124',
'ext': 'mp4',
'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
'description': 'Blame It All On My Roots',
},
'skip': 'Video not available',
}, {
'url': 'http://www.cmt.com/videos/misc/1504699/still-the-king-ep-109-in-3-minutes.jhtml#id=1739908',
'md5': 'e61a801ca4a183a466c08bd98dccbb1c',
'info_dict': {
'id': '1504699',
'ext': 'mp4',
'title': 'Still The King Ep. 109 in 3 Minutes',
'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9.',
'timestamp': 1469421000.0,
'upload_date': '20160725',
},
}, {
'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
'only_matching': True,
}, {
'url': 'http://www.cmt.com/full-episodes/537qb3/nashville-the-wayfaring-stranger-season-5-ep-501',
'only_matching': True,
}, {
'url': 'http://www.cmt.com/video-clips/t9e4ci/nashville-juliette-in-2-minutes',
'only_matching': True,
}]
def _extract_mgid(self, webpage, url):
mgid = self._search_regex(
r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
webpage, 'mgid', group='mgid', default=None)
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
return mgid
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mgid = self._extract_mgid(webpage, url)
return self.url_result(f'http://media.mtvnservices.com/embed/{mgid}')
plugins/youtube_download/yt_dlp/extractor/cnn.py
+1
View File
@@ -272,6 +272,7 @@ class CNNIndonesiaIE(InfoExtractor):
return merge_dicts(json_ld_data, {
'_type': 'url_transparent',
'url': embed_url,
'id': video_id,
'upload_date': upload_date,
'tags': try_call(lambda: self._html_search_meta('keywords', webpage).split(', ')),
})
plugins/youtube_download/yt_dlp/extractor/comedycentral.py
+20 -48
View File
@@ -1,55 +1,27 @@
from .mtv import MTVServicesInfoExtractor
from .mtv import MTVServicesBaseIE
class ComedyCentralIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?|collection-playlist|movies)/(?P<id>[0-9a-z]{6})'
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
class ComedyCentralIE(MTVServicesBaseIE):
_VALID_URL = r'https?://(?:www\.)?cc\.com/video-clips/(?P<id>[\da-z]{6})'
_TESTS = [{
'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
'md5': 'b8acb347177c680ff18a292aa2166f80',
'url': 'https://www.cc.com/video-clips/wl12cx',
'info_dict': {
'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
'id': 'dec6953e-80c8-43b3-96cd-05e9230e704d',
'ext': 'mp4',
'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
'timestamp': 1598670000,
'upload_date': '20200829',
'display_id': 'wl12cx',
'title': 'Alison Brie and Dave Franco -"Together"- Extended Interview',
'description': 'md5:ec68e38d3282f863de9cde0ce5cd231c',
'duration': 516.76,
'thumbnail': r're:https://images\.paramount\.tech/uri/mgid:arc:imageassetref:',
'series': 'The Daily Show',
'season': 'Season 30',
'season_number': 30,
'episode': 'Episode 0',
'episode_number': 0,
'timestamp': 1753973314,
'upload_date': '20250731',
'release_timestamp': 1753977914,
'release_date': '20250731',
},
}, {
'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
'only_matching': True,
}, {
'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
'only_matching': True,
}, {
'url': 'https://www.cc.com/collection-playlist/cosnej/stand-up-specials/t6vtjb',
'only_matching': True,
}, {
'url': 'https://www.cc.com/movies/tkp406/a-cluesterfuenke-christmas',
'only_matching': True,
'params': {'skip_download': 'm3u8'},
}]
class ComedyCentralTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
_TESTS = [{
'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
'info_dict': {
'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
'ext': 'mp4',
'title': 'Josh Investigates',
'description': 'Steht uns das Ende der Welt bevor?',
},
}]
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
_GEO_COUNTRIES = ['DE']
def _get_feed_query(self, uri):
return {
'accountOverride': 'intl.mtvi.com',
'arcEp': 'web.cc.tv',
'ep': 'b9032c3a',
'imageEp': 'web.cc.tv',
'mgid': uri,
}
plugins/youtube_download/yt_dlp/extractor/common.py
+169 -43
View File
@@ -1,5 +1,6 @@
import base64
import collections
import contextlib
import functools
import getpass
import http.client
@@ -37,7 +38,6 @@ from ..networking.exceptions import (
TransportError,
network_exceptions,
)
from ..networking.impersonate import ImpersonateTarget
from ..utils import (
IDENTITY,
JSON_LD_RE,
@@ -101,6 +101,7 @@ from ..utils import (
xpath_with_ns,
)
from ..utils._utils import _request_dump_filename
from ..utils.jslib import devalue
class InfoExtractor:
@@ -242,7 +243,7 @@ class InfoExtractor:
* extra_param_to_segment_url A query string to append to each
fragment's URL, or to update each existing query string
with. If it is an HLS stream with an AES-128 decryption key,
the query paramaters will be passed to the key URI as well,
the query parameters will be passed to the key URI as well,
unless there is an `extra_param_to_key_url` given,
or unless an external key URI is provided via `hls_aes`.
Only applied by the native HLS/DASH downloaders.
@@ -257,11 +258,20 @@ class InfoExtractor:
* key The key (as hex) used to decrypt fragments.
If `key` is given, any key URI will be ignored
* iv The IV (as hex) used to decrypt fragments
* impersonate Impersonate target(s). Can be any of the following entities:
* an instance of yt_dlp.networking.impersonate.ImpersonateTarget
* a string in the format of CLIENT[:OS]
* a list or a tuple of CLIENT[:OS] strings or ImpersonateTarget instances
* a boolean value; True means any impersonate target is sufficient
* available_at Unix timestamp of when a format will be available to download
* downloader_options A dictionary of downloader options
(For internal use only)
* http_chunk_size Chunk size for HTTP downloads
* ffmpeg_args Extra arguments for ffmpeg downloader (input)
* ffmpeg_args_out Extra arguments for ffmpeg downloader (output)
* ws (NiconicoLiveFD only) WebSocketResponse
* ws_url (NiconicoLiveFD only) Websockets URL
* max_quality (NiconicoLiveFD only) Max stream quality string
* is_dash_periods Whether the format is a result of merging
multiple DASH periods.
RTMP formats can also have the additional fields: page_url,
@@ -331,6 +341,7 @@ class InfoExtractor:
* "name": Name or description of the subtitles
* "http_headers": A dictionary of additional HTTP headers
to add to the request.
* "impersonate": Impersonate target(s); same as the "formats" field
"ext" will be calculated from URL if missing
automatic_captions: Like 'subtitles'; contains automatically generated
captions instead of normal subtitles
@@ -387,6 +398,8 @@ class InfoExtractor:
chapters: A list of dictionaries, with the following entries:
* "start_time" - The start time of the chapter in seconds
* "end_time" - The end time of the chapter in seconds
(optional: core code can determine this value from
the next chapter's start_time or the video's duration)
* "title" (optional, string)
heatmap: A list of dictionaries, with the following entries:
* "start_time" - The start time of the data point in seconds
@@ -401,12 +414,13 @@ class InfoExtractor:
'unlisted' or 'public'. Use 'InfoExtractor._availability'
to set it
media_type: The type of media as classified by the site, e.g. "episode", "clip", "trailer"
_old_archive_ids: A list of old archive ids needed for backward compatibility
_old_archive_ids: A list of old archive ids needed for backward
compatibility. Use yt_dlp.utils.make_archive_id to generate ids
_format_sort_fields: A list of fields to use for sorting formats
__post_extractor: A function to be called just before the metadata is
written to either disk, logger or console. The function
must return a dict which will be added to the info_dict.
This is usefull for additional information that is
This is useful for additional information that is
time-consuming to extract. Note that the fields thus
extracted will not be available to output template and
match_filter. So, only "comments" and "comment_count" are
@@ -879,26 +893,17 @@ class InfoExtractor:
extensions = {}
if impersonate in (True, ''):
impersonate = ImpersonateTarget()
requested_targets = [
t if isinstance(t, ImpersonateTarget) else ImpersonateTarget.from_str(t)
for t in variadic(impersonate)
] if impersonate else []
available_target = next(filter(self._downloader._impersonate_target_available, requested_targets), None)
available_target, requested_targets = self._downloader._parse_impersonate_targets(impersonate)
if available_target:
extensions['impersonate'] = available_target
elif requested_targets:
message = 'The extractor is attempting impersonation, but '
message += (
'no impersonate target is available' if not str(impersonate)
else f'none of these impersonate targets are available: "{", ".join(map(str, requested_targets))}"')
info_msg = ('see https://github.com/yt-dlp/yt-dlp#impersonation '
'for information on installing the required dependencies')
msg = 'The extractor is attempting impersonation'
if require_impersonation:
raise ExtractorError(f'{message}; {info_msg}', expected=True)
self.report_warning(f'{message}; if you encounter errors, then {info_msg}', only_once=True)
raise ExtractorError(
self._downloader._unavailable_targets_message(requested_targets, note=msg, is_error=True),
expected=True)
self.report_warning(
self._downloader._unavailable_targets_message(requested_targets, note=msg), only_once=True)
try:
return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query, extensions))
@@ -1523,11 +1528,11 @@ class InfoExtractor:
r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
]
age_limit = 0
age_limit = None
for marker in AGE_LIMIT_MARKERS:
mobj = re.search(marker, html)
if mobj:
age_limit = max(age_limit, int(traverse_obj(mobj, 1, default=18)))
age_limit = max(age_limit or 0, int(traverse_obj(mobj, 1, default=18)))
return age_limit
def _media_rating_search(self, html):
@@ -1658,7 +1663,7 @@ class InfoExtractor:
'end_time': part.get('endOffset'),
} for part in variadic(e.get('hasPart') or []) if part.get('@type') == 'Clip']
for idx, (last_c, current_c, next_c) in enumerate(zip(
[{'end_time': 0}, *chapters], chapters, chapters[1:])):
[{'end_time': 0}, *chapters], chapters, chapters[1:], strict=False)):
current_c['end_time'] = current_c['end_time'] or next_c['start_time']
current_c['start_time'] = current_c['start_time'] or last_c['end_time']
if None in current_c.values():
@@ -1675,9 +1680,9 @@ class InfoExtractor:
'ext': mimetype2ext(e.get('encodingFormat')),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnails': [{'url': unescapeHTML(url)}
for url in variadic(traverse_obj(e, 'thumbnailUrl', 'thumbnailURL'))
if url_or_none(url)],
'thumbnails': traverse_obj(e, (('thumbnailUrl', 'thumbnailURL', 'thumbnail_url'), (None, ...), {
'url': ({str}, {unescapeHTML}, {self._proto_relative_url}, {url_or_none}),
})),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
# author can be an instance of 'Organization' or 'Person' types.
@@ -1778,6 +1783,59 @@ class InfoExtractor:
r'<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>', webpage, 'next.js data',
video_id, end_pattern='</script>', fatal=fatal, default=default, **kw)
def _search_nextjs_v13_data(self, webpage, video_id, fatal=True):
"""Parses Next.js app router flight data that was introduced in Next.js v13"""
nextjs_data = {}
if not fatal and not isinstance(webpage, str):
return nextjs_data
def flatten(flight_data):
if not isinstance(flight_data, list):
return
if len(flight_data) == 4 and flight_data[0] == '$':
_, name, _, data = flight_data
if not isinstance(data, dict):
return
children = data.pop('children', None)
if data and isinstance(name, str) and re.fullmatch(r'\$L[0-9a-f]+', name):
# It is useful hydration JSON data
nextjs_data[name[2:]] = data
flatten(children)
return
for f in flight_data:
flatten(f)
flight_text = ''
# The pattern for the surrounding JS/tag should be strict as it's a hardcoded string in the next.js source
# Ref: https://github.com/vercel/next.js/blob/5a4a08fdc/packages/next/src/server/app-render/use-flight-response.tsx#L189
for flight_segment in re.findall(r'<script\b[^>]*>self\.__next_f\.push\((\[.+?\])\)</script>', webpage):
segment = self._parse_json(flight_segment, video_id, fatal=fatal, errnote=None if fatal else False)
# Some earlier versions of next.js "optimized" away this array structure; this is unsupported
# Ref: https://github.com/vercel/next.js/commit/0123a9d5c9a9a77a86f135b7ae30b46ca986d761
if not isinstance(segment, list) or len(segment) != 2:
self.write_debug(
f'{video_id}: Unsupported next.js flight data structure detected', only_once=True)
continue
# Only use the relevant payload type (1 == data)
# Ref: https://github.com/vercel/next.js/blob/5a4a08fdc/packages/next/src/server/app-render/use-flight-response.tsx#L11-L14
payload_type, chunk = segment
if payload_type == 1:
flight_text += chunk
for f in flight_text.splitlines():
prefix, _, body = f.lstrip().partition(':')
if not re.fullmatch(r'[0-9a-f]+', prefix):
continue
# The body still isn't guaranteed to be valid JSON, so parsing should always be non-fatal
if body.startswith('[') and body.endswith(']'):
flatten(self._parse_json(body, video_id, fatal=False, errnote=False))
elif body.startswith('{') and body.endswith('}'):
data = self._parse_json(body, video_id, fatal=False, errnote=False)
if data is not None:
nextjs_data[prefix] = data
return nextjs_data
def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal=True, traverse=('data', 0)):
"""Parses Nuxt.js metadata. This works as long as the function __NUXT__ invokes is a pure function"""
rectx = re.escape(context_name)
@@ -1790,11 +1848,68 @@ class InfoExtractor:
return {}
args = dict(zip(arg_keys.split(','), map(json.dumps, self._parse_json(
f'[{arg_vals}]', video_id, transform_source=js_to_json, fatal=fatal) or ())))
f'[{arg_vals}]', video_id, transform_source=js_to_json, fatal=fatal) or ()), strict=True))
ret = self._parse_json(js, video_id, transform_source=functools.partial(js_to_json, vars=args), fatal=fatal)
return traverse_obj(ret, traverse) or {}
def _resolve_nuxt_array(self, array, video_id, *, fatal=True, default=NO_DEFAULT):
"""Resolves Nuxt rich JSON payload arrays"""
# Ref: https://github.com/nuxt/nuxt/commit/9e503be0f2a24f4df72a3ccab2db4d3e63511f57
# https://github.com/nuxt/nuxt/pull/19205
if default is not NO_DEFAULT:
fatal = False
if not isinstance(array, list) or not array:
error_msg = 'Unable to resolve Nuxt JSON data: invalid input'
if fatal:
raise ExtractorError(error_msg, video_id=video_id)
elif default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id)
return {} if default is NO_DEFAULT else default
def indirect_reviver(data):
return data
def json_reviver(data):
return json.loads(data)
gen = devalue.parse_iter(array, revivers={
'NuxtError': indirect_reviver,
'EmptyShallowRef': json_reviver,
'EmptyRef': json_reviver,
'ShallowRef': indirect_reviver,
'ShallowReactive': indirect_reviver,
'Ref': indirect_reviver,
'Reactive': indirect_reviver,
})
while True:
try:
error_msg = f'Error resolving Nuxt JSON: {gen.send(None)}'
if fatal:
raise ExtractorError(error_msg, video_id=video_id)
elif default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id, only_once=True)
else:
self.write_debug(f'{video_id}: {error_msg}', only_once=True)
except StopIteration as error:
return error.value or ({} if default is NO_DEFAULT else default)
def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT):
"""Parses metadata from Nuxt rich JSON payloads embedded in HTML"""
passed_default = default is not NO_DEFAULT
array = self._search_json(
r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage,
'Nuxt JSON data', video_id, contains_pattern=r'\[(?s:.+)\]',
fatal=fatal, default=NO_DEFAULT if not passed_default else None)
if not array:
return default if passed_default else {}
return self._resolve_nuxt_array(array, video_id, fatal=fatal, default=default)
@staticmethod
def _hidden_inputs(html):
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
@@ -2068,21 +2183,33 @@ class InfoExtractor:
raise ExtractorError(errnote, video_id=video_id)
self.report_warning(f'{errnote}{bug_reports_message()}')
return [], {}
res = self._download_webpage_handle(
m3u8_url, video_id,
note='Downloading m3u8 information' if note is None else note,
errnote='Failed to download m3u8 information' if errnote is None else errnote,
if note is None:
note = 'Downloading m3u8 information'
if errnote is None:
errnote = 'Failed to download m3u8 information'
response = self._request_webpage(
m3u8_url, video_id, note=note, errnote=errnote,
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
if response is False:
return [], {}
m3u8_doc, urlh = res
m3u8_url = urlh.url
with contextlib.closing(response):
prefix = response.read(512)
if not prefix.startswith(b'#EXTM3U'):
msg = 'Response data has no m3u header'
if fatal:
raise ExtractorError(msg, video_id=video_id)
self.report_warning(f'{msg}{bug_reports_message()}', video_id=video_id)
return [], {}
content = self._webpage_read_content(
response, m3u8_url, video_id, note=note, errnote=errnote,
fatal=fatal, prefix=prefix, data=data)
if content is False:
return [], {}
return self._parse_m3u8_formats_and_subtitles(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
content, response.url, ext=ext, entry_protocol=entry_protocol,
preference=preference, quality=quality, m3u8_id=m3u8_id,
note=note, errnote=errnote, fatal=fatal, live=live, data=data,
headers=headers, query=query, video_id=video_id)
@@ -2842,7 +2969,7 @@ class InfoExtractor:
else:
codecs = parse_codecs(codec_str)
if content_type not in ('video', 'audio', 'text'):
if mime_type == 'image/jpeg':
if mime_type in ('image/avif', 'image/jpeg'):
content_type = mime_type
elif codecs.get('vcodec', 'none') != 'none':
content_type = 'video'
@@ -2902,14 +3029,14 @@ class InfoExtractor:
'manifest_url': mpd_url,
'filesize': filesize,
}
elif content_type == 'image/jpeg':
elif content_type in ('image/avif', 'image/jpeg'):
# See test case in VikiIE
# https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1
f = {
'format_id': format_id,
'ext': 'mhtml',
'manifest_url': mpd_url,
'format_note': 'DASH storyboards (jpeg)',
'format_note': f'DASH storyboards ({mimetype2ext(mime_type)})',
'acodec': 'none',
'vcodec': 'none',
}
@@ -2981,7 +3108,6 @@ class InfoExtractor:
else:
# $Number*$ or $Time$ in media template with S list available
# Example $Number*$: http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg
# Example $Time$: https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411
representation_ms_info['fragments'] = []
segment_time = 0
segment_d = None
@@ -3051,7 +3177,7 @@ class InfoExtractor:
'url': mpd_url or base_url,
'fragment_base_url': base_url,
'fragments': [],
'protocol': 'http_dash_segments' if mime_type != 'image/jpeg' else 'mhtml',
'protocol': 'mhtml' if mime_type in ('image/avif', 'image/jpeg') else 'http_dash_segments',
})
if 'initialization_url' in representation_ms_info:
initialization_url = representation_ms_info['initialization_url']
@@ -3066,7 +3192,7 @@ class InfoExtractor:
else:
# Assuming direct URL to unfragmented media.
f['url'] = base_url
if content_type in ('video', 'audio', 'image/jpeg'):
if content_type in ('video', 'audio', 'image/avif', 'image/jpeg'):
f['manifest_stream_number'] = stream_numbers[f['url']]
stream_numbers[f['url']] += 1
period_entry['formats'].append(f)
plugins/youtube_download/yt_dlp/extractor/condenast.py
+18
View File
@@ -96,6 +96,24 @@ class CondeNastIE(InfoExtractor):
'upload_date': '20150916',
'timestamp': 1442434920,
},
}, {
# FIXME: Subtitles
'url': 'https://www.vanityfair.com/video/watch/vf-quiz-show-squid-game-s3',
'info_dict': {
'id': '6862f999c1afbc5ff06b4803',
'ext': 'mp4',
'title': '\'Squid Game\' Cast Tests How Well They Know Each Other',
'categories': ['Arts & Culture', 'Hollywood'],
'description': 'md5:7a9c668a1fc87648e77da13842ec1534',
'duration': 955,
'season': 'Season 1',
'series': 'Quizzing Each Other',
'tags': 'count:2',
'thumbnail': r're:https?://dwgyu36up6iuz\.cloudfront\.net/.+\.jpg',
'timestamp': 1751341306,
'upload_date': '20250701',
'uploader': 'vanityfair',
},
}, {
'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player',
'only_matching': True,
plugins/youtube_download/yt_dlp/extractor/crackle.py
-243
View File
@@ -1,243 +0,0 @@
import hashlib
import hmac
import re
import time
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
float_or_none,
int_or_none,
orderedSet,
parse_age_limit,
parse_duration,
url_or_none,
)
class CrackleIE(InfoExtractor):
_VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?(?:sony)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
_TESTS = [{
# Crackle is available in the United States and territories
'url': 'https://www.crackle.com/thanksgiving/2510064',
'info_dict': {
'id': '2510064',
'ext': 'mp4',
'title': 'Touch Football',
'description': 'md5:cfbb513cf5de41e8b56d7ab756cff4df',
'duration': 1398,
'view_count': int,
'average_rating': 0,
'age_limit': 17,
'genre': 'Comedy',
'creator': 'Daniel Powell',
'artist': 'Chris Elliott, Amy Sedaris',
'release_year': 2016,
'series': 'Thanksgiving',
'episode': 'Touch Football',
'season_number': 1,
'episode_number': 1,
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': [
'Trying with a list of known countries',
],
}, {
'url': 'https://www.sonycrackle.com/thanksgiving/2510064',
'only_matching': True,
}]
_MEDIA_FILE_SLOTS = {
'360p.mp4': {
'width': 640,
'height': 360,
},
'480p.mp4': {
'width': 768,
'height': 432,
},
'480p_1mbps.mp4': {
'width': 852,
'height': 480,
},
}
def _download_json(self, url, *args, **kwargs):
# Authorization generation algorithm is reverse engineered from:
# https://www.sonycrackle.com/static/js/main.ea93451f.chunk.js
timestamp = time.strftime('%Y%m%d%H%M', time.gmtime())
h = hmac.new(b'IGSLUQCBDFHEOIFM', '|'.join([url, timestamp]).encode(), hashlib.sha1).hexdigest().upper()
headers = {
'Accept': 'application/json',
'Authorization': '|'.join([h, timestamp, '117', '1']),
}
return InfoExtractor._download_json(self, url, *args, headers=headers, **kwargs)
def _real_extract(self, url):
video_id = self._match_id(url)
geo_bypass_country = self.get_param('geo_bypass_country', None)
countries = orderedSet((geo_bypass_country, 'US', 'AU', 'CA', 'AS', 'FM', 'GU', 'MP', 'PR', 'PW', 'MH', 'VI', ''))
num_countries, num = len(countries) - 1, 0
media = {}
for num, country in enumerate(countries):
if num == 1: # start hard-coded list
self.report_warning('%s. Trying with a list of known countries' % (
f'Unable to obtain video formats from {geo_bypass_country} API' if geo_bypass_country
else 'No country code was given using --geo-bypass-country'))
elif num == num_countries: # end of list
geo_info = self._download_json(
'https://web-api-us.crackle.com/Service.svc/geo/country',
video_id, fatal=False, note='Downloading geo-location information from crackle API',
errnote='Unable to fetch geo-location information from crackle') or {}
country = geo_info.get('CountryCode')
if country is None:
continue
self.to_screen(f'{self.IE_NAME} identified country as {country}')
if country in countries:
self.to_screen(f'Downloading from {country} API was already attempted. Skipping...')
continue
if country is None:
continue
try:
media = self._download_json(
f'https://web-api-us.crackle.com/Service.svc/details/media/{video_id}/{country}?disableProtocols=true',
video_id, note=f'Downloading media JSON from {country} API',
errnote='Unable to download media JSON')
except ExtractorError as e:
# 401 means geo restriction, trying next country
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
continue
raise
status = media.get('status')
if status.get('messageCode') != '0':
raise ExtractorError(
'{} said: {} {} - {}'.format(
self.IE_NAME, status.get('messageCodeDescription'), status.get('messageCode'), status.get('message')),
expected=True)
# Found video formats
if isinstance(media.get('MediaURLs'), list):
break
ignore_no_formats = self.get_param('ignore_no_formats_error')
if not media or (not media.get('MediaURLs') and not ignore_no_formats):
raise ExtractorError(
'Unable to access the crackle API. Try passing your country code '
'to --geo-bypass-country. If it still does not work and the '
'video is available in your country')
title = media['Title']
formats, subtitles = [], {}
has_drm = False
for e in media.get('MediaURLs') or []:
if e.get('UseDRM'):
has_drm = True
format_url = url_or_none(e.get('DRMPath'))
else:
format_url = url_or_none(e.get('Path'))
if not format_url:
continue
ext = determine_ext(format_url)
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
elif ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(
format_url, video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
elif format_url.endswith('.ism/Manifest'):
fmts, subs = self._extract_ism_formats_and_subtitles(
format_url, video_id, ism_id='mss', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
else:
mfs_path = e.get('Type')
mfs_info = self._MEDIA_FILE_SLOTS.get(mfs_path)
if not mfs_info:
continue
formats.append({
'url': format_url,
'format_id': 'http-' + mfs_path.split('.')[0],
'width': mfs_info['width'],
'height': mfs_info['height'],
})
if not formats and has_drm:
self.report_drm(video_id)
description = media.get('Description')
duration = int_or_none(media.get(
'DurationInSeconds')) or parse_duration(media.get('Duration'))
view_count = int_or_none(media.get('CountViews'))
average_rating = float_or_none(media.get('UserRating'))
age_limit = parse_age_limit(media.get('Rating'))
genre = media.get('Genre')
release_year = int_or_none(media.get('ReleaseYear'))
creator = media.get('Directors')
artist = media.get('Cast')
if media.get('MediaTypeDisplayValue') == 'Full Episode':
series = media.get('ShowName')
episode = title
season_number = int_or_none(media.get('Season'))
episode_number = int_or_none(media.get('Episode'))
else:
series = episode = season_number = episode_number = None
cc_files = media.get('ClosedCaptionFiles')
if isinstance(cc_files, list):
for cc_file in cc_files:
if not isinstance(cc_file, dict):
continue
cc_url = url_or_none(cc_file.get('Path'))
if not cc_url:
continue
lang = cc_file.get('Locale') or 'en'
subtitles.setdefault(lang, []).append({'url': cc_url})
thumbnails = []
images = media.get('Images')
if isinstance(images, list):
for image_key, image_url in images.items():
mobj = re.search(r'Img_(\d+)[xX](\d+)', image_key)
if not mobj:
continue
thumbnails.append({
'url': image_url,
'width': int(mobj.group(1)),
'height': int(mobj.group(2)),
})
return {
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'view_count': view_count,
'average_rating': average_rating,
'age_limit': age_limit,
'genre': genre,
'creator': creator,
'artist': artist,
'release_year': release_year,
'series': series,
'episode': episode,
'season_number': season_number,
'episode_number': episode_number,
'thumbnails': thumbnails,
'subtitles': subtitles,
'formats': formats,
}
plugins/youtube_download/yt_dlp/extractor/crooksandliars.py
+15 -2
View File
@@ -8,7 +8,6 @@ from ..utils import (
class CrooksAndLiarsIE(InfoExtractor):
_VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
_EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
_TESTS = [{
'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
'info_dict': {
@@ -16,7 +15,7 @@ class CrooksAndLiarsIE(InfoExtractor):
'ext': 'mp4',
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:https?://crooksandliars\.com/files/.+',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
@@ -26,6 +25,20 @@ class CrooksAndLiarsIE(InfoExtractor):
'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'duration': 236,
'thumbnail': r're:https?://crooksandliars\.com/files/.+',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
plugins/youtube_download/yt_dlp/extractor/ctv.py
-49
View File
@@ -1,49 +0,0 @@
from .common import InfoExtractor
class CTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ctv\.ca/(?P<id>(?:show|movie)s/[^/]+/[^/?#&]+)'
_TESTS = [{
'url': 'https://www.ctv.ca/shows/your-morning/wednesday-december-23-2020-s5e88',
'info_dict': {
'id': '2102249',
'ext': 'flv',
'title': 'Wednesday, December 23, 2020',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'Your Morning delivers original perspectives and unique insights into the headlines of the day.',
'timestamp': 1608732000,
'upload_date': '20201223',
'series': 'Your Morning',
'season': '2020-2021',
'season_number': 5,
'episode_number': 88,
'tags': ['Your Morning'],
'categories': ['Talk Show'],
'duration': 7467.126,
},
}, {
'url': 'https://www.ctv.ca/movies/adam-sandlers-eight-crazy-nights/adam-sandlers-eight-crazy-nights',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
content = self._download_json(
'https://www.ctv.ca/space-graphql/graphql', display_id, query={
'query': '''{
resolvedPath(path: "/%s") {
lastSegment {
content {
... on AxisContent {
axisId
videoPlayerDestCode
}
}
}
}
}''' % display_id, # noqa: UP031
})['data']['resolvedPath']['lastSegment']['content']
video_id = content['axisId']
return self.url_result(
'9c9media:{}:{}'.format(content['videoPlayerDestCode'], video_id),
'NineCNineMedia', video_id)
plugins/youtube_download/yt_dlp/extractor/cwtv.py
-180
View File
@@ -1,180 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
parse_iso8601,
parse_qs,
smuggle_url,
str_or_none,
update_url_query,
)
from ..utils.traversal import traverse_obj
class CWTVIE(InfoExtractor):
IE_NAME = 'cwtv'
_VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch|guid)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
_TESTS = [{
'url': 'https://www.cwtv.com/shows/continuum/a-stitch-in-time/?play=9149a1e1-4cb2-46d7-81b2-47d35bbd332b',
'info_dict': {
'id': '9149a1e1-4cb2-46d7-81b2-47d35bbd332b',
'ext': 'mp4',
'title': 'A Stitch in Time',
'description': r're:(?s)City Protective Services officer Kiera Cameron is transported from 2077.+',
'thumbnail': r're:https?://.+\.jpe?g',
'duration': 2632,
'timestamp': 1736928000,
'uploader': 'CWTV',
'chapters': 'count:5',
'series': 'Continuum',
'season_number': 1,
'episode_number': 1,
'age_limit': 14,
'upload_date': '20250115',
'season': 'Season 1',
'episode': 'Episode 1',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
'info_dict': {
'id': '6b15e985-9345-4f60-baf8-56e96be57c63',
'ext': 'mp4',
'title': 'Legends of Yesterday',
'description': r're:(?s)Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote.+',
'duration': 2665,
'series': 'Arrow',
'season_number': 4,
'season': '4',
'episode_number': 8,
'upload_date': '20151203',
'timestamp': 1449122100,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'redirect to http://cwtv.com/shows/arrow/',
}, {
'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
'info_dict': {
'id': '24282b12-ead2-42f2-95ad-26770c2c6088',
'ext': 'mp4',
'title': 'Jeff Davis 4',
'description': 'Jeff Davis is back to make you laugh.',
'duration': 1263,
'series': 'Whose Line Is It Anyway?',
'season_number': 11,
'episode_number': 20,
'upload_date': '20151006',
'timestamp': 1444107300,
'age_limit': 14,
'uploader': 'CWTV',
'thumbnail': r're:https?://.+\.jpe?g',
'chapters': 'count:4',
'episode': 'Episode 20',
'season': 'Season 11',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
'only_matching': True,
}, {
'url': 'http://cwtvpr.com/the-cw/video?watch=9eee3f60-ef4e-440b-b3b2-49428ac9c54e',
'only_matching': True,
}, {
'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63',
'only_matching': True,
}, {
'url': 'http://www.cwtv.com/movies/play/?guid=0a8e8b5b-1356-41d5-9a6a-4eda1a6feb6c',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
f'https://images.cwtv.com/feed/app-2/video-meta/apiversion_22/device_android/guid_{video_id}', video_id)
if traverse_obj(data, 'result') != 'ok':
raise ExtractorError(traverse_obj(data, (('error_msg', 'msg'), {str}, any)), expected=True)
video_data = data['video']
title = video_data['title']
mpx_url = update_url_query(
video_data.get('mpx_url') or f'https://link.theplatform.com/s/cwtv/media/guid/2703454149/{video_id}',
{'formats': 'M3U+none'})
season = str_or_none(video_data.get('season'))
episode = str_or_none(video_data.get('episode'))
if episode and season:
episode = episode[len(season):]
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'url': smuggle_url(mpx_url, {'force_smil_url': True}),
'description': video_data.get('description_long'),
'duration': int_or_none(video_data.get('duration_secs')),
'series': video_data.get('series_name'),
'season_number': int_or_none(season),
'episode_number': int_or_none(episode),
'timestamp': parse_iso8601(video_data.get('start_time')),
'age_limit': parse_age_limit(video_data.get('rating')),
'ie_key': 'ThePlatform',
'thumbnail': video_data.get('large_thumbnail'),
}
class CWTVMovieIE(InfoExtractor):
IE_NAME = 'cwtv:movie'
_VALID_URL = r'https?://(?:www\.)?cwtv\.com/shows/(?P<id>[\w-]+)/?\?(?:[^#]+&)?viewContext=Movies'
_TESTS = [{
'url': 'https://www.cwtv.com/shows/the-crush/?viewContext=Movies+Swimlane',
'info_dict': {
'id': '0a8e8b5b-1356-41d5-9a6a-4eda1a6feb6c',
'ext': 'mp4',
'title': 'The Crush',
'upload_date': '20241112',
'description': 'md5:1549acd90dff4a8273acd7284458363e',
'chapters': 'count:9',
'timestamp': 1731398400,
'age_limit': 16,
'duration': 5337,
'series': 'The Crush',
'season': 'Season 1',
'uploader': 'CWTV',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
'thumbnail': r're:https?://.+\.jpe?g',
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
_UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
app_url = (
self._html_search_meta('al:ios:url', webpage, default=None)
or self._html_search_meta('al:android:url', webpage, default=None))
video_id = (
traverse_obj(parse_qs(app_url), ('video_id', 0, {lambda x: re.fullmatch(self._UUID_RE, x)}, 0))
or self._search_regex([
rf'CWTV\.Site\.curPlayingGUID\s*=\s*["\']({self._UUID_RE})',
rf'CWTV\.Site\.viewInAppURL\s*=\s*["\']/shows/[\w-]+/watch-in-app/\?play=({self._UUID_RE})',
], webpage, 'video ID'))
return self.url_result(
f'https://www.cwtv.com/shows/{display_id}/{display_id}/?play={video_id}', CWTVIE, video_id)
plugins/youtube_download/yt_dlp/extractor/dailymail.py
+11
View File
@@ -19,11 +19,22 @@ class DailyMailIE(InfoExtractor):
'ext': 'mp4',
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
'thumbnail': r're:https?://i\.dailymail\.co\.uk/.+\.jpg',
},
}, {
'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.daily-news.gr/lifestyle/%ce%b7-%cf%84%cf%81%ce%b1%ce%b3%ce%bf%cf%85%ce%b4%ce%af%cf%83%cf%84%cf%81%ce%b9%ce%b1-jessie-j-%ce%bc%ce%bf%ce%b9%cf%81%ce%ac%cf%83%cf%84%ce%b7%ce%ba%ce%b5-%cf%83%cf%85%ce%b3%ce%ba%ce%bb%ce%bf%ce%bd/',
'info_dict': {
'id': '3463585',
'ext': 'mp4',
'title': 'Jessie J reveals she has undergone surgery as she shares clips',
'description': 'md5:9fa9a25feca5b656b0b4a39c922fad1e',
'thumbnail': r're:https?://i\.dailymail\.co\.uk/.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
plugins/youtube_download/yt_dlp/extractor/dailymotion.py
+34 -30
View File
@@ -119,13 +119,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
_EMBED_REGEX = [rf'(?ix)<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)["\'](?P<url>{_VALID_URL[5:]})']
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
'info_dict': {
'id': 'x5kesuj',
'ext': 'mp4',
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'duration': 187,
'tags': 'count:5',
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1493651285,
'upload_date': '20170501',
'uploader': 'Deadline',
@@ -133,18 +134,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'age_limit': 0,
'view_count': int,
'like_count': int,
'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1cmt4ZcZ9KiM/x1080',
},
}, {
'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
'md5': 'e2f9717c6604773f963f069ca53a07f8',
'info_dict': {
'id': 'x89eyek',
'ext': 'mp4',
'title': "En quête d'esprit du 27/03/2022",
'title': 'En quête d\'esprit du 27/03/2022',
'description': 'md5:66542b9f4df2eb23f314fc097488e553',
'duration': 2756,
'tags': 'count:1',
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1648383669,
'upload_date': '20220327',
'uploader': 'CNEWS',
@@ -152,8 +152,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'age_limit': 0,
'view_count': int,
'like_count': int,
'tags': ['en_quete_d_esprit'],
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1clTH6StrxMP/x1080',
},
}, {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
@@ -163,8 +161,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'ext': 'mp4',
'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
'description': 'Several come bundled with the Steam Controller.',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 74,
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1425657362,
'upload_date': '20150306',
'uploader': 'IGN',
@@ -173,20 +171,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'view_count': int,
},
'skip': 'video gone',
}, {
# Vevo video
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
'info_dict': {
'title': 'Roar (Official)',
'id': 'USUV71301934',
'ext': 'mp4',
'uploader': 'Katy Perry',
'upload_date': '20130905',
},
'params': {
'skip_download': True,
},
'skip': 'VEVO is only available in some countries',
}, {
# age-restricted video
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
@@ -259,9 +243,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader_id': 'x2vtgmm',
'age_limit': 0,
'tags': [],
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'view_count': int,
'like_count': int,
'thumbnail': r're:https://\w+.dmcdn.net/v/WnEY61cmvMxt2Fi6d/x1080',
},
}, {
# https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj
@@ -276,18 +260,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'info_dict': {
'id': 'x8u4owg',
'ext': 'mp4',
'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
'like_count': int,
'uploader': 'Le Parisien',
'thumbnail': 'https://www.leparisien.fr/resizer/ho_GwveeYftNkLwg_cEta--5Bv4=/1200x675/cloudfront-eu-central-1.images.arcpublishing.com/leparisien/BFXJNEBN75EUNHGYJLORUC3TX4.jpg',
'upload_date': '20240309',
'view_count': int,
'tags': 'count:7',
'thumbnail': r're:https?://www\.leparisien\.fr/.+\.jpg',
'timestamp': 1709997866,
'age_limit': 0,
'uploader_id': 'x32f7b',
'title': 'VIDÉO. Le «\xa0véloto\xa0», la voiture à pédales qui aimerait se faire une place sur les routes',
'duration': 428.0,
'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
'tags': ['biclou', 'vélo', 'véloto', 'campagne', 'voiture', 'environnement', 'véhicules intermédiaires'],
},
}, {
# https://geo.dailymotion.com/player/xry80.html?video=x8vu47w
@@ -297,9 +281,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'ext': 'mp4',
'like_count': int,
'uploader': 'Metatube',
'thumbnail': r're:https://\w+.dmcdn.net/v/W1G_S1coGSFTfkTeR/x1080',
'upload_date': '20240326',
'view_count': int,
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1711496732,
'age_limit': 0,
'uploader_id': 'x2xpy74',
@@ -308,6 +292,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'description': 'Que lindura',
'tags': [],
},
'skip': 'Invalid URL',
}, {
# //geo.dailymotion.com/player/xysxq.html?video=k2Y4Mjp7krAF9iCuINM
'url': 'https://lcp.fr/programmes/avant-la-catastrophe-la-naissance-de-la-dictature-nazie-1933-1936-346819',
@@ -322,11 +307,30 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'like_count': int,
'age_limit': 0,
'duration': 3220,
'thumbnail': 'https://s1.dmcdn.net/v/Xvumk1djJBUZfjj2a/x1080',
'tags': [],
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1739919947,
'upload_date': '20250218',
},
'skip': 'Invalid URL',
}, {
'url': 'https://forum.ionicframework.com/t/ionic-2-jw-player-dailymotion-player/83248',
'info_dict': {
'id': 'xwr14q',
'ext': 'mp4',
'title': 'Macklemore & Ryan Lewis - Thrift Shop (feat. Wanz)',
'age_limit': 0,
'description': 'md5:47fbe168b5a6ddc4a205e20dd6c841b2',
'duration': 234,
'like_count': int,
'tags': 'count:5',
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1358177670,
'upload_date': '20130114',
'uploader': 'Macklemore Official',
'uploader_id': 'x19qlwr',
'view_count': int,
},
}]
_GEO_BYPASS = False
_COMMON_MEDIA_FIELDS = '''description
@@ -540,7 +544,7 @@ class DailymotionSearchIE(DailymotionPlaylistBaseIE):
'id': 'king of turtles',
'title': 'king of turtles',
},
'playlist_mincount': 90,
'playlist_mincount': 0,
}]
_SEARCH_QUERY = 'query SEARCH_QUERY( $query: String! $page: Int $limit: Int ) { search { videos( query: $query first: $limit page: $page ) { edges { node { xid } } } } } '
@@ -584,7 +588,7 @@ class DailymotionUserIE(DailymotionPlaylistBaseIE):
'info_dict': {
'id': 'nqtv',
},
'playlist_mincount': 152,
'playlist_mincount': 148,
}, {
'url': 'http://www.dailymotion.com/user/UnderProject',
'info_dict': {
plugins/youtube_download/yt_dlp/extractor/dangalplay.py
+20 -7
View File
@@ -11,8 +11,14 @@ from ..utils.traversal import traverse_obj
class DangalPlayBaseIE(InfoExtractor):
_NETRC_MACHINE = 'dangalplay'
_REGION = 'IN'
_OTV_USER_ID = None
_LOGIN_HINT = 'Pass credentials as -u "token" -p "USER_ID" where USER_ID is the `otv_user_id` in browser local storage'
_LOGIN_HINT = (
'Pass credentials as -u "token" -p "USER_ID" '
'(where USER_ID is the value of "otv_user_id" in your browser local storage). '
'Your login region can be optionally suffixed to the username as @REGION '
'(where REGION is the two-letter "region" code found in your browser local storage), '
'e.g.: -u "token@IN" -p "USER_ID"')
_API_BASE = 'https://ottapi.dangalplay.com'
_AUTH_TOKEN = 'jqeGWxRKK7FK5zEk3xCM' # from https://www.dangalplay.com/main.48ad19e24eb46acccef3.js
_SECRET_KEY = 'f53d31a4377e4ef31fa0' # same as above
@@ -20,8 +26,12 @@ class DangalPlayBaseIE(InfoExtractor):
def _perform_login(self, username, password):
if self._OTV_USER_ID:
return
if username != 'token' or not re.fullmatch(r'[\da-f]{32}', password):
mobj = re.fullmatch(r'token(?:@(?P<region>[A-Z]{2}))?', username)
if not mobj or not re.fullmatch(r'[\da-f]{32}', password):
raise ExtractorError(self._LOGIN_HINT, expected=True)
if region := mobj.group('region'):
self._REGION = region
self.write_debug(f'Setting login region to "{self._REGION}"')
self._OTV_USER_ID = password
def _real_initialize(self):
@@ -52,7 +62,7 @@ class DangalPlayBaseIE(InfoExtractor):
f'{self._API_BASE}/{path}', display_id, note, fatal=fatal,
headers={'Accept': 'application/json'}, query={
'auth_token': self._AUTH_TOKEN,
'region': 'IN',
'region': self._REGION,
**query,
})
@@ -106,7 +116,7 @@ class DangalPlayIE(DangalPlayBaseIE):
'catalog_id': catalog_id,
'content_id': content_id,
'category': '',
'region': 'IN',
'region': self._REGION,
'auth_token': self._AUTH_TOKEN,
'id': self._OTV_USER_ID,
'md5': hashlib.md5(unhashed.encode()).hexdigest(),
@@ -129,11 +139,14 @@ class DangalPlayIE(DangalPlayBaseIE):
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 422:
error_info = traverse_obj(e.cause.response.read().decode(), ({json.loads}, 'error', {dict})) or {}
if error_info.get('code') == '1016':
error_code = error_info.get('code')
if error_code == '1016':
self.raise_login_required(
f'Your token has expired or is invalid. {self._LOGIN_HINT}', method=None)
elif msg := error_info.get('message'):
raise ExtractorError(msg)
elif error_code == '4028':
self.raise_login_required(
f'Your login region is unspecified or incorrect. {self._LOGIN_HINT}', method=None)
raise ExtractorError(join_nonempty(error_code, error_info.get('message'), delim=': '))
raise
m3u8_url = traverse_obj(details, (
plugins/youtube_download/yt_dlp/extractor/dbtv.py
+16 -2
View File
@@ -12,13 +12,13 @@ class DBTVIE(InfoExtractor):
'ext': 'mp4',
'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
'thumbnail': r're:https?://.*\.jpg',
'thumbnail': r're:https?://.+\.jpg',
'upload_date': '20160916',
'duration': 69,
'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
'uploader': 'Dagbladet',
},
'add_ie': ['Youtube'],
'skip': 'Invalid URL',
}, {
'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
'only_matching': True,
@@ -26,6 +26,20 @@ class DBTVIE(InfoExtractor):
'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://www.dagbladet.no/nyheter/rekordstort-russisk-angrep/83325693',
'info_dict': {
'id': '1HW7fYry',
'ext': 'mp4',
'title': 'Putin taler - så skjer dette',
'description': 'md5:3e8bacee33de861a9663d9a3fcc54e5e',
'display_id': 'putin-taler-sa-skjer-dette',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1751043600,
'upload_date': '20250627',
},
}]
def _real_extract(self, url):
display_id, video_id = self._match_valid_url(url).groups()
plugins/youtube_download/yt_dlp/extractor/digitalconcerthall.py
+13 -5
View File
@@ -4,6 +4,7 @@ from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
jwt_decode_hs256,
parse_codecs,
try_get,
@@ -222,11 +223,18 @@ class DigitalConcertHallIE(InfoExtractor):
raise
formats = []
for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for fmt in formats:
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
fmt.update(parse_codecs(fmt['format_note']))
for fmt_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
ext = determine_ext(fmt_url)
if ext == 'm3u8':
fmts = self._extract_m3u8_formats(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
for fmt in fmts:
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
fmt.update(parse_codecs(fmt['format_note']))
formats.extend(fmts)
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(fmt_url, video_id, mpd_id='dash', fatal=False))
else:
self.report_warning(f'Skipping unsupported format extension "{ext}"')
yield {
'id': video_id,
plugins/youtube_download/yt_dlp/extractor/douyutv.py
+1 -1
View File
@@ -206,7 +206,7 @@ class DouyuTVIE(DouyuBaseIE):
'is_live': True,
**traverse_obj(room, {
'display_id': ('url', {str}, {lambda i: i[1:]}),
'title': ('room_name', {unescapeHTML}),
'title': ('room_name', {str}, {unescapeHTML}),
'description': ('show_details', {str}),
'uploader': ('nickname', {str}),
'thumbnail': ('room_src', {url_or_none}),
plugins/youtube_download/yt_dlp/extractor/dreisat.py
+1 -1
View File
@@ -64,7 +64,7 @@ class DreiSatIE(ZDFBaseIE):
'title': 'dein buch - Das Beste von der Leipziger Buchmesse 2025 - Teil 1',
'description': 'md5:bae51bfc22f15563ce3acbf97d2e8844',
'duration': 5399.0,
'thumbnail': 'https://www.3sat.de/assets/buchmesse-kerkeling-100~original?cb=1743329640903',
'thumbnail': 'https://www.3sat.de/assets/buchmesse-kerkeling-100~original?cb=1747256996338',
'chapters': 'count:24',
'episode': 'dein buch - Das Beste von der Leipziger Buchmesse 2025 - Teil 1',
'episode_id': 'POS_1ef236cc-b390-401e-acd0-4fb4b04315fb',
plugins/youtube_download/yt_dlp/extractor/dropout.py
+26 -26
View File
@@ -18,15 +18,15 @@ from ..utils import (
class DropoutIE(InfoExtractor):
_LOGIN_URL = 'https://www.dropout.tv/login'
_LOGIN_URL = 'https://watch.dropout.tv/login'
_NETRC_MACHINE = 'dropout'
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
_VALID_URL = r'https?://(?:watch\.)?dropout\.tv/(?:[^/?#]+/)*videos/(?P<id>[^/?#]+)/?(?:[?#]|$)'
_TESTS = [
{
'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
'url': 'https://watch.dropout.tv/game-changer/season:2/videos/yes-or-no',
'note': 'Episode in a series',
'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
'md5': '4b76963f904f8bc4ba22dcf0e66ada06',
'info_dict': {
'id': '738153',
'display_id': 'yes-or-no',
@@ -45,35 +45,35 @@ class DropoutIE(InfoExtractor):
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest', 'Failed to parse XML: not well-formed'],
},
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
'url': 'https://watch.dropout.tv/tablepop-presents-megadungeon-live/season:1/videos/enter-through-the-gift-shop',
'note': 'Episode in a series (missing release_date)',
'md5': '712caf7c191f1c47c8f1879520c2fa5c',
'md5': 'b08fb03050585ea25cd7ee092db9134c',
'info_dict': {
'id': '320562',
'display_id': 'episode-1',
'id': '624270',
'display_id': 'enter-through-the-gift-shop',
'ext': 'mp4',
'title': 'The Beginning Begins',
'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
'series': 'Dimension 20: Fantasy High',
'title': 'Enter Through the Gift Shop',
'description': 'A new adventuring party explores a gift shop and runs into a friendly orc -- and some angry goblins.',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/a1d876c3-3dee-4cd0-87c6-27a851b1d0ec.jpg',
'series': 'TablePop Presents: MEGADUNGEON LIVE!',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'The Beginning Begins',
'duration': 6838,
'episode': 'Enter Through the Gift Shop',
'duration': 7101,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest', 'Failed to parse XML: not well-formed'],
},
{
'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
'url': 'https://watch.dropout.tv/videos/misfits-magic-holiday-special',
'note': 'Episode not in a series',
'md5': 'c30fa18999c5880d156339f13c953a26',
'md5': '1e6428f7756b02c93b573d39ddd789fe',
'info_dict': {
'id': '1915774',
'display_id': 'misfits-magic-holiday-special',
@@ -87,7 +87,7 @@ class DropoutIE(InfoExtractor):
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest', 'Failed to parse XML: not well-formed'],
},
]
@@ -125,7 +125,7 @@ class DropoutIE(InfoExtractor):
display_id = self._match_id(url)
webpage = None
if self._get_cookies('https://www.dropout.tv').get('_session'):
if self._get_cookies('https://watch.dropout.tv').get('_session'):
webpage = self._download_webpage(url, display_id)
if not webpage or '<div id="watch-unauthorized"' in webpage:
login_err = self._login(display_id)
@@ -148,7 +148,7 @@ class DropoutIE(InfoExtractor):
return {
'_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(),
'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://watch.dropout.tv'),
'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
'display_id': display_id,
'title': title,
@@ -167,10 +167,10 @@ class DropoutIE(InfoExtractor):
class DropoutSeasonIE(InfoExtractor):
_PAGE_SIZE = 24
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VALID_URL = r'https?://(?:watch\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_TESTS = [
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
'url': 'https://watch.dropout.tv/dimension-20-fantasy-high/season:1',
'note': 'Multi-season series with the season in the url',
'playlist_count': 24,
'info_dict': {
@@ -179,7 +179,7 @@ class DropoutSeasonIE(InfoExtractor):
},
},
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high',
'url': 'https://watch.dropout.tv/dimension-20-fantasy-high',
'note': 'Multi-season series with the season not in the url',
'playlist_count': 24,
'info_dict': {
@@ -188,7 +188,7 @@ class DropoutSeasonIE(InfoExtractor):
},
},
{
'url': 'https://www.dropout.tv/dimension-20-shriek-week',
'url': 'https://watch.dropout.tv/dimension-20-shriek-week',
'note': 'Single-season series',
'playlist_count': 4,
'info_dict': {
@@ -197,7 +197,7 @@ class DropoutSeasonIE(InfoExtractor):
},
},
{
'url': 'https://www.dropout.tv/breaking-news-no-laugh-newsroom/season:3',
'url': 'https://watch.dropout.tv/breaking-news-no-laugh-newsroom/season:3',
'note': 'Multi-season series with season in the url that requires pagination',
'playlist_count': 25,
'info_dict': {
plugins/youtube_download/yt_dlp/extractor/dtube.py
+1 -2
View File
@@ -1,5 +1,4 @@
import json
import socket
from .common import InfoExtractor
from ..utils import (
@@ -56,7 +55,7 @@ class DTubeIE(InfoExtractor):
try:
self.to_screen(f'{video_id}: Checking {format_id} video format URL')
self._downloader._opener.open(video_url, timeout=5).close()
except socket.timeout:
except TimeoutError:
self.to_screen(
f'{video_id}: {format_id} URL is invalid, skipping')
continue
plugins/youtube_download/yt_dlp/extractor/eagleplatform.py
-215
View File
@@ -1,215 +0,0 @@
import functools
import re
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
smuggle_url,
unsmuggle_url,
url_or_none,
)
class EaglePlatformIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
eagleplatform:(?P<custom_host>[^/]+):|
https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
)
(?P<id>\d+)
'''
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1']
_TESTS = [{
# http://lenta.ru/news/2015/03/06/navalny/
'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
'info_dict': {
'id': '227304',
'ext': 'mp4',
'title': 'Навальный вышел на свободу',
'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 87,
'view_count': int,
'age_limit': 0,
},
}, {
# http://muz-tv.ru/play/7129/
# http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
'url': 'eagleplatform:media.clipyou.ru:12820',
'md5': '358597369cf8ba56675c1df15e7af624',
'info_dict': {
'id': '12820',
'ext': 'mp4',
'title': "'O Sole Mio",
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 216,
'view_count': int,
},
'skip': 'Georestricted',
}, {
# referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
'only_matching': True,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
add_referer = functools.partial(smuggle_url, data={'referrer': url})
res = tuple(super()._extract_embed_urls(url, webpage))
if res:
return map(add_referer, res)
PLAYER_JS_RE = r'''
<script[^>]+
src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
.+?
'''
# "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
mobj = re.search(
rf'''(?xs)
{PLAYER_JS_RE}
<div[^>]+
class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
data-id=["\'](?P<id>\d+)
''', webpage)
if mobj is not None:
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
# Generalization of "Javascript code usage", "Combined usage" and
# "Usage without attaching to DOM" embeddings (see
# http://dultonmedia.github.io/eplayer/)
mobj = re.search(
r'''(?xs)
%s
<script>
.+?
new\s+EaglePlayer\(
(?:[^,]+\s*,\s*)?
{
.+?
\bid\s*:\s*["\']?(?P<id>\d+)
.+?
}
\s*\)
.+?
</script>
''' % PLAYER_JS_RE, webpage) # noqa: UP031
if mobj is not None:
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
@staticmethod
def _handle_error(response):
status = int_or_none(response.get('status', 200))
if status != 200:
raise ExtractorError(' '.join(response['errors']), expected=True)
def _download_json(self, url_or_request, video_id, *args, **kwargs):
try:
response = super()._download_json(
url_or_request, video_id, *args, **kwargs)
except ExtractorError as ee:
if isinstance(ee.cause, HTTPError):
response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
self._handle_error(response)
raise
return response
def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
return self._download_json(url_or_request, video_id, note)['data'][0]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = self._match_valid_url(url)
host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
headers = {}
query = {
'id': video_id,
}
referrer = smuggled_data.get('referrer')
if referrer:
headers['Referer'] = referrer
query['referrer'] = referrer
player_data = self._download_json(
f'http://{host}/api/player_data', video_id,
headers=headers, query=query)
media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
title = media['title']
description = media.get('description')
thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
duration = int_or_none(media.get('duration'))
view_count = int_or_none(media.get('views'))
age_restriction = media.get('age_restriction')
age_limit = None
if age_restriction:
age_limit = 0 if age_restriction == 'allow_all' else 18
secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
formats = []
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
m3u8_formats_dict = {}
for f in m3u8_formats:
if f.get('height') is not None:
m3u8_formats_dict[f['height']] = f
mp4_data = self._download_json(
# Secure mp4 URL is constructed according to Player.prototype.mp4 from
# http://lentaru.media.eagleplatform.com/player/player.js
re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
video_id, 'Downloading mp4 JSON', fatal=False)
if mp4_data:
for format_id, format_url in mp4_data.get('data', {}).items():
if not url_or_none(format_url):
continue
height = int_or_none(format_id)
if height is not None and m3u8_formats_dict.get(height):
f = m3u8_formats_dict[height].copy()
f.update({
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
else:
f = {
'format_id': f'http-{format_id}',
'height': int_or_none(format_id),
}
f['url'] = format_url
formats.append(f)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'age_limit': age_limit,
'formats': formats,
}
class ClipYouEmbedIE(InfoExtractor):
_VALID_URL = False
@classmethod
def _extract_embed_urls(cls, url, webpage):
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:
yield smuggle_url('eagleplatform:{host}:{id}'.format(**mobj.groupdict()), {'referrer': url})
plugins/youtube_download/yt_dlp/extractor/ertgr.py
+24 -15
View File
@@ -64,14 +64,12 @@ class ERTFlixCodenameIE(ERTFlixBaseIE):
_VALID_URL = r'ertflix:(?P<id>[\w-]+)'
_TESTS = [{
'url': 'ertflix:monogramma-praxitelis-tzanoylinos',
'md5': '5b9c2cd171f09126167e4082fc1dd0ef',
'info_dict': {
'id': 'monogramma-praxitelis-tzanoylinos',
'ext': 'mp4',
'title': 'md5:ef0b439902963d56c43ac83c3f41dd0e',
'title': 'monogramma-praxitelis-tzanoylinos',
},
},
]
}]
def _extract_formats_and_subs(self, video_id):
media_info = self._call_api(video_id, codename=video_id)
@@ -131,13 +129,14 @@ class ERTFlixIE(ERTFlixBaseIE):
'duration': 3166,
'age_limit': 8,
},
'skip': 'Invalid URL',
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
'title': 'Monogramma',
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
},
'playlist_mincount': 64,
}, {
@@ -145,28 +144,28 @@ class ERTFlixIE(ERTFlixBaseIE):
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
'title': 'Monogramma',
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
},
'playlist_count': 22,
'playlist_mincount': 66,
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1&season=2021%20-%202022',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
'title': 'Monogramma',
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
},
'playlist_mincount': 36,
'playlist_mincount': 25,
}, {
'url': 'https://www.ertflix.gr/series/ser.164991-to-diktuo-1?season=1-9',
'info_dict': {
'id': 'ser.164991',
'age_limit': 8,
'description': 'Η πρώτη ελληνική εκπομπή με θεματολογία αποκλειστικά γύρω από το ίντερνετ.',
'title': 'Το δίκτυο',
'title': 'The Network',
'description': 'The first Greek show featuring topics exclusively around the internet.',
},
'playlist_mincount': 9,
'playlist_mincount': 0,
}, {
'url': 'https://www.ertflix.gr/en/vod/vod.127652-ta-kalytera-mas-chronia-ep1-mia-volta-sto-feggari',
'only_matching': True,
@@ -282,6 +281,16 @@ class ERTWebtvEmbedIE(InfoExtractor):
'ext': 'mp4',
'thumbnail': 'https://program.ert.gr/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
},
'skip': 'Invalid URL',
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.ertnews.gr/video/manolis-goyalles-o-anthropos-piso-apo-ti-diadiktyaki-vasilopita/',
'info_dict': {
'id': '2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
'ext': 'mp4',
'title': 'VOD - 2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
'thumbnail': r're:https?://www\.ert\.gr/themata/photos/.+\.jpg',
},
}]
def _real_extract(self, url):
plugins/youtube_download/yt_dlp/extractor/espn.py
+5 -7
View File
@@ -5,7 +5,6 @@ import urllib.parse
from .adobepass import AdobePassIE
from .common import InfoExtractor
from .once import OnceIE
from ..utils import (
determine_ext,
dict_get,
@@ -16,7 +15,7 @@ from ..utils import (
)
class ESPNIE(OnceIE):
class ESPNIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
@@ -131,9 +130,7 @@ class ESPNIE(OnceIE):
return
format_urls.add(source_url)
ext = determine_ext(source_url)
if OnceIE.suitable(source_url):
formats.extend(self._extract_once_formats(source_url))
elif ext == 'smil':
if ext == 'smil':
formats.extend(self._extract_smil_formats(
source_url, video_id, fatal=False))
elif ext == 'f4m':
@@ -332,6 +329,7 @@ class WatchESPNIE(AdobePassIE):
}]
_API_KEY = 'ZXNwbiZicm93c2VyJjEuMC4w.ptUt7QxsteaRruuPmGZFaJByOoqKvDP2a5YkInHrc7c'
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIyZGJmZWM4My03OWE1LTQyNzEtYTVmZC04NTZjYTMxMjRjNjMiLCJuYmYiOjE1NDAyMTI3NjEsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQwMjEyNzYxfQ.yaK3r4AI2uLVvsyN1GLzqzgzRlxMPtasSaiYYBV0wIstqih5tvjTmeoLmi8Xy9Kp_U7Md-bOffwiyK3srHkpUkhhwXLH2x6RPjmS1tPmhaG7-3LBcHTf2ySPvXhVf7cN4ngldawK4tdtLtsw6rF_JoZE2yaC6XbS2F51nXSFEDDnOQWIHEQRG3aYAj-38P2CLGf7g-Yfhbp5cKXeksHHQ90u3eOO4WH0EAjc9oO47h33U8KMEXxJbvjV5J8Va2G2fQSgLDZ013NBI3kQnE313qgqQh2feQILkyCENpB7g-TVBreAjOaH1fU471htSoGGYepcAXv-UDtpgitDiLy7CQ'
def _call_bamgrid_api(self, path, video_id, payload=None, headers={}):
if 'Authorization' not in headers:
@@ -408,8 +406,8 @@ class WatchESPNIE(AdobePassIE):
# TV Provider required
else:
resource = self._get_mvpd_resource('ESPN', video_data['name'], video_id, None)
auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource).encode()
resource = self._get_mvpd_resource('espn1', video_data['name'], video_id, None)
auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource, self._SOFTWARE_STATEMENT).encode()
asset = self._download_json(
f'https://watch.auth.api.espn.com/video/auth/media/{video_id}/asset?apikey=uiqlbgzdwuru14v627vdusswb',
plugins/youtube_download/yt_dlp/extractor/facebook.py
+98 -46
View File
@@ -81,13 +81,14 @@ class FacebookIE(InfoExtractor):
'description': 'md5:34675bda53336b1d16400265c2bb9b3b',
'uploader': 'RADIO KICKS FM',
'upload_date': '20230818',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1692346159,
'thumbnail': r're:^https?://.*',
'uploader_id': '100063551323670',
'duration': 3133.583,
'view_count': int,
'concurrent_view_count': 0,
},
'expected_warnings': ['Cannot parse data'],
}, {
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'md5': '6a40d33c0eccbb1af76cf0485a052659',
@@ -106,17 +107,18 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
'title': 'Asif',
'title': '119 reactions · 1.4K shares | Asif Nawab Butt on Reels',
'description': '',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1399398998,
'thumbnail': r're:^https?://.*',
'uploader_id': 'pfbid05AzrFTXgY37tqwaSgbFTTEpCLBjjEJHkigogwGiRPtKEpAsJYJpzE94H1RxYXWEtl',
'uploader_id': 'pfbid028xue38TBXRyNbiqBSV2LFs3QK3yopvKjupbqFoL6U9SKbx4p2SMdJjQSBvnjsHGWl',
'duration': 131.03,
'concurrent_view_count': int,
'view_count': int,
},
'expected_warnings': ['Cannot parse data'],
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
@@ -158,7 +160,7 @@ class FacebookIE(InfoExtractor):
'id': '10153664894881749',
'ext': 'mp4',
'title': 'Average time to confirm recent Supreme Court nominees: 67 days Longest it\'s t...',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1456259628,
'upload_date': '20160223',
'uploader': 'Barack Obama',
@@ -168,7 +170,7 @@ class FacebookIE(InfoExtractor):
# have 1080P, but only up to 720p in swf params
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
'md5': '1659aa21fb3dd1585874f668e81a72c8',
'md5': '70b82ebf5f0e9b91b2a49d3db3563611',
'info_dict': {
'id': '10155529876156509',
'ext': 'mp4',
@@ -177,7 +179,7 @@ class FacebookIE(InfoExtractor):
'timestamp': 1477818095,
'upload_date': '20161030',
'uploader': 'CNN',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'view_count': int,
'uploader_id': '100059479812265',
'concurrent_view_count': int,
@@ -198,13 +200,11 @@ class FacebookIE(InfoExtractor):
'uploader': 'Yaroslav Korpan',
'uploader_id': 'pfbid06AScABAWcW91qpiuGrLt99Ef9tvwHoXP6t8KeFYEqkSfreMtfa9nTveh8b2ZEVSWl',
'concurrent_view_count': int,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'view_count': int,
'duration': 11736.446,
},
'params': {
'skip_download': True,
},
'skip': 'Invalid URL',
}, {
# FIXME: Cannot parse data error
'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
@@ -215,7 +215,7 @@ class FacebookIE(InfoExtractor):
'timestamp': 1477305000,
'upload_date': '20161024',
'uploader': 'La Guía Del Varón',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
},
'skip': 'Requires logging in',
}, {
@@ -244,9 +244,10 @@ class FacebookIE(InfoExtractor):
'upload_date': '20171124',
'uploader': 'Vickie Gentry',
'uploader_id': 'pfbid0FkkycT95ySNNyfCw4Cho6u5G7WbbZEcxT496Hq8rtx1K3LcTCATpR3wnyYhmyGC5l',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'duration': 148.224,
},
'skip': 'Invalid URL',
}, {
# data.node.comet_sections.content.story.attachments[].styles.attachment.media
'url': 'https://www.facebook.com/attn/posts/pfbid0j1Czf2gGDVqeQ8KiMLFm3pWN8GxsQmeRrVhimWDzMuKQoR8r4b1knNsejELmUgyhl',
@@ -260,7 +261,7 @@ class FacebookIE(InfoExtractor):
'duration': 132.675,
'uploader_id': '100064451419378',
'view_count': int,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1701975646,
},
}, {
@@ -271,9 +272,9 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'Lela Evans',
'description': 'Today Makkovik\'s own Pilot Mandy Smith made her inaugural landing on the airstrip in her hometown. What a proud moment as we all cheered and...',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'uploader': 'Lela Evans',
'uploader_id': 'pfbid0swT2y7t6TAsZVBvcyeYPdhTMefGaS26mzUwML3vd1ma6ndGZKxsyS4Ssu3jitZLXl',
'uploader_id': 'pfbid02wjMpknobSMnyynK3TNKN4Ww1StcpAKXgowqTyge3bz7LwHZMQ68uiXzzbu7xeryBl',
'upload_date': '20231228',
'timestamp': 1703804085,
'duration': 394.347,
@@ -326,28 +327,27 @@ class FacebookIE(InfoExtractor):
'uploader_id': '100066514874195',
'duration': 4524.001,
'view_count': int,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'concurrent_view_count': int,
},
'params': {
'skip_download': True,
},
'params': {'skip_download': True},
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.all_subattachments.nodes[].media
'url': 'https://www.facebook.com/100033620354545/videos/106560053808006/',
'info_dict': {
'id': '106560053808006',
'ext': 'mp4',
'title': 'Josef',
'thumbnail': r're:^https?://.*',
'title': 'Josef Novak on Reels',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'concurrent_view_count': int,
'uploader_id': 'pfbid02gpfwRM2XvdEJfsERupwQiNmBiDArc38RMRYZnap372q6Vs7MtFTVy72mmFWpJBTKl',
'uploader_id': 'pfbid0cjYJYXpePWqhZ9DgpB6gKXrN2q3obwducdKm4wT7K5nkhbfKg5cneocYbsdaji7fl',
'timestamp': 1549275572,
'duration': 3.283,
'uploader': 'Josef Novak',
'description': '',
'upload_date': '20190204',
},
'expected_warnings': ['Cannot parse data'],
}, {
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/watch/?v=647537299265662',
@@ -406,7 +406,7 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'ANALISI IN CAMPO OSCURO " Coaguli nel sangue dei vaccinati"',
'description': 'Other event by Comitato Liberi Pensatori on Tuesday, October 18 2022',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'uploader': 'Comitato Liberi Pensatori',
'uploader_id': '100065709540881',
},
@@ -414,6 +414,56 @@ class FacebookIE(InfoExtractor):
'url': 'https://www.facebook.com/groups/1513990329015294/posts/d41d8cd9/2013209885760000/?app=fbl',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# <iframe> embed
'url': 'http://www.unique-almeria.com/mini-hollywood.html',
'md5': 'cba5d8c5021e9340dcefe925255e2c3e',
'info_dict': {
'id': '1529066599879',
'ext': 'mp4',
'title': 'Facebook video #1529066599879',
},
'expected_warnings': ['unable to extract uploader'],
}, {
# FIXME: Embed detection
# <iframe> embed, plugin video
'url': 'https://www.newsmemory.com/eedition/e-publishing-solutions/2-in-one-app/',
'md5': 'ae97d4a44f8cc9a8b1a4c03b9ed793af',
'info_dict': {
'id': '10155710648695814',
'ext': 'mp4',
'title': 'Download the all new and improved Trinidad Express App',
'concurrent_view_count': int,
'description': 'md5:4806195c99908e4189b45b1c23bd4f89',
'duration': 69.408,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1533919195,
'upload_date': '20180810',
'uploader': 'Trinidad Express Newspapers',
'uploader_id': '100064446413648',
'view_count': int,
},
'expected_warnings': ['Cannot parse data'],
}, {
# API embed
'url': 'https://www.curs.md/ro',
'md5': '090bae53b9bff2be993c896edc2ea205',
'info_dict': {
'id': '334484292523563',
'ext': 'mp4',
'title': 'md5:9abffe1c86cdd967ffa224e1ccc13b90',
'concurrent_view_count': int,
'description': 'md5:0ba98567a61c640f9fabf1882235b33d',
'duration': 8789.891,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1700603114,
'upload_date': '20231121',
'uploader': 'Istoria Moldovei',
'uploader_id': '100063529778592',
'view_count': int,
},
'params': {'extractor_args': {'generic': {'impersonate': ['chrome']}}},
}]
_SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
_api_config = {
'graphURI': '/api/graphql/',
@@ -898,20 +948,24 @@ class FacebookIE(InfoExtractor):
class FacebookPluginsVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
_TESTS = [{
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
'md5': '5954e92cdfe51fe5782ae9bda7058a07',
'md5': 'af83aeae1d595f377c6e47a450828155',
'info_dict': {
'id': '10154383743583686',
'ext': 'mp4',
# TODO: Fix title, uploader
'title': 'What to do during the haze?',
'uploader': 'Gov.sg',
'upload_date': '20160826',
'concurrent_view_count': int,
'description': 'md5:81839c0979803a014b20798df255ed0b',
'duration': 65.087,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1472184808,
'upload_date': '20160826',
'uploader': 'gov.sg',
'uploader_id': '100064718678925',
'view_count': int,
},
'add_ie': [FacebookIE.ie_key()],
'expected_warnings': ['Cannot parse data'],
}, {
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
'only_matching': True,
@@ -945,7 +999,7 @@ class FacebookRedirectURLIE(InfoExtractor):
'tags': 'count:11',
'duration': 3332,
'live_status': 'not_live',
'thumbnail': 'https://i.ytimg.com/vi/pO8h3EaFRdo/maxresdefault.jpg',
'thumbnail': r're:https?://i\.ytimg\.com/vi/.+',
'channel_url': 'https://www.youtube.com/channel/UCGBpxWJr9FNOcFYA5GkKrMg',
'availability': 'public',
'uploader_url': 'http://www.youtube.com/user/brtvofficial',
@@ -954,8 +1008,7 @@ class FacebookRedirectURLIE(InfoExtractor):
'view_count': int,
'like_count': int,
},
'add_ie': ['Youtube'],
'params': {'skip_download': 'Youtube'},
'skip': 'Youtube video is now private',
}]
def _real_extract(self, url):
@@ -968,22 +1021,20 @@ class FacebookRedirectURLIE(InfoExtractor):
class FacebookReelIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/reel/(?P<id>\d+)'
IE_NAME = 'facebook:reel'
_TESTS = [{
'url': 'https://www.facebook.com/reel/1195289147628387',
'md5': 'a53256d10fc2105441fe0c4212ed8cea',
'md5': 'aeb0153ecb2eaacdf2dc2bf88f593fef',
'info_dict': {
'id': '1195289147628387',
'ext': 'mp4',
'title': r're:9\.6K views · 355 reactions .+ Let the “Slapathon” commence!! .+ LL COOL J · Mama Said Knock You Out$',
'description': r're:When your trying to help your partner .+ LL COOL J · Mama Said Knock You Out$',
'uploader': 'Beast Camp Training',
'title': '9.7K views · 352 reactions | When your trying to help your partner out with an arrest and #FAAFO games begin. Let the “Slapathon” commence!! 👊👋 | Beast Camp Training',
'description': 'md5:5a767dc7e78718667b150a7facc4a34f',
'uploader': '9.7K views &#xb7; 352 reactions | When your trying to help your partner out with an arrest and #FAAFO games begin. Let the &#x201c;Slapathon&#x201d; commence!! &#x1f44a;&#x1f44b; | Beast Camp Training',
'uploader_id': '100040874179269',
'duration': 9.579,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1637502609,
'upload_date': '20211121',
'thumbnail': r're:^https?://.*',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
@@ -998,7 +1049,6 @@ class FacebookReelIE(InfoExtractor):
class FacebookAdsIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/ads/library/?\?(?:[^#]+&)?id=(?P<id>\d+)'
IE_NAME = 'facebook:ads'
_TESTS = [{
'url': 'https://www.facebook.com/ads/library/?id=899206155126718',
'info_dict': {
@@ -1008,12 +1058,13 @@ class FacebookAdsIE(InfoExtractor):
'description': 'md5:0822724069e3aca97cbed5dabbab282e',
'uploader': 'Kandao',
'uploader_id': '774114102743284',
'uploader_url': r're:^https?://.*',
'uploader_url': 'https://facebook.com/KandaoVR',
'timestamp': 1702548330,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'upload_date': '20231214',
'like_count': int,
},
'skip': 'Invalid URL',
}, {
# key 'watermarked_video_sd_url' missing
'url': 'https://www.facebook.com/ads/library/?id=501152689226254',
@@ -1024,9 +1075,9 @@ class FacebookAdsIE(InfoExtractor):
'description': 'md5:02a446ace7ff8c3c37a2892922492490',
'uploader': 'mat.nawrocki',
'uploader_id': '148586968341456',
'uploader_url': r're:^https?://.*',
'uploader_url': 'https://www.instagram.com/_u/mat.nawrocki',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1723452305,
'thumbnail': r're:^https?://.*',
'upload_date': '20240812',
'like_count': int,
},
@@ -1037,12 +1088,13 @@ class FacebookAdsIE(InfoExtractor):
'title': 'Jusqu\u2019\u00e0 -25% sur une s\u00e9lection de vins p\u00e9tillants italiens ',
'uploader': 'Eataly Paris Marais',
'uploader_id': '2086668958314152',
'uploader_url': r're:^https?://.*',
'uploader_url': 'https://facebook.com/EatalyParisMarais',
'timestamp': 1703571529,
'upload_date': '20231226',
'like_count': int,
},
'playlist_count': 3,
'skip': 'Invalid URL',
}, {
'url': 'https://es-la.facebook.com/ads/library/?id=901230958115569',
'only_matching': True,
plugins/youtube_download/yt_dlp/extractor/faulio.py
+237
View File
@@ -0,0 +1,237 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import int_or_none, js_to_json, url_or_none
from ..utils.traversal import traverse_obj
class FaulioBaseIE(InfoExtractor):
_DOMAINS = (
'aloula.sba.sa',
'bahry.com',
'maraya.sba.net.ae',
'sat7plus.org',
)
_LANGUAGES = ('ar', 'en', 'fa')
_BASE_URL_RE = fr'https?://(?:{"|".join(map(re.escape, _DOMAINS))})/(?:(?:{"|".join(_LANGUAGES)})/)?'
def _get_headers(self, url):
parsed_url = urllib.parse.urlparse(url)
return {
'Referer': url,
'Origin': f'{parsed_url.scheme}://{parsed_url.hostname}',
}
def _get_api_base(self, url, video_id):
webpage = self._download_webpage(url, video_id)
config_data = self._search_json(
r'window\.__NUXT__\.config=', webpage, 'config', video_id, transform_source=js_to_json)
return config_data['public']['TRANSLATIONS_API_URL']
class FaulioIE(FaulioBaseIE):
_VALID_URL = fr'{FaulioBaseIE._BASE_URL_RE}(?:episode|media)/(?P<id>[a-zA-Z0-9-]+)'
_TESTS = [{
'url': 'https://aloula.sba.sa/en/episode/29102',
'info_dict': {
'id': 'aloula.faulio.com_29102',
'ext': 'mp4',
'display_id': 'هذا-مكانك-03-004-v-29102',
'title': 'الحلقة 4',
'episode': 'الحلقة 4',
'description': '',
'series': 'هذا مكانك',
'season': 'Season 3',
'season_number': 3,
'episode_number': 4,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 4855,
'age_limit': 3,
},
}, {
'url': 'https://bahry.com/en/media/1191',
'info_dict': {
'id': 'bahry.faulio.com_1191',
'ext': 'mp4',
'display_id': 'Episode-4-1191',
'title': 'Episode 4',
'episode': 'Episode 4',
'description': '',
'series': 'Wild Water',
'season': 'Season 1',
'season_number': 1,
'episode_number': 4,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1653,
'age_limit': 0,
},
}, {
'url': 'https://maraya.sba.net.ae/episode/127735',
'info_dict': {
'id': 'maraya.faulio.com_127735',
'ext': 'mp4',
'display_id': 'عبدالله-الهاجري---عبدالرحمن-المطروشي-127735',
'title': 'عبدالله الهاجري - عبدالرحمن المطروشي',
'episode': 'عبدالله الهاجري - عبدالرحمن المطروشي',
'description': 'md5:53de01face66d3d6303221e5a49388a0',
'series': 'أبناؤنا في الخارج',
'season': 'Season 3',
'season_number': 3,
'episode_number': 7,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1316,
'age_limit': 0,
},
}, {
'url': 'https://sat7plus.org/episode/18165',
'info_dict': {
'id': 'sat7.faulio.com_18165',
'ext': 'mp4',
'display_id': 'ep-13-ADHD-18165',
'title': 'ADHD and creativity',
'episode': 'ADHD and creativity',
'description': '',
'series': 'ADHD Podcast',
'season': 'Season 1',
'season_number': 1,
'episode_number': 13,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2492,
'age_limit': 0,
},
}, {
'url': 'https://aloula.sba.sa/en/episode/0',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
api_base = self._get_api_base(url, video_id)
video_info = self._download_json(f'{api_base}/video/{video_id}', video_id, fatal=False)
player_info = self._download_json(f'{api_base}/video/{video_id}/player', video_id)
headers = self._get_headers(url)
formats = []
subtitles = {}
if hls_url := traverse_obj(player_info, ('settings', 'protocols', 'hls', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False, headers=headers)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if mpd_url := traverse_obj(player_info, ('settings', 'protocols', 'dash', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(
mpd_url, video_id, mpd_id='dash', fatal=False, headers=headers)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': f'{urllib.parse.urlparse(api_base).hostname}_{video_id}',
**traverse_obj(traverse_obj(video_info, ('blocks', 0)), {
'display_id': ('slug', {str}),
'title': ('title', {str}),
'episode': ('title', {str}),
'description': ('description', {str}),
'series': ('program_title', {str}),
'season_number': ('season_number', {int_or_none}),
'episode_number': ('episode', {int_or_none}),
'thumbnail': ('image', {url_or_none}),
'duration': ('duration', 'total', {int_or_none}),
'age_limit': ('age_rating', {int_or_none}),
}),
'formats': formats,
'subtitles': subtitles,
'http_headers': headers,
}
class FaulioLiveIE(FaulioBaseIE):
_VALID_URL = fr'{FaulioBaseIE._BASE_URL_RE}live/(?P<id>[a-zA-Z0-9-]+)'
_TESTS = [{
'url': 'https://aloula.sba.sa/live/saudiatv',
'info_dict': {
'id': 'aloula.faulio.com_saudiatv',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://bahry.com/live/1',
'info_dict': {
'id': 'bahry.faulio.com_1',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://maraya.sba.net.ae/live/1',
'info_dict': {
'id': 'maraya.faulio.com_1',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://sat7plus.org/live/pars',
'info_dict': {
'id': 'sat7.faulio.com_pars',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://sat7plus.org/fa/live/arabic',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
api_base = self._get_api_base(url, video_id)
channel = traverse_obj(
self._download_json(f'{api_base}/channels', video_id),
(lambda k, v: v['url'] == video_id, any))
headers = self._get_headers(url)
formats = []
subtitles = {}
if hls_url := traverse_obj(channel, ('streams', 'hls', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, 'mp4', m3u8_id='hls', live=True, fatal=False, headers=headers)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if mpd_url := traverse_obj(channel, ('streams', 'mpd', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(
mpd_url, video_id, mpd_id='dash', fatal=False, headers=headers)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': f'{urllib.parse.urlparse(api_base).hostname}_{video_id}',
**traverse_obj(channel, {
'title': ('title', {str}),
'description': ('description', {str}),
}),
'formats': formats,
'subtitles': subtitles,
'http_headers': headers,
'is_live': True,
}
plugins/youtube_download/yt_dlp/extractor/fc2.py
+17 -2
View File
@@ -22,8 +22,23 @@ class FC2IE(InfoExtractor):
'md5': 'a6ebe8ebe0396518689d963774a54eb7',
'info_dict': {
'id': '20121103kUan1KHs',
'ext': 'flv',
'title': 'Boxing again with Puff',
'ext': 'mp4',
'thumbnail': r're:https?://.+\.jpe?g',
},
'params': {
'skip_download': 'm3u8',
},
}, {
# Direct video url
'url': 'https://video.fc2.com/content/20121209FP73fxDx',
'md5': '066bdb9b3a56a97f49cbf0d0b8a75a1f',
'info_dict': {
'id': '20121209FP73fxDx',
'title': 'Farewelling The Wiggles Live in Sydney Dec 8 2012',
'ext': 'mp4',
'thumbnail': r're:https?://.+\.jpe?g',
'description': 'Saying goodbye to the Wiggles at their Celebration Concert in Sydney, and what a concert that was!',
},
}, {
'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
@@ -104,7 +119,7 @@ class FC2IE(InfoExtractor):
'title': title,
'url': vid_url,
'ext': 'mp4',
'protocol': 'm3u8_native',
'protocol': 'm3u8_native' if vidplaylist.get('type') == 2 else 'https',
'description': description,
'thumbnail': thumbnail,
}
plugins/youtube_download/yt_dlp/extractor/fifa.py
+2 -2
View File
@@ -7,7 +7,7 @@ from ..utils import (
class FifaIE(InfoExtractor):
_VALID_URL = r'https?://www\.fifa\.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
_VALID_URL = r'https?://www\.fifa\.com/fifaplus/\w{2}/watch/([^#?]+/)?(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
'info_dict': {
@@ -51,7 +51,7 @@ class FifaIE(InfoExtractor):
}]
def _real_extract(self, url):
video_id, locale = self._match_valid_url(url).group('id', 'locale')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
preconnect_link = self._search_regex(
plugins/youtube_download/yt_dlp/extractor/firsttv.py
+78 -99
View File
@@ -2,11 +2,15 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
qualities,
join_nonempty,
mimetype2ext,
parse_qs,
unified_strdate,
url_or_none,
)
from ..utils.traversal import traverse_obj
class FirstTVIE(InfoExtractor):
@@ -15,40 +19,51 @@ class FirstTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:sport)?1tv\.ru/(?:[^/?#]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# single format
'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
# single format; has item.id
'url': 'https://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
'md5': '8011ae8e88ff4150107ab9c5a8f5b659',
'info_dict': {
'id': '40049',
'ext': 'mp4',
'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
'thumbnail': r're:https?://.+/.+\.jpg',
'upload_date': '20150212',
'duration': 2694,
},
'params': {'skip_download': 'm3u8'},
}, {
# multiple formats
'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
# multiple formats; has item.id
'url': 'https://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
'info_dict': {
'id': '364746',
'ext': 'mp4',
'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
'thumbnail': r're:https?://.+/.+\.jpg',
'upload_date': '20160407',
'duration': 179,
'formats': 'mincount:3',
},
'params': {
'skip_download': True,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://www.1tv.ru/news/issue/2016-12-01/14:00',
'url': 'https://www.1tv.ru/news/issue/2016-12-01/14:00',
'info_dict': {
'id': '14:00',
'title': 'Выпуск новостей в 14:00 1 декабря 2016 года. Новости. Первый канал',
'description': 'md5:2e921b948f8c1ff93901da78ebdb1dfd',
'title': 'Выпуск программы «Время» в 20:00 1 декабря 2016 года. Новости. Первый канал',
'thumbnail': 'https://static.1tv.ru/uploads/photo/image/8/big/338448_big_8fc7eb236f.jpg',
},
'playlist_count': 13,
}, {
# has timestamp; has item.uid but not item.id
'url': 'https://www.1tv.ru/shows/segodnya-vecherom/vypuski/avtory-odnogo-hita-segodnya-vecherom-vypusk-ot-03-05-2025',
'info_dict': {
'id': '270411',
'ext': 'mp4',
'title': 'Авторы одного хита. Сегодня вечером. Выпуск от 03.05.2025',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1746286020,
'upload_date': '20250503',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016',
'only_matching': True,
@@ -57,96 +72,60 @@ class FirstTVIE(InfoExtractor):
'only_matching': True,
}]
def _entries(self, items):
for item in items:
video_id = str(item.get('id') or item['uid'])
formats, subtitles = [], {}
for f in traverse_obj(item, ('sources', lambda _, v: url_or_none(v['src']))):
src = f['src']
ext = mimetype2ext(f.get('type'), default=determine_ext(src))
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
src, video_id, 'mp4', m3u8_id='hls', fatal=False)
elif ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(
src, video_id, mpd_id='dash', fatal=False)
else:
tbr = self._search_regex(fr'_(\d{{3,}})\.{ext}', src, 'tbr', default=None)
formats.append({
'url': src,
'ext': ext,
'format_id': join_nonempty('http', ext, tbr),
'tbr': int_or_none(tbr),
# quality metadata of http formats may be incorrect
'quality': -10,
})
continue
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
yield {
**traverse_obj(item, {
'title': ('title', {str}),
'thumbnail': ('poster', {url_or_none}),
'timestamp': ('dvr_begin_at', {int_or_none}),
'upload_date': ('date_air', {unified_strdate}),
'duration': ('duration', {int_or_none}),
}),
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
playlist_url = urllib.parse.urljoin(url, self._search_regex(
playlist_url = urllib.parse.urljoin(url, self._html_search_regex(
r'data-playlist-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'playlist url', group='url'))
parsed_url = urllib.parse.urlparse(playlist_url)
qs = urllib.parse.parse_qs(parsed_url.query)
item_ids = qs.get('videos_ids[]') or qs.get('news_ids[]')
item_ids = traverse_obj(parse_qs(playlist_url), 'video_id', 'videos_ids[]', 'news_ids[]')
items = traverse_obj(
self._download_json(playlist_url, display_id),
lambda _, v: v['uid'] and (str(v['uid']) in item_ids if item_ids else True))
items = self._download_json(playlist_url, display_id)
if item_ids:
items = [
item for item in items
if item.get('uid') and str(item['uid']) in item_ids]
else:
items = [items[0]]
entries = []
QUALITIES = ('ld', 'sd', 'hd')
for item in items:
title = item['title']
quality = qualities(QUALITIES)
formats = []
path = None
for f in item.get('mbr', []):
src = url_or_none(f.get('src'))
if not src:
continue
tbr = int_or_none(self._search_regex(
r'_(\d{3,})\.mp4', src, 'tbr', default=None))
if not path:
path = self._search_regex(
r'//[^/]+/(.+?)_\d+\.mp4', src,
'm3u8 path', default=None)
formats.append({
'url': src,
'format_id': f.get('name'),
'tbr': tbr,
'source_preference': quality(f.get('name')),
# quality metadata of http formats may be incorrect
'preference': -10,
})
# m3u8 URL format is reverse engineered from [1] (search for
# master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
# is taken from [2].
# 1. http://static.1tv.ru/player/eump1tv-current/eump-1tv.all.min.js?rnd=9097422834:formatted
# 2. http://static.1tv.ru/player/eump1tv-config/config-main.js?rnd=9097422834
if not path and len(formats) == 1:
path = self._search_regex(
r'//[^/]+/(.+?$)', formats[0]['url'],
'm3u8 path', default=None)
if path:
if len(formats) == 1:
m3u8_path = ','
else:
tbrs = [str(t) for t in sorted(f['tbr'] for f in formats)]
m3u8_path = '_,{},{}'.format(','.join(tbrs), '.mp4')
formats.extend(self._extract_m3u8_formats(
f'http://balancer-vod.1tv.ru/{path}{m3u8_path}.urlset/master.m3u8',
display_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)
duration = int_or_none(item.get('duration') or self._html_search_meta(
'video:duration', webpage, 'video duration', fatal=False))
upload_date = unified_strdate(self._html_search_meta(
'ya:ovs:upload_date', webpage, 'upload date', default=None))
entries.append({
'id': str(item.get('id') or item['uid']),
'thumbnail': thumbnail,
'title': title,
'upload_date': upload_date,
'duration': int_or_none(duration),
'formats': formats,
})
title = self._html_search_regex(
(r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
r"'title'\s*:\s*'([^']+)'"),
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None)
description = self._html_search_regex(
r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
webpage, 'description', default=None) or self._html_search_meta(
'description', webpage, 'description', default=None)
return self.playlist_result(entries, display_id, title, description)
return self.playlist_result(
self._entries(items), display_id, self._og_search_title(webpage, default=None),
thumbnail=self._og_search_thumbnail(webpage, default=None))
plugins/youtube_download/yt_dlp/extractor/flextv.py
+22 -7
View File
@@ -3,15 +3,19 @@ from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
UserNotLive,
int_or_none,
join_nonempty,
parse_iso8601,
str_or_none,
traverse_obj,
url_or_none,
)
from ..utils.traversal import traverse_obj
class FlexTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?flextv\.co\.kr/channels/(?P<id>\d+)/live'
IE_NAME = 'ttinglive'
IE_DESC = '띵라이브 (formerly FlexTV)'
_VALID_URL = r'https?://(?:www\.)?(?:ttinglive\.com|flextv\.co\.kr)/channels/(?P<id>\d+)/live'
_TESTS = [{
'url': 'https://www.flextv.co.kr/channels/231638/live',
'info_dict': {
@@ -36,21 +40,32 @@ class FlexTVIE(InfoExtractor):
try:
stream_data = self._download_json(
f'https://api.flextv.co.kr/api/channels/{channel_id}/stream',
f'https://api.ttinglive.com/api/channels/{channel_id}/stream',
channel_id, query={'option': 'all'})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
raise UserNotLive(video_id=channel_id)
raise
playlist_url = stream_data['sources'][0]['url']
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
playlist_url, channel_id, 'mp4')
formats = []
for stream in traverse_obj(stream_data, ('sources', ..., {dict})):
if stream.get('format') == 'ivs' and url_or_none(stream.get('url')):
formats.extend(self._extract_m3u8_formats(
stream['url'], channel_id, 'mp4', live=True, fatal=False, m3u8_id='ivs'))
for format_type in ['hls', 'flv']:
for data in traverse_obj(stream, (
'urlDetail', format_type, 'resolution', lambda _, v: url_or_none(v['url']))):
formats.append({
'format_id': join_nonempty(format_type, data.get('suffixName'), delim=''),
'url': data['url'],
'height': int_or_none(data.get('resolution')),
'ext': 'mp4' if format_type == 'hls' else 'flv',
'protocol': 'm3u8_native' if format_type == 'hls' else 'http',
})
return {
'id': channel_id,
'formats': formats,
'subtitles': subtitles,
'is_live': True,
**traverse_obj(stream_data, {
'title': ('stream', 'title', {str}),
plugins/youtube_download/yt_dlp/extractor/floatplane.py
+134 -98
View File
@@ -17,8 +17,140 @@ from ..utils import (
from ..utils.traversal import traverse_obj
class FloatplaneIE(InfoExtractor):
class FloatplaneBaseIE(InfoExtractor):
def _real_extract(self, url):
post_id = self._match_id(url)
post_data = self._download_json(
f'{self._BASE_URL}/api/v3/content/post', post_id, query={'id': post_id},
note='Downloading post data', errnote='Unable to download post data',
impersonate=self._IMPERSONATE_TARGET)
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
raise ExtractorError('Post does not contain a video or audio track', expected=True)
uploader_url = format_field(
post_data, [('creator', 'urlname')], f'{self._BASE_URL}/channel/%s/home') or None
common_info = {
'uploader_url': uploader_url,
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
'availability': self._availability(needs_subscription=True),
**traverse_obj(post_data, {
'uploader': ('creator', 'title', {str}),
'uploader_id': ('creator', 'id', {str}),
'channel': ('channel', 'title', {str}),
'channel_id': ('channel', 'id', {str}),
'release_timestamp': ('releaseDate', {parse_iso8601}),
}),
}
items = []
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
media_id = media['id']
media_typ = media.get('type') or 'video'
metadata = self._download_json(
f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id, query={'id': media_id},
note=f'Downloading {media_typ} metadata', impersonate=self._IMPERSONATE_TARGET)
stream = self._download_json(
f'{self._BASE_URL}/api/v2/cdn/delivery', media_id, query={
'type': 'vod' if media_typ == 'video' else 'aod',
'guid': metadata['guid'],
}, note=f'Downloading {media_typ} stream data',
impersonate=self._IMPERSONATE_TARGET)
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
formats = []
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
url = urljoin(stream['cdn'], format_path(traverse_obj(
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
format_id = traverse_obj(quality, ('name', {str}))
hls_aes = {}
m3u8_data = None
# If we need impersonation for the API, then we need it for HLS keys too: extract in advance
if self._IMPERSONATE_TARGET is not None:
m3u8_data = self._download_webpage(
url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
if not m3u8_data:
continue
key_url = self._search_regex(
r'#EXT-X-KEY:METHOD=AES-128,URI="(https?://[^"]+)"',
m3u8_data, 'HLS AES key URI', default=None)
if key_url:
urlh = self._request_webpage(
key_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
note=join_nonempty('Downloading', format_id, 'HLS AES key', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'HLS AES key', delim=' '))
if urlh:
hls_aes['key'] = urlh.read().hex()
formats.append({
**traverse_obj(quality, {
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
'format_id': format_id,
'hls_media_playlist_data': m3u8_data,
'hls_aes': hls_aes or None,
})
items.append({
**common_info,
'id': media_id,
**traverse_obj(metadata, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
})
post_info = {
**common_info,
'id': post_id,
'display_id': post_id,
**traverse_obj(post_data, {
'title': ('title', {str}),
'description': ('text', {clean_html}),
'like_count': ('likes', {int_or_none}),
'dislike_count': ('dislikes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'http_headers': self._HEADERS,
}
if len(items) > 1:
return self.playlist_result(items, **post_info)
post_info.update(items[0])
return post_info
class FloatplaneIE(FloatplaneBaseIE):
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/post/(?P<id>\w+)'
_BASE_URL = 'https://www.floatplane.com'
_IMPERSONATE_TARGET = None
_HEADERS = {
'Origin': _BASE_URL,
'Referer': f'{_BASE_URL}/',
}
_TESTS = [{
'url': 'https://www.floatplane.com/post/2Yf3UedF7C',
'info_dict': {
@@ -170,105 +302,9 @@ class FloatplaneIE(InfoExtractor):
}]
def _real_initialize(self):
if not self._get_cookies('https://www.floatplane.com').get('sails.sid'):
if not self._get_cookies(self._BASE_URL).get('sails.sid'):
self.raise_login_required()
def _real_extract(self, url):
post_id = self._match_id(url)
post_data = self._download_json(
'https://www.floatplane.com/api/v3/content/post', post_id, query={'id': post_id},
note='Downloading post data', errnote='Unable to download post data')
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
raise ExtractorError('Post does not contain a video or audio track', expected=True)
uploader_url = format_field(
post_data, [('creator', 'urlname')], 'https://www.floatplane.com/channel/%s/home') or None
common_info = {
'uploader_url': uploader_url,
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
'availability': self._availability(needs_subscription=True),
**traverse_obj(post_data, {
'uploader': ('creator', 'title', {str}),
'uploader_id': ('creator', 'id', {str}),
'channel': ('channel', 'title', {str}),
'channel_id': ('channel', 'id', {str}),
'release_timestamp': ('releaseDate', {parse_iso8601}),
}),
}
items = []
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
media_id = media['id']
media_typ = media.get('type') or 'video'
metadata = self._download_json(
f'https://www.floatplane.com/api/v3/content/{media_typ}', media_id, query={'id': media_id},
note=f'Downloading {media_typ} metadata')
stream = self._download_json(
'https://www.floatplane.com/api/v2/cdn/delivery', media_id, query={
'type': 'vod' if media_typ == 'video' else 'aod',
'guid': metadata['guid'],
}, note=f'Downloading {media_typ} stream data')
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
formats = []
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
url = urljoin(stream['cdn'], format_path(traverse_obj(
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
formats.append({
**traverse_obj(quality, {
'format_id': ('name', {str}),
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
})
items.append({
**common_info,
'id': media_id,
**traverse_obj(metadata, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
})
post_info = {
**common_info,
'id': post_id,
'display_id': post_id,
**traverse_obj(post_data, {
'title': ('title', {str}),
'description': ('text', {clean_html}),
'like_count': ('likes', {int_or_none}),
'dislike_count': ('dislikes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
}
if len(items) > 1:
return self.playlist_result(items, **post_info)
post_info.update(items[0])
return post_info
class FloatplaneChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'
plugins/youtube_download/yt_dlp/extractor/francaisfacile.py
+1 -12
View File
@@ -1,9 +1,7 @@
import urllib.parse
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
url_or_none,
)
@@ -58,16 +56,7 @@ class FrancaisFacileIE(InfoExtractor):
def _real_extract(self, url):
display_id = urllib.parse.unquote(self._match_id(url))
try: # yt-dlp's default user-agents are too old and blocked by the site
webpage = self._download_webpage(url, display_id, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
})
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
raise
# Retry with impersonation if hardcoded UA is insufficient
webpage = self._download_webpage(url, display_id, impersonate=True)
webpage = self._download_webpage(url, display_id)
data = self._search_json(
r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',
plugins/youtube_download/yt_dlp/extractor/francetv.py
+25 -28
View File
@@ -1,4 +1,3 @@
import json
import re
import urllib.parse
@@ -19,7 +18,11 @@ from ..utils import (
unsmuggle_url,
url_or_none,
)
from ..utils.traversal import find_element, traverse_obj
from ..utils.traversal import (
find_element,
get_first,
traverse_obj,
)
class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -121,9 +124,10 @@ class FranceTVIE(InfoExtractor):
elif code := traverse_obj(dinfo, ('code', {int})):
if code == 2009:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
elif code in (2015, 2017):
elif code in (2015, 2017, 2019):
# 2015: L'accès à cette vidéo est impossible. (DRM-only)
# 2017: Cette vidéo n'est pas disponible depuis le site web mobile (b/c DRM)
# 2019: L'accès à cette vidéo est incompatible avec votre configuration. (DRM-only)
drm_formats = True
continue
self.report_warning(
@@ -258,7 +262,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
_TESTS = [{
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
'info_dict': {
'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1', # old: c5bda21d-2c6f-4470-8849-3d8327adb2ba'
'id': 'b2cf9fd8-e971-4757-8651-848f2772df61', # old: ec217ecc-0733-48cf-ac06-af1347b849d1
'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus',
'timestamp': 1502623500,
@@ -269,7 +273,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
'skip': 'Unfortunately, this video is no longer available',
}, {
# geo-restricted
'url': 'https://www.france.tv/enfants/six-huit-ans/foot2rue/saison-1/3066387-duel-au-vieux-port.html',
@@ -287,7 +291,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1441,
},
'skip': 'No longer available',
'skip': 'Unfortunately, this video is no longer available',
}, {
# geo-restricted livestream (workflow == 'token-akamai')
'url': 'https://www.france.tv/france-4/direct.html',
@@ -308,6 +312,19 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'live_status': 'is_live',
},
'params': {'skip_download': 'livestream'},
}, {
# Not geo-restricted
'url': 'https://www.france.tv/france-2/la-maison-des-maternelles/5574051-nous-sommes-amis-et-nous-avons-fait-un-enfant-ensemble.html',
'info_dict': {
'id': 'b448bfe4-9fe7-11ee-97d8-2ba3426fa3df',
'ext': 'mp4',
'title': 'Nous sommes amis et nous avons fait un enfant ensemble - Émission du jeudi 21 décembre 2023',
'duration': 1065,
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1703147921,
'upload_date': '20231221',
},
'params': {'skip_download': 'm3u8'},
}, {
# france3
'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
@@ -342,31 +359,11 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'only_matching': True,
}]
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.goplay
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nextjs_data = traverse_obj(
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
(..., {json.loads}, ..., {self._find_json}, ..., 'children', ..., ..., 'children', ..., ..., 'children'))
if traverse_obj(nextjs_data, (..., ..., 'children', ..., 'isLive', {bool}, any)):
# For livestreams we need the id of the stream instead of the currently airing episode id
video_id = traverse_obj(nextjs_data, (
..., ..., 'children', ..., 'children', ..., 'children', ..., 'children', ..., ...,
'children', ..., ..., 'children', ..., ..., 'children', (..., (..., ...)),
'options', 'id', {str}, any))
else:
video_id = traverse_obj(nextjs_data, (
..., ..., ..., 'children',
lambda _, v: v['video']['url'] == urllib.parse.urlparse(url).path,
'video', ('playerReplayId', 'siId'), {str}, any))
nextjs_data = self._search_nextjs_v13_data(webpage, display_id)
video_id = get_first(nextjs_data, ('options', 'id', {str}))
if not video_id:
raise ExtractorError('Unable to extract video ID')
plugins/youtube_download/yt_dlp/extractor/fujitv.py
+1 -1
View File
@@ -56,7 +56,7 @@ class FujiTVFODPlus7IE(InfoExtractor):
fmt, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, 'ts')
for f in fmt:
f.update(dict(zip(('height', 'width'),
self._BITRATE_MAP.get(f.get('tbr'), ()))))
self._BITRATE_MAP.get(f.get('tbr'), ()), strict=False)))
formats.extend(fmt)
subtitles = self._merge_subtitles(subtitles, subs)
plugins/youtube_download/yt_dlp/extractor/gamespot.py
+2 -2
View File
@@ -1,9 +1,9 @@
import urllib.parse
from .once import OnceIE
from .common import InfoExtractor
class GameSpotIE(OnceIE):
class GameSpotIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
plugins/youtube_download/yt_dlp/extractor/generic.py
+501 -2100
View File
File diff suppressed because it is too large Load Diff
plugins/youtube_download/yt_dlp/extractor/glomex.py
+21 -4
View File
@@ -112,16 +112,17 @@ class GlomexIE(GlomexBaseIE):
_TESTS = [{
'url': 'https://video.glomex.com/sport/v-cb24uwg77hgh-nach-2-0-sieg-guardiola-mit-mancity-vor-naechstem-titel',
'md5': 'cec33a943c4240c9cb33abea8c26242e',
'info_dict': {
'id': 'v-cb24uwg77hgh',
'ext': 'mp4',
'title': 'md5:38a90cedcfadd72982c81acf13556e0c',
'title': 'Nach 2:0-Sieg: Guardiola mit ManCity vor nächstem Titel',
'description': 'md5:1ea6b6caff1443fcbbba159e432eedb8',
'duration': 29600,
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
'timestamp': 1619895017,
'upload_date': '20210501',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
@@ -140,16 +141,17 @@ class GlomexEmbedIE(GlomexBaseIE):
_TESTS = [{
'url': 'https://player.glomex.com/integration/1/iframe-player.html?integrationId=4059a013k56vb2yd&playlistId=v-cfa6lye0dkdd-sf',
'md5': '68f259b98cc01918ac34180142fce287',
'info_dict': {
'id': 'v-cfa6lye0dkdd-sf',
'ext': 'mp4',
'title': 'Φώφη Γεννηματά: Ο επικήδειος λόγος του 17χρονου γιου της, Γιώργου',
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
'timestamp': 1635337199,
'duration': 133080,
'upload_date': '20211027',
'description': 'md5:e741185fc309310ff5d0c789b437be66',
'title': 'md5:35647293513a6c92363817a0fb0a7961',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://player.glomex.com/integration/1/iframe-player.html?origin=fullpage&integrationId=19syy24xjn1oqlpc&playlistId=rl-vcb49w1fb592p&playlistIndex=0',
'info_dict': {
@@ -157,12 +159,27 @@ class GlomexEmbedIE(GlomexBaseIE):
},
'playlist_count': 100,
}, {
# Geo-restricted
'url': 'https://player.glomex.com/integration/1/iframe-player.html?playlistId=cl-bgqaata6aw8x&integrationId=19syy24xjn1oqlpc',
'info_dict': {
'id': 'cl-bgqaata6aw8x',
},
'playlist_mincount': 2,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.skai.gr/news/world/iatrikos-syllogos-tourkias-to-turkovac-aplo-dialyma-erntogan-eiste-apateones-kai-pseytes',
'info_dict': {
'id': 'v-ch2nkhcirwc9-sf',
'ext': 'mp4',
'title': 'Ιατρικός Σύλλογος Τουρκίας: Το Turkovac είναι ένα απλό διάλυμα –Ερντογάν: Είστε απατεώνες και ψεύτες',
'description': 'md5:8b517a61d577efe7e36fde72fd535995',
'duration': 460000,
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
'timestamp': 1641885019,
'upload_date': '20220111',
},
'params': {'skip_download': 'm3u8'},
}]
@classmethod
def build_player_url(cls, video_id, integration, origin_url=None):
plugins/youtube_download/yt_dlp/extractor/go.py
+147 -175
View File
@@ -7,161 +7,157 @@ from ..utils import (
int_or_none,
join_nonempty,
parse_age_limit,
remove_end,
remove_start,
traverse_obj,
try_get,
unified_timestamp,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class GoIE(AdobePassIE):
_SITE_INFO = {
'abc': {
'brand': '001',
'requestor_id': 'ABC',
'requestor_id': 'dtci',
'provider_id': 'ABC',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI4OTcwMjlkYS0yYjM1LTQyOWUtYWQ0NS02ZjZiZjVkZTdhOTUiLCJuYmYiOjE2MjAxNzM5NjksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNjIwMTczOTY5fQ.SC69DVJWSL8sIe-vVUrP6xS_kzHKqwz9PdKYexs_y-f7Vin6mM-7S-W1TE_-K55O0pyf-TL4xYgvm6LIye8CckG-nZfVwNPV4huduov0jmIcxCQFeUwkHULG2IaA44wfBVUBdaHgkhPweZ2amjycO_IXtez-gBXOLbE3B7Gx9j_5ISCFtyVUblThKfoGyQv6KT6t8Vpmc4ZSKCCQp74KWFFypydb9ucego1taW_nQD06Cdf4yByLd6NaTBceMcIKbug9b9gxFm3XBgJ5q3z7KGo1Kr6XalAV5j4m-fQ91wczlTilX8FM4AljMupyRM9mA_aEADILQ4hS79q4SM0w6w',
},
'freeform': {
'brand': '002',
'requestor_id': 'ABCFamily',
},
'watchdisneychannel': {
'brand': '004',
'resource_id': 'Disney',
},
'watchdisneyjunior': {
'brand': '008',
'resource_id': 'DisneyJunior',
},
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
'provider_id': 'ABCFamily',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhZWM2MGYyNC0xYzRjLTQ1NzQtYjc0Zi03ZmM4N2E5YWMzMzgiLCJuYmYiOjE1ODc2NjU5MjMsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NjY1OTIzfQ.flCn3dhvmvPnWmV0JV8Fm0YFyj07yPez9-n1GFEwVIm_S2wQVWbWyJhqsAyLZVFrhOMZYTqmPS3OHxGwTwXkEYn6PD7o_vIVG3oqi-Xn1m5jRt_Gazw5qEtpat6VE7bvKGSD3ZhcidOrsCk8NcYyq75u61NHDvSl81pcedJjVRVUpsqrEwmo0aVbA0C8PX3ri0mEbGvkMKvHn8E60xp-PSE-VK8SDT0plwPu_TwUszkZ6-_I8_2xcv_WBqcXFkAVg7Q-iNJXgQvmNsrpcrYuLvi6hEH4ZLtoDcXU6MhwTQAJTiHSo8x9aHX1_qFP09CzlNOFQbC2ZEJdP9SvA53SLQ',
},
'disneynow': {
'brand': '011',
'brand': '011', # also: '004', '008', '009'
'requestor_id': 'DisneyChannels',
'provider_id': 'DisneyChannels',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzAzNTRiOS04NDNiLTRkNjAtYTQ3ZS0yNzk1MzlkOTIyNTciLCJuYmYiOjE1NTg5ODc0NDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTU4OTg3NDQ5fQ.Jud6YS6-J2h0h6po0oMheDym0qRTJQGj4kzacrz4DFuEwhcBkkykW6pF5pKuAUJy9HCZ40oDAHe2KcTlDJjCZF5tDaUEfdihakZ9cC_rG7MU-QoRne8qaB_dPDKwGuk-ZyWD8eV3zwTJmbGo8hDxYTEU81YNCxwhyc_BPDr5TYiubbmpP3_pTnXmSpuL58isJ2peSKWlX9BacuXtBY25c_QnPFKk-_EETm7IHkTpDazde1QfHWGu4s4yJpKGk8RVVujVG6h6ELlL-ZeYLilBm7iS7h1TYG1u7fJhyZRL7isaom6NvAzsvN3ngss1fLwt8decP8wzdFHrbYTdTjW8qw',
'resource_id': 'Disney',
},
'fxnow.fxnetworks': {
'brand': '025',
'fxnetworks': {
'brand': '025', # also: '020'
'requestor_id': 'dtci',
'provider_id': 'fx', # also 'fxx', 'fxm'
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIzYWRhYWZiNC02OTAxLTRlYzktOTdmNy1lYWZkZTJkODJkN2EiLCJuYmYiOjE1NjIwMjQwNzYsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDI0MDc2fQ.dhKMpZK50AObbZYrMiYPSfWtzXHUaeMP3jrIY4Cgfvh0GaEgk0Mns_zp78jypFeZgRtPVleQMQDNq2YEloRLcAGqP1aa6WVDglnK77ZWUm4IKai14Rwf3A6YBhSRoO2_lMmUGkuTf6gZY-kMIPqBYKqzTQiQl4HbniPFodIzFRiuI9QJVrkoyTGrJL4oqiX08PoFI3Z-TOti1Heu3EbFC-GveQHhlinYrzU7rbiAqLEz7FImtfBDsnXX1Y3uJDLYM3Bq4Oh0nrzTv1Fd62wNsCNErHHIbELidh1zZF0ujvt7ReuZUwAitm0UhEJ7OxNOUbEQWtae6pVNscvdvTFMpg',
},
'nationalgeographic': {
'brand': '026', # also '023'
'requestor_id': 'dtci',
'provider_id': 'ngc', # also 'ngw'
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxMzE4YTM1Ni05Mjc4LTQ4NjEtYTFmNi1jMTIzMzg1ZWMzYzMiLCJuYmYiOjE1NjIwMjM4MjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDIzODI4fQ.Le-2OzF9-jrhJ7ZfWtLWk5iSHGVZoxeU1w0_fO--Heli0OwRZsRq2slSmx-oZTzxuWmAgDEiBkWSDcDK6sM25DrCLsdsJa3MBuZ-slBRtH8aq3HpNoqqLkU-vg6gRUEKMtwBUtwCu_9aKUCayYtndWv4b1DjVQeSrteOW5NNudWVYleAe0kxeNJQHo5If9SCzDudKVJktFUjhNks4QPOC_uONPkRRlL9D0fNvtOY-LRFckfcHhf5z9l1iZjeukV0YhdKnuw1wyiaWrQXBUDiBfbkCRd2DM-KnelqPxfiXCaTjGKDURRBO3pz33ebge3IFXSiU5vl4qHQ8xvunzGpFw',
},
}
_VALID_URL = r'''(?x)
https?://
(?P<sub_domain>
(?:{}\.)?go|fxnow\.fxnetworks|
(?:www\.)?(?:abc|freeform|disneynow)
)\.com/
(?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+)
)
'''.format(r'\.|'.join(list(_SITE_INFO.keys())))
_URL_PATH_RE = r'(?:video|episode|movies-and-specials)/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_VALID_URL = [
fr'https?://(?:www\.)?(?P<site>abc)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>freeform)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>disneynow)\.com/{_URL_PATH_RE}',
fr'https?://fxnow\.(?P<site>fxnetworks)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>nationalgeographic)\.com/tv/{_URL_PATH_RE}',
]
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'url': 'https://abc.com/episode/4192c0e6-26e5-47a8-817b-ce8272b9e440/playlist/PL551127435',
'info_dict': {
'id': 'VDKA3807643',
'id': 'VDKA10805898',
'ext': 'mp4',
'title': 'The Traitor in the White House',
'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'This content is no longer available.',
}, {
'url': 'https://disneynow.com/shows/big-hero-6-the-series',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': {
'id': 'VDKA3609139',
'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'title': 'Switch the Flip',
'description': 'To help get Brian’s life in order, Stewie and Brian swap bodies using a machine that Stewie invents.',
'age_limit': 14,
'duration': 1297,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Family Guy',
'season': 'Season 16',
'season_number': 16,
'episode': 'Episode 17',
'episode_number': 17,
'timestamp': 1746082800.0,
'upload_date': '20250501',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://disneynow.com/episode/21029660-ba06-4406-adb0-a9a78f6e265e/playlist/PL553044961',
'info_dict': {
'id': 'VDKA39546942',
'ext': 'mp4',
'title': 'Zero Friends Again',
'description': 'Relationships fray under the pressures of a difficult journey.',
'age_limit': 0,
'duration': 1721,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Star Wars: Skeleton Crew',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 6',
'episode_number': 6,
'timestamp': 1746946800.0,
'upload_date': '20250511',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://fxnow.fxnetworks.com/episode/09f4fa6f-c293-469e-aebe-32c9ca5842a7/playlist/PL554408064',
'info_dict': {
'id': 'VDKA38112033',
'ext': 'mp4',
'title': 'The Return of Jerry',
'description': 'The vampires’ long-lost fifth roommate returns. Written by Paul Simms; directed by Kyle Newacheck.',
'age_limit': 17,
'duration': 1493,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'What We Do in the Shadows',
'season': 'Season 6',
'season_number': 6,
'episode': 'Episode 1',
'upload_date': '20170102',
'season': 'Season 2',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abcf/Shadowhunters/video/201/ae5f75608d86bf88aa4f9f4aa76ab1b7/579x325-Q100_ae5f75608d86bf88aa4f9f4aa76ab1b7.jpg',
'duration': 2544,
'season_number': 2,
'series': 'Shadowhunters',
'episode_number': 1,
'timestamp': 1483387200,
'ext': 'mp4',
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'timestamp': 1729573200.0,
'upload_date': '20241022',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/12-the-knock',
'url': 'https://www.freeform.com/episode/bda0eaf7-761a-4838-aa44-96f794000844/playlist/PL553044961',
'info_dict': {
'id': 'VDKA26050359',
'title': 'The Knock',
'description': 'md5:0c2947e3ada4c31f28296db7db14aa64',
'age_limit': 14,
'id': 'VDKA39007340',
'ext': 'mp4',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abc/TheRookie/video/412/daf830d06e83b11eaf5c0a299d993ae3/1556x876-Q75_daf830d06e83b11eaf5c0a299d993ae3.jpg',
'episode': 'Episode 12',
'season_number': 4,
'season': 'Season 4',
'timestamp': 1642975200,
'episode_number': 12,
'upload_date': '20220123',
'series': 'The Rookie',
'duration': 2572,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'title': 'Angel\'s Landing',
'description': 'md5:91bf084e785c968fab16734df7313446',
'age_limit': 14,
'duration': 2523,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'How I Escaped My Cult',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'timestamp': 1740038400.0,
'upload_date': '20250220',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
'url': 'https://www.nationalgeographic.com/tv/episode/ca694661-1186-41ae-8089-82f64d69b16d/playlist/PL554408064',
'info_dict': {
'id': 'VDKA12782841',
'title': 'First Look: Better Things - Season 2',
'description': 'md5:fa73584a95761c605d9d54904e35b407',
'id': 'VDKA39492078',
'ext': 'mp4',
'age_limit': 14,
'upload_date': '20170825',
'duration': 161,
'series': 'Better Things',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/fx/BetterThings/video/12782841/b6b05e58264121cc2c98811318e6d507/1556x876-Q75_b6b05e58264121cc2c98811318e6d507.jpg',
'timestamp': 1503661074,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'title': 'Heart of the Emperors',
'description': 'md5:4fc50a2878f030bb3a7eac9124dca677',
'age_limit': 0,
'duration': 2775,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Secrets of the Penguins',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
'timestamp': 1745204400.0,
'upload_date': '20250421',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'url': 'https://www.freeform.com/movies-and-specials/c38281fc-9f8f-47c7-8220-22394f9df2e1',
'only_matching': True,
}, {
'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
'only_matching': True,
}, {
# brand 004
'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
'only_matching': True,
}, {
# brand 008
'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
'url': 'https://abc.com/video/219a454a-172c-41bf-878a-d169e6bc0bdc/playlist/PL5523098420',
'only_matching': True,
}]
@@ -171,58 +167,29 @@ class GoIE(AdobePassIE):
f'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/{brand}/001/-1/{show_id}/-1/{video_id}/-1/-1.json',
display_id)['video']
def _extract_global_var(self, name, webpage, video_id):
return self._search_json(
fr'window\[["\']{re.escape(name)}["\']\]\s*=',
webpage, f'{name.strip("_")} JSON', video_id)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
data = self._parse_json(
self._search_regex(
r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
'data', default='{}'),
display_id or video_id, fatal=False)
# https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
video_id = None
if layout:
video_id = try_get(
layout,
(lambda x: x['videoid'], lambda x: x['video']['id']),
str)
if not video_id:
video_id = self._search_regex(
(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)',
# page.analytics.videoIdCode
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
# https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)',
), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',
r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
default='004')
site_info = next(
si for _, si in self._SITE_INFO.items()
if si.get('brand') == brand)
if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(
video['url'], 'Go', video.get('id'), video.get('title')))
entries.reverse()
return self.playlist_result(entries, show_id, show_title)
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
config = self._extract_global_var('__CONFIG__', webpage, display_id)
data = self._extract_global_var(config['globalVar'], webpage, display_id)
video_id = traverse_obj(data, (
'page', 'content', 'video', 'layout', (('video', 'id'), 'videoid'), {str}, any))
if not video_id:
video_id = self._search_regex([
# data-track-video_id="VDKA39492078"
# data-track-video_id_code="vdka39492078"
# data-video-id="'VDKA3609139'"
r'data-(?:track-)?video[_-]id(?:_code)?=["\']*((?:vdka|VDKA)\d+)',
# page.analytics.videoIdCode
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\d+)'], webpage, 'video ID')
site_info = self._SITE_INFO[site]
brand = site_info['brand']
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title']
@@ -238,26 +205,31 @@ class GoIE(AdobePassIE):
if ext == 'm3u8':
video_type = video_data.get('type')
data = {
'video_id': video_data['id'],
'video_id': video_id,
'video_type': video_type,
'brand': brand,
'device': '001',
'app_name': 'webplayer-abc',
}
if video_data.get('accesslevel') == '1':
requestor_id = site_info.get('requestor_id', 'DisneyChannels')
provider_id = site_info['provider_id']
software_statement = traverse_obj(data, ('app', 'config', (
('features', 'auth', 'softwareStatement'),
('tvAuth', 'SOFTWARE_STATEMENTS', 'PRODUCTION'),
), {str}, any)) or site_info['software_statement']
resource = site_info.get('resource_id') or self._get_mvpd_resource(
requestor_id, title, video_id, None)
provider_id, title, video_id, None)
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
url, video_id, site_info['requestor_id'], resource, software_statement)
data.update({
'token': auth,
'token_type': 'ap',
'adobe_requestor_id': requestor_id,
'adobe_requestor_id': provider_id,
})
else:
self._initialize_geo_bypass({'countries': ['US']})
entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
'https://prod.gatekeeper.us-abc.symphony.edgedatg.go.com/vp2/ws-secure/entitlement/2020/playmanifest_secure.json',
video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
@@ -267,7 +239,7 @@ class GoIE(AdobePassIE):
error['message'], countries=['US'])
error_message = ', '.join([error['message'] for error in errors])
raise ExtractorError(f'{self.IE_NAME} said: {error_message}', expected=True)
asset_url += '?' + entitlement['uplynkData']['sessionKey']
asset_url += '?' + entitlement['entitlement']['uplynkData']['sessionKey']
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)
formats.extend(fmts)
plugins/youtube_download/yt_dlp/extractor/googledrive.py
+14 -10
View File
@@ -12,6 +12,7 @@ from ..utils import (
get_element_html_by_id,
int_or_none,
lowercase_escape,
parse_qs,
try_get,
update_url_query,
)
@@ -111,14 +112,18 @@ class GoogleDriveIE(InfoExtractor):
self._caption_formats_ext.append(f.attrib['fmt_code'])
def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
origin_lang_code=None):
origin_lang_code=None, origin_lang_name=None):
if not subtitles_id or not caption_type:
return
captions = {}
for caption_entry in self._captions_xml.findall(
self._CAPTIONS_ENTRY_TAG[caption_type]):
caption_lang_code = caption_entry.attrib.get('lang_code')
if not caption_lang_code:
caption_name = caption_entry.attrib.get('name') or origin_lang_name
if not caption_lang_code or not caption_name:
self.report_warning(f'Missing necessary caption metadata. '
f'Need lang_code and name attributes. '
f'Found: {caption_entry.attrib}')
continue
caption_format_data = []
for caption_format in self._caption_formats_ext:
@@ -129,7 +134,7 @@ class GoogleDriveIE(InfoExtractor):
'lang': (caption_lang_code if origin_lang_code is None
else origin_lang_code),
'type': 'track',
'name': '',
'name': caption_name,
'kind': '',
}
if origin_lang_code is not None:
@@ -155,14 +160,15 @@ class GoogleDriveIE(InfoExtractor):
self._download_subtitles_xml(video_id, subtitles_id, hl)
if not self._captions_xml:
return
track = self._captions_xml.find('track')
track = next((t for t in self._captions_xml.findall('track') if t.attrib.get('cantran') == 'true'), None)
if track is None:
return
origin_lang_code = track.attrib.get('lang_code')
if not origin_lang_code:
origin_lang_name = track.attrib.get('name')
if not origin_lang_code or not origin_lang_name:
return
return self._get_captions_by_type(
video_id, subtitles_id, 'automatic_captions', origin_lang_code)
video_id, subtitles_id, 'automatic_captions', origin_lang_code, origin_lang_name)
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -268,10 +274,8 @@ class GoogleDriveIE(InfoExtractor):
subtitles_id = None
ttsurl = get_value('ttsurl')
if ttsurl:
# the video Id for subtitles will be the last value in the ttsurl
# query string
subtitles_id = ttsurl.encode().decode(
'unicode_escape').split('=')[-1]
# the subtitles ID is the vid param of the ttsurl query
subtitles_id = parse_qs(ttsurl).get('vid', [None])[-1]
self.cookiejar.clear(domain='.google.com', path='/', name='NID')
plugins/youtube_download/yt_dlp/extractor/goplay.py
+15 -29
View File
@@ -5,16 +5,11 @@ import hashlib
import hmac
import json
import os
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
remove_end,
traverse_obj,
)
from ..utils import ExtractorError, int_or_none
from ..utils.traversal import get_first, traverse_obj
class GoPlayIE(InfoExtractor):
@@ -27,10 +22,10 @@ class GoPlayIE(InfoExtractor):
'info_dict': {
'id': '2baa4560-87a0-421b-bffc-359914e3c387',
'ext': 'mp4',
'title': 'S22 - Aflevering 1',
'title': 'De Slimste Mens ter Wereld - S22 - Aflevering 1',
'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
'series': 'De Slimste Mens ter Wereld',
'episode': 'Episode 1',
'episode': 'Wordt aangekondigd',
'season_number': 22,
'episode_number': 1,
'season': 'Season 22',
@@ -52,7 +47,7 @@ class GoPlayIE(InfoExtractor):
'info_dict': {
'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
'ext': 'mp4',
'title': 'S11 - Aflevering 1',
'title': 'De Mol - S11 - Aflevering 1',
'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
'episode': 'Episode 1',
'series': 'De Mol',
@@ -75,21 +70,13 @@ class GoPlayIE(InfoExtractor):
if not self._id_token:
raise self.raise_login_required(method='password')
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.francetv
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nextjs_data = traverse_obj(
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
(..., {json.loads}, ..., {self._find_json}, ...))
meta = traverse_obj(nextjs_data, (
..., ..., 'children', ..., ..., 'children',
lambda _, v: v['video']['path'] == urllib.parse.urlparse(url).path, 'video', any))
nextjs_data = self._search_nextjs_v13_data(webpage, display_id)
meta = get_first(nextjs_data, (
lambda k, v: k in ('video', 'meta') and v['path'] == urllib.parse.urlparse(url).path))
video_id = meta['uuid']
info_dict = traverse_obj(meta, {
@@ -98,19 +85,18 @@ class GoPlayIE(InfoExtractor):
})
if traverse_obj(meta, ('program', 'subtype')) != 'movie':
for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
episode_data = traverse_obj(
season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
for season_data in traverse_obj(nextjs_data, (..., 'playlists', ..., {dict})):
episode_data = traverse_obj(season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
if not episode_data:
continue
episode_title = traverse_obj(
episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
season_number = traverse_obj(season_data, ('season', {int_or_none}))
info_dict.update({
'title': episode_title or info_dict.get('title'),
'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
'season_number': traverse_obj(season_data, ('season', {int_or_none})),
'episode': traverse_obj(episode_data, ('episodeTitle', {str})),
'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
'season_number': season_number,
'series': self._search_regex(
fr'^(.+)? - S{season_number} - ', info_dict.get('title'), 'series', default=None),
})
break
plugins/youtube_download/yt_dlp/extractor/hotstar.py
+169 -154
View File
@@ -1,3 +1,4 @@
import functools
import hashlib
import hmac
import json
@@ -9,77 +10,126 @@ from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
filter_dict,
int_or_none,
join_nonempty,
jwt_decode_hs256,
parse_iso8601,
str_or_none,
traverse_obj,
url_or_none,
)
from ..utils.traversal import require, traverse_obj
class HotStarBaseIE(InfoExtractor):
_TOKEN_NAME = 'userUP'
_BASE_URL = 'https://www.hotstar.com'
_API_URL = 'https://api.hotstar.com'
_API_URL_V2 = 'https://apix.hotstar.com/v2'
_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
_FREE_HEADERS = {
'user-agent': 'Hotstar;in.startv.hotstar/25.06.30.0.11580 (Android/12)',
'x-hs-client': 'platform:android;app_id:in.startv.hotstar;app_version:25.06.30.0;os:Android;os_version:12;schema_version:0.0.1523',
'x-hs-platform': 'android',
}
_SUB_HEADERS = {
'user-agent': 'Disney+;in.startv.hotstar.dplus.tv/23.08.14.4.2915 (Android/13)',
'x-hs-client': 'platform:androidtv;app_id:in.startv.hotstar.dplus.tv;app_version:23.08.14.4;os:Android;os_version:13;schema_version:0.0.970',
'x-hs-platform': 'androidtv',
}
def _has_active_subscription(self, cookies, server_time):
server_time = int_or_none(server_time) or int(time.time())
expiry = traverse_obj(cookies, (
self._TOKEN_NAME, 'value', {jwt_decode_hs256}, 'sub', {json.loads},
'subscriptions', 'in', ..., 'expiry', {parse_iso8601}, all, {max})) or 0
return expiry > server_time
def _call_api_v1(self, path, *args, **kwargs):
return self._download_json(
f'{self._API_URL}/o/v1/{path}', *args, **kwargs,
headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
def _call_api_impl(self, path, video_id, query, cookies=None, st=None):
st = int_or_none(st) or int(time.time())
exp = st + 6000
auth = f'st={st}~exp={exp}~acl=/*'
auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
if cookies and cookies.get('userUP'):
token = cookies.get('userUP').value
else:
token = self._download_json(
f'{self._API_URL}/um/v3/users',
video_id, note='Downloading token',
data=json.dumps({'device_ids': [{'id': str(uuid.uuid4()), 'type': 'device_id'}]}).encode(),
headers={
'hotstarauth': auth,
'x-hs-platform': 'PCTV', # or 'web'
'Content-Type': 'application/json',
})['user_identity']
response = self._download_json(
f'{self._API_URL}/{path}', video_id, query=query,
headers={
f'{self._API_URL_V2}/{path}', video_id, query=query,
headers=filter_dict({
**(self._SUB_HEADERS if self._has_active_subscription(cookies, st) else self._FREE_HEADERS),
'hotstarauth': auth,
'x-hs-appversion': '6.72.2',
'x-hs-platform': 'web',
'x-hs-usertoken': token,
})
'x-hs-usertoken': traverse_obj(cookies, (self._TOKEN_NAME, 'value')),
'x-hs-device-id': traverse_obj(cookies, ('deviceId', 'value')) or str(uuid.uuid4()),
'content-type': 'application/json',
}))
if response['message'] != "Playback URL's fetched successfully":
raise ExtractorError(
response['message'], expected=True)
return response['data']
if not traverse_obj(response, ('success', {dict})):
raise ExtractorError('API call was unsuccessful')
return response['success']
def _call_api_v2(self, path, video_id, st=None, cookies=None):
return self._call_api_impl(
f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
'device-id': cookies.get('device_id').value if cookies.get('device_id') else str(uuid.uuid4()),
'os-name': 'Windows',
'os-version': '10',
})
def _call_api_v2(self, path, video_id, content_type, cookies=None, st=None):
return self._call_api_impl(f'{path}', video_id, query={
'content_id': video_id,
'filters': f'content_type={content_type}',
'client_capabilities': json.dumps({
'package': ['dash', 'hls'],
'container': ['fmp4', 'fmp4br', 'ts'],
'ads': ['non_ssai', 'ssai'],
'audio_channel': ['stereo', 'dolby51', 'atmos'],
'encryption': ['plain', 'widevine'], # wv only so we can raise appropriate error
'video_codec': ['h264', 'h265'],
'video_codec_non_secure': ['h264', 'h265', 'vp9'],
'ladder': ['phone', 'tv', 'full'],
'resolution': ['hd', '4k'],
'true_resolution': ['hd', '4k'],
'dynamic_range': ['sdr', 'hdr'],
}, separators=(',', ':')),
'drm_parameters': json.dumps({
'widevine_security_level': ['SW_SECURE_DECODE', 'SW_SECURE_CRYPTO'],
'hdcp_version': ['HDCP_V2_2', 'HDCP_V2_1', 'HDCP_V2', 'HDCP_V1'],
}, separators=(',', ':')),
}, cookies=cookies, st=st)
def _playlist_entries(self, path, item_id, root=None, **kwargs):
results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
for video in traverse_obj(results, (('assets', None), 'items', ...)):
if video.get('contentId'):
yield self.url_result(
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
@staticmethod
def _parse_metadata_v1(video_data):
return traverse_obj(video_data, {
'id': ('contentId', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'duration': ('duration', {int_or_none}),
'timestamp': (('broadcastDate', 'startDate'), {int_or_none}, any),
'release_year': ('year', {int_or_none}),
'channel': ('channelName', {str}),
'channel_id': ('channelId', {int}, {str_or_none}),
'series': ('showName', {str}),
'season': ('seasonName', {str}),
'season_number': ('seasonNo', {int_or_none}),
'season_id': ('seasonId', {int}, {str_or_none}),
'episode': ('title', {str}),
'episode_number': ('episodeNo', {int_or_none}),
})
def _fetch_page(self, path, item_id, name, query, root, page):
results = self._call_api_v1(
path, item_id, note=f'Downloading {name} page {page + 1} JSON', query={
**query,
'tao': page * self._PAGE_SIZE,
'tas': self._PAGE_SIZE,
})['body']['results']
for video in traverse_obj(results, (('assets', None), 'items', lambda _, v: v['contentId'])):
yield self.url_result(
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, **self._parse_metadata_v1(video))
class HotStarIE(HotStarBaseIE):
IE_NAME = 'hotstar'
IE_DESC = 'JioHotstar'
_VALID_URL = r'''(?x)
https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
(?:
@@ -114,15 +164,16 @@ class HotStarIE(HotStarBaseIE):
'upload_date': '20190501',
'duration': 1219,
'channel': 'StarPlus',
'channel_id': '3',
'channel_id': '821',
'series': 'Ek Bhram - Sarvagun Sampanna',
'season': 'Chapter 1',
'season_number': 1,
'season_id': '6771',
'season_id': '1260004607',
'episode': 'Janhvi Targets Suman',
'episode_number': 8,
},
}, {
'params': {'skip_download': 'm3u8'},
}, { # Metadata call gets HTTP Error 504 with tas=10000
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
'info_dict': {
'id': '1000282843',
@@ -134,14 +185,14 @@ class HotStarIE(HotStarBaseIE):
'channel': 'StarPlus',
'series': 'Anupama',
'season_number': 1,
'season_id': '7399',
'season_id': '1260022018',
'upload_date': '20230307',
'episode': 'Anupama, Anuj Share a Moment',
'episode_number': 853,
'duration': 1272,
'channel_id': '3',
'duration': 1266,
'channel_id': '821',
},
'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
'info_dict': {
@@ -154,14 +205,15 @@ class HotStarIE(HotStarBaseIE):
'channel': 'Hotstar Specials',
'series': 'Kana Kaanum Kaalangal',
'season_number': 1,
'season_id': '9441',
'season_id': '1260097089',
'upload_date': '20220421',
'episode': 'Back To School',
'episode_number': 1,
'duration': 1810,
'channel_id': '54',
'channel_id': '1260003991',
},
}, {
'params': {'skip_download': 'm3u8'},
}, { # Metadata call gets HTTP Error 504 with tas=10000
'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
'info_dict': {
'id': '1000262286',
@@ -173,6 +225,7 @@ class HotStarIE(HotStarBaseIE):
'timestamp': 1622943900,
'duration': 5395,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
'info_dict': {
@@ -180,12 +233,13 @@ class HotStarIE(HotStarBaseIE):
'ext': 'mp4',
'title': 'Premam',
'release_year': 2015,
'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
'description': 'md5:096cd8aaae8dab56524823dc19dfa9f7',
'timestamp': 1462149000,
'upload_date': '20160502',
'episode': 'Premam',
'duration': 8994,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
'only_matching': True,
@@ -208,6 +262,13 @@ class HotStarIE(HotStarBaseIE):
None: 'content',
}
_CONTENT_TYPE = {
'movie': 'MOVIE',
'episode': 'EPISODE',
'match': 'SPORT',
'content': 'CLIPS',
}
_IGNORE_MAP = {
'res': 'resolution',
'vcodec': 'video_codec',
@@ -229,38 +290,50 @@ class HotStarIE(HotStarBaseIE):
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
video_type = self._TYPE.get(video_type, video_type)
video_type = self._TYPE[video_type]
cookies = self._get_cookies(url) # Cookies before any request
if not cookies or not cookies.get(self._TOKEN_NAME):
self.raise_login_required()
video_data = traverse_obj(
self._call_api_v1(
f'{video_type}/detail', video_id, fatal=False, query={'tas': 10000, 'contentId': video_id}),
('body', 'results', 'item', {dict})) or {}
if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
self._call_api_v1(f'{video_type}/detail', video_id, fatal=False, query={
'tas': 5, # See https://github.com/yt-dlp/yt-dlp/issues/7946
'contentId': video_id,
}), ('body', 'results', 'item', {dict})) or {}
if video_data.get('drmProtected'):
self.report_drm(video_id)
# See https://github.com/yt-dlp/yt-dlp/issues/396
st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
geo_restricted = False
formats, subs = [], {}
formats, subs, has_drm = [], {}, False
headers = {'Referer': f'{self._BASE_URL}/in'}
content_type = traverse_obj(video_data, ('contentType', {str})) or self._CONTENT_TYPE[video_type]
# change to v2 in the future
playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
for playback_set in playback_sets:
if not isinstance(playback_set, dict):
continue
tags = str_or_none(playback_set.get('tagsCombination')) or ''
# See https://github.com/yt-dlp/yt-dlp/issues/396
st = self._request_webpage(
f'{self._BASE_URL}/in', video_id, 'Fetching server time').get_header('x-origin-date')
watch = self._call_api_v2('pages/watch', video_id, content_type, cookies, st)
player_config = traverse_obj(watch, (
'page', 'spaces', 'player', 'widget_wrappers', lambda _, v: v['template'] == 'PlayerWidget',
'widget', 'data', 'player_config', {dict}, any, {require('player config')}))
for playback_set in traverse_obj(player_config, (
('media_asset', 'media_asset_v2'),
('primary', 'fallback'),
all, lambda _, v: url_or_none(v['content_url']),
)):
tags = str_or_none(playback_set.get('playback_tags')) or ''
if any(f'{prefix}:{ignore}' in tags
for key, prefix in self._IGNORE_MAP.items()
for ignore in self._configuration_arg(key)):
continue
format_url = url_or_none(playback_set.get('playbackUrl'))
if not format_url:
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
if tag_dict.get('encryption') not in ('plain', None):
has_drm = True
continue
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', playback_set['content_url'])
ext = determine_ext(format_url)
current_formats, current_subs = [], {}
@@ -280,14 +353,12 @@ class HotStarIE(HotStarBaseIE):
'height': int_or_none(playback_set.get('height')),
}]
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
if isinstance(e.cause, HTTPError) and e.cause.status in (403, 474):
geo_restricted = True
else:
self.write_debug(e)
continue
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
if tag_dict.get('encryption') not in ('plain', None):
for f in current_formats:
f['has_drm'] = True
for f in current_formats:
for k, v in self._TAG_FIELDS.items():
if not f.get(k):
@@ -299,6 +370,11 @@ class HotStarIE(HotStarBaseIE):
'stereo': 2,
'dolby51': 6,
}.get(tag_dict.get('audio_channel'))
if (
'Audio_Description' in f['format_id']
or 'Audio Description' in (f.get('format_note') or '')
):
f['source_preference'] = -99 + (f.get('source_preference') or -1)
f['format_note'] = join_nonempty(
tag_dict.get('ladder'),
tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
@@ -308,29 +384,22 @@ class HotStarIE(HotStarBaseIE):
formats.extend(current_formats)
subs = self._merge_subtitles(subs, current_subs)
if not formats and geo_restricted:
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
if not formats:
if geo_restricted:
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
elif has_drm:
self.report_drm(video_id)
elif not self._has_active_subscription(cookies, st):
self.raise_no_formats('Your account does not have access to this content', expected=True)
self._remove_duplicate_formats(formats)
for f in formats:
f.setdefault('http_headers', {}).update(headers)
return {
**self._parse_metadata_v1(video_data),
'id': video_id,
'title': video_data.get('title'),
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
'release_year': int_or_none(video_data.get('year')),
'formats': formats,
'subtitles': subs,
'channel': video_data.get('channelName'),
'channel_id': str_or_none(video_data.get('channelId')),
'series': video_data.get('showName'),
'season': video_data.get('seasonName'),
'season_number': int_or_none(video_data.get('seasonNo')),
'season_id': str_or_none(video_data.get('seasonId')),
'episode': video_data.get('title'),
'episode_number': int_or_none(video_data.get('episodeNo')),
}
@@ -371,64 +440,6 @@ class HotStarPrefixIE(InfoExtractor):
return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
class HotStarPlaylistIE(HotStarBaseIE):
IE_NAME = 'hotstar:playlist'
_VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
'info_dict': {
'id': '3_2_26',
},
'playlist_mincount': 20,
}, {
'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
'only_matching': True,
}, {
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
'only_matching': True,
}, {
'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
'only_matching': True,
}]
def _real_extract(self, url):
id_ = self._match_id(url)
return self.playlist_result(
self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
class HotStarSeasonIE(HotStarBaseIE):
IE_NAME = 'hotstar:season'
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
'info_dict': {
'id': '8028',
},
'playlist_mincount': 35,
}, {
'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
'info_dict': {
'id': '4357',
},
'playlist_mincount': 30,
}, {
'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
'info_dict': {
'id': '8208',
},
'playlist_mincount': 19,
}, {
'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
'only_matching': True,
}]
def _real_extract(self, url):
url, season_id = self._match_valid_url(url).groups()
return self.playlist_result(self._playlist_entries(
'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
class HotStarSeriesIE(HotStarBaseIE):
IE_NAME = 'hotstar:series'
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
@@ -443,25 +454,29 @@ class HotStarSeriesIE(HotStarBaseIE):
'info_dict': {
'id': '1260050431',
},
'playlist_mincount': 43,
'playlist_mincount': 42,
}, {
'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
'info_dict': {
'id': '435',
},
'playlist_mincount': 267,
}, {
}, { # HTTP Error 504 with tas=10000 (possibly because total size is over 1000 items?)
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
'info_dict': {
'id': '1260022017',
},
'playlist_mincount': 940,
'playlist_mincount': 1601,
}]
_PAGE_SIZE = 100
def _real_extract(self, url):
url, series_id = self._match_valid_url(url).groups()
id_ = self._call_api_v1(
url, series_id = self._match_valid_url(url).group('url', 'id')
eid = self._call_api_v1(
'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
return self.playlist_result(self._playlist_entries(
'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
entries = OnDemandPagedList(functools.partial(
self._fetch_page, 'tray/g/1/items', series_id,
'series', {'etid': 0, 'eid': eid}, url), self._PAGE_SIZE)
return self.playlist_result(entries, series_id)
plugins/youtube_download/yt_dlp/extractor/huya.py
+59 -27
View File
@@ -7,12 +7,13 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
parse_duration,
str_or_none,
try_get,
unescapeHTML,
unified_strdate,
update_url,
update_url_query,
url_or_none,
)
@@ -22,8 +23,8 @@ from ..utils.traversal import traverse_obj
class HuyaLiveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P<id>[^/#?&]+)(?:\D|$)'
IE_NAME = 'huya:live'
IE_DESC = 'huya.com'
TESTS = [{
IE_DESC = '虎牙直播'
_TESTS = [{
'url': 'https://www.huya.com/572329',
'info_dict': {
'id': '572329',
@@ -149,63 +150,94 @@ class HuyaVideoIE(InfoExtractor):
'id': '1002412640',
'ext': 'mp4',
'title': '8月3日',
'thumbnail': r're:https?://.*\.jpg',
'duration': 14,
'categories': ['主机游戏'],
'duration': 14.0,
'uploader': '虎牙-ATS欧卡车队青木',
'uploader_id': '1564376151',
'upload_date': '20240803',
'view_count': int,
'comment_count': int,
'like_count': int,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1722675433,
},
},
{
}, {
'url': 'https://www.huya.com/video/play/556054543.html',
'info_dict': {
'id': '556054543',
'ext': 'mp4',
'title': '我不挑事 也不怕事',
'thumbnail': r're:https?://.*\.jpg',
'duration': 1864,
'categories': ['英雄联盟'],
'description': 'md5:58184869687d18ce62dc7b4b2ad21201',
'duration': 1864.0,
'uploader': '卡尔',
'uploader_id': '367138632',
'upload_date': '20210811',
'view_count': int,
'comment_count': int,
'like_count': int,
'tags': 'count:4',
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1628675950,
},
}, {
# Only m3u8 available
'url': 'https://www.huya.com/video/play/1063345618.html',
'info_dict': {
'id': '1063345618',
'ext': 'mp4',
'title': '峡谷第一中！黑铁上钻石顶级教学对抗elo',
'categories': ['英雄联盟'],
'comment_count': int,
'duration': 21603.0,
'like_count': int,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1749668803,
'upload_date': '20250611',
'uploader': '北枫CC',
'uploader_id': '2183525275',
'view_count': int,
},
}]
def _real_extract(self, url: str):
video_id = self._match_id(url)
video_data = self._download_json(
'https://liveapi.huya.com/moment/getMomentContent', video_id,
query={'videoId': video_id})['data']['moment']['videoInfo']
moment = self._download_json(
'https://liveapi.huya.com/moment/getMomentContent',
video_id, query={'videoId': video_id})['data']['moment']
formats = []
for definition in traverse_obj(video_data, ('definitions', lambda _, v: url_or_none(v['url']))):
formats.append({
'url': definition['url'],
**traverse_obj(definition, {
'format_id': ('defName', {str}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
for definition in traverse_obj(moment, (
'videoInfo', 'definitions', lambda _, v: url_or_none(v['m3u8']),
)):
fmts = self._extract_m3u8_formats(definition['m3u8'], video_id, 'mp4', fatal=False)
for fmt in fmts:
fmt.update(**traverse_obj(definition, {
'filesize': ('size', {int_or_none}),
}),
})
'format_id': ('defName', {str}),
'height': ('height', {int_or_none}),
'quality': ('definition', {int_or_none}),
'width': ('width', {int_or_none}),
}))
formats.extend(fmts)
return {
'id': video_id,
'formats': formats,
**traverse_obj(video_data, {
**traverse_obj(moment, {
'comment_count': ('commentCount', {int_or_none}),
'description': ('content', {clean_html}, filter),
'like_count': ('favorCount', {int_or_none}),
'timestamp': ('cTime', {int_or_none}),
}),
**traverse_obj(moment, ('videoInfo', {
'title': ('videoTitle', {str}),
'thumbnail': ('videoCover', {url_or_none}),
'categories': ('category', {str}, filter, all, filter),
'duration': ('videoDuration', {parse_duration}),
'tags': ('tags', ..., {str}, filter, all, filter),
'thumbnail': (('videoBigCover', 'videoCover'), {url_or_none}, {update_url(query=None)}, any),
'uploader': ('nickName', {str}),
'uploader_id': ('uid', {str_or_none}),
'upload_date': ('videoUploadTime', {unified_strdate}),
'view_count': ('videoPlayNum', {int_or_none}),
'comment_count': ('videoCommentNum', {int_or_none}),
'like_count': ('favorCount', {int_or_none}),
}),
})),
}
plugins/youtube_download/yt_dlp/extractor/hypergryph.py
+45 -11
View File
@@ -1,32 +1,66 @@
from .common import InfoExtractor
from ..utils import js_to_json, traverse_obj
from ..utils import (
ExtractorError,
clean_html,
url_or_none,
)
from ..utils.traversal import subs_list_to_dict, traverse_obj
class MonsterSirenHypergryphMusicIE(InfoExtractor):
IE_NAME = 'monstersiren'
IE_DESC = '塞壬唱片'
_API_BASE = 'https://monster-siren.hypergryph.com/api'
_VALID_URL = r'https?://monster-siren\.hypergryph\.com/music/(?P<id>\d+)'
_TESTS = [{
'url': 'https://monster-siren.hypergryph.com/music/514562',
'info_dict': {
'id': '514562',
'ext': 'wav',
'artists': ['塞壬唱片-MSR'],
'album': 'Flame Shadow',
'title': 'Flame Shadow',
'album': 'Flame Shadow',
'artists': ['塞壬唱片-MSR'],
'description': 'md5:19e2acfcd1b65b41b29e8079ab948053',
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
},
}, {
'url': 'https://monster-siren.hypergryph.com/music/514518',
'info_dict': {
'id': '514518',
'ext': 'wav',
'title': 'Heavenly Me (Instrumental)',
'album': 'Heavenly Me',
'artists': ['塞壬唱片-MSR', 'AIYUE blessed : 理名'],
'description': 'md5:ce790b41c932d1ad72eb791d1d8ae598',
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
},
}]
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
json_data = self._search_json(
r'window\.g_initialProps\s*=', webpage, 'data', audio_id, transform_source=js_to_json)
song = self._download_json(f'{self._API_BASE}/song/{audio_id}', audio_id)
if traverse_obj(song, 'code') != 0:
msg = traverse_obj(song, ('msg', {str}, filter))
raise ExtractorError(
msg or 'API returned an error response', expected=bool(msg))
album = None
if album_id := traverse_obj(song, ('data', 'albumCid', {str})):
album = self._download_json(
f'{self._API_BASE}/album/{album_id}/detail', album_id, fatal=False)
return {
'id': audio_id,
'title': traverse_obj(json_data, ('player', 'songDetail', 'name')),
'url': traverse_obj(json_data, ('player', 'songDetail', 'sourceUrl')),
'ext': 'wav',
'vcodec': 'none',
'artists': traverse_obj(json_data, ('player', 'songDetail', 'artists', ...)),
'album': traverse_obj(json_data, ('musicPlay', 'albumDetail', 'name')),
**traverse_obj(song, ('data', {
'title': ('name', {str}),
'artists': ('artists', ..., {str}),
'subtitles': ({'url': 'lyricUrl'}, all, {subs_list_to_dict(lang='en')}),
'url': ('sourceUrl', {url_or_none}),
})),
**traverse_obj(album, ('data', {
'album': ('name', {str}),
'description': ('intro', {clean_html}),
'thumbnail': ('coverUrl', {url_or_none}),
})),
}
plugins/youtube_download/yt_dlp/extractor/idagio.py
+262
View File
@@ -0,0 +1,262 @@
from .common import InfoExtractor
from ..utils import int_or_none, unified_timestamp, url_or_none
from ..utils.traversal import traverse_obj
class IdagioTrackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?app\.idagio\.com(?:/[a-z]{2})?/recordings/\d+\?(?:[^#]+&)?trackId=(?P<id>\d+)'
_TESTS = [{
'url': 'https://app.idagio.com/recordings/30576934?trackId=30576943',
'md5': '15148bd71804b2450a2508931a116b56',
'info_dict': {
'id': '30576943',
'ext': 'mp3',
'title': 'Theme. Andante',
'duration': 82,
'composers': ['Edward Elgar'],
'artists': ['Vasily Petrenko', 'Royal Liverpool Philharmonic Orchestra'],
'genres': ['Orchestral', 'Other Orchestral Music'],
'track': 'Theme. Andante',
'timestamp': 1554474370,
'upload_date': '20190405',
},
}, {
'url': 'https://app.idagio.com/recordings/20514467?trackId=20514478&utm_source=pcl',
'md5': '3acef2ea0feadf889123b70e5a1e7fa7',
'info_dict': {
'id': '20514478',
'ext': 'mp3',
'title': 'I. Adagio sostenuto',
'duration': 316,
'composers': ['Ludwig van Beethoven'],
'genres': ['Keyboard', 'Sonata (Keyboard)'],
'track': 'I. Adagio sostenuto',
'timestamp': 1518076337,
'upload_date': '20180208',
},
}, {
'url': 'https://app.idagio.com/de/recordings/20514467?trackId=20514478&utm_source=pcl',
'only_matching': True,
}]
def _real_extract(self, url):
track_id = self._match_id(url)
track_info = self._download_json(
f'https://api.idagio.com/v2.0/metadata/tracks/{track_id}',
track_id, fatal=False, expected_status=406)
if traverse_obj(track_info, 'error_code') == 'idagio.error.blocked.location':
self.raise_geo_restricted()
content_info = self._download_json(
f'https://api.idagio.com/v1.8/content/track/{track_id}', track_id,
query={
'quality': '0',
'format': '2',
'client_type': 'web-4',
})
return {
'ext': 'mp3',
'vcodec': 'none',
'id': track_id,
'url': traverse_obj(content_info, ('url', {url_or_none})),
**traverse_obj(track_info, ('result', {
'title': ('piece', 'title', {str}),
'timestamp': ('recording', 'created_at', {int_or_none(scale=1000)}),
'location': ('recording', 'location', {str}),
'duration': ('duration', {int_or_none}),
'track': ('piece', 'title', {str}),
'artists': ('recording', ('conductor', ('ensembles', ...), ('soloists', ...)), 'name', {str}, filter),
'composers': ('piece', 'workpart', 'work', 'composer', 'name', {str}, filter, all, filter),
'genres': ('piece', 'workpart', 'work', ('genre', 'subgenre'), 'title', {str}, filter),
})),
}
class IdagioPlaylistBaseIE(InfoExtractor):
"""Subclasses must set _API_URL_TMPL and define _parse_playlist_metadata"""
_PLAYLIST_ID_KEY = 'id' # vs. 'display_id'
def _entries(self, playlist_info):
for track_data in traverse_obj(playlist_info, ('tracks', lambda _, v: v['id'] and v['recording']['id'])):
track_id = track_data['id']
recording_id = track_data['recording']['id']
yield self.url_result(
f'https://app.idagio.com/recordings/{recording_id}?trackId={track_id}',
ie=IdagioTrackIE, video_id=track_id)
def _real_extract(self, url):
playlist_id = self._match_id(url)
playlist_info = self._download_json(
self._API_URL_TMPL.format(playlist_id), playlist_id)['result']
return {
'_type': 'playlist',
self._PLAYLIST_ID_KEY: playlist_id,
'entries': self._entries(playlist_info),
**self._parse_playlist_metadata(playlist_info),
}
class IdagioRecordingIE(IdagioPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?app\.idagio\.com(?:/[a-z]{2})?/recordings/(?P<id>\d+)(?![^#]*[&?]trackId=\d+)'
_TESTS = [{
'url': 'https://app.idagio.com/recordings/30576934',
'info_dict': {
'id': '30576934',
'title': 'Variations on an Original Theme op. 36',
'composers': ['Edward Elgar'],
'artists': ['Vasily Petrenko', 'Royal Liverpool Philharmonic Orchestra'],
'genres': ['Orchestral', 'Other Orchestral Music'],
'timestamp': 1554474370,
'modified_timestamp': 1554474370,
'modified_date': '20190405',
'upload_date': '20190405',
},
'playlist_count': 15,
}, {
'url': 'https://app.idagio.com/de/recordings/20514467',
'info_dict': {
'id': '20514467',
'title': 'Sonata for Piano No. 14 in C sharp minor op. 27/2',
'composers': ['Ludwig van Beethoven'],
'genres': ['Keyboard', 'Sonata (Keyboard)'],
'timestamp': 1518076337,
'upload_date': '20180208',
'modified_timestamp': 1518076337,
'modified_date': '20180208',
},
'playlist_count': 3,
}]
_API_URL_TMPL = 'https://api.idagio.com/v2.0/metadata/recordings/{}'
def _parse_playlist_metadata(self, playlist_info):
return traverse_obj(playlist_info, {
'title': ('work', 'title', {str}),
'timestamp': ('created_at', {int_or_none(scale=1000)}),
'modified_timestamp': ('created_at', {int_or_none(scale=1000)}),
'location': ('location', {str}),
'artists': (('conductor', ('ensembles', ...), ('soloists', ...)), 'name', {str}),
'composers': ('work', 'composer', 'name', {str}, all),
'genres': ('work', ('genre', 'subgenre'), 'title', {str}),
'tags': ('tags', ..., {str}),
})
class IdagioAlbumIE(IdagioPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?app\.idagio\.com(?:/[a-z]{2})?/albums/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://app.idagio.com/albums/elgar-enigma-variations-in-the-south-serenade-for-strings',
'info_dict': {
'id': 'a9f139b8-f70d-4b8a-a9a4-5fe8d35eaf9c',
'display_id': 'elgar-enigma-variations-in-the-south-serenade-for-strings',
'title': 'Elgar: Enigma Variations, In the South, Serenade for Strings',
'description': '',
'thumbnail': r're:https://.+/albums/880040420521/main\.jpg',
'artists': ['Vasily Petrenko', 'Royal Liverpool Philharmonic Orchestra', 'Edward Elgar'],
'timestamp': 1553817600,
'upload_date': '20190329',
'modified_timestamp': 1562566559.0,
'modified_date': '20190708',
},
'playlist_count': 19,
}, {
'url': 'https://app.idagio.com/de/albums/brahms-ein-deutsches-requiem-3B403DF6-62D7-4A42-807B-47173F3E0192',
'info_dict': {
'id': '2862ad4e-4a61-45ad-9ce4-7fcf0c2626fe',
'display_id': 'brahms-ein-deutsches-requiem-3B403DF6-62D7-4A42-807B-47173F3E0192',
'title': 'Brahms: Ein deutsches Requiem',
'description': 'GRAMOPHONE CLASSICAL MUSIC AWARDS 2025 Recording of the Year & Choral',
'thumbnail': r're:https://.+/albums/3149020954522/main\.jpg',
'artists': ['Sabine Devieilhe', 'Stéphane Degout', 'Raphaël Pichon', 'Pygmalion', 'Johannes Brahms'],
'timestamp': 1760054400,
'upload_date': '20251010',
'modified_timestamp': 1760624868,
'modified_date': '20251016',
'tags': ['recommended', 'recent-release'],
},
'playlist_count': 7,
}]
_API_URL_TMPL = 'https://api.idagio.com/v2.0/metadata/albums/{}'
_PLAYLIST_ID_KEY = 'display_id'
def _parse_playlist_metadata(self, playlist_info):
return traverse_obj(playlist_info, {
'id': ('id', {str}),
'title': ('title', {str}),
'timestamp': ('publishDate', {unified_timestamp}),
'modified_timestamp': ('lastModified', {unified_timestamp}),
'thumbnail': ('imageUrl', {url_or_none}),
'description': ('description', {str}),
'artists': ('participants', ..., 'name', {str}),
'tags': ('tags', ..., {str}),
})
class IdagioPlaylistIE(IdagioPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?app\.idagio\.com(?:/[a-z]{2})?/playlists/(?!personal/)(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://app.idagio.com/playlists/beethoven-the-most-beautiful-piano-music',
'info_dict': {
'id': '31652bec-8c5b-460e-a3f0-cf1f69817f53',
'display_id': 'beethoven-the-most-beautiful-piano-music',
'title': 'Beethoven: the most beautiful piano music',
'description': 'md5:d41bb04b8896bb69377f5c2cd9345ad1',
'thumbnail': r're:https://.+/playlists/31652bec-8c5b-460e-a3f0-cf1f69817f53/main\.jpg',
'creators': ['IDAGIO'],
},
'playlist_mincount': 16, # one entry is geo-restricted
}, {
'url': 'https://app.idagio.com/de/playlists/piano-music-for-an-autumn-day',
'info_dict': {
'id': 'd70e9c7f-7080-4308-ae0f-f890dddeda82',
'display_id': 'piano-music-for-an-autumn-day',
'title': 'Piano Music for an Autumn Day',
'description': 'Get ready to snuggle up and enjoy all the musical colours of this cosy, autumnal playlist.',
'thumbnail': r're:https://.+/playlists/d70e9c7f-7080-4308-ae0f-f890dddeda82/main\.jpg',
'creators': ['IDAGIO'],
},
'playlist_count': 35,
}]
_API_URL_TMPL = 'https://api.idagio.com/v2.0/playlists/{}'
_PLAYLIST_ID_KEY = 'display_id'
def _parse_playlist_metadata(self, playlist_info):
return traverse_obj(playlist_info, {
'id': ('id', {str}),
'title': ('title', {str}),
'thumbnail': ('imageUrl', {url_or_none}),
'description': ('description', {str}),
'creators': ('curator', 'name', {str}, all),
})
class IdagioPersonalPlaylistIE(IdagioPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?app\.idagio\.com(?:/[a-z]{2})?/playlists/personal/(?P<id>[\da-f-]+)'
_TESTS = [{
'url': 'https://app.idagio.com/playlists/personal/99dad72e-7b3a-45a4-b216-867c08046ed8',
'info_dict': {
'id': '99dad72e-7b3a-45a4-b216-867c08046ed8',
'title': 'Test',
'creators': ['1a6f16a6-4514-4d0c-b481-3a9877835626'],
'thumbnail': r're:https://.+/artists/86371/main\.jpg',
'timestamp': 1602859138,
'modified_timestamp': 1755616667,
'upload_date': '20201016',
'modified_date': '20250819',
},
'playlist_count': 100,
}, {
'url': 'https://app.idagio.com/de/playlists/personal/99dad72e-7b3a-45a4-b216-867c08046ed8',
'only_matching': True,
}]
_API_URL_TMPL = 'https://api.idagio.com/v1.0/personal-playlists/{}'
def _parse_playlist_metadata(self, playlist_info):
return traverse_obj(playlist_info, {
'title': ('title', {str}),
'thumbnail': ('image_url', {url_or_none}),
'creators': ('user_id', {str}, all),
'timestamp': ('created_at', {int_or_none(scale=1000)}),
'modified_timestamp': ('updated_at', {int_or_none(scale=1000)}),
})
plugins/youtube_download/yt_dlp/extractor/indavideo.py
+20 -5
View File
@@ -11,7 +11,6 @@ from ..utils import (
class IndavideoEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
# Some example URLs covered by generic extractor:
# https://indavideo.hu/video/Vicces_cica_1
# https://index.indavideo.hu/video/Hod_Nemetorszagban
# https://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
# https://film.indavideo.hu/video/f_farkaslesen
@@ -25,14 +24,14 @@ class IndavideoEmbedIE(InfoExtractor):
'ext': 'mp4',
'title': 'Cicatánc',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'cukiajanlo',
'uploader_id': '83729',
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
'timestamp': 1439193826,
'upload_date': '20150810',
'duration': 72,
'age_limit': 0,
'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
'tags': 'count:5',
},
}, {
'url': 'https://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
@@ -45,14 +44,30 @@ class IndavideoEmbedIE(InfoExtractor):
'ext': 'mp4',
'title': 'Vicces cica',
'description': 'Játszik a tablettel. :D',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
'uploader': 'Jet_Pack',
'uploader_id': '491217',
'timestamp': 1390821212,
'upload_date': '20140127',
'duration': 7,
'age_limit': 0,
'tags': ['cica', 'Jet_Pack'],
'tags': 'count:2',
},
}, {
'url': 'https://palyazat.indavideo.hu/video/RUSH_1',
'info_dict': {
'id': '3808180',
'ext': 'mp4',
'title': 'RUSH',
'age_limit': 0,
'description': '',
'duration': 650,
'tags': 'count:2',
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
'timestamp': 1729136266,
'upload_date': '20241017',
'uploader': '7summerfilms',
'uploader_id': '1628496',
},
}]
plugins/youtube_download/yt_dlp/extractor/iprima.py
+11 -43
View File
@@ -1,3 +1,4 @@
import json
import re
import time
@@ -6,9 +7,7 @@ from ..utils import (
ExtractorError,
determine_ext,
js_to_json,
parse_qs,
traverse_obj,
urlencode_postdata,
)
@@ -16,7 +15,6 @@ class IPrimaIE(InfoExtractor):
_VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_GEO_BYPASS = False
_NETRC_MACHINE = 'iprima'
_AUTH_ROOT = 'https://auth.iprima.cz'
access_token = None
_TESTS = [{
@@ -86,48 +84,18 @@ class IPrimaIE(InfoExtractor):
if self.access_token:
return
login_page = self._download_webpage(
f'{self._AUTH_ROOT}/oauth2/login', None, note='Downloading login page',
errnote='Downloading login page failed')
login_form = self._hidden_inputs(login_page)
login_form.update({
'_email': username,
'_password': password})
profile_select_html, login_handle = self._download_webpage_handle(
f'{self._AUTH_ROOT}/oauth2/login', None, data=urlencode_postdata(login_form),
note='Logging in')
# a profile may need to be selected first, even when there is only a single one
if '/profile-select' in login_handle.url:
profile_id = self._search_regex(
r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id')
login_handle = self._request_webpage(
f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None,
query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile')
code = traverse_obj(login_handle.url, ({parse_qs}, 'code', 0))
if not code:
raise ExtractorError('Login failed', expected=True)
token_request_data = {
'scope': 'openid+email+profile+phone+address+offline_access',
'client_id': 'prima_sso',
'grant_type': 'authorization_code',
'code': code,
'redirect_uri': f'{self._AUTH_ROOT}/sso/auth-check'}
token_data = self._download_json(
f'{self._AUTH_ROOT}/oauth2/token', None,
note='Downloading token', errnote='Downloading token failed',
data=urlencode_postdata(token_request_data))
'https://ucet.iprima.cz/api/session/create', None,
note='Logging in', errnote='Failed to log in',
data=json.dumps({
'email': username,
'password': password,
'deviceName': 'Windows Chrome',
}).encode(), headers={'content-type': 'application/json'})
self.access_token = token_data.get('access_token')
if self.access_token is None:
raise ExtractorError('Getting token failed', expected=True)
self.access_token = token_data['accessToken']['value']
if not self.access_token:
raise ExtractorError('Failed to fetch access token')
def _real_initialize(self):
if not self.access_token:
plugins/youtube_download/yt_dlp/extractor/itv.py
+3 -1
View File
@@ -18,6 +18,7 @@ from ..utils import (
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class ITVIE(InfoExtractor):
@@ -223,6 +224,7 @@ class ITVBTCCIE(InfoExtractor):
},
'playlist_count': 12,
}, {
# news page, can have absent `data` field
'url': 'https://www.itv.com/news/2021-10-27/i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
'info_dict': {
'id': 'i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
@@ -243,7 +245,7 @@ class ITVBTCCIE(InfoExtractor):
entries = []
for video in json_map:
if not any(video['data'].get(attr) == 'Brightcove' for attr in ('name', 'type')):
if not any(traverse_obj(video, ('data', attr)) == 'Brightcove' for attr in ('name', 'type')):
continue
video_id = video['data']['id']
account_id = video['data']['accountId']
plugins/youtube_download/yt_dlp/extractor/jiocinema.py
-408
View File
@@ -1,408 +0,0 @@
import base64
import itertools
import json
import random
import re
import string
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
jwt_decode_hs256,
parse_age_limit,
try_call,
url_or_none,
)
from ..utils.traversal import traverse_obj
class JioCinemaBaseIE(InfoExtractor):
_NETRC_MACHINE = 'jiocinema'
_GEO_BYPASS = False
_ACCESS_TOKEN = None
_REFRESH_TOKEN = None
_GUEST_TOKEN = None
_USER_ID = None
_DEVICE_ID = None
_API_HEADERS = {'Origin': 'https://www.jiocinema.com', 'Referer': 'https://www.jiocinema.com/'}
_APP_NAME = {'appName': 'RJIL_JioCinema'}
_APP_VERSION = {'appVersion': '5.0.0'}
_API_SIGNATURES = 'o668nxgzwff'
_METADATA_API_BASE = 'https://content-jiovoot.voot.com/psapi'
_ACCESS_HINT = 'the `accessToken` from your browser local storage'
_LOGIN_HINT = (
'Log in with "-u phone -p <PHONE_NUMBER>" to authenticate with OTP, '
f'or use "-u token -p <ACCESS_TOKEN>" to log in with {_ACCESS_HINT}. '
'If you have previously logged in with yt-dlp and your session '
'has been cached, you can use "-u device -p <DEVICE_ID>"')
def _cache_token(self, token_type):
assert token_type in ('access', 'refresh', 'all')
if token_type in ('access', 'all'):
self.cache.store(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-access', JioCinemaBaseIE._ACCESS_TOKEN)
if token_type in ('refresh', 'all'):
self.cache.store(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh', JioCinemaBaseIE._REFRESH_TOKEN)
def _call_api(self, url, video_id, note='Downloading API JSON', headers={}, data={}):
return self._download_json(
url, video_id, note, data=json.dumps(data, separators=(',', ':')).encode(), headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
**self._API_HEADERS,
**headers,
}, expected_status=(400, 403, 474))
def _call_auth_api(self, service, endpoint, note, headers={}, data={}):
return self._call_api(
f'https://auth-jiocinema.voot.com/{service}service/apis/v4/{endpoint}',
None, note=note, headers=headers, data=data)
def _refresh_token(self):
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._DEVICE_ID:
raise ExtractorError('User token has expired', expected=True)
response = self._call_auth_api(
'token', 'refreshtoken', 'Refreshing token',
headers={'accesstoken': self._ACCESS_TOKEN}, data={
**self._APP_NAME,
'deviceId': self._DEVICE_ID,
'refreshToken': self._REFRESH_TOKEN,
**self._APP_VERSION,
})
refresh_token = response.get('refreshTokenId')
if refresh_token and refresh_token != JioCinemaBaseIE._REFRESH_TOKEN:
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
self._cache_token('refresh')
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
self._cache_token('access')
def _fetch_guest_token(self):
JioCinemaBaseIE._DEVICE_ID = ''.join(random.choices(string.digits, k=10))
guest_token = self._call_auth_api(
'token', 'guest', 'Downloading guest token', data={
**self._APP_NAME,
'deviceType': 'phone',
'os': 'ios',
'deviceId': self._DEVICE_ID,
'freshLaunch': False,
'adId': self._DEVICE_ID,
**self._APP_VERSION,
})
self._GUEST_TOKEN = guest_token['authToken']
self._USER_ID = guest_token['userId']
def _call_login_api(self, endpoint, guest_token, data, note):
return self._call_auth_api(
'user', f'loginotp/{endpoint}', note, headers={
**self.geo_verification_headers(),
'accesstoken': self._GUEST_TOKEN,
**self._APP_NAME,
**traverse_obj(guest_token, 'data', {
'deviceType': ('deviceType', {str}),
'os': ('os', {str}),
})}, data=data)
def _is_token_expired(self, token):
return (try_call(lambda: jwt_decode_hs256(token)['exp']) or 0) <= int(time.time() - 180)
def _perform_login(self, username, password):
if self._ACCESS_TOKEN and not self._is_token_expired(self._ACCESS_TOKEN):
return
UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
if username.lower() == 'token':
if try_call(lambda: jwt_decode_hs256(password)):
JioCinemaBaseIE._ACCESS_TOKEN = password
refresh_hint = 'the `refreshToken` UUID from your browser local storage'
refresh_token = self._configuration_arg('refresh_token', [''], ie_key=JioCinemaIE)[0]
if not refresh_token:
self.to_screen(
'To extend the life of your login session, in addition to your access token, '
'you can pass --extractor-args "jiocinema:refresh_token=REFRESH_TOKEN" '
f'where REFRESH_TOKEN is {refresh_hint}')
elif re.fullmatch(UUID_RE, refresh_token):
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
else:
self.report_warning(f'Invalid refresh_token value. Use {refresh_hint}')
else:
raise ExtractorError(
f'The password given could not be decoded as a token; use {self._ACCESS_HINT}', expected=True)
elif username.lower() == 'device' and re.fullmatch(rf'(?:{UUID_RE}|\d+)', password):
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-refresh')
JioCinemaBaseIE._ACCESS_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-access')
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._ACCESS_TOKEN:
raise ExtractorError(f'Failed to load cached tokens for device ID "{password}"', expected=True)
elif username.lower() == 'phone' and re.fullmatch(r'\+?\d+', password):
self._fetch_guest_token()
guest_token = jwt_decode_hs256(self._GUEST_TOKEN)
initial_data = {
'number': base64.b64encode(password.encode()).decode(),
**self._APP_VERSION,
}
response = self._call_login_api('send', guest_token, initial_data, 'Requesting OTP')
if not traverse_obj(response, ('OTPInfo', {dict})):
raise ExtractorError('There was a problem with the phone number login attempt')
is_iphone = guest_token.get('os') == 'ios'
response = self._call_login_api('verify', guest_token, {
'deviceInfo': {
'consumptionDeviceName': 'iPhone' if is_iphone else 'Android',
'info': {
'platform': {'name': 'iPhone OS' if is_iphone else 'Android'},
'androidId': self._DEVICE_ID,
'type': 'iOS' if is_iphone else 'Android',
},
},
**initial_data,
'otp': self._get_tfa_info('the one-time password sent to your phone'),
}, 'Submitting OTP')
if traverse_obj(response, 'code') == 1043:
raise ExtractorError('Wrong OTP', expected=True)
JioCinemaBaseIE._REFRESH_TOKEN = response['refreshToken']
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
else:
raise ExtractorError(self._LOGIN_HINT, expected=True)
user_token = jwt_decode_hs256(JioCinemaBaseIE._ACCESS_TOKEN)['data']
JioCinemaBaseIE._USER_ID = user_token['userId']
JioCinemaBaseIE._DEVICE_ID = user_token['deviceId']
if JioCinemaBaseIE._REFRESH_TOKEN and username != 'device':
self._cache_token('all')
if self.get_param('cachedir') is not False:
self.to_screen(
f'NOTE: For subsequent logins you can use "-u device -p {JioCinemaBaseIE._DEVICE_ID}"')
elif not JioCinemaBaseIE._REFRESH_TOKEN:
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh')
if JioCinemaBaseIE._REFRESH_TOKEN:
self._cache_token('access')
self.to_screen(f'Logging in as device ID "{JioCinemaBaseIE._DEVICE_ID}"')
if self._is_token_expired(JioCinemaBaseIE._ACCESS_TOKEN):
self._refresh_token()
class JioCinemaIE(JioCinemaBaseIE):
IE_NAME = 'jiocinema'
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/?(?:movies?/[^/?#]+/|tv-shows/(?:[^/?#]+/){3})(?P<id>\d{3,})'
_TESTS = [{
'url': 'https://www.jiocinema.com/tv-shows/agnisakshi-ek-samjhauta/1/pradeep-to-stop-the-wedding/3759931',
'info_dict': {
'id': '3759931',
'ext': 'mp4',
'title': 'Pradeep to stop the wedding?',
'description': 'md5:75f72d1d1a66976633345a3de6d672b1',
'episode': 'Pradeep to stop the wedding?',
'episode_number': 89,
'season': 'Agnisakshi…Ek Samjhauta-S1',
'season_number': 1,
'series': 'Agnisakshi Ek Samjhauta',
'duration': 1238.0,
'thumbnail': r're:https?://.+\.jpg',
'age_limit': 13,
'season_id': '3698031',
'upload_date': '20230606',
'timestamp': 1686009600,
'release_date': '20230607',
'genres': ['Drama'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.jiocinema.com/movies/bhediya/3754021/watch',
'info_dict': {
'id': '3754021',
'ext': 'mp4',
'title': 'Bhediya',
'description': 'md5:a6bf2900371ac2fc3f1447401a9f7bb0',
'episode': 'Bhediya',
'duration': 8500.0,
'thumbnail': r're:https?://.+\.jpg',
'age_limit': 13,
'upload_date': '20230525',
'timestamp': 1685026200,
'release_date': '20230524',
'genres': ['Comedy'],
},
'params': {'skip_download': 'm3u8'},
}]
def _extract_formats_and_subtitles(self, playback, video_id):
m3u8_url = traverse_obj(playback, (
'data', 'playbackUrls', lambda _, v: v['streamtype'] == 'hls', 'url', {url_or_none}, any))
if not m3u8_url: # DRM-only content only serves dash urls
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls')
self._remove_duplicate_formats(formats)
return {
# '/_definst_/smil:vod/' m3u8 manifests claim to have 720p+ formats but max out at 480p
'formats': traverse_obj(formats, (
lambda _, v: '/_definst_/smil:vod/' not in v['url'] or v['height'] <= 480)),
'subtitles': subtitles,
}
def _real_extract(self, url):
video_id = self._match_id(url)
if not self._ACCESS_TOKEN and self._is_token_expired(self._GUEST_TOKEN):
self._fetch_guest_token()
elif self._ACCESS_TOKEN and self._is_token_expired(self._ACCESS_TOKEN):
self._refresh_token()
playback = self._call_api(
f'https://apis-jiovoot.voot.com/playbackjv/v3/{video_id}', video_id,
'Downloading playback JSON', headers={
**self.geo_verification_headers(),
'accesstoken': self._ACCESS_TOKEN or self._GUEST_TOKEN,
**self._APP_NAME,
'deviceid': self._DEVICE_ID,
'uniqueid': self._USER_ID,
'x-apisignatures': self._API_SIGNATURES,
'x-platform': 'androidweb',
'x-platform-token': 'web',
}, data={
'4k': False,
'ageGroup': '18+',
'appVersion': '3.4.0',
'bitrateProfile': 'xhdpi',
'capability': {
'drmCapability': {
'aesSupport': 'yes',
'fairPlayDrmSupport': 'none',
'playreadyDrmSupport': 'none',
'widevineDRMSupport': 'none',
},
'frameRateCapability': [{
'frameRateSupport': '30fps',
'videoQuality': '1440p',
}],
},
'continueWatchingRequired': False,
'dolby': False,
'downloadRequest': False,
'hevc': False,
'kidsSafe': False,
'manufacturer': 'Windows',
'model': 'Windows',
'multiAudioRequired': True,
'osVersion': '10',
'parentalPinValid': True,
'x-apisignatures': self._API_SIGNATURES,
})
status_code = traverse_obj(playback, ('code', {int}))
if status_code == 474:
self.raise_geo_restricted(countries=['IN'])
elif status_code == 1008:
error_msg = 'This content is only available for premium users'
if self._ACCESS_TOKEN:
raise ExtractorError(error_msg, expected=True)
self.raise_login_required(f'{error_msg}. {self._LOGIN_HINT}', method=None)
elif status_code == 400:
raise ExtractorError('The requested content is not available', expected=True)
elif status_code is not None and status_code != 200:
raise ExtractorError(
f'JioCinema says: {traverse_obj(playback, ("message", {str})) or status_code}')
metadata = self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/query/asset-details',
video_id, fatal=False, query={
'ids': f'include:{video_id}',
'responseType': 'common',
'devicePlatformType': 'desktop',
})
return {
'id': video_id,
'http_headers': self._API_HEADERS,
**self._extract_formats_and_subtitles(playback, video_id),
**traverse_obj(playback, ('data', {
# fallback metadata
'title': ('name', {str}),
'description': ('fullSynopsis', {str}),
'series': ('show', 'name', {str}, filter),
'season': ('tournamentName', {str}, {lambda x: x if x != 'Season 0' else None}),
'season_number': ('episode', 'season', {int_or_none}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', 'episodeNo', {int_or_none}, filter),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('totalDuration', {float_or_none}),
'thumbnail': ('images', {url_or_none}),
})),
**traverse_obj(metadata, ('result', 0, {
'title': ('fullTitle', {str}),
'description': ('fullSynopsis', {str}),
'series': ('showName', {str}, filter),
'season': ('seasonName', {str}, filter),
'season_number': ('season', {int_or_none}),
'season_id': ('seasonId', {str}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', {int_or_none}),
'timestamp': ('uploadTime', {int_or_none}),
'release_date': ('telecastDate', {str}),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('duration', {float_or_none}),
'genres': ('genres', ..., {str}),
'thumbnail': ('seo', 'ogImage', {url_or_none}),
})),
}
class JioCinemaSeriesIE(JioCinemaBaseIE):
IE_NAME = 'jiocinema:series'
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/tv-shows/(?P<slug>[\w-]+)/(?P<id>\d{3,})'
_TESTS = [{
'url': 'https://www.jiocinema.com/tv-shows/naagin/3499917',
'info_dict': {
'id': '3499917',
'title': 'naagin',
},
'playlist_mincount': 120,
}, {
'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
'info_dict': {
'id': '3499820',
'title': 'mtv-splitsvilla-x5',
},
'playlist_mincount': 310,
}]
def _entries(self, series_id):
seasons = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
'Downloading series metadata JSON', query={'responseType': 'common'}), (
'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
'trayTabs', lambda _, v: v['id']))
for season_num, season in enumerate(seasons, start=1):
season_id = season['id']
label = season.get('label') or season_num
for page_num in itertools.count(1):
episodes = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',
season_id, f'Downloading season {label} page {page_num} JSON', query={
'sort': 'episode:asc',
'id': season_id,
'responseType': 'common',
'page': page_num,
}), ('result', lambda _, v: v['id'] and url_or_none(v['slug'])))
if not episodes:
break
for episode in episodes:
yield self.url_result(
episode['slug'], JioCinemaIE, **traverse_obj(episode, {
'video_id': 'id',
'video_title': ('fullTitle', {str}),
'season_number': ('season', {int_or_none}),
'episode_number': ('episode', {int_or_none}),
}))
def _real_extract(self, url):
slug, series_id = self._match_valid_url(url).group('slug', 'id')
return self.playlist_result(self._entries(series_id), series_id, slug)
plugins/youtube_download/yt_dlp/extractor/jiosaavn.py
+261 -50
View File
@@ -1,23 +1,33 @@
import functools
import itertools
import math
import re
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
ISO639Utils,
OnDemandPagedList,
clean_html,
int_or_none,
js_to_json,
make_archive_id,
orderedSet,
smuggle_url,
unified_strdate,
unified_timestamp,
unsmuggle_url,
url_basename,
url_or_none,
urlencode_postdata,
urljoin,
variadic,
)
from ..utils.traversal import traverse_obj
class JioSaavnBaseIE(InfoExtractor):
_URL_BASE_RE = r'https?://(?:www\.)?(?:jio)?saavn\.com'
_API_URL = 'https://www.jiosaavn.com/api.php'
_VALID_BITRATES = {'16', '32', '64', '128', '320'}
@@ -30,16 +40,20 @@ class JioSaavnBaseIE(InfoExtractor):
f'Valid bitrates are: {", ".join(sorted(self._VALID_BITRATES, key=int))}')
return requested_bitrates
def _extract_formats(self, song_data):
def _extract_formats(self, item_data):
# Show/episode JSON data has a slightly different structure than song JSON data
if media_url := traverse_obj(item_data, ('more_info', 'encrypted_media_url', {str})):
item_data.setdefault('encrypted_media_url', media_url)
for bitrate in self.requested_bitrates:
media_data = self._download_json(
self._API_URL, song_data['id'],
self._API_URL, item_data['id'],
f'Downloading format info for {bitrate}',
fatal=False, data=urlencode_postdata({
'__call': 'song.generateAuthToken',
'_format': 'json',
'bitrate': bitrate,
'url': song_data['encrypted_media_url'],
'url': item_data['encrypted_media_url'],
}))
if not traverse_obj(media_data, ('auth_url', {url_or_none})):
self.report_warning(f'Unable to extract format info for {bitrate}')
@@ -53,24 +67,6 @@ class JioSaavnBaseIE(InfoExtractor):
'vcodec': 'none',
}
def _extract_song(self, song_data, url=None):
info = traverse_obj(song_data, {
'id': ('id', {str}),
'title': ('song', {clean_html}),
'album': ('album', {clean_html}),
'thumbnail': ('image', {url_or_none}, {lambda x: re.sub(r'-\d+x\d+\.', '-500x500.', x)}),
'duration': ('duration', {int_or_none}),
'view_count': ('play_count', {int_or_none}),
'release_year': ('year', {int_or_none}),
'artists': ('primary_artists', {lambda x: x.split(', ') if x else None}),
'webpage_url': ('perma_url', {url_or_none}),
})
if webpage_url := info.get('webpage_url') or url:
info['display_id'] = url_basename(webpage_url)
info['_old_archive_ids'] = [make_archive_id(JioSaavnSongIE, info['display_id'])]
return info
def _call_api(self, type_, token, note='API', params={}):
return self._download_json(
self._API_URL, token, f'Downloading {note} JSON', f'Unable to download {note} JSON',
@@ -84,19 +80,89 @@ class JioSaavnBaseIE(InfoExtractor):
**params,
})
def _yield_songs(self, playlist_data):
for song_data in traverse_obj(playlist_data, ('songs', lambda _, v: v['id'] and v['perma_url'])):
song_info = self._extract_song(song_data)
url = smuggle_url(song_info['webpage_url'], {
'id': song_data['id'],
'encrypted_media_url': song_data['encrypted_media_url'],
})
yield self.url_result(url, JioSaavnSongIE, url_transparent=True, **song_info)
@staticmethod
def _extract_song(song_data, url=None):
info = traverse_obj(song_data, {
'id': ('id', {str}),
'title': (('song', 'title'), {clean_html}, any),
'album': ((None, 'more_info'), 'album', {clean_html}, any),
'duration': ((None, 'more_info'), 'duration', {int_or_none}, any),
'channel': ((None, 'more_info'), 'label', {str}, any),
'channel_id': ((None, 'more_info'), 'label_id', {str}, any),
'channel_url': ((None, 'more_info'), 'label_url', {urljoin('https://www.jiosaavn.com/')}, any),
'release_date': ((None, 'more_info'), 'release_date', {unified_strdate}, any),
'release_year': ('year', {int_or_none}),
'thumbnail': ('image', {url_or_none}, {lambda x: re.sub(r'-\d+x\d+\.', '-500x500.', x)}),
'view_count': ('play_count', {int_or_none}),
'language': ('language', {lambda x: ISO639Utils.short2long(x.casefold()) or 'und'}),
'webpage_url': ('perma_url', {url_or_none}),
'artists': ('more_info', 'artistMap', 'primary_artists', ..., 'name', {str}, filter, all),
})
if webpage_url := info.get('webpage_url') or url:
info['display_id'] = url_basename(webpage_url)
info['_old_archive_ids'] = [make_archive_id(JioSaavnSongIE, info['display_id'])]
if primary_artists := traverse_obj(song_data, ('primary_artists', {lambda x: x.split(', ') if x else None})):
info['artists'].extend(primary_artists)
if featured_artists := traverse_obj(song_data, ('featured_artists', {str}, filter)):
info['artists'].extend(featured_artists.split(', '))
info['artists'] = orderedSet(info['artists']) or None
return info
@staticmethod
def _extract_episode(episode_data, url=None):
info = JioSaavnBaseIE._extract_song(episode_data, url)
info.pop('_old_archive_ids', None)
info.update(traverse_obj(episode_data, {
'description': ('more_info', 'description', {str}),
'timestamp': ('more_info', 'release_time', {unified_timestamp}),
'series': ('more_info', 'show_title', {str}),
'series_id': ('more_info', 'show_id', {str}),
'season': ('more_info', 'season_title', {str}),
'season_number': ('more_info', 'season_no', {int_or_none}),
'season_id': ('more_info', 'season_id', {str}),
'episode_number': ('more_info', 'episode_number', {int_or_none}),
'cast': ('starring', {lambda x: x.split(', ') if x else None}),
}))
return info
def _extract_jiosaavn_result(self, url, endpoint, response_key, parse_func):
url, smuggled_data = unsmuggle_url(url)
data = traverse_obj(smuggled_data, ({
'id': ('id', {str}),
'encrypted_media_url': ('encrypted_media_url', {str}),
}))
if 'id' in data and 'encrypted_media_url' in data:
result = {'id': data['id']}
else:
# only extract metadata if this is not a url_transparent result
data = self._call_api(endpoint, self._match_id(url))[response_key][0]
result = parse_func(data, url)
result['formats'] = list(self._extract_formats(data))
return result
def _yield_items(self, playlist_data, keys=None, parse_func=None):
"""Subclasses using this method must set _ENTRY_IE"""
if parse_func is None:
parse_func = self._extract_song
for item_data in traverse_obj(playlist_data, (
*variadic(keys, (str, bytes, dict, set)), lambda _, v: v['id'] and v['perma_url'],
)):
info = parse_func(item_data)
url = smuggle_url(info['webpage_url'], traverse_obj(item_data, {
'id': ('id', {str}),
'encrypted_media_url': ((None, 'more_info'), 'encrypted_media_url', {str}, any),
}))
yield self.url_result(url, self._ENTRY_IE, url_transparent=True, **info)
class JioSaavnSongIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:song'
_VALID_URL = r'https?://(?:www\.)?(?:jiosaavn\.com/song/[^/?#]+/|saavn\.com/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'(?:/song/[^/?#]+/|/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/song/leja-re/OQsEfQFVUXk',
'md5': '3b84396d15ed9e083c3106f1fa589c04',
@@ -106,12 +172,38 @@ class JioSaavnSongIE(JioSaavnBaseIE):
'ext': 'm4a',
'title': 'Leja Re',
'album': 'Leja Re',
'thumbnail': r're:https?://c.saavncdn.com/258/Leja-Re-Hindi-2018-20181124024539-500x500.jpg',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 205,
'view_count': int,
'release_year': 2018,
'artists': ['Sandesh Shandilya', 'Dhvani Bhanushali', 'Tanishk Bagchi'],
'_old_archive_ids': ['jiosaavnsong OQsEfQFVUXk'],
'channel': 'T-Series',
'language': 'hin',
'channel_id': '34297',
'channel_url': 'https://www.jiosaavn.com/label/t-series-albums/6DLuXO3VoTo_',
'release_date': '20181124',
},
}, {
'url': 'https://www.jiosaavn.com/song/chuttamalle/P1FfWjZkQ0Q',
'md5': '96296c58d6ce488a417ef0728fd2d680',
'info_dict': {
'id': 'O94kBTtw',
'display_id': 'P1FfWjZkQ0Q',
'ext': 'm4a',
'title': 'Chuttamalle',
'album': 'Devara Part 1 - Telugu',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 222,
'view_count': int,
'release_year': 2024,
'artists': 'count:3',
'_old_archive_ids': ['jiosaavnsong P1FfWjZkQ0Q'],
'channel': 'T-Series',
'language': 'tel',
'channel_id': '34297',
'channel_url': 'https://www.jiosaavn.com/label/t-series-albums/6DLuXO3VoTo_',
'release_date': '20240926',
},
}, {
'url': 'https://www.saavn.com/s/song/hindi/Saathiya/O-Humdum-Suniyo-Re/KAMiazoCblU',
@@ -119,26 +211,51 @@ class JioSaavnSongIE(JioSaavnBaseIE):
}]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url)
song_data = traverse_obj(smuggled_data, ({
'id': ('id', {str}),
'encrypted_media_url': ('encrypted_media_url', {str}),
}))
return self._extract_jiosaavn_result(url, 'song', 'songs', self._extract_song)
if 'id' in song_data and 'encrypted_media_url' in song_data:
result = {'id': song_data['id']}
else:
# only extract metadata if this is not a url_transparent result
song_data = self._call_api('song', self._match_id(url))['songs'][0]
result = self._extract_song(song_data, url)
result['formats'] = list(self._extract_formats(song_data))
return result
class JioSaavnShowIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:show'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/shows/[^/?#]+/(?P<id>[^/?#]{11,})/?(?:$|[?#])'
_TESTS = [{
'url': 'https://www.jiosaavn.com/shows/non-food-ways-to-boost-your-energy/XFMcKICOCgc_',
'md5': '0733cd254cfe74ef88bea1eaedcf1f4f',
'info_dict': {
'id': 'qqzh3RKZ',
'display_id': 'XFMcKICOCgc_',
'ext': 'mp3',
'title': 'Non-Food Ways To Boost Your Energy',
'description': 'md5:26e7129644b5c6aada32b8851c3997c8',
'episode': 'Episode 1',
'timestamp': 1640563200,
'series': 'Holistic Lifestyle With Neha Ranglani',
'series_id': '52397',
'season': 'Holistic Lifestyle With Neha Ranglani',
'season_number': 1,
'season_id': '61273',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 311,
'view_count': int,
'release_year': 2021,
'language': 'eng',
'channel': 'Saavn OG',
'channel_id': '1953876',
'episode_number': 1,
'upload_date': '20211227',
'release_date': '20211227',
},
}, {
'url': 'https://www.jiosaavn.com/shows/himesh-reshammiya/Kr8fmfSN4vo_',
'only_matching': True,
}]
def _real_extract(self, url):
return self._extract_jiosaavn_result(url, 'episode', 'episodes', self._extract_episode)
class JioSaavnAlbumIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:album'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/album/[^/?#]+/(?P<id>[^/?#]+)'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/album/[^/?#]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/album/96/buIOjYZDrNA_',
'info_dict': {
@@ -147,18 +264,19 @@ class JioSaavnAlbumIE(JioSaavnBaseIE):
},
'playlist_count': 10,
}]
_ENTRY_IE = JioSaavnSongIE
def _real_extract(self, url):
display_id = self._match_id(url)
album_data = self._call_api('album', display_id)
return self.playlist_result(
self._yield_songs(album_data), display_id, traverse_obj(album_data, ('title', {str})))
self._yield_items(album_data, 'songs'), display_id, traverse_obj(album_data, ('title', {str})))
class JioSaavnPlaylistIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:playlist'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/s/playlist/2279fbe391defa793ad7076929a2f5c9/mood-english/LlJ8ZWT1ibN5084vKHRj2Q__',
'info_dict': {
@@ -172,15 +290,16 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
'id': 'DVR,pFUOwyXqIp77B1JF,A__',
'title': 'Mood Hindi',
},
'playlist_mincount': 801,
'playlist_mincount': 750,
}, {
'url': 'https://www.jiosaavn.com/featured/taaza-tunes/Me5RridRfDk_',
'info_dict': {
'id': 'Me5RridRfDk_',
'title': 'Taaza Tunes',
},
'playlist_mincount': 301,
'playlist_mincount': 50,
}]
_ENTRY_IE = JioSaavnSongIE
_PAGE_SIZE = 50
def _fetch_page(self, token, page):
@@ -189,7 +308,7 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
def _entries(self, token, first_page_data, page):
page_data = first_page_data if not page else self._fetch_page(token, page + 1)
yield from self._yield_songs(page_data)
yield from self._yield_items(page_data, 'songs')
def _real_extract(self, url):
display_id = self._match_id(url)
@@ -199,3 +318,95 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
return self.playlist_result(InAdvancePagedList(
functools.partial(self._entries, display_id, playlist_data),
total_pages, self._PAGE_SIZE), display_id, traverse_obj(playlist_data, ('listname', {str})))
class JioSaavnShowPlaylistIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:show:playlist'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/shows/(?P<show>[^#/?]+)/(?P<season>\d+)/[^/?#]+'
_TESTS = [{
'url': 'https://www.jiosaavn.com/shows/talking-music/1/PjReFP-Sguk_',
'info_dict': {
'id': 'talking-music-1',
'title': 'Talking Music',
},
'playlist_mincount': 11,
}]
_ENTRY_IE = JioSaavnShowIE
_PAGE_SIZE = 10
def _fetch_page(self, show_id, season_id, page):
return self._call_api('show', show_id, f'show page {page}', {
'p': page,
'__call': 'show.getAllEpisodes',
'show_id': show_id,
'season_number': season_id,
'api_version': '4',
'sort_order': 'desc',
})
def _entries(self, show_id, season_id, page):
page_data = self._fetch_page(show_id, season_id, page + 1)
yield from self._yield_items(page_data, keys=None, parse_func=self._extract_episode)
def _real_extract(self, url):
show_slug, season_id = self._match_valid_url(url).group('show', 'season')
playlist_id = f'{show_slug}-{season_id}'
webpage = self._download_webpage(url, playlist_id)
show_info = self._search_json(
r'window\.__INITIAL_DATA__\s*=', webpage, 'initial data',
playlist_id, transform_source=js_to_json)['showView']
show_id = show_info['current_id']
entries = OnDemandPagedList(functools.partial(self._entries, show_id, season_id), self._PAGE_SIZE)
return self.playlist_result(
entries, playlist_id, traverse_obj(show_info, ('show', 'title', 'text', {str})))
class JioSaavnArtistIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:artist'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/artist/[^/?#]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/artist/krsna-songs/rYLBEve2z3U_',
'info_dict': {
'id': 'rYLBEve2z3U_',
'title': 'KR$NA',
},
'playlist_mincount': 38,
}, {
'url': 'https://www.jiosaavn.com/artist/sanam-puri-songs/SkNEv3qRhDE_',
'info_dict': {
'id': 'SkNEv3qRhDE_',
'title': 'Sanam Puri',
},
'playlist_mincount': 51,
}]
_ENTRY_IE = JioSaavnSongIE
_PAGE_SIZE = 50
def _fetch_page(self, artist_id, page):
return self._call_api('artist', artist_id, f'artist page {page + 1}', {
'p': page,
'n_song': self._PAGE_SIZE,
'n_album': self._PAGE_SIZE,
'sub_type': '',
'includeMetaTags': '',
'api_version': '4',
'category': 'alphabetical',
'sort_order': 'asc',
})
def _entries(self, artist_id, first_page):
for page in itertools.count():
playlist_data = first_page if not page else self._fetch_page(artist_id, page)
if not traverse_obj(playlist_data, ('topSongs', ..., {dict})):
break
yield from self._yield_items(playlist_data, 'topSongs')
def _real_extract(self, url):
artist_id = self._match_id(url)
first_page = self._fetch_page(artist_id, 0)
return self.playlist_result(
self._entries(artist_id, first_page), artist_id,
traverse_obj(first_page, ('name', {str})))
plugins/youtube_download/yt_dlp/extractor/joj.py
+11 -3
View File
@@ -22,18 +22,17 @@ class JojIE(InfoExtractor):
'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
'ext': 'mp4',
'title': 'NOVÉ BÝVANIE',
'thumbnail': r're:^https?://.*?$',
'duration': 3118,
'thumbnail': r're:https?://img\.joj\.sk/.+',
},
}, {
'url': 'https://media.joj.sk/embed/CSM0Na0l0p1',
'info_dict': {
'id': 'CSM0Na0l0p1',
'ext': 'mp4',
'height': 576,
'title': 'Extrémne rodiny 2 - POKRAČOVANIE (2012/04/09 21:30:00)',
'duration': 3937,
'thumbnail': r're:^https?://.*?$',
'thumbnail': r're:https?://img\.joj\.sk/.+',
},
}, {
'url': 'https://media.joj.sk/embed/9i1cxv',
@@ -45,6 +44,15 @@ class JojIE(InfoExtractor):
'url': 'joj:9i1cxv',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'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,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
plugins/youtube_download/yt_dlp/extractor/joqrag.py
-112
View File
@@ -1,112 +0,0 @@
import datetime as dt
import urllib.parse
from .common import InfoExtractor
from ..utils import (
clean_html,
datetime_from_str,
unified_timestamp,
urljoin,
)
class JoqrAgIE(InfoExtractor):
IE_DESC = '超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)'
_VALID_URL = [r'https?://www\.uniqueradio\.jp/agplayer5/(?:player|inc-player-hls)\.php',
r'https?://(?:www\.)?joqr\.co\.jp/ag/',
r'https?://(?:www\.)?joqr\.co\.jp/qr/ag(?:daily|regular)program/?(?:$|[#?])']
_TESTS = [{
'url': 'https://www.uniqueradio.jp/agplayer5/player.php',
'info_dict': {
'id': 'live',
'title': str,
'channel': '超!A&G+',
'description': str,
'live_status': 'is_live',
'release_timestamp': int,
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}, {
'url': 'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php',
'only_matching': True,
}, {
'url': 'https://www.joqr.co.jp/ag/article/103760/',
'only_matching': True,
}, {
'url': 'http://www.joqr.co.jp/qr/agdailyprogram/',
'only_matching': True,
}, {
'url': 'http://www.joqr.co.jp/qr/agregularprogram/',
'only_matching': True,
}]
def _extract_metadata(self, variable, html):
return clean_html(urllib.parse.unquote_plus(self._search_regex(
rf'var\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
html, 'metadata', group='value', default=''))) or None
def _extract_start_timestamp(self, video_id, is_live):
def extract_start_time_from(date_str):
dt_ = datetime_from_str(date_str) + dt.timedelta(hours=9)
date = dt_.strftime('%Y%m%d')
start_time = self._search_regex(
r'<h3[^>]+\bclass="dailyProgram-itemHeaderTime"[^>]*>[\s\d:]+–\s*(\d{1,2}:\d{1,2})',
self._download_webpage(
f'https://www.joqr.co.jp/qr/agdailyprogram/?date={date}', video_id,
note=f'Downloading program list of {date}', fatal=False,
errnote=f'Failed to download program list of {date}') or '',
'start time', default=None)
if start_time:
return unified_timestamp(f'{dt_.strftime("%Y/%m/%d")} {start_time} +09:00')
return None
start_timestamp = extract_start_time_from('today')
if not start_timestamp:
return None
if not is_live or start_timestamp < datetime_from_str('now').timestamp():
return start_timestamp
else:
return extract_start_time_from('yesterday')
def _real_extract(self, url):
video_id = 'live'
metadata = self._download_webpage(
'https://www.uniqueradio.jp/aandg', video_id,
note='Downloading metadata', errnote='Failed to download metadata')
title = self._extract_metadata('Program_name', metadata)
if not title or title == '放送休止':
formats = []
live_status = 'is_upcoming'
release_timestamp = self._extract_start_timestamp(video_id, False)
msg = 'This stream is not currently live'
if release_timestamp:
msg += (' and will start at '
+ dt.datetime.fromtimestamp(release_timestamp).strftime('%Y-%m-%d %H:%M:%S'))
self.raise_no_formats(msg, expected=True)
else:
m3u8_path = self._search_regex(
r'<source\s[^>]*\bsrc="([^"]+)"',
self._download_webpage(
'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php', video_id,
note='Downloading player data', errnote='Failed to download player data'),
'm3u8 url')
formats = self._extract_m3u8_formats(
urljoin('https://www.uniqueradio.jp/', m3u8_path), video_id)
live_status = 'is_live'
release_timestamp = self._extract_start_timestamp(video_id, True)
return {
'id': video_id,
'title': title,
'channel': '超!A&G+',
'description': self._extract_metadata('Program_text', metadata),
'formats': formats,
'live_status': live_status,
'release_timestamp': release_timestamp,
}
plugins/youtube_download/yt_dlp/extractor/jwplatform.py
+19 -7
View File
@@ -8,7 +8,6 @@ class JWPlatformIE(InfoExtractor):
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
_TESTS = [{
'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
'md5': '3aa16e4f6860e6e78b7df5829519aed3',
'info_dict': {
'id': 'nPripu9l',
'ext': 'mp4',
@@ -17,13 +16,12 @@ class JWPlatformIE(InfoExtractor):
'upload_date': '20081127',
'timestamp': 1227796140,
'duration': 32.0,
'thumbnail': 'https://cdn.jwplayer.com/v2/media/nPripu9l/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
},
}, {
'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# JWPlatform iframe
'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
@@ -33,10 +31,11 @@ class JWPlatformIE(InfoExtractor):
'upload_date': '20160719',
'timestamp': 1468923808,
'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/AG26UQXM/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'description': '',
'duration': 294.0,
},
'skip': 'Site no longer embeds JWPlatform',
}, {
# Player url not surrounded by quotes
'url': 'https://www.deutsche-kinemathek.de/en/online/streaming/school-trip',
@@ -45,12 +44,12 @@ class JWPlatformIE(InfoExtractor):
'title': 'Klassenfahrt',
'ext': 'mp4',
'upload_date': '20230109',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/jUxh5uin/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1673270298,
'description': '',
'duration': 5193.0,
},
'params': {'allowed_extractors': ['generic', 'jwplatform']},
'skip': 'Site no longer embeds JWPlatform',
}, {
# iframe src attribute includes backslash before URL string
'url': 'https://www.elespectador.com/colombia/video-asi-se-evito-la-fuga-de-john-poulos-presunto-feminicida-de-valentina-trespalacios-explicacion',
@@ -59,11 +58,24 @@ class JWPlatformIE(InfoExtractor):
'title': 'Así se evitó la fuga de John Poulos, presunto feminicida de Valentina Trespalacios',
'ext': 'mp4',
'upload_date': '20230127',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/QD3gsexj/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1674862986,
'description': 'md5:128fd74591c4e1fc2da598c5cb6f5ce4',
'duration': 263.0,
},
}, {
'url': 'https://www.skimag.com/video/ski-people-1980',
'info_dict': {
'id': 'YTmgRiNU',
'ext': 'mp4',
'title': 'Ski People (1980)',
'channel': 'snow',
'description': 'md5:cf9c3d101452c91e141f292b19fe4843',
'duration': 5688.0,
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1610407738,
'upload_date': '20210111',
},
}]
@classmethod
plugins/youtube_download/yt_dlp/extractor/kaltura.py
+173 -134
View File
@@ -41,149 +41,188 @@ class KalturaIE(InfoExtractor):
2: 'ttml',
3: 'vtt',
}
_TESTS = [
{
'url': 'kaltura:269692:1_1jc2y3e4',
'md5': '3adcbdb3dcc02d647539e53f284ba171',
'info_dict': {
'id': '1_1jc2y3e4',
'ext': 'mp4',
'title': 'Straight from the Heart',
'upload_date': '20131219',
'uploader_id': '[email protected]',
'description': 'The Allman Brothers Band, 12/16/1981',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'timestamp': int,
_TESTS = [{
'url': 'kaltura:269692:1_1jc2y3e4',
'md5': '3adcbdb3dcc02d647539e53f284ba171',
'info_dict': {
'id': '1_1jc2y3e4',
'ext': 'mp4',
'title': 'Straight from the Heart',
'upload_date': '20131219',
'uploader_id': '[email protected]',
'description': 'The Allman Brothers Band, 12/16/1981',
'thumbnail': r're:https?://.+/thumbnail/.+',
'timestamp': int,
},
'skip': 'The access to this service is forbidden since the specified partner is blocked',
}, {
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
'only_matching': True,
}, {
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
'only_matching': True,
}, {
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
'only_matching': True,
}, {
# video with subtitles
'url': 'kaltura:111032:1_cw786r8q',
'only_matching': True,
}, {
# video with ttml subtitles (no fileExt)
'url': 'kaltura:1926081:0_l5ye1133',
'info_dict': {
'id': '0_l5ye1133',
'ext': 'mp4',
'title': 'What Can You Do With Python?',
'upload_date': '20160221',
'uploader_id': 'stork',
'thumbnail': r're:https?://.+/thumbnail/.+',
'timestamp': int,
'subtitles': {
'en': [{
'ext': 'ttml',
}],
},
'skip': 'The access to this service is forbidden since the specified partner is blocked',
},
{
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
'only_matching': True,
'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
'params': {'skip_download': True},
}, {
'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
# unavailable source format
'url': 'kaltura:513551:1_66x4rg7o',
'only_matching': True,
}, {
# html5lib URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.46/mwEmbedFrame.php/p/691292/uiconf_id/20499062/entry_id/0_c076mna6?wid=_691292&iframeembed=true&playerId=kaltura_player_1420508608&entry_id=0_c076mna6&flashvars%5BakamaiHD.loadingPolicy%5D=preInitialize&flashvars%5BakamaiHD.asyncInit%5D=true&flashvars%5BstreamerType%5D=hdnetwork',
'info_dict': {
'id': '0_c076mna6',
'ext': 'mp4',
'title': 'md5:4883e7acbcbf42583a2dddc97dee4855',
'duration': 3608,
'uploader_id': '[email protected]',
'timestamp': 1408086874,
'view_count': int,
'upload_date': '20140815',
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
},
{
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
'only_matching': True,
}, {
# html5lib playlist URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.89/mwEmbedFrame.php/p/2019031/uiconf_id/40436601?wid=1_4j3m32cv&iframeembed=true&playerId=kaltura_player_&flashvars[playlistAPI.kpl0Id]=1_jovey5nu&flashvars[ks]=&&flashvars[imageDefaultDuration]=30&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[forceMobileHTML5]=true&flashvars[nextPrevBtn.plugin]=true&flashvars[hotspots.plugin]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[playlistAPI.playlistUrl]=https://canvasgatechtest.kaf.kaltura.com/playlist/details/{playlistAPI.kpl0Id}/categoryid/126428551',
'info_dict': {
'id': '1_jovey5nu',
'title': '00-00 Introduction',
},
{
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
'only_matching': True,
},
{
# video with subtitles
'url': 'kaltura:111032:1_cw786r8q',
'only_matching': True,
},
{
# video with ttml subtitles (no fileExt)
'url': 'kaltura:1926081:0_l5ye1133',
'info_dict': {
'id': '0_l5ye1133',
'ext': 'mp4',
'title': 'What Can You Do With Python?',
'upload_date': '20160221',
'uploader_id': 'stork',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'timestamp': int,
'subtitles': {
'en': [{
'ext': 'ttml',
}],
'playlist': [
{
'info_dict': {
'id': '1_b1y5hlvx',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Introduction',
'duration': 91,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154447,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_jfb7mdpn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Three parts to the course',
'duration': 63,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154489,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_8xflxdp7',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Textbooks',
'duration': 37,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154512,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_3hqew8kn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Prerequisites',
'duration': 49,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154536,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
},
'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
'params': {
'skip_download': True,
},
],
}]
_WEBPAGE_TESTS = [{
'url': 'https://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',
'duration': 5420,
'thumbnail': r're:https?://cdnsecakmi\.kaltura\.com/.+',
'timestamp': 1321158993,
'upload_date': '20111113',
'uploader_id': 'kps1',
'view_count': int,
},
{
'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
'info_dict': {
'id': '0_utuok90b',
'ext': 'mp4',
'title': '06_matthew_brender_raj_dutt',
'duration': 331,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'timestamp': 1466638791,
'upload_date': '20160622',
'uploader_id': '',
'view_count': int,
},
{
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
'url': 'https://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
'info_dict': {
'id': '0_izeg5utt',
'ext': 'mp4',
'title': '35871',
'duration': 3403,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'timestamp': 1355743100,
'upload_date': '20121217',
'uploader_id': '[email protected]',
'view_count': int,
},
{
# unavailable source format
'url': 'kaltura:513551:1_66x4rg7o',
'only_matching': True,
}, {
'url': 'https://www.cns.nyu.edu/~eero/math-tools17/Videos/lecture-05sep2017.html',
'info_dict': {
'id': '1_9gzouybz',
'ext': 'mp4',
'title': 'lecture-05sep2017',
'duration': 7219,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'timestamp': 1505340777,
'upload_date': '20170913',
'uploader_id': 'eps2',
'view_count': int,
},
{
# html5lib URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.46/mwEmbedFrame.php/p/691292/uiconf_id/20499062/entry_id/0_c076mna6?wid=_691292&iframeembed=true&playerId=kaltura_player_1420508608&entry_id=0_c076mna6&flashvars%5BakamaiHD.loadingPolicy%5D=preInitialize&flashvars%5BakamaiHD.asyncInit%5D=true&flashvars%5BstreamerType%5D=hdnetwork',
'info_dict': {
'id': '0_c076mna6',
'ext': 'mp4',
'title': 'md5:4883e7acbcbf42583a2dddc97dee4855',
'duration': 3608,
'uploader_id': '[email protected]',
'timestamp': 1408086874,
'view_count': int,
'upload_date': '20140815',
'thumbnail': 'http://cfvod.kaltura.com/p/691292/sp/69129200/thumbnail/entry_id/0_c076mna6/version/100022',
},
},
{
# html5lib playlist URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.89/mwEmbedFrame.php/p/2019031/uiconf_id/40436601?wid=1_4j3m32cv&iframeembed=true&playerId=kaltura_player_&flashvars[playlistAPI.kpl0Id]=1_jovey5nu&flashvars[ks]=&&flashvars[imageDefaultDuration]=30&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[forceMobileHTML5]=true&flashvars[nextPrevBtn.plugin]=true&flashvars[hotspots.plugin]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[playlistAPI.playlistUrl]=https://canvasgatechtest.kaf.kaltura.com/playlist/details/{playlistAPI.kpl0Id}/categoryid/126428551',
'info_dict': {
'id': '1_jovey5nu',
'title': '00-00 Introduction',
},
'playlist': [
{
'info_dict': {
'id': '1_b1y5hlvx',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Introduction',
'duration': 91,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_b1y5hlvx/version/100001',
'view_count': int,
'timestamp': 1533154447,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_jfb7mdpn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Three parts to the course',
'duration': 63,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_jfb7mdpn/version/100001',
'view_count': int,
'timestamp': 1533154489,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_8xflxdp7',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Textbooks',
'duration': 37,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_8xflxdp7/version/100001',
'view_count': int,
'timestamp': 1533154512,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_3hqew8kn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Prerequisites',
'duration': 49,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_3hqew8kn/version/100001',
'view_count': int,
'timestamp': 1533154536,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
},
],
},
]
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
@@ -398,7 +437,7 @@ class KalturaIE(InfoExtractor):
params = urllib.parse.parse_qs(query)
if path:
splitted_path = path.split('/')
params.update(dict(zip(splitted_path[::2], [[v] for v in splitted_path[1::2]])))
params.update(dict(zip(splitted_path[::2], [[v] for v in splitted_path[1::2]]))) # noqa: B905
if 'wid' in params:
partner_id = remove_start(params['wid'][0], '_')
elif 'p' in params:
plugins/youtube_download/yt_dlp/extractor/kick.py
+43 -25
View File
@@ -1,12 +1,12 @@
import functools
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
UserNotLive,
determine_ext,
float_or_none,
int_or_none,
merge_dicts,
parse_iso8601,
str_or_none,
traverse_obj,
@@ -16,21 +16,17 @@ from ..utils import (
class KickBaseIE(InfoExtractor):
def _real_initialize(self):
self._request_webpage(
HEADRequest('https://kick.com/'), None, 'Setting up session', fatal=False, impersonate=True)
xsrf_token = self._get_cookies('https://kick.com/').get('XSRF-TOKEN')
if not xsrf_token:
self.write_debug('kick.com did not set XSRF-TOKEN cookie')
KickBaseIE._API_HEADERS = {
'Authorization': f'Bearer {xsrf_token.value}',
'X-XSRF-TOKEN': xsrf_token.value,
} if xsrf_token else {}
@functools.cached_property
def _api_headers(self):
token = traverse_obj(
self._get_cookies('https://kick.com/'),
('session_token', 'value', {urllib.parse.unquote}))
return {'Authorization': f'Bearer {token}'} if token else {}
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
return self._download_json(
f'https://kick.com/api/{path}', display_id, note=note,
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
headers={**self._api_headers, **headers}, impersonate=True, **kwargs)
class KickIE(KickBaseIE):
@@ -99,26 +95,47 @@ class KickVODIE(KickBaseIE):
IE_NAME = 'kick:vod'
_VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/videos/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://kick.com/xqc/videos/8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
'md5': '3870f94153e40e7121a6e46c068b70cb',
# Regular VOD
'url': 'https://kick.com/xqc/videos/5c697a87-afce-4256-b01f-3c8fe71ef5cb',
'info_dict': {
'id': '8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
'id': '5c697a87-afce-4256-b01f-3c8fe71ef5cb',
'ext': 'mp4',
'title': '18+ #ad 🛑LIVE🛑CLICK🛑DRAMA🛑NEWS🛑STUFF🛑REACT🛑GET IN HHERE🛑BOP BOP🛑WEEEE WOOOO🛑',
'title': '🐗LIVE🐗CLICK🐗HERE🐗DRAMA🐗ALL DAY🐗NEWS🐗VIDEOS🐗CLIPS🐗GAMES🐗STUFF🐗WOW🐗IM HERE🐗LETS GO🐗COOL🐗VERY NICE🐗',
'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.',
'channel': 'xqc',
'channel_id': '668',
'uploader': 'xQc',
'uploader_id': '676',
'upload_date': '20240909',
'timestamp': 1725919141,
'duration': 10155.0,
'thumbnail': r're:^https?://.*\.jpg',
'channel': 'xqc',
'channel_id': '668',
'view_count': int,
'categories': ['Just Chatting'],
'age_limit': 0,
'age_limit': 18,
'duration': 22278.0,
'thumbnail': r're:^https?://.*\.jpg',
'categories': ['Deadlock'],
'timestamp': 1756082443,
'upload_date': '20250825',
},
'params': {'skip_download': 'm3u8'},
}, {
# VOD of ongoing livestream (at the time of writing the test, ID rotates every two days)
'url': 'https://kick.com/a-log-burner/videos/5230df84-ea38-46e1-be4f-f5949ae55641',
'info_dict': {
'id': '5230df84-ea38-46e1-be4f-f5949ae55641',
'ext': 'mp4',
'title': r're:😴 Cozy Fireplace ASMR 🔥 | Relax, Focus, Sleep 💤',
'description': 'md5:080bc713eac0321a7b376a1b53816d1b',
'uploader': 'A_Log_Burner',
'uploader_id': '65114691',
'channel': 'a-log-burner',
'channel_id': '63967687',
'view_count': int,
'age_limit': 18,
'thumbnail': r're:^https?://.*\.jpg',
'categories': ['Other, Watch Party'],
'timestamp': int,
'upload_date': str,
'live_status': 'is_live',
},
'skip': 'live',
}]
def _real_extract(self, url):
@@ -141,6 +158,7 @@ class KickVODIE(KickBaseIE):
'categories': ('livestream', 'categories', ..., 'name', {str}),
'view_count': ('views', {int_or_none}),
'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
'is_live': ('livestream', 'is_live', {bool}),
}),
}
plugins/youtube_download/yt_dlp/extractor/kinja.py
+9
View File
@@ -89,6 +89,15 @@ class KinjaEmbedIE(InfoExtractor):
'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-video-00QyL0AgPAE',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
'info_dict': {
'id': '106351',
'ext': 'mp4',
'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
},
'skip': 'Invalid URL',
}]
_JWPLATFORM_PROVIDER = ('cdn.jwplayer.com/v2/media/', 'JWPlatform')
_PROVIDER_MAP = {
'fb': ('facebook.com/video.php?v=', 'Facebook'),
plugins/youtube_download/yt_dlp/extractor/lcp.py
+3 -18
View File
@@ -1,8 +1,8 @@
from .arkena import ArkenaIE
from .common import InfoExtractor
class LcpPlayIE(ArkenaIE): # XXX: Do not subclass from concrete IE
class LcpPlayIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://play\.lcp\.fr/embed/(?P<id>[^/]+)/(?P<account_id>[^/]+)/[^/]+/[^/]+'
_TESTS = [{
'url': 'http://play.lcp.fr/embed/327336/131064/darkmatter/0',
@@ -21,24 +21,9 @@ class LcpPlayIE(ArkenaIE): # XXX: Do not subclass from concrete IE
class LcpIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?lcp\.fr/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
# arkena embed
'url': 'http://www.lcp.fr/la-politique-en-video/schwartzenberg-prg-preconise-francois-hollande-de-participer-une-primaire',
'md5': 'b8bd9298542929c06c1c15788b1f277a',
'info_dict': {
'id': 'd56d03e9',
'ext': 'mp4',
'title': 'Schwartzenberg (PRG) préconise à François Hollande de participer à une primaire à gauche',
'description': 'md5:96ad55009548da9dea19f4120c6c16a8',
'timestamp': 1456488895,
'upload_date': '20160226',
},
'params': {
'skip_download': True,
},
}, {
# dailymotion live stream
'url': 'http://www.lcp.fr/le-direct',
'info_dict': {
plugins/youtube_download/yt_dlp/extractor/libsyn.py
+28 -6
View File
@@ -18,12 +18,10 @@ class LibsynIE(InfoExtractor):
'info_dict': {
'id': '6385796',
'ext': 'mp3',
'title': 'Champion Minded - Developing a Growth Mindset',
# description fetched using another request:
# http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
# 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
'title': 'The Allistair McCaw Podcast - Developing a Growth Mindset',
'duration': 834.0,
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
'upload_date': '20180320',
'thumbnail': 're:^https?://.*',
},
}, {
'url': 'https://html5-player.libsyn.com/embed/episode/id/3727166/height/75/width/200/theme/standard/direction/no/autoplay/no/autonext/no/thumbnail/no/preload/no/no_addthis/no/',
@@ -32,8 +30,32 @@ class LibsynIE(InfoExtractor):
'id': '3727166',
'ext': 'mp3',
'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
'upload_date': '20150818',
'thumbnail': 're:^https?://.*',
},
'skip': 'Invalid URL',
}]
_WEBPAGE_TESTS = [{
'url': 'https://html5-player.libsyn.com/',
'md5': '50cff329596b8f674d4449ed077ef2f9',
'info_dict': {
'id': '2378831',
'ext': 'mp3',
'title': 'md5:54108b15f98e1b4056612c10b50106b2',
'duration': 3561.0,
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
'upload_date': '20130630',
},
}, {
'url': 'https://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
'md5': '23576952577f9604520a730d90371761',
'info_dict': {
'id': '3793998',
'ext': 'mp3',
'title': 'Underground Wellness Radio - Jack Tips: 5 Steps to Permanent Gut Healing',
'duration': 3989.0,
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
'upload_date': '20141126',
},
}]
plugins/youtube_download/yt_dlp/extractor/limelight.py
-358
View File
@@ -1,358 +0,0 @@
import re
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
float_or_none,
int_or_none,
smuggle_url,
try_get,
unsmuggle_url,
)
class LimelightBaseIE(InfoExtractor):
_PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
@classmethod
def _extract_embed_urls(cls, url, webpage):
lm = {
'Media': 'media',
'Channel': 'channel',
'ChannelList': 'channel_list',
}
def smuggle(url):
return smuggle_url(url, {'source_url': url})
entries = []
for kind, video_id in re.findall(
r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})',
webpage):
entries.append(cls.url_result(
smuggle(f'limelight:{lm[kind]}:{video_id}'),
f'Limelight{kind}', video_id))
for mobj in re.finditer(
# As per [1] class attribute should be exactly equal to
# LimelightEmbeddedPlayerFlash but numerous examples seen
# that don't exactly match it (e.g. [2]).
# 1. http://support.3playmedia.com/hc/en-us/articles/227732408-Limelight-Embedding-the-Captions-Plugin-with-the-Limelight-Player-on-Your-Webpage
# 2. http://www.sedona.com/FacilitatorTraining2017
r'''(?sx)
<object[^>]+class=(["\'])(?:(?!\1).)*\bLimelightEmbeddedPlayerFlash\b(?:(?!\1).)*\1[^>]*>.*?
<param[^>]+
name=(["\'])flashVars\2[^>]+
value=(["\'])(?:(?!\3).)*(?P<kind>media|channel(?:List)?)Id=(?P<id>[a-z0-9]{32})
''', webpage):
kind, video_id = mobj.group('kind'), mobj.group('id')
entries.append(cls.url_result(
smuggle(f'limelight:{kind}:{video_id}'),
f'Limelight{kind.capitalize()}', video_id))
# http://support.3playmedia.com/hc/en-us/articles/115009517327-Limelight-Embedding-the-Audio-Description-Plugin-with-the-Limelight-Player-on-Your-Web-Page)
for video_id in re.findall(
r'(?s)LimelightPlayerUtil\.embed\s*\(\s*{.*?\bmediaId["\']\s*:\s*["\'](?P<id>[a-z0-9]{32})',
webpage):
entries.append(cls.url_result(
smuggle(f'limelight:media:{video_id}'),
LimelightMediaIE.ie_key(), video_id))
return entries
def _call_playlist_service(self, item_id, method, fatal=True, referer=None):
headers = {}
if referer:
headers['Referer'] = referer
try:
return self._download_json(
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
item_id, f'Downloading PlaylistService {method} JSON',
fatal=fatal, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
error = self._parse_json(e.cause.response.read().decode(), item_id)['detail']['contentAccessPermission']
if error == 'CountryDisabled':
self.raise_geo_restricted()
raise ExtractorError(error, expected=True)
raise
def _extract(self, item_id, pc_method, mobile_method, referer=None):
pc = self._call_playlist_service(item_id, pc_method, referer=referer)
mobile = self._call_playlist_service(
item_id, mobile_method, fatal=False, referer=referer)
return pc, mobile
def _extract_info(self, pc, mobile, i, referer):
get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {}
pc_item = get_item(pc, 'playlistItems')
mobile_item = get_item(mobile, 'mediaList')
video_id = pc_item.get('mediaId') or mobile_item['mediaId']
title = pc_item.get('title') or mobile_item['title']
formats = []
urls = []
for stream in pc_item.get('streams', []):
stream_url = stream.get('url')
if not stream_url or stream_url in urls:
continue
if not self.get_param('allow_unplayable_formats') and stream.get('drmProtected'):
continue
urls.append(stream_url)
ext = determine_ext(stream_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
stream_url, video_id, f4m_id='hds', fatal=False))
else:
fmt = {
'url': stream_url,
'abr': float_or_none(stream.get('audioBitRate')),
'fps': float_or_none(stream.get('videoFrameRate')),
'ext': ext,
}
width = int_or_none(stream.get('videoWidthInPixels'))
height = int_or_none(stream.get('videoHeightInPixels'))
vbr = float_or_none(stream.get('videoBitRate'))
if width or height or vbr:
fmt.update({
'width': width,
'height': height,
'vbr': vbr,
})
else:
fmt['vcodec'] = 'none'
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', stream_url)
if rtmp:
format_id = 'rtmp'
if stream.get('videoBitRate'):
format_id += '-%d' % int_or_none(stream['videoBitRate'])
http_format_id = format_id.replace('rtmp', 'http')
CDN_HOSTS = (
('delvenetworks.com', 'cpl.delvenetworks.com'),
('video.llnw.net', 's2.content.video.llnw.net'),
)
for cdn_host, http_host in CDN_HOSTS:
if cdn_host not in rtmp.group('host').lower():
continue
http_url = 'http://{}/{}'.format(http_host, rtmp.group('playpath')[4:])
urls.append(http_url)
if self._is_valid_url(http_url, video_id, http_format_id):
http_fmt = fmt.copy()
http_fmt.update({
'url': http_url,
'format_id': http_format_id,
})
formats.append(http_fmt)
break
fmt.update({
'url': rtmp.group('url'),
'play_path': rtmp.group('playpath'),
'app': rtmp.group('app'),
'ext': 'flv',
'format_id': format_id,
})
formats.append(fmt)
for mobile_url in mobile_item.get('mobileUrls', []):
media_url = mobile_url.get('mobileUrl')
format_id = mobile_url.get('targetMediaPlatform')
if not media_url or media_url in urls:
continue
if (format_id in ('Widevine', 'SmoothStreaming')
and not self.get_param('allow_unplayable_formats', False)):
continue
urls.append(media_url)
ext = determine_ext(media_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
stream_url, video_id, f4m_id=format_id, fatal=False))
else:
formats.append({
'url': media_url,
'format_id': format_id,
'quality': -10,
'ext': ext,
})
subtitles = {}
for flag in mobile_item.get('flags'):
if flag == 'ClosedCaptions':
closed_captions = self._call_playlist_service(
video_id, 'getClosedCaptionsDetailsByMediaId',
False, referer) or []
for cc in closed_captions:
cc_url = cc.get('webvttFileUrl')
if not cc_url:
continue
lang = cc.get('languageCode') or self._search_regex(r'/([a-z]{2})\.vtt', cc_url, 'lang', default='en')
subtitles.setdefault(lang, []).append({
'url': cc_url,
})
break
get_meta = lambda x: pc_item.get(x) or mobile_item.get(x)
return {
'id': video_id,
'title': title,
'description': get_meta('description'),
'formats': formats,
'duration': float_or_none(get_meta('durationInMilliseconds'), 1000),
'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'),
'subtitles': subtitles,
}
class LimelightMediaIE(LimelightBaseIE):
IE_NAME = 'limelight'
_VALID_URL = r'''(?x)
(?:
limelight:media:|
https?://
(?:
link\.videoplatform\.limelight\.com/media/|
assets\.delvenetworks\.com/player/loader\.swf
)
\?.*?\bmediaId=
)
(?P<id>[a-z0-9]{32})
'''
_TESTS = [{
'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
'info_dict': {
'id': '3ffd040b522b4485b6d84effc750cd86',
'ext': 'mp4',
'title': 'HaP and the HB Prince Trailer',
'description': 'md5:8005b944181778e313d95c1237ddb640',
'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 144.23,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# video with subtitles
'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335',
'md5': '2fa3bad9ac321e23860ca23bc2c69e3d',
'info_dict': {
'id': 'a3e00274d4564ec4a9b29b9466432335',
'ext': 'mp4',
'title': '3Play Media Overview Video',
'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 78.101,
# TODO: extract all languages that were accessible via API
# 'subtitles': 'mincount:9',
'subtitles': 'mincount:1',
},
}, {
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'media'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
source_url = smuggled_data.get('source_url')
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
pc, mobile = self._extract(
video_id, 'getPlaylistByMediaId',
'getMobilePlaylistByMediaId', source_url)
return self._extract_info(pc, mobile, 0, source_url)
class LimelightChannelIE(LimelightBaseIE):
IE_NAME = 'limelight:channel'
_VALID_URL = r'''(?x)
(?:
limelight:channel:|
https?://
(?:
link\.videoplatform\.limelight\.com/media/|
assets\.delvenetworks\.com/player/loader\.swf
)
\?.*?\bchannelId=
)
(?P<id>[a-z0-9]{32})
'''
_TESTS = [{
'url': 'http://link.videoplatform.limelight.com/media/?channelId=ab6a524c379342f9b23642917020c082',
'info_dict': {
'id': 'ab6a524c379342f9b23642917020c082',
'title': 'Javascript Sample Code',
'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html',
},
'playlist_mincount': 3,
}, {
'url': 'http://assets.delvenetworks.com/player/loader.swf?channelId=ab6a524c379342f9b23642917020c082',
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'channel'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
channel_id = self._match_id(url)
source_url = smuggled_data.get('source_url')
pc, mobile = self._extract(
channel_id, 'getPlaylistByChannelId',
'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
source_url)
entries = [
self._extract_info(pc, mobile, i, source_url)
for i in range(len(pc['playlistItems']))]
return self.playlist_result(
entries, channel_id, pc.get('title'), mobile.get('description'))
class LimelightChannelListIE(LimelightBaseIE):
IE_NAME = 'limelight:channel_list'
_VALID_URL = r'''(?x)
(?:
limelight:channel_list:|
https?://
(?:
link\.videoplatform\.limelight\.com/media/|
assets\.delvenetworks\.com/player/loader\.swf
)
\?.*?\bchannelListId=
)
(?P<id>[a-z0-9]{32})
'''
_TESTS = [{
'url': 'http://link.videoplatform.limelight.com/media/?channelListId=301b117890c4465c8179ede21fd92e2b',
'info_dict': {
'id': '301b117890c4465c8179ede21fd92e2b',
'title': 'Website - Hero Player',
},
'playlist_mincount': 2,
}, {
'url': 'https://assets.delvenetworks.com/player/loader.swf?channelListId=301b117890c4465c8179ede21fd92e2b',
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'channel_list'
def _real_extract(self, url):
channel_list_id = self._match_id(url)
channel_list = self._call_playlist_service(
channel_list_id, 'getMobileChannelListById')
entries = [
self.url_result('limelight:channel:{}'.format(channel['id']), 'LimelightChannel')
for channel in channel_list['channelList']]
return self.playlist_result(
entries, channel_list_id, channel_list['title'])
plugins/youtube_download/yt_dlp/extractor/livejournal.py
+1
View File
@@ -3,6 +3,7 @@ from ..utils import int_or_none
class LiveJournalIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
_TEST = {
'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
plugins/youtube_download/yt_dlp/extractor/loco.py
+5 -5
View File
@@ -37,7 +37,7 @@ class LocoIE(InfoExtractor):
},
}, {
'url': 'https://loco.com/stream/c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
'md5': '45ebc8a47ee1c2240178757caf8881b5',
'md5': '8b9bda03eba4d066928ae8d71f19befb',
'info_dict': {
'id': 'c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
'ext': 'mp4',
@@ -55,9 +55,9 @@ class LocoIE(InfoExtractor):
'tags': ['Gameplay'],
'series': 'GTA 5',
'timestamp': 1740612872,
'modified_timestamp': 1740613037,
'modified_timestamp': 1750948439,
'upload_date': '20250226',
'modified_date': '20250226',
'modified_date': '20250626',
},
}, {
# Requires video authorization
@@ -123,8 +123,8 @@ class LocoIE(InfoExtractor):
def _real_extract(self, url):
video_type, video_id = self._match_valid_url(url).group('type', 'id')
webpage = self._download_webpage(url, video_id)
stream = traverse_obj(self._search_nextjs_data(webpage, video_id), (
'props', 'pageProps', ('liveStreamData', 'stream', 'liveStream'), {dict}, any, {require('stream info')}))
stream = traverse_obj(self._search_nextjs_v13_data(webpage, video_id), (
..., (None, 'ssrData'), ('liveStreamData', 'stream', 'liveStream'), {dict}, any, {require('stream info')}))
if access_token := self._get_access_token(video_id):
self._request_webpage(
plugins/youtube_download/yt_dlp/extractor/lrt.py
+78 -61
View File
@@ -1,23 +1,14 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
merge_dicts,
str_or_none,
traverse_obj,
unified_timestamp,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class LRTBaseIE(InfoExtractor):
def _extract_js_var(self, webpage, var_name, default=None):
return self._search_regex(
fr'{var_name}\s*=\s*(["\'])((?:(?!\1).)+)\1',
webpage, var_name.replace('_', ' '), default, group=2)
class LRTStreamIE(LRTBaseIE):
class LRTStreamIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/tiesiogiai/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://www.lrt.lt/mediateka/tiesiogiai/lrt-opus',
@@ -32,86 +23,110 @@ class LRTStreamIE(LRTBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
streams_data = self._download_json(self._extract_js_var(webpage, 'tokenURL'), video_id)
# TODO: Use _search_nextjs_v13_data once fixed
get_stream_url = self._search_regex(
r'\\"get_streams_url\\":\\"([^"]+)\\"', webpage, 'stream URL')
streams_data = self._download_json(get_stream_url, video_id)
formats, subtitles = [], {}
for stream_url in traverse_obj(streams_data, (
'response', 'data', lambda k, _: k.startswith('content')), expected_type=url_or_none):
fmts, subs = self._extract_m3u8_formats_and_subtitles(stream_url, video_id, 'mp4', m3u8_id='hls', live=True)
'response', 'data', lambda k, _: k.startswith('content'), {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
stream_url, video_id, 'mp4', m3u8_id='hls', live=True)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
stream_title = self._extract_js_var(webpage, 'video_title', 'LRT')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'is_live': True,
'title': f'{self._og_search_title(webpage)} - {stream_title}',
'title': self._og_search_title(webpage),
}
class LRTVODIE(LRTBaseIE):
_VALID_URL = r'https?://(?:www\.)?lrt\.lt(?P<path>/mediateka/irasas/(?P<id>[0-9]+))'
class LRTVODIE(InfoExtractor):
_VALID_URL = [
r'https?://(?:(?:www|archyvai)\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)',
r'https?://(?:(?:www|archyvai)\.)?lrt\.lt/mediateka/video/[^?#]+\?(?:[^#]*&)?episode=(?P<id>[0-9]+)',
]
_TESTS = [{
# m3u8 download
'url': 'https://www.lrt.lt/mediateka/irasas/2000127261/greita-ir-gardu-sicilijos-ikvepta-klasikiniu-makaronu-su-baklazanais-vakariene',
'info_dict': {
'id': '2000127261',
'ext': 'mp4',
'title': 'Greita ir gardu: Sicilijos įkvėpta klasikinių makaronų su baklažanais vakarienė',
'title': 'Nustebinkite svečius klasikiniu makaronų su baklažanais receptu',
'description': 'md5:ad7d985f51b0dc1489ba2d76d7ed47fa',
'duration': 3035,
'timestamp': 1604079000,
'timestamp': 1604086200,
'upload_date': '20201030',
'tags': ['LRT TELEVIZIJA', 'Beatos virtuvė', 'Beata Nicholson', 'Makaronai', 'Baklažanai', 'Vakarienė', 'Receptas'],
'thumbnail': 'https://www.lrt.lt/img/2020/10/30/764041-126478-1287x836.jpg',
'channel': 'Beatos virtuvė',
},
}, {
# direct mp3 download
'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
# audio download
'url': 'https://www.lrt.lt/mediateka/irasas/1013074524/kita-tema',
'md5': 'fc982f10274929c66fdff65f75615cb0',
'info_dict': {
'id': '1013074524',
'ext': 'mp3',
'title': 'Kita tema 2016-09-05 15:05',
'ext': 'mp4',
'title': 'Kita tema',
'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
'duration': 3008,
'view_count': int,
'like_count': int,
'channel': 'Kita tema',
'timestamp': 1473087900,
'upload_date': '20160905',
},
}, {
'url': 'https://www.lrt.lt/mediateka/video/auksinis-protas-vasara?episode=2000420320&season=%2Fmediateka%2Fvideo%2Fauksinis-protas-vasara%2F2025',
'info_dict': {
'id': '2000420320',
'ext': 'mp4',
'title': 'Kuris senovės romėnų poetas aprašė Narcizo mitą?',
'description': 'Intelektinė viktorina. Ved. Arūnas Valinskas ir Andrius Tapinas.',
'channel': 'Auksinis protas. Vasara',
'thumbnail': 'https://www.lrt.lt/img/2025/06/09/2094343-987905-1287x836.jpg',
'tags': ['LRT TELEVIZIJA', 'Auksinis protas'],
'timestamp': 1749851040,
'upload_date': '20250613',
},
}, {
'url': 'https://archyvai.lrt.lt/mediateka/video/ziniu-riteriai-ir-damos?episode=49685&season=%2Fmediateka%2Fvideo%2Fziniu-riteriai-ir-damos%2F2013',
'only_matching': True,
}, {
'url': 'https://archyvai.lrt.lt/mediateka/irasas/2000077058/panorama-1989-baltijos-kelias',
'only_matching': True,
}]
def _real_extract(self, url):
path, video_id = self._match_valid_url(url).group('path', 'id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
media_url = self._extract_js_var(webpage, 'main_url', path)
media = self._download_json(self._extract_js_var(
webpage, 'media_info_url',
'https://www.lrt.lt/servisai/stream_url/vod/media_info/'),
video_id, query={'url': media_url})
# TODO: Use _search_nextjs_v13_data once fixed
canonical_url = (
self._search_regex(r'\\"(?:article|data)\\":{[^}]*\\"url\\":\\"(/[^"]+)\\"', webpage, 'content URL', fatal=False)
or self._search_regex(r'<link\s+rel="canonical"\s*href="(/[^"]+)"', webpage, 'canonical URL'))
media = self._download_json(
'https://www.lrt.lt/servisai/stream_url/vod/media_info/',
video_id, query={'url': canonical_url})
jw_data = self._parse_jwplayer_data(
media['playlist_item'], video_id, base_url=url)
json_ld_data = self._search_json_ld(webpage, video_id)
tags = []
for tag in (media.get('tags') or []):
tag_name = tag.get('name')
if not tag_name:
continue
tags.append(tag_name)
clean_info = {
'description': clean_html(media.get('content')),
'tags': tags,
return {
**jw_data,
**traverse_obj(media, {
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('content', {clean_html}),
'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
'tags': ('tags', ..., 'name', {str}),
}),
}
return merge_dicts(clean_info, jw_data, json_ld_data)
class LRTRadioIE(LRTBaseIE):
class LRTRadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?lrt\.lt/radioteka/irasas/(?P<id>\d+)/(?P<path>[^?#/]+)'
_TESTS = [{
# m3u8 download
@@ -135,16 +150,18 @@ class LRTRadioIE(LRTBaseIE):
def _real_extract(self, url):
video_id, path = self._match_valid_url(url).group('id', 'path')
media = self._download_json(
'https://www.lrt.lt/radioteka/api/media', video_id,
'https://www.lrt.lt/rest-api/media', video_id,
query={'url': f'/mediateka/irasas/{video_id}/{path}'})
return traverse_obj(media, {
'id': ('id', {int}, {str_or_none}),
'title': ('title', {str}),
'tags': ('tags', ..., 'name', {str}),
'categories': ('playlist_item', 'category', {str}, filter, all, filter),
'description': ('content', {clean_html}, {str}),
'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
'formats': ('playlist_item', 'file', {lambda x: self._extract_m3u8_formats(x, video_id)}),
})
return {
'id': video_id,
'formats': self._extract_m3u8_formats(media['playlist_item']['file'], video_id),
**traverse_obj(media, {
'title': ('title', {str}),
'tags': ('tags', ..., 'name', {str}),
'categories': ('playlist_item', 'category', {str}, filter, all, filter),
'description': ('content', {clean_html}, {str}),
'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
}),
}
plugins/youtube_download/yt_dlp/extractor/lsm.py
+30 -13
View File
@@ -167,11 +167,11 @@ class LSMLTVEmbedIE(InfoExtractor):
'duration': 1442,
'upload_date': '20231121',
'title': 'D23-6000-105_cetstud',
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
},
}, {
'url': 'https://ltv.lsm.lv/embed?enablesdkjs=1&c=eyJpdiI6IncwVzZmUFk2MU12enVWK1I3SUcwQ1E9PSIsInZhbHVlIjoid3FhV29vamc3T2sxL1RaRmJ5Rm1GTXozU0o2dVczdUtLK0cwZEZJMDQ2a3ZIRG5DK2pneGlnbktBQy9uazVleHN6VXhxdWIweWNvcHRDSnlISlNYOHlVZ1lpcTUrcWZSTUZPQW14TVdkMW9aOUtRWVNDcFF4eWpHNGcrT0VZbUNFQStKQk91cGpndW9FVjJIa0lpbkh3PT0iLCJtYWMiOiIyZGI1NDJlMWRlM2QyMGNhOGEwYTM2MmNlN2JlOGRhY2QyYjdkMmEzN2RlOTEzYTVkNzI1ODlhZDlhZjU4MjQ2IiwidGFnIjoiIn0=',
'md5': 'a1711e190fe680fdb68fd8413b378e87',
'md5': 'f236cef2fd5953612754e4e66be51e7a',
'info_dict': {
'id': 'wUnFArIPDSY',
'ext': 'mp4',
@@ -198,6 +198,8 @@ class LSMLTVEmbedIE(InfoExtractor):
'uploader_url': 'https://www.youtube.com/@LTV16plus',
'like_count': int,
'description': 'md5:7ff0c42ba971e3c13e4b8a2ff03b70b5',
'media_type': 'livestream',
'timestamp': 1652550741,
},
}]
@@ -208,7 +210,7 @@ class LSMLTVEmbedIE(InfoExtractor):
r'window\.ltvEmbedPayload\s*=', webpage, 'embed json', video_id)
embed_type = traverse_obj(data, ('source', 'name', {str}))
if embed_type == 'telia':
if embed_type in ('backscreen', 'telia'): # 'telia' only for backwards compat
ie_key = 'CloudyCDN'
embed_url = traverse_obj(data, ('source', 'embed_url', {url_or_none}))
elif embed_type == 'youtube':
@@ -226,9 +228,9 @@ class LSMLTVEmbedIE(InfoExtractor):
class LSMReplayIE(InfoExtractor):
_VALID_URL = r'https?://replay\.lsm\.lv/[^/?#]+/(?:ieraksts|statja)/[^/?#]+/(?P<id>\d+)'
_VALID_URL = r'https?://replay\.lsm\.lv/[^/?#]+/(?:skaties/|klausies/)?(?:ieraksts|statja)/[^/?#]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://replay.lsm.lv/lv/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'url': 'https://replay.lsm.lv/lv/skaties/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'md5': '64f72a360ca530d5ed89c77646c9eee5',
'info_dict': {
'id': '46k_d23-6000-105',
@@ -241,20 +243,23 @@ class LSMReplayIE(InfoExtractor):
'thumbnail': 'https://ltv.lsm.lv/storage/media/8/7/large/5/1f9604e1.jpg',
},
}, {
'url': 'https://replay.lsm.lv/lv/ieraksts/lr/183522/138-nepilniga-kompensejamo-zalu-sistema-pat-menesiem-dzena-pacientus-pa-aptiekam',
'md5': '719b33875cd1429846eeeaeec6df2830',
'url': 'https://replay.lsm.lv/lv/klausies/ieraksts/lr/183522/138-nepilniga-kompensejamo-zalu-sistema-pat-menesiem-dzena-pacientus-pa-aptiekam',
'md5': '84feb80fd7e6ec07744726a9f01cda4d',
'info_dict': {
'id': 'a342781',
'ext': 'mp3',
'id': '183522',
'ext': 'm4a',
'duration': 1823,
'title': '#138 Nepilnīgā kompensējamo zāļu sistēma pat mēnešiem dzenā pacientus pa aptiekām',
'thumbnail': 'https://pic.latvijasradio.lv/public/assets/media/9/d/large_fd4675ac.jpg',
'upload_date': '20231102',
'timestamp': 1698921060,
'timestamp': 1698913860,
'description': 'md5:7bac3b2dd41e44325032943251c357b1',
},
}, {
'url': 'https://replay.lsm.lv/ru/statja/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'url': 'https://replay.lsm.lv/ru/skaties/statja/ltv/355067/v-kengaragse-nacalas-ukladka-relsov',
'only_matching': True,
}, {
'url': 'https://replay.lsm.lv/lv/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'only_matching': True,
}]
@@ -267,12 +272,24 @@ class LSMReplayIE(InfoExtractor):
data = self._search_nuxt_data(
self._fix_nuxt_data(webpage), video_id, context_name='__REPLAY__')
playback_type = data['playback']['type']
if playback_type == 'playable_audio_lr':
playback_data = {
'formats': self._extract_m3u8_formats(data['playback']['service']['hls_url'], video_id),
}
elif playback_type == 'embed':
playback_data = {
'_type': 'url_transparent',
'url': data['playback']['service']['url'],
}
else:
raise ExtractorError(f'Unsupported playback type "{playback_type}"')
return {
'_type': 'url_transparent',
'id': video_id,
**playback_data,
**traverse_obj(data, {
'url': ('playback', 'service', 'url', {url_or_none}),
'title': ('mediaItem', 'title'),
'description': ('mediaItem', ('lead', 'body')),
'duration': ('mediaItem', 'duration', {int_or_none}),
plugins/youtube_download/yt_dlp/extractor/lynda.py
+2 -1
View File
@@ -1,3 +1,4 @@
import itertools
import re
import urllib.parse
@@ -216,7 +217,7 @@ class LyndaIE(LyndaBaseIE):
def _fix_subtitles(self, subs):
srt = ''
seq_counter = 0
for seq_current, seq_next in zip(subs, subs[1:]):
for seq_current, seq_next in itertools.pairwise(subs):
m_current = re.match(self._TIMECODE_REGEX, seq_current['Timecode'])
if m_current is None:
continue
plugins/youtube_download/yt_dlp/extractor/mainstreaming.py
+96 -84
View File
@@ -16,91 +16,103 @@ class MainStreamingIE(InfoExtractor):
_EMBED_REGEX = [rf'<iframe[^>]+?src=["\']?(?P<url>{_VALID_URL})["\']?']
IE_DESC = 'MainStreaming Player'
_TESTS = [
{
# Live stream offline, has alternative content id
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/53EN6GxbWaJC',
'info_dict': {
'id': '53EN6GxbWaJC',
'title': 'Diretta homepage 2021-12-31 12:00',
'description': '',
'live_status': 'was_live',
'ext': 'mp4',
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
},
'expected_warnings': [
'Ignoring alternative content ID: WDAF1KOWUpH3',
'MainStreaming said: Live event is OFFLINE',
],
'skip': 'live stream offline',
}, {
# playlist
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/WDAF1KOWUpH3',
'info_dict': {
'id': 'WDAF1KOWUpH3',
'title': 'Playlist homepage',
},
'playlist_mincount': 2,
}, {
# livestream
'url': 'https://webtools-859c1818ed614cc5b0047439470927b0.msvdn.net/embed/tDoFkZD3T1Lw',
'info_dict': {
'id': 'tDoFkZD3T1Lw',
'title': r're:Class CNBC Live \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'live_status': 'is_live',
'ext': 'mp4',
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
},
'skip': 'live stream',
}, {
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/EUlZfGWkGpOd?autoPlay=false',
'info_dict': {
'id': 'EUlZfGWkGpOd',
'title': 'La Settimana ',
'description': '03 Ottobre ore 02:00',
'ext': 'mp4',
'live_status': 'not_live',
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
'duration': 1512,
},
}, {
# video without webtools- prefix
'url': 'https://f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/MfuWmzL2lGkA?autoplay=false&T=1635860445',
'info_dict': {
'id': 'MfuWmzL2lGkA',
'title': 'TG Mattina',
'description': '06 Ottobre ore 08:00',
'ext': 'mp4',
'live_status': 'not_live',
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
'duration': 789.04,
},
}, {
# always-on livestream with DVR
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/HVvPMzy',
'info_dict': {
'id': 'HVvPMzy',
'title': r're:^Diretta LaC News24 \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'description': 'canale all news',
'live_status': 'is_live',
'ext': 'mp4',
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
},
'params': {
'skip_download': True,
},
}, {
# no host
'url': 'https://webtools.msvdn.net/embed/MfuWmzL2lGkA',
'only_matching': True,
}, {
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/amp_embed/tDoFkZD3T1Lw',
'only_matching': True,
}, {
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/content/tDoFkZD3T1Lw#',
'only_matching': True,
_TESTS = [{
# Live stream offline, has alternative content id
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/53EN6GxbWaJC',
'info_dict': {
'id': '53EN6GxbWaJC',
'title': 'Diretta homepage 2021-12-31 12:00',
'description': '',
'live_status': 'was_live',
'ext': 'mp4',
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
},
]
'expected_warnings': [
'Ignoring alternative content ID: WDAF1KOWUpH3',
'MainStreaming said: Live event is OFFLINE',
],
'skip': 'live stream offline',
}, {
# playlist
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/WDAF1KOWUpH3',
'info_dict': {
'id': 'WDAF1KOWUpH3',
'title': 'Playlist homepage',
},
'playlist_mincount': 2,
}, {
# livestream
'url': 'https://webtools-859c1818ed614cc5b0047439470927b0.msvdn.net/embed/tDoFkZD3T1Lw',
'info_dict': {
'id': 'tDoFkZD3T1Lw',
'title': str,
'live_status': 'is_live',
'ext': 'mp4',
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
},
'skip': 'live stream',
}, {
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/EUlZfGWkGpOd?autoPlay=false',
'info_dict': {
'id': 'EUlZfGWkGpOd',
'title': 'La Settimana ',
'description': '03 Ottobre ore 02:00',
'ext': 'mp4',
'live_status': 'not_live',
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
'duration': 1512,
},
'skip': 'Invalid URL',
}, {
# video without webtools- prefix
'url': 'https://f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/MfuWmzL2lGkA?autoplay=false&T=1635860445',
'info_dict': {
'id': 'MfuWmzL2lGkA',
'title': 'TG Mattina',
'description': '06 Ottobre ore 08:00',
'ext': 'mp4',
'live_status': 'not_live',
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
'duration': 789.04,
},
'skip': 'Invalid URL',
}, {
# always-on livestream with DVR
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/HVvPMzy',
'info_dict': {
'id': 'HVvPMzy',
'title': str,
'description': 'canale all news',
'live_status': 'is_live',
'ext': 'mp4',
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
},
'params': {'skip_download': 'm3u8'},
}, {
# no host
'url': 'https://webtools.msvdn.net/embed/MfuWmzL2lGkA',
'only_matching': True,
}, {
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/amp_embed/tDoFkZD3T1Lw',
'only_matching': True,
}, {
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/content/tDoFkZD3T1Lw#',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://www.lacplay.it/video/in-evidenza_728/lac-storie-p-250-i-santi-pietro-e-paolo_77297/',
'info_dict': {
'id': 'u7kiX5DUaHYr',
'ext': 'mp4',
'title': 'I Santi Pietro e Paolo',
'description': 'md5:ff6be24916ba6b9ae990bf5f3df4911e',
'duration': 1700.0,
'thumbnail': r're:https?://.+',
'tags': '06/07/2025',
'live_status': 'not_live',
},
}]
def _playlist_entries(self, host, playlist_content):
for entry in playlist_content:
plugins/youtube_download/yt_dlp/extractor/mave.py
+107
View File
@@ -0,0 +1,107 @@
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
parse_iso8601,
urljoin,
)
from ..utils.traversal import require, traverse_obj
class MaveIE(InfoExtractor):
_VALID_URL = r'https?://(?P<channel>[\w-]+)\.mave\.digital/(?P<id>ep-\d+)'
_TESTS = [{
'url': 'https://ochenlichnoe.mave.digital/ep-25',
'md5': 'aa3e513ef588b4366df1520657cbc10c',
'info_dict': {
'id': '4035f587-914b-44b6-aa5a-d76685ad9bc2',
'ext': 'mp3',
'display_id': 'ochenlichnoe-ep-25',
'title': 'Между мной и миром: психология самооценки',
'description': 'md5:4b7463baaccb6982f326bce5c700382a',
'uploader': 'Самарский университет',
'channel': 'Очень личное',
'channel_id': 'ochenlichnoe',
'channel_url': 'https://ochenlichnoe.mave.digital/',
'view_count': int,
'like_count': int,
'dislike_count': int,
'duration': 3744,
'thumbnail': r're:https://.+/storage/podcasts/.+\.jpg',
'series': 'Очень личное',
'series_id': '2e0c3749-6df2-4946-82f4-50691419c065',
'season': 'Season 3',
'season_number': 3,
'episode': 'Episode 3',
'episode_number': 3,
'timestamp': 1747817300,
'upload_date': '20250521',
},
}, {
'url': 'https://budem.mave.digital/ep-12',
'md5': 'e1ce2780fcdb6f17821aa3ca3e8c919f',
'info_dict': {
'id': '41898bb5-ff57-4797-9236-37a8e537aa21',
'ext': 'mp3',
'display_id': 'budem-ep-12',
'title': 'Екатерина Михайлова: "Горе от ума" не про женщин написана',
'description': 'md5:fa3bdd59ee829dfaf16e3efcb13f1d19',
'uploader': 'Полина Цветкова+Евгения Акопова',
'channel': 'Все там будем',
'channel_id': 'budem',
'channel_url': 'https://budem.mave.digital/',
'view_count': int,
'like_count': int,
'dislike_count': int,
'age_limit': 18,
'duration': 3664,
'thumbnail': r're:https://.+/storage/podcasts/.+\.jpg',
'series': 'Все там будем',
'series_id': 'fe9347bf-c009-4ebd-87e8-b06f2f324746',
'season': 'Season 2',
'season_number': 2,
'episode': 'Episode 5',
'episode_number': 5,
'timestamp': 1735538400,
'upload_date': '20241230',
},
}]
_API_BASE_URL = 'https://api.mave.digital/'
def _real_extract(self, url):
channel_id, slug = self._match_valid_url(url).group('channel', 'id')
display_id = f'{channel_id}-{slug}'
webpage = self._download_webpage(url, display_id)
data = traverse_obj(
self._search_nuxt_json(webpage, display_id),
('data', lambda _, v: v['activeEpisodeData'], any, {require('podcast data')}))
return {
'display_id': display_id,
'channel_id': channel_id,
'channel_url': f'https://{channel_id}.mave.digital/',
'vcodec': 'none',
'thumbnail': re.sub(r'_\d+(?=\.(?:jpg|png))', '', self._og_search_thumbnail(webpage, default='')) or None,
**traverse_obj(data, ('activeEpisodeData', {
'url': ('audio', {urljoin(self._API_BASE_URL)}),
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('description', {clean_html}),
'duration': ('duration', {int_or_none}),
'season_number': ('season', {int_or_none}),
'episode_number': ('number', {int_or_none}),
'view_count': ('listenings', {int_or_none}),
'like_count': ('reactions', lambda _, v: v['type'] == 'like', 'count', {int_or_none}, any),
'dislike_count': ('reactions', lambda _, v: v['type'] == 'dislike', 'count', {int_or_none}, any),
'age_limit': ('is_explicit', {bool}, {lambda x: 18 if x else None}),
'timestamp': ('publish_date', {parse_iso8601}),
})),
**traverse_obj(data, ('podcast', 'podcast', {
'series_id': ('id', {str}),
'series': ('title', {str}),
'channel': ('title', {str}),
'uploader': ('author', {str}),
})),
}
plugins/youtube_download/yt_dlp/extractor/mediaklikk.py
+37 -94
View File
@@ -11,121 +11,65 @@ from ..utils import (
class MediaKlikkIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?
(?:mediaklikk|m4sport|hirado|petofilive)\.hu/.*?(?:videok?|cikk)/
(?:mediaklikk|m4sport|hirado)\.hu/.*?(?:videok?|cikk)/
(?:(?P<year>[0-9]{4})/(?P<month>[0-9]{1,2})/(?P<day>[0-9]{1,2})/)?
(?P<id>[^/#?_]+)'''
_TESTS = [{
'url': 'https://mediaklikk.hu/filmajanlo/cikk/az-ajto/',
# mediaklikk
'url': 'https://mediaklikk.hu/ajanlo/video/2025/08/04/heviz-dzsungel-a-viz-alatt-ajanlo-08-10/',
'info_dict': {
'id': '668177',
'title': 'Az ajtó',
'display_id': 'az-ajto',
'id': '8573769',
'title': 'Hévíz - dzsungel a víz alatt – Ajánló (08.10.)',
'display_id': 'heviz-dzsungel-a-viz-alatt-ajanlo-08-10',
'ext': 'mp4',
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2016/01/vlcsnap-2023-07-31-14h18m52s111.jpg',
'upload_date': '20250804',
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/vlcsnap-2025-08-04-13h48m24s336.jpg',
},
}, {
# (old) mediaklikk. date in html.
'url': 'https://mediaklikk.hu/video/hazajaro-delnyugat-bacska-a-duna-menten-palankatol-doroszloig/',
# mediaklikk - date in html
'url': 'https://mediaklikk.hu/video/hazajaro-bilo-hegyseg-verocei-barangolas-a-drava-menten/',
'info_dict': {
'id': '4754129',
'title': 'Hazajáró, DÉLNYUGAT-BÁCSKA – A Duna mentén Palánkától Doroszlóig',
'id': '8482167',
'title': 'Hazajáró, Bilo-hegység - Verőcei barangolás a Dráva mentén',
'display_id': 'hazajaro-bilo-hegyseg-verocei-barangolas-a-drava-menten',
'ext': 'mp4',
'upload_date': '20210901',
'thumbnail': 'http://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg',
'upload_date': '20250703',
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/07/2024-000307-M0010-01_3700_cover_01.jpg',
},
'skip': 'Webpage redirects to 404 page',
}, {
# mediaklikk. date in html.
'url': 'https://mediaklikk.hu/video/hazajaro-fabova-hegyseg-kishont-koronaja/',
'info_dict': {
'id': '6696133',
'title': 'Hazajáró, Fabova-hegység - Kishont koronája',
'display_id': 'hazajaro-fabova-hegyseg-kishont-koronaja',
'ext': 'mp4',
'upload_date': '20230903',
'thumbnail': 'https://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg',
},
'skip': 'Webpage redirects to 404 page',
}, {
# (old) m4sport
'url': 'https://m4sport.hu/video/2021/08/30/gyemant-liga-parizs/',
'info_dict': {
'id': '4754999',
'title': 'Gyémánt Liga, Párizs',
'ext': 'mp4',
'upload_date': '20210830',
'thumbnail': 'http://m4sport.hu/wp-content/uploads/sites/4/2021/08/vlcsnap-2021-08-30-18h21m20s10-1024x576.jpg',
},
'skip': 'Webpage redirects to 404 page',
}, {
# m4sport
'url': 'https://m4sport.hu/sportkozvetitesek/video/2023/09/08/atletika-gyemant-liga-brusszel/',
'url': 'https://m4sport.hu/video/2025/08/07/holnap-kezdodik-a-12-vilagjatekok/',
'info_dict': {
'id': '6711136',
'title': 'Atlétika – Gyémánt Liga, Brüsszel',
'display_id': 'atletika-gyemant-liga-brusszel',
'id': '8581887',
'title': 'Holnap kezdődik a 12. Világjátékok',
'display_id': 'holnap-kezdodik-a-12-vilagjatekok',
'ext': 'mp4',
'upload_date': '20230908',
'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-08-22h43m18s691.jpg',
'upload_date': '20250807',
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/vlcsnap-2025-08-06-20h30m48s817.jpg',
},
'skip': 'Webpage redirects to 404 page',
}, {
# m4sport with *video/ url and no date
'url': 'https://m4sport.hu/bl-video/real-madrid-chelsea-1-1/',
'info_dict': {
'id': '4492099',
'title': 'Real Madrid - Chelsea 1-1',
'display_id': 'real-madrid-chelsea-1-1',
'ext': 'mp4',
'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2021/04/Sequence-01.Still001-1024x576.png',
},
'skip': 'Webpage redirects to 404 page',
}, {
# (old) hirado
'url': 'https://hirado.hu/videok/felteteleket-szabott-a-fovaros/',
'info_dict': {
'id': '4760120',
'title': 'Feltételeket szabott a főváros',
'ext': 'mp4',
'thumbnail': 'http://hirado.hu/wp-content/uploads/sites/4/2021/09/vlcsnap-2021-09-01-20h20m37s165.jpg',
},
'skip': 'Webpage redirects to video list page',
}, {
# hirado
'url': 'https://hirado.hu/belfold/video/2023/09/11/marad-az-eves-elszamolas-a-napelemekre-beruhazo-csaladoknal',
'url': 'https://hirado.hu/video/2025/08/09/idojaras-jelentes-2025-augusztus-9-2230',
'info_dict': {
'id': '6716068',
'title': 'Marad az éves elszámolás a napelemekre beruházó családoknál',
'display_id': 'marad-az-eves-elszamolas-a-napelemekre-beruhazo-csaladoknal',
'id': '8592033',
'title': 'Időjárás-jelentés, 2025. augusztus 9. 22:30',
'display_id': 'idojaras-jelentes-2025-augusztus-9-2230',
'ext': 'mp4',
'upload_date': '20230911',
'thumbnail': 'https://hirado.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-11-09h16m09s882.jpg',
'upload_date': '20250809',
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/Idojaras-jelentes-35-1.jpg',
},
'skip': 'Webpage redirects to video list page',
}, {
# (old) petofilive
'url': 'https://petofilive.hu/video/2021/06/07/tha-shudras-az-akusztikban/',
# hirado - subcategory
'url': 'https://hirado.hu/belfold/video/2025/08/09/nyitott-porta-napok-2025/',
'info_dict': {
'id': '4571948',
'title': 'Tha Shudras az Akusztikban',
'id': '8590581',
'title': 'Nyitott Porta Napok 2025',
'display_id': 'nyitott-porta-napok-2025',
'ext': 'mp4',
'upload_date': '20210607',
'thumbnail': 'http://petofilive.hu/wp-content/uploads/sites/4/2021/06/vlcsnap-2021-06-07-22h14m23s915-1024x576.jpg',
'upload_date': '20250809',
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/vlcsnap-2025-08-09-10h35m01s887.jpg',
},
'skip': 'Webpage redirects to empty page',
}, {
# petofilive
'url': 'https://petofilive.hu/video/2023/09/09/futball-fesztival-a-margitszigeten/',
'info_dict': {
'id': '6713233',
'title': 'Futball Fesztivál a Margitszigeten',
'display_id': 'futball-fesztival-a-margitszigeten',
'ext': 'mp4',
'upload_date': '20230909',
'thumbnail': 'https://petofilive.hu/wp-content/uploads/sites/4/2023/09/Clipboard11-2.jpg',
},
'skip': 'Webpage redirects to video list page',
}]
def _real_extract(self, url):
@@ -133,9 +77,8 @@ class MediaKlikkIE(InfoExtractor):
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
player_data_str = self._html_search_regex(
r'mtva_player_manager\.player\(document.getElementById\(.*\),\s?(\{.*\}).*\);', webpage, 'player data')
player_data = self._parse_json(player_data_str, display_id, urllib.parse.unquote)
player_data = self._search_json(
r'loadPlayer\((?:\s*["\'][^"\']+["\']\s*,)?', webpage, 'player data', mobj)
video_id = str(player_data['contentId'])
title = player_data.get('title') or self._og_search_title(webpage, fatal=False) or \
self._html_search_regex(r'<h\d+\b[^>]+\bclass="article_title">([^<]+)<', webpage, 'title')
@@ -146,7 +89,7 @@ class MediaKlikkIE(InfoExtractor):
upload_date = unified_strdate(self._html_search_regex(
r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
player_data['video'] = player_data.pop('token')
player_data['video'] = urllib.parse.unquote(player_data.pop('token'))
player_page = self._download_webpage(
'https://player.mediaklikk.hu/playernew/player.php', video_id,
query=player_data, headers={'Referer': url})
plugins/youtube_download/yt_dlp/extractor/medialaan.py
+164 -51
View File
@@ -1,15 +1,73 @@
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
extract_attributes,
int_or_none,
mimetype2ext,
parse_iso8601,
parse_resolution,
str_or_none,
url_or_none,
)
from ..utils.traversal import find_elements, traverse_obj
class MedialaanIE(InfoExtractor):
class MedialaanBaseIE(InfoExtractor):
def _extract_from_mychannels_api(self, mychannels_id):
webpage = self._download_webpage(
f'https://mychannels.video/embed/{mychannels_id}', mychannels_id)
brand_config = self._search_json(
r'window\.mychannels\.brand_config\s*=', webpage, 'brand config', mychannels_id)
response = self._download_json(
f'https://api.mychannels.world/v1/embed/video/{mychannels_id}',
mychannels_id, headers={'X-Mychannels-Brand': brand_config['brand']})
formats = []
for stream in traverse_obj(response, (
'streams', lambda _, v: url_or_none(v['url']),
)):
source_url = stream['url']
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, mychannels_id, 'mp4', m3u8_id='hls', fatal=False))
else:
format_id = traverse_obj(stream, ('quality', {str}))
formats.append({
'ext': ext,
'format_id': format_id,
'url': source_url,
**parse_resolution(format_id),
})
return {
'id': mychannels_id,
'formats': formats,
**traverse_obj(response, {
'title': ('title', {clean_html}),
'description': ('description', {clean_html}, filter),
'duration': ('durationMs', {int_or_none(scale=1000)}, {lambda x: x if x >= 0 else None}),
'genres': ('genre', 'title', {str}, filter, all, filter),
'is_live': ('live', {bool}),
'release_timestamp': ('publicationTimestampMs', {int_or_none(scale=1000)}),
'tags': ('tags', ..., 'title', {str}, filter, all, filter),
'thumbnail': ('image', 'baseUrl', {url_or_none}),
}),
**traverse_obj(response, ('channel', {
'channel': ('title', {clean_html}),
'channel_id': ('id', {str_or_none}),
})),
**traverse_obj(response, ('organisation', {
'uploader': ('title', {clean_html}),
'uploader_id': ('id', {str_or_none}),
})),
**traverse_obj(response, ('show', {
'series': ('title', {clean_html}),
'series_id': ('id', {str_or_none}),
})),
}
class MedialaanIE(MedialaanBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
@@ -32,7 +90,7 @@ class MedialaanIE(InfoExtractor):
tubantia|
volkskrant
)\.nl
)/video/(?:[^/]+/)*[^/?&#]+~p
)/videos?/(?:[^/?#]+/)*[^/?&#]+(?:-|~p)
)
(?P<id>\d+)
'''
@@ -42,18 +100,83 @@ class MedialaanIE(InfoExtractor):
'id': '193993',
'ext': 'mp4',
'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?',
'timestamp': 1611663540,
'upload_date': '20210126',
'description': 'In een nieuwe Gegenpressing video bespreken Yadran Blanco en Dennis Kas het nieuws omrent NAC.',
'duration': 238,
},
'params': {
'skip_download': True,
'channel': 'BN DeStem',
'channel_id': '418',
'genres': ['Sports'],
'release_date': '20210126',
'release_timestamp': 1611663540,
'series': 'Korte Reportage',
'series_id': '972',
'tags': 'count:2',
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
'uploader': 'BN De Stem',
'uploader_id': '26',
},
}, {
'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093',
'only_matching': True,
'info_dict': {
'id': '194093',
'ext': 'mp4',
'title': 'Noodbevel in Doetinchem: politie stuurt mensen centrum uit',
'description': 'md5:77e85b2cb26cfff9dc1fe2b1db524001',
'duration': 44,
'channel': 'De Gelderlander',
'channel_id': '320',
'genres': ['News'],
'release_date': '20210126',
'release_timestamp': 1611690600,
'series': 'Snel Nieuws',
'series_id': '984',
'tags': 'count:1',
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
'uploader': 'De Gelderlander',
'uploader_id': '25',
},
}, {
'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default',
'url': 'https://www.7sur7.be/videos/production/lla-tendance-tiktok-qui-enflamme-lespagne-707650',
'info_dict': {
'id': '707650',
'ext': 'mp4',
'title': 'La tendance TikTok qui enflamme l’Espagne',
'description': 'md5:c7ec4cb733190f227fc8935899f533b5',
'duration': 70,
'channel': 'Lifestyle',
'channel_id': '770',
'genres': ['Beauty & Lifestyle'],
'release_date': '20240906',
'release_timestamp': 1725617330,
'series': 'Lifestyle',
'series_id': '1848',
'tags': 'count:1',
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
'uploader': '7sur7',
'uploader_id': '67',
},
}, {
'url': 'https://mychannels.video/embed/313117',
'info_dict': {
'id': '313117',
'ext': 'mp4',
'title': str,
'description': 'md5:255e2e52f6fe8a57103d06def438f016',
'channel': 'AD',
'channel_id': '238',
'genres': ['News'],
'live_status': 'is_live',
'release_date': '20241225',
'release_timestamp': 1735169425,
'series': 'Nieuws Update',
'series_id': '3337',
'tags': 'count:1',
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
'uploader': 'AD',
'uploader_id': '1',
},
'params': {'skip_download': 'Livestream'},
}, {
'url': 'https://embed.mychannels.video/sdk/production/193993',
'only_matching': True,
}, {
'url': 'https://embed.mychannels.video/script/production/193993',
@@ -61,51 +184,41 @@ class MedialaanIE(InfoExtractor):
}, {
'url': 'https://embed.mychannels.video/production/193993',
'only_matching': True,
}, {
'url': 'https://mychannels.video/embed/193993',
'only_matching': True,
}, {
'url': 'https://embed.mychannels.video/embed/193993',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.demorgen.be/snelnieuws/tom-waes-promoot-alcoholtesten-op-werchter-ik-ben-de-laatste-persoon-die-met-de-vinger-moet-wijzen~b7457c0d/',
'info_dict': {
'id': '1576607',
'ext': 'mp4',
'title': 'Tom Waes blaastest',
'channel': 'De Morgen',
'channel_id': '352',
'description': 'Tom Waes werkt mee aan een alcoholcampagne op Werchter',
'duration': 62,
'genres': ['News'],
'release_date': '20250705',
'release_timestamp': 1751730795,
'series': 'Nieuwsvideo\'s',
'series_id': '1683',
'tags': 'count:1',
'thumbnail': r're:https?://video-images\.persgroep\.be/aws_generated.+\.jpg',
'uploader': 'De Morgen',
'uploader_id': '17',
},
'params': {'extractor_args': {'generic': {'impersonate': ['chrome']}}},
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
entries = []
for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
mychannels_id = extract_attributes(element).get('data-mychannels-id')
if mychannels_id:
entries.append('https://mychannels.video/embed/' + mychannels_id)
return entries
yield from traverse_obj(webpage, (
{find_elements(tag='div', attr='data-mychannels-type', value='video', html=True)},
..., {extract_attributes}, 'data-mychannels-id', {str}, filter,
{lambda x: f'https://mychannels.video/embed/{x}'}))
def _real_extract(self, url):
production_id = self._match_id(url)
production = self._download_json(
'https://embed.mychannels.video/sdk/production/' + production_id,
production_id, query={'options': 'UUUU_default'})['productions'][0]
title = production['title']
mychannels_id = self._match_id(url)
formats = []
for source in (production.get('sources') or []):
src = source.get('src')
if not src:
continue
ext = mimetype2ext(source.get('type'))
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
src, production_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'ext': ext,
'url': src,
})
return {
'id': production_id,
'title': title,
'formats': formats,
'thumbnail': production.get('posterUrl'),
'timestamp': parse_iso8601(production.get('publicationDate'), ' '),
'duration': int_or_none(production.get('duration')) or None,
}
return self._extract_from_mychannels_api(mychannels_id)
plugins/youtube_download/yt_dlp/extractor/megatvcom.py
+15 -7
View File
@@ -31,10 +31,9 @@ class MegaTVComIE(MegaTVComBaseIE):
IE_NAME = 'megatvcom'
IE_DESC = 'megatv.com videos'
_VALID_URL = r'https?://(?:www\.)?megatv\.com/(?:\d{4}/\d{2}/\d{2}|[^/]+/(?P<id>\d+))/(?P<slug>[^/]+)'
_TESTS = [{
# FIXME: Unable to extract article id
'url': 'https://www.megatv.com/2021/10/23/egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia/',
'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
'info_dict': {
'id': '520979',
'ext': 'mp4',
@@ -43,20 +42,19 @@ class MegaTVComIE(MegaTVComBaseIE):
'timestamp': 1634975747,
'upload_date': '20211023',
'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
'thumbnail': r're:https?://www\.megatv\.com/wp-content/uploads/.+\.jpg',
},
}, {
'url': 'https://www.megatv.com/tvshows/527800/epeisodio-65-12/',
'md5': 'cba2085d45c1abeb8e7e9b7e1d6c0072',
'info_dict': {
'id': '527800',
'ext': 'mp4',
'title': 'md5:fc322cb51f682eecfe2f54cd5ab3a157',
'title': 'Η Γη της Ελιάς: Επεισόδιο 65 - A\' ΚΥΚΛΟΣ ',
'description': 'md5:b2b7ed3690a78f2a0156eb790fdc00df',
'timestamp': 1636048859,
'upload_date': '20211104',
'display_id': 'epeisodio-65-12',
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/16-1-1.jpg',
'thumbnail': r're:https?://www\.megatv\.com/wp-content/uploads/.+\.jpg',
},
}]
@@ -104,8 +102,8 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
IE_DESC = 'megatv.com embedded videos'
_VALID_URL = r'(?:https?:)?//(?:www\.)?megatv\.com/embed/?\?p=(?P<id>\d+)'
_EMBED_REGEX = [rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''']
_TESTS = [{
# FIXME: Unable to extract article id
'url': 'https://www.megatv.com/embed/?p=2020520979',
'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
'info_dict': {
@@ -119,6 +117,7 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
},
}, {
# FIXME: Unable to extract article id
'url': 'https://www.megatv.com/embed/?p=2020534081',
'md5': '6ac8b3ce4dc6120c802f780a1e6b3812',
'info_dict': {
@@ -132,6 +131,15 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/Capture-266.jpg',
},
}]
_WEBPAGE_TESTS = [{
# FIXME: Unable to extract article id
'url': 'https://www.in.gr/2021/12/18/greece/apokalypsi-mega-poios-parelave-tin-ereyna-tsiodra-ek-merous-tis-kyvernisis-o-prothypourgos-telika-gnorize/',
'info_dict': {
'id': 'apokalypsi-mega-poios-parelave-tin-ereyna-tsiodra-ek-merous-tis-kyvernisis-o-prothypourgos-telika-gnorize',
'title': 'md5:5e569cf996ec111057c2764ec272848f',
},
'playlist_count': 2,
}]
def _match_canonical_url(self, webpage):
LINK_RE = r'''(?x)
plugins/youtube_download/yt_dlp/extractor/mir24tv.py
+37
View File
@@ -0,0 +1,37 @@
from .common import InfoExtractor
from ..utils import parse_qs, url_or_none
from ..utils.traversal import require, traverse_obj
class Mir24TvIE(InfoExtractor):
IE_NAME = 'mir24.tv'
_VALID_URL = r'https?://(?:www\.)?mir24\.tv/news/(?P<id>[0-9]+)/[^/?#]+'
_TESTS = [{
'url': 'https://mir24.tv/news/16635210/dni-kultury-rossii-otkrylis-v-uzbekistane.-na-prazdnichnom-koncerte-vystupili-zvezdy-rossijskoj-estrada',
'info_dict': {
'id': '16635210',
'title': 'Дни культуры России открылись в Узбекистане. На праздничном концерте выступили звезды российской эстрады',
'ext': 'mp4',
'thumbnail': r're:https://images\.mir24\.tv/.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, impersonate=True)
iframe_url = self._search_regex(
r'<iframe\b[^>]+\bsrc=["\'](https?://mir24\.tv/players/[^"\']+)',
webpage, 'iframe URL')
m3u8_url = traverse_obj(iframe_url, (
{parse_qs}, 'source', -1, {self._proto_relative_url}, {url_or_none}, {require('m3u8 URL')}))
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'title': self._og_search_title(webpage, default=None) or self._html_extract_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': formats,
'subtitles': subtitles,
}

Some files were not shown because too many files have changed in this diff Show More