From df773c3d5d1cc1f877cf8582f0072e386fc49318 Mon Sep 17 00:00:00 2001 From: sepro <4618135+seproDev@users.noreply.github.com> Date: Sat, 9 Mar 2024 01:02:45 +0100 Subject: [PATCH] [cleanup] Mark broken and remove dead extractors (#9238) Authored by: seproDev --- yt_dlp/extractor/_extractors.py | 27 ---- yt_dlp/extractor/bleacherreport.py | 2 + yt_dlp/extractor/cbs.py | 1 + yt_dlp/extractor/cbsinteractive.py | 98 ------------- yt_dlp/extractor/cbssports.py | 3 + yt_dlp/extractor/chingari.py | 199 --------------------------- yt_dlp/extractor/cinemax.py | 1 + yt_dlp/extractor/cliphunter.py | 76 ---------- yt_dlp/extractor/cliprs.py | 1 + yt_dlp/extractor/closertotruth.py | 1 + yt_dlp/extractor/digg.py | 54 -------- yt_dlp/extractor/dtube.py | 1 + yt_dlp/extractor/dw.py | 4 + yt_dlp/extractor/europa.py | 1 + yt_dlp/extractor/fancode.py | 2 + yt_dlp/extractor/filmmodu.py | 69 ---------- yt_dlp/extractor/gameinformer.py | 46 ------- yt_dlp/extractor/gazeta.py | 1 + yt_dlp/extractor/gdcvault.py | 1 + yt_dlp/extractor/giga.py | 93 ------------- yt_dlp/extractor/godtube.py | 1 + yt_dlp/extractor/hotnewhiphop.py | 1 + yt_dlp/extractor/instagram.py | 1 + yt_dlp/extractor/jeuxvideo.py | 2 + yt_dlp/extractor/kanal2.py | 66 --------- yt_dlp/extractor/kankanews.py | 1 + yt_dlp/extractor/karrierevideos.py | 96 ------------- yt_dlp/extractor/kelbyone.py | 1 + yt_dlp/extractor/konserthusetplay.py | 119 ---------------- yt_dlp/extractor/koo.py | 1 + yt_dlp/extractor/krasview.py | 1 + yt_dlp/extractor/kusi.py | 83 ----------- yt_dlp/extractor/kuwo.py | 6 + yt_dlp/extractor/lecture2go.py | 1 + yt_dlp/extractor/lenta.py | 1 + yt_dlp/extractor/localnews8.py | 42 ------ yt_dlp/extractor/malltv.py | 107 -------------- yt_dlp/extractor/manyvids.py | 1 + yt_dlp/extractor/markiza.py | 2 + yt_dlp/extractor/miaopai.py | 36 ----- yt_dlp/extractor/ministrygrid.py | 55 -------- yt_dlp/extractor/morningstar.py | 45 ------ yt_dlp/extractor/motorsport.py | 1 + yt_dlp/extractor/mtv.py | 1 + yt_dlp/extractor/muenchentv.py | 1 + yt_dlp/extractor/murrtube.py | 2 + yt_dlp/extractor/ndtv.py | 1 + yt_dlp/extractor/netzkino.py | 1 + yt_dlp/extractor/nextmedia.py | 2 + yt_dlp/extractor/nobelprize.py | 1 + yt_dlp/extractor/noz.py | 1 + yt_dlp/extractor/odatv.py | 47 ------- yt_dlp/extractor/parlview.py | 2 +- yt_dlp/extractor/playstuff.py | 63 --------- yt_dlp/extractor/plutotv.py | 1 + yt_dlp/extractor/podomatic.py | 1 + yt_dlp/extractor/pornovoisines.py | 1 + yt_dlp/extractor/pornoxo.py | 1 + yt_dlp/extractor/projectveritas.py | 1 + yt_dlp/extractor/r7.py | 4 + yt_dlp/extractor/radiode.py | 1 + yt_dlp/extractor/radiojavan.py | 1 + yt_dlp/extractor/rbmaradio.py | 68 --------- yt_dlp/extractor/rds.py | 1 + yt_dlp/extractor/redbee.py | 1 + yt_dlp/extractor/regiotv.py | 55 -------- yt_dlp/extractor/rentv.py | 2 + yt_dlp/extractor/restudy.py | 1 + yt_dlp/extractor/reuters.py | 1 + yt_dlp/extractor/rockstargames.py | 1 + yt_dlp/extractor/rts.py | 1 + yt_dlp/extractor/saitosan.py | 1 + yt_dlp/extractor/savefrom.py | 30 ---- yt_dlp/extractor/seeker.py | 55 -------- yt_dlp/extractor/senalcolombia.py | 1 + yt_dlp/extractor/sendtonews.py | 1 + yt_dlp/extractor/sexu.py | 1 + yt_dlp/extractor/skylinewebcams.py | 1 + yt_dlp/extractor/skynewsarabia.py | 2 + yt_dlp/extractor/startrek.py | 1 + yt_dlp/extractor/streamff.py | 30 ---- yt_dlp/extractor/syfy.py | 1 + yt_dlp/extractor/tagesschau.py | 1 + yt_dlp/extractor/tass.py | 1 + yt_dlp/extractor/tdslifeway.py | 31 ----- yt_dlp/extractor/teachable.py | 1 + yt_dlp/extractor/teachertube.py | 2 + yt_dlp/extractor/teachingchannel.py | 1 + yt_dlp/extractor/tele5.py | 1 + yt_dlp/extractor/telemb.py | 1 + yt_dlp/extractor/telemundo.py | 2 +- yt_dlp/extractor/teletask.py | 1 + yt_dlp/extractor/tonline.py | 2 + yt_dlp/extractor/tv2.py | 2 + yt_dlp/extractor/tvn24.py | 1 + yt_dlp/extractor/tvnoe.py | 1 + yt_dlp/extractor/ukcolumn.py | 1 + yt_dlp/extractor/umg.py | 1 + yt_dlp/extractor/unity.py | 1 + yt_dlp/extractor/urort.py | 1 + yt_dlp/extractor/varzesh3.py | 1 + yt_dlp/extractor/vesti.py | 1 + yt_dlp/extractor/videofyme.py | 1 + yt_dlp/extractor/viqeo.py | 1 + yt_dlp/extractor/voicy.py | 2 + yt_dlp/extractor/vtm.py | 1 + yt_dlp/extractor/weiqitv.py | 1 + yt_dlp/extractor/xinpianchang.py | 1 + yt_dlp/extractor/xminus.py | 1 + yt_dlp/extractor/yapfiles.py | 1 + yt_dlp/extractor/yappy.py | 1 + yt_dlp/extractor/zeenews.py | 2 + 112 files changed, 113 insertions(+), 1692 deletions(-) delete mode 100644 yt_dlp/extractor/cbsinteractive.py delete mode 100644 yt_dlp/extractor/chingari.py delete mode 100644 yt_dlp/extractor/cliphunter.py delete mode 100644 yt_dlp/extractor/digg.py delete mode 100644 yt_dlp/extractor/filmmodu.py delete mode 100644 yt_dlp/extractor/gameinformer.py delete mode 100644 yt_dlp/extractor/giga.py delete mode 100644 yt_dlp/extractor/kanal2.py delete mode 100644 yt_dlp/extractor/karrierevideos.py delete mode 100644 yt_dlp/extractor/konserthusetplay.py delete mode 100644 yt_dlp/extractor/kusi.py delete mode 100644 yt_dlp/extractor/localnews8.py delete mode 100644 yt_dlp/extractor/malltv.py delete mode 100644 yt_dlp/extractor/miaopai.py delete mode 100644 yt_dlp/extractor/ministrygrid.py delete mode 100644 yt_dlp/extractor/morningstar.py delete mode 100644 yt_dlp/extractor/odatv.py delete mode 100644 yt_dlp/extractor/playstuff.py delete mode 100644 yt_dlp/extractor/rbmaradio.py delete mode 100644 yt_dlp/extractor/regiotv.py delete mode 100644 yt_dlp/extractor/savefrom.py delete mode 100644 yt_dlp/extractor/seeker.py delete mode 100644 yt_dlp/extractor/streamff.py delete mode 100644 yt_dlp/extractor/tdslifeway.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index c8a701050f..c753655368 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -320,7 +320,6 @@ CBSIE, ParamountPressExpressIE, ) -from .cbsinteractive import CBSInteractiveIE from .cbsnews import ( CBSNewsEmbedIE, CBSNewsIE, @@ -348,10 +347,6 @@ from .charlierose import CharlieRoseIE from .chaturbate import ChaturbateIE from .chilloutzone import ChilloutzoneIE -from .chingari import ( - ChingariIE, - ChingariUserIE, -) from .chzzk import ( CHZZKLiveIE, CHZZKVideoIE, @@ -369,7 +364,6 @@ from .ciscowebex import CiscoWebexIE from .cjsw import CJSWIE from .clipchamp import ClipchampIE -from .cliphunter import CliphunterIE from .clippit import ClippitIE from .cliprs import ClipRsIE from .closertotruth import CloserToTruthIE @@ -476,7 +470,6 @@ ) from .dfb import DFBIE from .dhm import DHMIE -from .digg import DiggIE from .douyutv import ( DouyuShowIE, DouyuTVIE, @@ -610,7 +603,6 @@ ) from .fczenit import FczenitIE from .fifa import FifaIE -from .filmmodu import FilmmoduIE from .filmon import ( FilmOnIE, FilmOnChannelIE, @@ -676,7 +668,6 @@ GabIE, ) from .gaia import GaiaIE -from .gameinformer import GameInformerIE from .gamejolt import ( GameJoltIE, GameJoltUserIE, @@ -705,7 +696,6 @@ GettrStreamingIE, ) from .giantbomb import GiantBombIE -from .giga import GigaIE from .glide import GlideIE from .globalplayer import ( GlobalPlayerLiveIE, @@ -896,10 +886,8 @@ from .jwplatform import JWPlatformIE from .kakao import KakaoIE from .kaltura import KalturaIE -from .kanal2 import Kanal2IE from .kankanews import KankaNewsIE from .karaoketv import KaraoketvIE -from .karrierevideos import KarriereVideosIE from .kelbyone import KelbyOneIE from .khanacademy import ( KhanAcademyIE, @@ -915,13 +903,11 @@ from .kinopoisk import KinoPoiskIE from .kommunetv import KommunetvIE from .kompas import KompasVideoIE -from .konserthusetplay import KonserthusetPlayIE from .koo import KooIE from .kth import KTHIE from .krasview import KrasViewIE from .ku6 import Ku6IE from .kukululive import KukuluLiveIE -from .kusi import KUSIIE from .kuwo import ( KuwoIE, KuwoAlbumIE, @@ -1003,7 +989,6 @@ LnkGoIE, LnkIE, ) -from .localnews8 import LocalNews8IE from .lovehomeporn import LoveHomePornIE from .lrt import ( LRTVODIE, @@ -1030,7 +1015,6 @@ MailRuMusicSearchIE, ) from .mainstreaming import MainStreamingIE -from .malltv import MallTVIE from .mangomolo import ( MangomoloVideoIE, MangomoloLiveIE, @@ -1074,7 +1058,6 @@ from .melonvod import MelonVODIE from .metacritic import MetacriticIE from .mgtv import MGTVIE -from .miaopai import MiaoPaiIE from .microsoftstream import MicrosoftStreamIE from .microsoftvirtualacademy import ( MicrosoftVirtualAcademyIE, @@ -1092,7 +1075,6 @@ MindsChannelIE, MindsGroupIE, ) -from .ministrygrid import MinistryGridIE from .minoto import MinotoIE from .mirrativ import ( MirrativIE, @@ -1120,7 +1102,6 @@ from .mocha import MochaVideoIE from .mojvideo import MojvideoIE from .monstercat import MonstercatIE -from .morningstar import MorningstarIE from .motherless import ( MotherlessIE, MotherlessGroupIE, @@ -1365,7 +1346,6 @@ from .nzherald import NZHeraldIE from .nzonscreen import NZOnScreenIE from .nzz import NZZIE -from .odatv import OdaTVIE from .odkmedia import OnDemandChinaEpisodeIE from .odnoklassniki import OdnoklassnikiIE from .oftv import ( @@ -1477,7 +1457,6 @@ PlatziCourseIE, ) from .playplustv import PlayPlusTVIE -from .playstuff import PlayStuffIE from .playsuisse import PlaySuisseIE from .playtvak import PlaytvakIE from .playwire import PlaywireIE @@ -1599,7 +1578,6 @@ RayWenderlichIE, RayWenderlichCourseIE, ) -from .rbmaradio import RBMARadioIE from .rbgtum import ( RbgTumIE, RbgTumCourseIE, @@ -1631,7 +1609,6 @@ RedGifsUserIE, ) from .redtube import RedTubeIE -from .regiotv import RegioTVIE from .rentv import ( RENTVIE, RENTVArticleIE, @@ -1739,7 +1716,6 @@ from .saitosan import SaitosanIE from .samplefocus import SampleFocusIE from .sapo import SapoIE -from .savefrom import SaveFromIE from .sbs import SBSIE from .sbscokr import ( SBSCoKrIE, @@ -1759,7 +1735,6 @@ SCTECourseIE, ) from .scrolller import ScrolllerIE -from .seeker import SeekerIE from .sejmpl import SejmIE from .senalcolombia import SenalColombiaLiveIE from .senategov import SenateISVPIE, SenateGovIE @@ -1902,7 +1877,6 @@ ) from .streamable import StreamableIE from .streamcz import StreamCZIE -from .streamff import StreamFFIE from .streetvoice import StreetVoiceIE from .stretchinternet import StretchInternetIE from .stripchat import StripchatIE @@ -1931,7 +1905,6 @@ TBSJPProgramIE, TBSJPPlaylistIE, ) -from .tdslifeway import TDSLifewayIE from .teachable import ( TeachableIE, TeachableCourseIE, diff --git a/yt_dlp/extractor/bleacherreport.py b/yt_dlp/extractor/bleacherreport.py index 12630fb86e..e875957cf5 100644 --- a/yt_dlp/extractor/bleacherreport.py +++ b/yt_dlp/extractor/bleacherreport.py @@ -9,6 +9,7 @@ class BleacherReportIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P\d+)' _TESTS = [{ 'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football', @@ -83,6 +84,7 @@ def _real_extract(self, url): class BleacherReportCMSIE(AMPIE): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P[0-9a-f-]{36}|\d{5})' _TESTS = [{ 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms', diff --git a/yt_dlp/extractor/cbs.py b/yt_dlp/extractor/cbs.py index d97fbd758c..cf830210f8 100644 --- a/yt_dlp/extractor/cbs.py +++ b/yt_dlp/extractor/cbs.py @@ -76,6 +76,7 @@ def _real_extract(self, url): class CBSIE(CBSBaseIE): + _WORKING = False _VALID_URL = r'''(?x) (?: cbs:| diff --git a/yt_dlp/extractor/cbsinteractive.py b/yt_dlp/extractor/cbsinteractive.py deleted file mode 100644 index b09e9823eb..0000000000 --- a/yt_dlp/extractor/cbsinteractive.py +++ /dev/null @@ -1,98 +0,0 @@ -from .cbs import CBSIE -from ..utils import int_or_none - - -class CBSInteractiveIE(CBSIE): # XXX: Do not subclass from concrete IE - _VALID_URL = r'https?://(?:www\.)?(?Pcnet|zdnet)\.com/(?:videos|video(?:/share)?)/(?P[^/?]+)' - _TESTS = [{ - 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', - 'info_dict': { - 'id': 'R49SYt__yAfmlXR85z4f7gNmCBDcN_00', - 'display_id': 'hands-on-with-microsofts-windows-8-1-update', - 'ext': 'mp4', - 'title': 'Hands-on with Microsoft Windows 8.1 Update', - 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', - 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861', - 'uploader': 'Sarah Mitroff', - 'duration': 70, - 'timestamp': 1396479627, - 'upload_date': '20140402', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, { - 'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/', - 'md5': 'f11d27b2fa18597fbf92444d2a9ed386', - 'info_dict': { - 'id': 'kjOJd_OoVJqbg_ZD8MZCOk8Wekb9QccK', - 'display_id': 'whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187', - 'ext': 'mp4', - 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)', - 'description': 'md5:d2b9a95a5ffe978ae6fbd4cf944d618f', - 'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40', - 'uploader': 'Ashley Esqueda', - 'duration': 1482, - 'timestamp': 1433289889, - 'upload_date': '20150603', - }, - }, { - 'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/', - 'info_dict': { - 'id': 'k0r4T_ehht4xW_hAOqiVQPuBDPZ8SRjt', - 'display_id': 'video-keeping-android-smartphones-and-tablets-secure', - 'ext': 'mp4', - 'title': 'Video: Keeping Android smartphones and tablets secure', - 'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.', - 'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0', - 'uploader': 'Adrian Kingsley-Hughes', - 'duration': 731, - 'timestamp': 1449129925, - 'upload_date': '20151203', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, { - 'url': 'http://www.zdnet.com/video/huawei-matebook-x-video/', - 'only_matching': True, - }] - - MPX_ACCOUNTS = { - 'cnet': 2198311517, - 'zdnet': 2387448114, - } - - def _real_extract(self, url): - site, display_id = self._match_valid_url(url).groups() - webpage = self._download_webpage(url, display_id) - - data_json = self._html_search_regex( - r"data(?:-(?:cnet|zdnet))?-video(?:-(?:uvp(?:js)?|player))?-options='([^']+)'", - webpage, 'data json') - data = self._parse_json(data_json, display_id) - vdata = data.get('video') or (data.get('videos') or data.get('playlist'))[0] - - video_id = vdata['mpxRefId'] - - title = vdata['title'] - author = vdata.get('author') - if author: - uploader = '%s %s' % (author['firstName'], author['lastName']) - uploader_id = author.get('id') - else: - uploader = None - uploader_id = None - - info = self._extract_video_info(video_id, site, self.MPX_ACCOUNTS[site]) - info.update({ - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'duration': int_or_none(vdata.get('duration')), - 'uploader': uploader, - 'uploader_id': uploader_id, - }) - return info diff --git a/yt_dlp/extractor/cbssports.py b/yt_dlp/extractor/cbssports.py index b5d85af12b..b9c82dab66 100644 --- a/yt_dlp/extractor/cbssports.py +++ b/yt_dlp/extractor/cbssports.py @@ -8,6 +8,7 @@ # class CBSSportsEmbedIE(CBSBaseIE): class CBSSportsEmbedIE(InfoExtractor): + _WORKING = False IE_NAME = 'cbssports:embed' _VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+? (?: @@ -75,6 +76,7 @@ def _real_extract(self, url): class CBSSportsIE(CBSSportsBaseIE): + _WORKING = False IE_NAME = 'cbssports' _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P[^/?#&]+)' _TESTS = [{ @@ -92,6 +94,7 @@ class CBSSportsIE(CBSSportsBaseIE): class TwentyFourSevenSportsIE(CBSSportsBaseIE): + _WORKING = False IE_NAME = '247sports' _VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P\d+)' _TESTS = [{ diff --git a/yt_dlp/extractor/chingari.py b/yt_dlp/extractor/chingari.py deleted file mode 100644 index fd194482e2..0000000000 --- a/yt_dlp/extractor/chingari.py +++ /dev/null @@ -1,199 +0,0 @@ -import itertools -import json -import urllib.parse - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - clean_html, - int_or_none, - str_to_int, - url_or_none, -) - - -class ChingariBaseIE(InfoExtractor): - def _get_post(self, id, post_data): - media_data = post_data['mediaLocation'] - base_url = media_data['base'] - author_data = post_data.get('authorData', {}) - song_data = post_data.get('song', {}) # revist this in future for differentiating b/w 'art' and 'author' - - formats = [{ - 'format_id': frmt, - 'width': str_to_int(frmt[1:]), - 'url': base_url + frmt_path, - } for frmt, frmt_path in media_data.get('transcoded', {}).items()] - - if media_data.get('path'): - formats.append({ - 'format_id': 'original', - 'format_note': 'Direct video.', - 'url': base_url + '/apipublic' + media_data['path'], - 'quality': 10, - }) - timestamp = str_to_int(post_data.get('created_at')) - if timestamp: - timestamp = int_or_none(timestamp, 1000) - - thumbnail, uploader_url = None, None - if media_data.get('thumbnail'): - thumbnail = base_url + media_data.get('thumbnail') - if author_data.get('username'): - uploader_url = 'https://chingari.io/' + author_data.get('username') - - return { - 'id': id, - 'extractor_key': ChingariIE.ie_key(), - 'extractor': 'Chingari', - 'title': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))), - 'description': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))), - 'duration': media_data.get('duration'), - 'thumbnail': url_or_none(thumbnail), - 'like_count': post_data.get('likeCount'), - 'view_count': post_data.get('viewsCount'), - 'comment_count': post_data.get('commentCount'), - 'repost_count': post_data.get('shareCount'), - 'timestamp': timestamp, - 'uploader_id': post_data.get('userId') or author_data.get('_id'), - 'uploader': author_data.get('name'), - 'uploader_url': url_or_none(uploader_url), - 'track': song_data.get('title'), - 'artist': song_data.get('author'), - 'formats': formats, - } - - -class ChingariIE(ChingariBaseIE): - _VALID_URL = r'https?://(?:www\.)?chingari\.io/share/post\?id=(?P[^&/#?]+)' - _TESTS = [{ - 'url': 'https://chingari.io/share/post?id=612f8f4ce1dc57090e8a7beb', - 'info_dict': { - 'id': '612f8f4ce1dc57090e8a7beb', - 'ext': 'mp4', - 'title': 'Happy birthday Srila Prabhupada', - 'description': 'md5:c7080ebfdfeb06016e638c286d6bc3fa', - 'duration': 0, - 'thumbnail': 'https://media.chingari.io/uploads/c41d30e2-06b6-4e3b-9b4b-edbb929cec06-1630506826911/thumbnail/198f993f-ce87-4623-82c6-cd071bd6d4f4-1630506828016.jpg', - 'like_count': int, - 'view_count': int, - 'comment_count': int, - 'repost_count': int, - 'timestamp': 1630506828, - 'upload_date': '20210901', - 'uploader_id': '5f0403982c8bd344f4813f8c', - 'uploader': 'ISKCON,Inc.', - 'uploader_url': 'https://chingari.io/iskcon,inc', - }, - 'params': {'skip_download': True} - }] - - def _real_extract(self, url): - id = self._match_id(url) - post_json = self._download_json(f'https://api.chingari.io/post/post_details/{id}', id) - if post_json['code'] != 200: - raise ExtractorError(post_json['message'], expected=True) - post_data = post_json['data'] - return self._get_post(id, post_data) - - -class ChingariUserIE(ChingariBaseIE): - _VALID_URL = r'https?://(?:www\.)?chingari\.io/(?!share/post)(?P[^/?]+)' - _TESTS = [{ - 'url': 'https://chingari.io/dada1023', - 'info_dict': { - 'id': 'dada1023', - }, - 'params': {'playlistend': 3}, - 'playlist': [{ - 'url': 'https://chingari.io/share/post?id=614781f3ade60b3a0bfff42a', - 'info_dict': { - 'id': '614781f3ade60b3a0bfff42a', - 'ext': 'mp4', - 'title': '#chingaribappa ', - 'description': 'md5:d1df21d84088770468fa63afe3b17857', - 'duration': 7, - 'thumbnail': 'https://media.chingari.io/uploads/346d86d4-abb2-474e-a164-ffccf2bbcb72-1632076273717/thumbnail/b0b3aac2-2b86-4dd1-909d-9ed6e57cf77c-1632076275552.jpg', - 'like_count': int, - 'view_count': int, - 'comment_count': int, - 'repost_count': int, - 'timestamp': 1632076275, - 'upload_date': '20210919', - 'uploader_id': '5efc4b12cca35c3d1794c2d3', - 'uploader': 'dada (girish) dhawale', - 'uploader_url': 'https://chingari.io/dada1023', - }, - 'params': {'skip_download': True} - }, { - 'url': 'https://chingari.io/share/post?id=6146b132bcbf860959e12cba', - 'info_dict': { - 'id': '6146b132bcbf860959e12cba', - 'ext': 'mp4', - 'title': 'Tactor harvesting', - 'description': 'md5:8403f12dce68828b77ecee7eb7e887b7', - 'duration': 59.3, - 'thumbnail': 'https://media.chingari.io/uploads/b353ca70-7a87-400d-93a6-fa561afaec86-1632022814584/thumbnail/c09302e3-2043-41b1-a2fe-77d97e5bd676-1632022834260.jpg', - 'like_count': int, - 'view_count': int, - 'comment_count': int, - 'repost_count': int, - 'timestamp': 1632022834, - 'upload_date': '20210919', - 'uploader_id': '5efc4b12cca35c3d1794c2d3', - 'uploader': 'dada (girish) dhawale', - 'uploader_url': 'https://chingari.io/dada1023', - }, - 'params': {'skip_download': True} - }, { - 'url': 'https://chingari.io/share/post?id=6145651b74cb030a64c40b82', - 'info_dict': { - 'id': '6145651b74cb030a64c40b82', - 'ext': 'mp4', - 'title': '#odiabhajan ', - 'description': 'md5:687ea36835b9276cf2af90f25e7654cb', - 'duration': 56.67, - 'thumbnail': 'https://media.chingari.io/uploads/6cbf216b-babc-4cce-87fe-ceaac8d706ac-1631937782708/thumbnail/8855754f-6669-48ce-b269-8cc0699ed6da-1631937819522.jpg', - 'like_count': int, - 'view_count': int, - 'comment_count': int, - 'repost_count': int, - 'timestamp': 1631937819, - 'upload_date': '20210918', - 'uploader_id': '5efc4b12cca35c3d1794c2d3', - 'uploader': 'dada (girish) dhawale', - 'uploader_url': 'https://chingari.io/dada1023', - }, - 'params': {'skip_download': True} - }], - }, { - 'url': 'https://chingari.io/iskcon%2Cinc', - 'playlist_mincount': 1025, - 'info_dict': { - 'id': 'iskcon%2Cinc', - }, - }] - - def _entries(self, id): - skip = 0 - has_more = True - for page in itertools.count(): - posts = self._download_json('https://api.chingari.io/users/getPosts', id, - data=json.dumps({'userId': id, 'ownerId': id, 'skip': skip, 'limit': 20}).encode(), - headers={'content-type': 'application/json;charset=UTF-8'}, - note='Downloading page %s' % page) - for post in posts.get('data', []): - post_data = post['post'] - yield self._get_post(post_data['_id'], post_data) - skip += 20 - has_more = posts['hasMoreData'] - if not has_more: - break - - def _real_extract(self, url): - alt_id = self._match_id(url) - post_json = self._download_json(f'https://api.chingari.io/user/{alt_id}', alt_id) - if post_json['code'] != 200: - raise ExtractorError(post_json['message'], expected=True) - id = post_json['data']['_id'] - return self.playlist_result(self._entries(id), playlist_id=alt_id) diff --git a/yt_dlp/extractor/cinemax.py b/yt_dlp/extractor/cinemax.py index 54cab2285e..706ec8553b 100644 --- a/yt_dlp/extractor/cinemax.py +++ b/yt_dlp/extractor/cinemax.py @@ -2,6 +2,7 @@ class CinemaxIE(HBOBaseIE): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?cinemax\.com/(?P[^/]+/video/[0-9a-z-]+-(?P\d+))' _TESTS = [{ 'url': 'https://www.cinemax.com/warrior/video/s1-ep-1-recap-20126903', diff --git a/yt_dlp/extractor/cliphunter.py b/yt_dlp/extractor/cliphunter.py deleted file mode 100644 index 2b907dc804..0000000000 --- a/yt_dlp/extractor/cliphunter.py +++ /dev/null @@ -1,76 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - int_or_none, - url_or_none, -) - - -class CliphunterIE(InfoExtractor): - IE_NAME = 'cliphunter' - - _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/ - (?P[0-9]+)/ - (?P.+?)(?:$|[#\?]) - ''' - _TESTS = [{ - 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', - 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480', - 'info_dict': { - 'id': '1012420', - 'ext': 'flv', - 'title': 'Fun Jynx Maze solo', - 'thumbnail': r're:^https?://.*\.jpg$', - 'age_limit': 18, - }, - 'skip': 'Video gone', - }, { - 'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz', - 'md5': '55a723c67bfc6da6b0cfa00d55da8a27', - 'info_dict': { - 'id': '2019449', - 'ext': 'mp4', - 'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz', - 'thumbnail': r're:^https?://.*\.jpg$', - 'age_limit': 18, - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_title = self._search_regex( - r'mediaTitle = "([^"]+)"', webpage, 'title') - - gexo_files = self._parse_json( - self._search_regex( - r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'), - video_id) - - formats = [] - for format_id, f in gexo_files.items(): - video_url = url_or_none(f.get('url')) - if not video_url: - continue - fmt = f.get('fmt') - height = f.get('h') - format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id - formats.append({ - 'url': video_url, - 'format_id': format_id, - 'width': int_or_none(f.get('w')), - 'height': int_or_none(height), - 'tbr': int_or_none(f.get('br')), - }) - - thumbnail = self._search_regex( - r"var\s+mov_thumb\s*=\s*'([^']+)';", - webpage, 'thumbnail', fatal=False) - - return { - 'id': video_id, - 'title': video_title, - 'formats': formats, - 'age_limit': self._rta_search(webpage), - 'thumbnail': thumbnail, - } diff --git a/yt_dlp/extractor/cliprs.py b/yt_dlp/extractor/cliprs.py index 567f77b94e..c2add02da4 100644 --- a/yt_dlp/extractor/cliprs.py +++ b/yt_dlp/extractor/cliprs.py @@ -2,6 +2,7 @@ class ClipRsIE(OnetBaseIE): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P[^/]+)/\d+' _TEST = { 'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732', diff --git a/yt_dlp/extractor/closertotruth.py b/yt_dlp/extractor/closertotruth.py index e78e26a113..1f9a5f6114 100644 --- a/yt_dlp/extractor/closertotruth.py +++ b/yt_dlp/extractor/closertotruth.py @@ -4,6 +4,7 @@ class CloserToTruthIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688', diff --git a/yt_dlp/extractor/digg.py b/yt_dlp/extractor/digg.py deleted file mode 100644 index 86e8a6facb..0000000000 --- a/yt_dlp/extractor/digg.py +++ /dev/null @@ -1,54 +0,0 @@ -from .common import InfoExtractor -from ..utils import js_to_json - - -class DiggIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?digg\.com/video/(?P[^/?#&]+)' - _TESTS = [{ - # JWPlatform via provider - 'url': 'http://digg.com/video/sci-fi-short-jonah-daniel-kaluuya-get-out', - 'info_dict': { - 'id': 'LcqvmS0b', - 'ext': 'mp4', - 'title': "'Get Out' Star Daniel Kaluuya Goes On 'Moby Dick'-Like Journey In Sci-Fi Short 'Jonah'", - 'description': 'md5:541bb847648b6ee3d6514bc84b82efda', - 'upload_date': '20180109', - 'timestamp': 1515530551, - }, - 'params': { - 'skip_download': True, - }, - }, { - # Youtube via provider - 'url': 'http://digg.com/video/dog-boat-seal-play', - 'only_matching': True, - }, { - # vimeo as regular embed - 'url': 'http://digg.com/video/dream-girl-short-film', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - info = self._parse_json( - self._search_regex( - r'(?s)video_info\s*=\s*({.+?});\n', webpage, 'video info', - default='{}'), display_id, transform_source=js_to_json, - fatal=False) - - video_id = info.get('video_id') - - if video_id: - provider = info.get('provider_name') - if provider == 'youtube': - return self.url_result( - video_id, ie='Youtube', video_id=video_id) - elif provider == 'jwplayer': - return self.url_result( - 'jwplatform:%s' % video_id, ie='JWPlatform', - video_id=video_id) - - return self.url_result(url, 'Generic') diff --git a/yt_dlp/extractor/dtube.py b/yt_dlp/extractor/dtube.py index 25a98f625b..bb06c42bef 100644 --- a/yt_dlp/extractor/dtube.py +++ b/yt_dlp/extractor/dtube.py @@ -9,6 +9,7 @@ class DTubeIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P[0-9a-z.-]+)/(?P[0-9a-z]{8})' _TEST = { 'url': 'https://d.tube/#!/v/broncnutz/x380jtr1', diff --git a/yt_dlp/extractor/dw.py b/yt_dlp/extractor/dw.py index 9c4a08e54f..f7b8520766 100644 --- a/yt_dlp/extractor/dw.py +++ b/yt_dlp/extractor/dw.py @@ -8,6 +8,8 @@ class DWIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE IE_NAME = 'dw' _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P\d+)' _TESTS = [{ @@ -82,6 +84,8 @@ def _real_extract(self, url): class DWArticleIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE IE_NAME = 'dw:article' _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P\d+)' _TEST = { diff --git a/yt_dlp/extractor/europa.py b/yt_dlp/extractor/europa.py index f3da95f5c9..191a4361a2 100644 --- a/yt_dlp/extractor/europa.py +++ b/yt_dlp/extractor/europa.py @@ -13,6 +13,7 @@ class EuropaIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P[A-Za-z0-9-]+)' _TESTS = [{ 'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758', diff --git a/yt_dlp/extractor/fancode.py b/yt_dlp/extractor/fancode.py index 1b5db818a1..cddf254978 100644 --- a/yt_dlp/extractor/fancode.py +++ b/yt_dlp/extractor/fancode.py @@ -10,6 +10,7 @@ class FancodeVodIE(InfoExtractor): + _WORKING = False IE_NAME = 'fancode:vod' _VALID_URL = r'https?://(?:www\.)?fancode\.com/video/(?P[0-9]+)\b' @@ -126,6 +127,7 @@ def _real_extract(self, url): class FancodeLiveIE(FancodeVodIE): # XXX: Do not subclass from concrete IE + _WORKING = False IE_NAME = 'fancode:live' _VALID_URL = r'https?://(www\.)?fancode\.com/match/(?P[0-9]+).+' diff --git a/yt_dlp/extractor/filmmodu.py b/yt_dlp/extractor/filmmodu.py deleted file mode 100644 index 1e793560d4..0000000000 --- a/yt_dlp/extractor/filmmodu.py +++ /dev/null @@ -1,69 +0,0 @@ -from .common import InfoExtractor -from ..utils import int_or_none - - -class FilmmoduIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?filmmodu\.org/(?P[^/]+-(?:turkce-dublaj-izle|altyazili-izle))' - _TESTS = [{ - 'url': 'https://www.filmmodu.org/f9-altyazili-izle', - 'md5': 'aeefd955c2a508a5bdaa3bcec8eeb0d4', - 'info_dict': { - 'id': '10804', - 'ext': 'mp4', - 'title': 'F9', - 'description': 'md5:2713f584a4d65afa2611e2948d0b953c', - 'subtitles': { - 'tr': [{ - 'ext': 'vtt', - }], - }, - 'thumbnail': r're:https://s[0-9]+.filmmodu.org/uploads/movie/cover/10804/xXHZeb1yhJvnSHPzZDqee0zfMb6.jpg', - }, - }, { - 'url': 'https://www.filmmodu.org/the-godfather-turkce-dublaj-izle', - 'md5': '109f2fcb9c941330eed133971c035c00', - 'info_dict': { - 'id': '3646', - 'ext': 'mp4', - 'title': 'Baba', - 'description': 'md5:d43fd651937cd75cc650883ebd8d8461', - 'thumbnail': r're:https://s[0-9]+.filmmodu.org/uploads/movie/cover/3646/6xKCYgH16UuwEGAyroLU6p8HLIn.jpg', - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage, fatal=True) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - real_video_id = self._search_regex(r'var\s*videoId\s*=\s*\'([0-9]+)\'', webpage, 'video_id') - video_type = self._search_regex(r'var\s*videoType\s*=\s*\'([a-z]+)\'', webpage, 'video_type') - data = self._download_json('https://www.filmmodu.org/get-source', real_video_id, query={ - 'movie_id': real_video_id, - 'type': video_type, - }) - formats = [{ - 'url': source['src'], - 'ext': 'mp4', - 'format_id': source['label'], - 'height': int_or_none(source.get('res')), - 'protocol': 'm3u8_native', - } for source in data['sources']] - - subtitles = {} - - if data.get('subtitle'): - subtitles['tr'] = [{ - 'url': data['subtitle'], - }] - - return { - 'id': real_video_id, - 'display_id': video_id, - 'title': title, - 'description': description, - 'formats': formats, - 'subtitles': subtitles, - 'thumbnail': thumbnail, - } diff --git a/yt_dlp/extractor/gameinformer.py b/yt_dlp/extractor/gameinformer.py deleted file mode 100644 index 2664edb816..0000000000 --- a/yt_dlp/extractor/gameinformer.py +++ /dev/null @@ -1,46 +0,0 @@ -from .brightcove import BrightcoveNewIE -from .common import InfoExtractor -from ..utils import ( - clean_html, - get_element_by_class, - get_element_by_id, -) - - -class GameInformerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P[^.?&#]+)' - _TESTS = [{ - # normal Brightcove embed code extracted with BrightcoveNewIE._extract_url - 'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx', - 'md5': '292f26da1ab4beb4c9099f1304d2b071', - 'info_dict': { - 'id': '4515472681001', - 'ext': 'mp4', - 'title': 'Replay - Animal Crossing', - 'description': 'md5:2e211891b215c85d061adc7a4dd2d930', - 'timestamp': 1443457610, - 'upload_date': '20150928', - 'uploader_id': '694940074001', - }, - }, { - # Brightcove id inside unique element with field--name-field-brightcove-video-id class - 'url': 'https://www.gameinformer.com/video-feature/new-gameplay-today/2019/07/09/new-gameplay-today-streets-of-rogue', - 'info_dict': { - 'id': '6057111913001', - 'ext': 'mp4', - 'title': 'New Gameplay Today – Streets Of Rogue', - 'timestamp': 1562699001, - 'upload_date': '20190709', - 'uploader_id': '694940074001', - - }, - }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s' - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage( - url, display_id, headers=self.geo_verification_headers()) - brightcove_id = clean_html(get_element_by_class('field--name-field-brightcove-video-id', webpage) or get_element_by_id('video-source-content', webpage)) - brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id if brightcove_id else BrightcoveNewIE._extract_url(self, webpage) - return self.url_result(brightcove_url, 'BrightcoveNew', brightcove_id) diff --git a/yt_dlp/extractor/gazeta.py b/yt_dlp/extractor/gazeta.py index c6868a6722..8925b69fd1 100644 --- a/yt_dlp/extractor/gazeta.py +++ b/yt_dlp/extractor/gazeta.py @@ -2,6 +2,7 @@ class GazetaIE(InfoExtractor): + _WORKING = False _VALID_URL = r'(?Phttps?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:main/)*(?:\d{4}/\d{2}/\d{2}/)?(?P[A-Za-z0-9-_.]+)\.s?html)' _TESTS = [{ 'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml', diff --git a/yt_dlp/extractor/gdcvault.py b/yt_dlp/extractor/gdcvault.py index 4265feb61f..b4d81b2e83 100644 --- a/yt_dlp/extractor/gdcvault.py +++ b/yt_dlp/extractor/gdcvault.py @@ -7,6 +7,7 @@ class GDCVaultIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P\d+)(?:/(?P[\w-]+))?' _NETRC_MACHINE = 'gdcvault' _TESTS = [ diff --git a/yt_dlp/extractor/giga.py b/yt_dlp/extractor/giga.py deleted file mode 100644 index b59c129abf..0000000000 --- a/yt_dlp/extractor/giga.py +++ /dev/null @@ -1,93 +0,0 @@ -import itertools - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import parse_duration, parse_iso8601, qualities, str_to_int - - -class GigaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P[^/]+)' - _TESTS = [{ - 'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/', - 'md5': '6bc5535e945e724640664632055a584f', - 'info_dict': { - 'id': '2622086', - 'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss', - 'ext': 'mp4', - 'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss', - 'description': 'md5:afdf5862241aded4718a30dff6a57baf', - 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 578, - 'timestamp': 1414749706, - 'upload_date': '20141031', - 'uploader': 'Robin Schweiger', - 'view_count': int, - }, - }, { - 'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/', - 'only_matching': True, - }, { - 'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/', - 'only_matching': True, - }, { - 'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - [r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'], - webpage, 'video id') - - playlist = self._download_json( - 'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/' - % video_id, video_id)[0] - - quality = qualities(['normal', 'hd720']) - - formats = [] - for format_id in itertools.count(0): - fmt = playlist.get(compat_str(format_id)) - if not fmt: - break - formats.append({ - 'url': fmt['src'], - 'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]), - 'quality': quality(fmt['quality']), - }) - - title = self._html_search_meta( - 'title', webpage, 'title', fatal=True) - description = self._html_search_meta( - 'description', webpage, 'description') - thumbnail = self._og_search_thumbnail(webpage) - - duration = parse_duration(self._search_regex( - r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?([^<]+)'.format(video_id), - webpage, 'duration', fatal=False)) - - timestamp = parse_iso8601(self._search_regex( - r'datetime="([^"]+)"', webpage, 'upload date', fatal=False)) - uploader = self._search_regex( - r'class="author">([^<]+)', webpage, 'uploader', fatal=False) - - view_count = str_to_int(self._search_regex( - r'([\d.,]+)', - webpage, 'view count', fatal=False)) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, - 'uploader': uploader, - 'view_count': view_count, - 'formats': formats, - } diff --git a/yt_dlp/extractor/godtube.py b/yt_dlp/extractor/godtube.py index 697540155a..35fb7a9c97 100644 --- a/yt_dlp/extractor/godtube.py +++ b/yt_dlp/extractor/godtube.py @@ -6,6 +6,7 @@ class GodTubeIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P[\da-zA-Z]+)' _TESTS = [ { diff --git a/yt_dlp/extractor/hotnewhiphop.py b/yt_dlp/extractor/hotnewhiphop.py index 3007fbb530..4f506cde75 100644 --- a/yt_dlp/extractor/hotnewhiphop.py +++ b/yt_dlp/extractor/hotnewhiphop.py @@ -5,6 +5,7 @@ class HotNewHipHopIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P.*)\.html' _TEST = { 'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html', diff --git a/yt_dlp/extractor/instagram.py b/yt_dlp/extractor/instagram.py index dbaa332c2a..f7f21505ea 100644 --- a/yt_dlp/extractor/instagram.py +++ b/yt_dlp/extractor/instagram.py @@ -617,6 +617,7 @@ def _real_extract(self, url): class InstagramUserIE(InstagramPlaylistBaseIE): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' diff --git a/yt_dlp/extractor/jeuxvideo.py b/yt_dlp/extractor/jeuxvideo.py index 56ea15cf95..793820600e 100644 --- a/yt_dlp/extractor/jeuxvideo.py +++ b/yt_dlp/extractor/jeuxvideo.py @@ -2,6 +2,8 @@ class JeuxVideoIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm' _TESTS = [{ diff --git a/yt_dlp/extractor/kanal2.py b/yt_dlp/extractor/kanal2.py deleted file mode 100644 index 3c0efe5981..0000000000 --- a/yt_dlp/extractor/kanal2.py +++ /dev/null @@ -1,66 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - join_nonempty, - traverse_obj, - unified_timestamp, - update_url_query, -) - - -class Kanal2IE(InfoExtractor): - _VALID_URL = r'https?://kanal2\.postimees\.ee/[^?#]+\?([^#]+&)?id=(?P\d+)' - _TESTS = [{ - 'note': 'Test standard url (#5575)', - 'url': 'https://kanal2.postimees.ee/pluss/video/?id=40792', - 'md5': '7ea7b16266ec1798743777df241883dd', - 'info_dict': { - 'id': '40792', - 'ext': 'mp4', - 'title': 'Aedniku aabits / Osa 53 (05.08.2016 20:00)', - 'thumbnail': r're:https?://.*\.jpg$', - 'description': 'md5:53cabf3c5d73150d594747f727431248', - 'upload_date': '20160805', - 'timestamp': 1470420000, - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - playlist = self._download_json( - f'https://kanal2.postimees.ee/player/playlist/{video_id}', - video_id, query={'type': 'episodes'}, - headers={'X-Requested-With': 'XMLHttpRequest'}) - - return { - 'id': video_id, - 'title': join_nonempty(*traverse_obj(playlist, ('info', ('title', 'subtitle'))), delim=' / '), - 'description': traverse_obj(playlist, ('info', 'description')), - 'thumbnail': traverse_obj(playlist, ('data', 'image')), - 'formats': self.get_formats(playlist, video_id), - 'timestamp': unified_timestamp(self._search_regex( - r'\((\d{2}\.\d{2}\.\d{4}\s\d{2}:\d{2})\)$', - traverse_obj(playlist, ('info', 'subtitle')), 'timestamp', default='') + ' +0200'), - } - - def get_formats(self, playlist, video_id): - path = traverse_obj(playlist, ('data', 'path')) - if not path: - raise ExtractorError('Path value not found in playlist JSON response') - session = self._download_json( - 'https://sts.postimees.ee/session/register', - video_id, note='Creating session', errnote='Error creating session', - headers={ - 'X-Original-URI': path, - 'Accept': 'application/json', - }) - if session.get('reason') != 'OK' or not session.get('session'): - reason = session.get('reason', 'unknown error') - raise ExtractorError(f'Unable to obtain session: {reason}') - - formats = [] - for stream in traverse_obj(playlist, ('data', 'streams', ..., 'file')): - formats.extend(self._extract_m3u8_formats( - update_url_query(stream, {'s': session['session']}), video_id, 'mp4')) - - return formats diff --git a/yt_dlp/extractor/kankanews.py b/yt_dlp/extractor/kankanews.py index 46e239bd6c..8f247b305a 100644 --- a/yt_dlp/extractor/kankanews.py +++ b/yt_dlp/extractor/kankanews.py @@ -8,6 +8,7 @@ class KankaNewsIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?kankanews\.com/a/\d+\-\d+\-\d+/(?P\d+)\.shtml' _TESTS = [{ 'url': 'https://www.kankanews.com/a/2022-11-08/00310276054.shtml?appid=1088227', diff --git a/yt_dlp/extractor/karrierevideos.py b/yt_dlp/extractor/karrierevideos.py deleted file mode 100644 index 28d4841aa3..0000000000 --- a/yt_dlp/extractor/karrierevideos.py +++ /dev/null @@ -1,96 +0,0 @@ -from .common import InfoExtractor -from ..compat import compat_urlparse -from ..utils import ( - fix_xml_ampersands, - float_or_none, - xpath_with_ns, - xpath_text, -) - - -class KarriereVideosIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P[^/]+)' - _TESTS = [{ - 'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin', - 'info_dict': { - 'id': '32c91', - 'ext': 'flv', - 'title': 'AltenpflegerIn', - 'description': 'md5:dbadd1259fde2159a9b28667cb664ae2', - 'thumbnail': r're:^http://.*\.png', - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { - # broken ampersands - 'url': 'http://www.karrierevideos.at/orientierung/vaeterkarenz-und-neue-chancen-fuer-muetter-baby-was-nun', - 'info_dict': { - 'id': '5sniu', - 'ext': 'flv', - 'title': 'Väterkarenz und neue Chancen für Mütter - "Baby - was nun?"', - 'description': 'md5:97092c6ad1fd7d38e9d6a5fdeb2bcc33', - 'thumbnail': r're:^http://.*\.png', - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - title = (self._html_search_meta('title', webpage, default=None) - or self._search_regex(r'

([^<]+)

', webpage, 'video title')) - - video_id = self._search_regex( - r'/config/video/(.+?)\.xml', webpage, 'video id') - # Server returns malformed headers - # Force Accept-Encoding: * to prevent gzipped results - playlist = self._download_xml( - 'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id, - video_id, transform_source=fix_xml_ampersands, - headers={'Accept-Encoding': '*'}) - - NS_MAP = { - 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats' - } - - def ns(path): - return xpath_with_ns(path, NS_MAP) - - item = playlist.find('./tracklist/item') - video_file = xpath_text( - item, ns('./jwplayer:file'), 'video url', fatal=True) - streamer = xpath_text( - item, ns('./jwplayer:streamer'), 'streamer', fatal=True) - - uploader = xpath_text( - item, ns('./jwplayer:author'), 'uploader') - duration = float_or_none( - xpath_text(item, ns('./jwplayer:duration'), 'duration')) - - description = self._html_search_regex( - r'(?s)
(.+?)
', - webpage, 'description') - - thumbnail = self._html_search_meta( - 'thumbnail', webpage, 'thumbnail') - if thumbnail: - thumbnail = compat_urlparse.urljoin(url, thumbnail) - - return { - 'id': video_id, - 'url': streamer.replace('rtmpt', 'rtmp'), - 'play_path': 'mp4:%s' % video_file, - 'ext': 'flv', - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'duration': duration, - } diff --git a/yt_dlp/extractor/kelbyone.py b/yt_dlp/extractor/kelbyone.py index 2ca9ad4261..bba527e292 100644 --- a/yt_dlp/extractor/kelbyone.py +++ b/yt_dlp/extractor/kelbyone.py @@ -3,6 +3,7 @@ class KelbyOneIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://members\.kelbyone\.com/course/(?P[^$&?#/]+)' _TESTS = [{ diff --git a/yt_dlp/extractor/konserthusetplay.py b/yt_dlp/extractor/konserthusetplay.py deleted file mode 100644 index 10767f1b69..0000000000 --- a/yt_dlp/extractor/konserthusetplay.py +++ /dev/null @@ -1,119 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - determine_ext, - float_or_none, - int_or_none, - url_or_none, -) - - -class KonserthusetPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:konserthusetplay|rspoplay)\.se/\?.*\bm=(?P[^&]+)' - _TESTS = [{ - 'url': 'http://www.konserthusetplay.se/?m=CKDDnlCY-dhWAAqiMERd-A', - 'md5': 'e3fd47bf44e864bd23c08e487abe1967', - 'info_dict': { - 'id': 'CKDDnlCY-dhWAAqiMERd-A', - 'ext': 'mp4', - 'title': 'Orkesterns instrument: Valthornen', - 'description': 'md5:f10e1f0030202020396a4d712d2fa827', - 'thumbnail': 're:^https?://.*$', - 'duration': 398.76, - }, - }, { - 'url': 'http://rspoplay.se/?m=elWuEH34SMKvaO4wO_cHBw', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - e = self._search_regex( - r'https?://csp\.picsearch\.com/rest\?.*\be=(.+?)[&"\']', webpage, 'e') - - rest = self._download_json( - 'http://csp.picsearch.com/rest?e=%s&containerId=mediaplayer&i=object' % e, - video_id, transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1]) - - media = rest['media'] - player_config = media['playerconfig'] - playlist = player_config['playlist'] - - source = next(f for f in playlist if f.get('bitrates') or f.get('provider')) - - FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4' - - formats = [] - - m3u8_url = source.get('url') - if m3u8_url and determine_ext(m3u8_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - - fallback_url = source.get('fallbackUrl') - fallback_format_id = None - if fallback_url: - fallback_format_id = self._search_regex( - FORMAT_ID_REGEX, fallback_url, 'format id', default=None) - - connection_url = (player_config.get('rtmp', {}).get( - 'netConnectionUrl') or player_config.get( - 'plugins', {}).get('bwcheck', {}).get('netConnectionUrl')) - if connection_url: - for f in source['bitrates']: - video_url = f.get('url') - if not video_url: - continue - format_id = self._search_regex( - FORMAT_ID_REGEX, video_url, 'format id', default=None) - f_common = { - 'vbr': int_or_none(f.get('bitrate')), - 'width': int_or_none(f.get('width')), - 'height': int_or_none(f.get('height')), - } - f = f_common.copy() - f.update({ - 'url': connection_url, - 'play_path': video_url, - 'format_id': 'rtmp-%s' % format_id if format_id else 'rtmp', - 'ext': 'flv', - }) - formats.append(f) - if format_id and format_id == fallback_format_id: - f = f_common.copy() - f.update({ - 'url': fallback_url, - 'format_id': 'http-%s' % format_id if format_id else 'http', - }) - formats.append(f) - - if not formats and fallback_url: - formats.append({ - 'url': fallback_url, - }) - - title = player_config.get('title') or media['title'] - description = player_config.get('mediaInfo', {}).get('description') - thumbnail = media.get('image') - duration = float_or_none(media.get('duration'), 1000) - - subtitles = {} - captions = source.get('captionsAvailableLanguages') - if isinstance(captions, dict): - for lang, subtitle_url in captions.items(): - subtitle_url = url_or_none(subtitle_url) - if lang != 'none' and subtitle_url: - subtitles.setdefault(lang, []).append({'url': subtitle_url}) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } diff --git a/yt_dlp/extractor/koo.py b/yt_dlp/extractor/koo.py index 9cfec5eb95..c78a7b9ca2 100644 --- a/yt_dlp/extractor/koo.py +++ b/yt_dlp/extractor/koo.py @@ -6,6 +6,7 @@ class KooIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?kooapp\.com/koo/[^/]+/(?P[^/&#$?]+)' _TESTS = [{ # Test for video in the comments 'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/946c4189-bc2d-4524-b95b-43f641e2adde', diff --git a/yt_dlp/extractor/krasview.py b/yt_dlp/extractor/krasview.py index 4323aa4292..0febf759ba 100644 --- a/yt_dlp/extractor/krasview.py +++ b/yt_dlp/extractor/krasview.py @@ -8,6 +8,7 @@ class KrasViewIE(InfoExtractor): + _WORKING = False IE_DESC = 'Красвью' _VALID_URL = r'https?://krasview\.ru/(?:video|embed)/(?P\d+)' diff --git a/yt_dlp/extractor/kusi.py b/yt_dlp/extractor/kusi.py deleted file mode 100644 index a23ad8945d..0000000000 --- a/yt_dlp/extractor/kusi.py +++ /dev/null @@ -1,83 +0,0 @@ -import random -import urllib.parse - -from .common import InfoExtractor -from ..utils import ( - float_or_none, - int_or_none, - timeconvert, - update_url_query, - xpath_text, -) - - -class KUSIIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?kusi\.com/(?Pstory/.+|video\?clipId=(?P\d+))' - _TESTS = [{ - 'url': 'http://www.kusi.com/story/32849881/turko-files-refused-to-help-it-aint-right', - 'md5': '4e76ce8e53660ce9697d06c0ba6fc47d', - 'info_dict': { - 'id': '12689020', - 'ext': 'mp4', - 'title': "Turko Files: Refused to Help, It Ain't Right!", - 'duration': 223.586, - 'upload_date': '20160826', - 'timestamp': 1472233118, - 'thumbnail': r're:^https?://.*\.jpg$' - }, - }, { - 'url': 'http://kusi.com/video?clipId=12203019', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - clip_id = mobj.group('clipId') - video_id = clip_id or mobj.group('path') - - webpage = self._download_webpage(url, video_id) - - if clip_id is None: - video_id = clip_id = self._html_search_regex( - r'"clipId"\s*,\s*"(\d+)"', webpage, 'clip id') - - affiliate_id = self._search_regex( - r'affiliateId\s*:\s*\'([^\']+)\'', webpage, 'affiliate id') - - # See __Packages/worldnow/model/GalleryModel.as of WNGallery.swf - xml_url = update_url_query('http://www.kusi.com/build.asp', { - 'buildtype': 'buildfeaturexmlrequest', - 'featureType': 'Clip', - 'featureid': clip_id, - 'affiliateno': affiliate_id, - 'clientgroupid': '1', - 'rnd': int(round(random.random() * 1000000)), - }) - - doc = self._download_xml(xml_url, video_id) - - video_title = xpath_text(doc, 'HEADLINE', fatal=True) - duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000) - description = xpath_text(doc, 'ABSTRACT') - thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME') - creation_time = timeconvert(xpath_text(doc, 'rfc822creationdate')) - - quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content') - formats = [] - for quality in quality_options: - formats.append({ - 'url': urllib.parse.unquote_plus(quality.attrib['url']), - 'height': int_or_none(quality.attrib.get('height')), - 'width': int_or_none(quality.attrib.get('width')), - 'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000), - }) - - return { - 'id': video_id, - 'title': video_title, - 'description': description, - 'duration': duration, - 'formats': formats, - 'thumbnail': thumbnail, - 'timestamp': creation_time, - } diff --git a/yt_dlp/extractor/kuwo.py b/yt_dlp/extractor/kuwo.py index e8a061a104..3c93dedac2 100644 --- a/yt_dlp/extractor/kuwo.py +++ b/yt_dlp/extractor/kuwo.py @@ -54,6 +54,7 @@ def _get_formats(self, song_id, tolerate_ip_deny=False): class KuwoIE(KuwoBaseIE): + _WORKING = False IE_NAME = 'kuwo:song' IE_DESC = '酷我音乐' _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P\d+)' @@ -133,6 +134,7 @@ def _real_extract(self, url): class KuwoAlbumIE(InfoExtractor): + _WORKING = False IE_NAME = 'kuwo:album' IE_DESC = '酷我音乐 - 专辑' _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P\d+?)/' @@ -169,6 +171,7 @@ def _real_extract(self, url): class KuwoChartIE(InfoExtractor): + _WORKING = False IE_NAME = 'kuwo:chart' IE_DESC = '酷我音乐 - 排行榜' _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P[^.]+).htm' @@ -194,6 +197,7 @@ def _real_extract(self, url): class KuwoSingerIE(InfoExtractor): + _WORKING = False IE_NAME = 'kuwo:singer' IE_DESC = '酷我音乐 - 歌手' _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P[^/]+)' @@ -251,6 +255,7 @@ def page_func(page_num): class KuwoCategoryIE(InfoExtractor): + _WORKING = False IE_NAME = 'kuwo:category' IE_DESC = '酷我音乐 - 分类' _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P\d+?).htm' @@ -290,6 +295,7 @@ def _real_extract(self, url): class KuwoMvIE(KuwoBaseIE): + _WORKING = False IE_NAME = 'kuwo:mv' IE_DESC = '酷我音乐 - MV' _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P\d+?)/' diff --git a/yt_dlp/extractor/lecture2go.py b/yt_dlp/extractor/lecture2go.py index 3a9b30a3c2..10fb5d4799 100644 --- a/yt_dlp/extractor/lecture2go.py +++ b/yt_dlp/extractor/lecture2go.py @@ -10,6 +10,7 @@ class Lecture2GoIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P\d+)' _TEST = { 'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473', diff --git a/yt_dlp/extractor/lenta.py b/yt_dlp/extractor/lenta.py index 10aac984e4..fe01bda1ca 100644 --- a/yt_dlp/extractor/lenta.py +++ b/yt_dlp/extractor/lenta.py @@ -2,6 +2,7 @@ class LentaIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/', diff --git a/yt_dlp/extractor/localnews8.py b/yt_dlp/extractor/localnews8.py deleted file mode 100644 index 6f3f02c705..0000000000 --- a/yt_dlp/extractor/localnews8.py +++ /dev/null @@ -1,42 +0,0 @@ -from .common import InfoExtractor - - -class LocalNews8IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?localnews8\.com/(?:[^/]+/)*(?P[^/]+)/(?P[0-9]+)' - _TEST = { - 'url': 'http://www.localnews8.com/news/rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings/35183304', - 'md5': 'be4d48aea61aa2bde7be2ee47691ad20', - 'info_dict': { - 'id': '35183304', - 'display_id': 'rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings', - 'ext': 'mp4', - 'title': 'Rexburg business turns carbon fiber scraps into wedding ring', - 'description': 'The process was first invented by Lamborghini and less than a dozen companies around the world use it.', - 'duration': 153, - 'timestamp': 1441844822, - 'upload_date': '20150910', - 'uploader_id': 'api', - } - } - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') - - webpage = self._download_webpage(url, display_id) - - partner_id = self._search_regex( - r'partnerId\s*[:=]\s*(["\'])(?P\d+)\1', - webpage, 'partner id', group='id') - kaltura_id = self._search_regex( - r'videoIdString\s*[:=]\s*(["\'])kaltura:(?P[0-9a-z_]+)\1', - webpage, 'videl id', group='id') - - return { - '_type': 'url_transparent', - 'url': 'kaltura:%s:%s' % (partner_id, kaltura_id), - 'ie_key': 'Kaltura', - 'id': video_id, - 'display_id': display_id, - } diff --git a/yt_dlp/extractor/malltv.py b/yt_dlp/extractor/malltv.py deleted file mode 100644 index e1031d8da4..0000000000 --- a/yt_dlp/extractor/malltv.py +++ /dev/null @@ -1,107 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - clean_html, - dict_get, - float_or_none, - int_or_none, - merge_dicts, - parse_duration, - try_get, -) - - -class MallTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P[^/?#&]+)' - _TESTS = [{ - 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'md5': 'cd69ce29176f6533b65bff69ed9a5f2a', - 'info_dict': { - 'id': 't0zzt0', - 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'ext': 'mp4', - 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', - 'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35', - 'duration': 216, - 'timestamp': 1538870400, - 'upload_date': '20181007', - 'view_count': int, - 'comment_count': int, - 'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnigfq/thumbnails/retina.jpg', - 'average_rating': 9.060869565217391, - 'dislike_count': int, - 'like_count': int, - } - }, { - 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'only_matching': True, - }, { - 'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka', - 'only_matching': True, - }, { - 'url': 'https://www.mall.tv/zivoty-slavnych/nadeje-vychodu-i-zapadu-jak-michail-gorbacov-zmenil-politickou-mapu-sveta-a-ziskal-za-to-nobelovu-cenu-miru', - 'info_dict': { - 'id': 'yx010y', - 'ext': 'mp4', - 'dislike_count': int, - 'description': 'md5:aee02bee5a8d072c6a8207b91d1905a9', - 'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnjdeu/thumbnails/retina.jpg', - 'comment_count': int, - 'display_id': 'md5:0ec2afa94d2e2b7091c019cef2a43a9b', - 'like_count': int, - 'duration': 752, - 'timestamp': 1646956800, - 'title': 'md5:fe79385daaf16d74c12c1ec4a26687af', - 'view_count': int, - 'upload_date': '20220311', - 'average_rating': 9.685714285714285, - } - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage( - url, display_id, headers=self.geo_verification_headers()) - - video = self._parse_json(self._search_regex( - r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);', - webpage, 'video object'), display_id) - - video_id = self._search_regex( - r']+value\s*=\s*(\w+)', webpage, 'video id') - - formats = self._extract_m3u8_formats( - video['VideoSource'], video_id, 'mp4', 'm3u8_native') - - subtitles = {} - for s in (video.get('Subtitles') or {}): - s_url = s.get('Url') - if not s_url: - continue - subtitles.setdefault(s.get('Language') or 'cz', []).append({ - 'url': s_url, - }) - - entity_counts = video.get('EntityCounts') or {} - - def get_count(k): - v = entity_counts.get(k + 's') or {} - return int_or_none(dict_get(v, ('Count', 'StrCount'))) - - info = self._search_json_ld(webpage, video_id, default={}) - - return merge_dicts({ - 'id': str(video_id), - 'display_id': display_id, - 'title': video.get('Title'), - 'description': clean_html(video.get('Description')), - 'thumbnail': video.get('ThumbnailUrl'), - 'formats': formats, - 'subtitles': subtitles, - 'duration': int_or_none(video.get('DurationSeconds')) or parse_duration(video.get('Duration')), - 'view_count': get_count('View'), - 'like_count': get_count('Like'), - 'dislike_count': get_count('Dislike'), - 'average_rating': float_or_none(try_get(video, lambda x: x['EntityRating']['AvarageRate'])), - 'comment_count': get_count('Comment'), - }, info) diff --git a/yt_dlp/extractor/manyvids.py b/yt_dlp/extractor/manyvids.py index 741745378b..2aa3a3c93b 100644 --- a/yt_dlp/extractor/manyvids.py +++ b/yt_dlp/extractor/manyvids.py @@ -12,6 +12,7 @@ class ManyVidsIE(InfoExtractor): + _WORKING = False _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P\d+)' _TESTS = [{ # preview video diff --git a/yt_dlp/extractor/markiza.py b/yt_dlp/extractor/markiza.py index 53ed79158f..ca465eae96 100644 --- a/yt_dlp/extractor/markiza.py +++ b/yt_dlp/extractor/markiza.py @@ -10,6 +10,7 @@ class MarkizaIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?videoarchiv\.markiza\.sk/(?:video/(?:[^/]+/)*|embed/)(?P\d+)(?:[_/]|$)' _TESTS = [{ 'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723_oteckovia-109', @@ -68,6 +69,7 @@ def _real_extract(self, url): class MarkizaPageIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?(?:(?:[^/]+\.)?markiza|tvnoviny)\.sk/(?:[^/]+/)*(?P\d+)_' _TESTS = [{ 'url': 'http://www.markiza.sk/soubiz/zahranicny/1923705_oteckovia-maju-svoj-den-ti-slavni-nie-su-o-nic-menej-rozkosni', diff --git a/yt_dlp/extractor/miaopai.py b/yt_dlp/extractor/miaopai.py deleted file mode 100644 index 329ce36582..0000000000 --- a/yt_dlp/extractor/miaopai.py +++ /dev/null @@ -1,36 +0,0 @@ -from .common import InfoExtractor - - -class MiaoPaiIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P[-A-Za-z0-9~_]+)' - _TEST = { - 'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm', - 'md5': '095ed3f1cd96b821add957bdc29f845b', - 'info_dict': { - 'id': 'n~0hO7sfV1nBEw4Y29-Hqg__', - 'ext': 'mp4', - 'title': '西游记音乐会的秒拍视频', - 'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg', - } - } - - _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1' - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD}) - - title = self._html_extract_title(webpage) - thumbnail = self._html_search_regex( - r']+class=(?P[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P[\'"])(?P[^\'"]+)(?P=q2)', - webpage, 'thumbnail', fatal=False, group='url') - videos = self._parse_html5_media_entries(url, webpage, video_id) - info = videos[0] - - info.update({ - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - }) - return info diff --git a/yt_dlp/extractor/ministrygrid.py b/yt_dlp/extractor/ministrygrid.py deleted file mode 100644 index 053c6726c3..0000000000 --- a/yt_dlp/extractor/ministrygrid.py +++ /dev/null @@ -1,55 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - smuggle_url, -) - - -class MinistryGridIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ministrygrid\.com/([^/?#]*/)*(?P[^/#?]+)/?(?:$|[?#])' - - _TEST = { - 'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers', - 'md5': '844be0d2a1340422759c2a9101bab017', - 'info_dict': { - 'id': '3453494717001', - 'ext': 'mp4', - 'title': 'The Gospel by Numbers', - 'thumbnail': r're:^https?://.*\.jpg', - 'upload_date': '20140410', - 'description': 'Coming soon from T4G 2014!', - 'uploader_id': '2034960640001', - 'timestamp': 1397145591, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['TDSLifeway'], - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - portlets = self._parse_json(self._search_regex( - r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list'), - video_id) - pl_id = self._search_regex( - r'getPlid:function\(\){return"(\d+)"}', webpage, 'p_l_id') - - for i, portlet in enumerate(portlets): - portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet) - portlet_code = self._download_webpage( - portlet_url, video_id, - note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)), - fatal=False) - video_iframe_url = self._search_regex( - r'[0-9]+)' - _TESTS = [{ - 'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869', - 'md5': '6c0acface7a787aadc8391e4bbf7b0f5', - 'info_dict': { - 'id': '615869', - 'ext': 'mp4', - 'title': 'Get Ahead of the Curve on 2013 Taxes', - 'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.", - 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' - } - }, { - 'url': 'http://news.morningstar.com/cover/videocenter.aspx?id=825556', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id) - title = self._html_search_regex( - r'

(.*?)

', webpage, 'title') - video_url = self._html_search_regex( - r'(.*?)', - webpage, 'description', fatal=False) - - return { - 'id': video_id, - 'title': title, - 'url': video_url, - 'thumbnail': thumbnail, - 'description': description, - } diff --git a/yt_dlp/extractor/motorsport.py b/yt_dlp/extractor/motorsport.py index efb087d035..167d85fa9b 100644 --- a/yt_dlp/extractor/motorsport.py +++ b/yt_dlp/extractor/motorsport.py @@ -5,6 +5,7 @@ class MotorsportIE(InfoExtractor): + _WORKING = False IE_DESC = 'motorsport.com' _VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P[^/]+)/?(?:$|[?#])' _TEST = { diff --git a/yt_dlp/extractor/mtv.py b/yt_dlp/extractor/mtv.py index e192453c72..404e431bc6 100644 --- a/yt_dlp/extractor/mtv.py +++ b/yt_dlp/extractor/mtv.py @@ -451,6 +451,7 @@ def _real_extract(self, url): class MTVDEIE(MTVServicesInfoExtractor): + _WORKING = False IE_NAME = 'mtv.de' _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P[0-9a-z]+)' _TESTS = [{ diff --git a/yt_dlp/extractor/muenchentv.py b/yt_dlp/extractor/muenchentv.py index 36a2d4688e..934cd4fbc8 100644 --- a/yt_dlp/extractor/muenchentv.py +++ b/yt_dlp/extractor/muenchentv.py @@ -9,6 +9,7 @@ class MuenchenTVIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?muenchen\.tv/livestream' IE_DESC = 'münchen.tv' _TEST = { diff --git a/yt_dlp/extractor/murrtube.py b/yt_dlp/extractor/murrtube.py index 6cdbbda168..74365c0c08 100644 --- a/yt_dlp/extractor/murrtube.py +++ b/yt_dlp/extractor/murrtube.py @@ -12,6 +12,7 @@ class MurrtubeIE(InfoExtractor): + _WORKING = False _VALID_URL = r'''(?x) (?: murrtube:| @@ -100,6 +101,7 @@ def _real_extract(self, url): class MurrtubeUserIE(MurrtubeIE): # XXX: Do not subclass from concrete IE + _WORKING = False IE_DESC = 'Murrtube user profile' _VALID_URL = r'https?://murrtube\.net/(?P[^/]+)$' _TEST = { diff --git a/yt_dlp/extractor/ndtv.py b/yt_dlp/extractor/ndtv.py index bfe52f77de..d099db37b1 100644 --- a/yt_dlp/extractor/ndtv.py +++ b/yt_dlp/extractor/ndtv.py @@ -5,6 +5,7 @@ class NDTVIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P\d+)' _TESTS = [ diff --git a/yt_dlp/extractor/netzkino.py b/yt_dlp/extractor/netzkino.py index 9c314e2233..e9422eebf1 100644 --- a/yt_dlp/extractor/netzkino.py +++ b/yt_dlp/extractor/netzkino.py @@ -8,6 +8,7 @@ class NetzkinoIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/[^/]+/(?P[^/]+)' _TESTS = [{ diff --git a/yt_dlp/extractor/nextmedia.py b/yt_dlp/extractor/nextmedia.py index 0e47a4d45a..871d3e6696 100644 --- a/yt_dlp/extractor/nextmedia.py +++ b/yt_dlp/extractor/nextmedia.py @@ -191,6 +191,8 @@ def _fetch_description(self, page): class NextTVIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE IE_DESC = '壹電視' _VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P\d+)' diff --git a/yt_dlp/extractor/nobelprize.py b/yt_dlp/extractor/nobelprize.py index 1aa9705be4..cddc72f716 100644 --- a/yt_dlp/extractor/nobelprize.py +++ b/yt_dlp/extractor/nobelprize.py @@ -10,6 +10,7 @@ class NobelPrizeIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P\d+)' _TEST = { 'url': 'http://www.nobelprize.org/mediaplayer/?id=2636', diff --git a/yt_dlp/extractor/noz.py b/yt_dlp/extractor/noz.py index 59d259f9df..c7b8038036 100644 --- a/yt_dlp/extractor/noz.py +++ b/yt_dlp/extractor/noz.py @@ -9,6 +9,7 @@ class NozIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?noz\.de/video/(?P[0-9]+)/' _TESTS = [{ 'url': 'http://www.noz.de/video/25151/32-Deutschland-gewinnt-Badminton-Lnderspiel-in-Melle', diff --git a/yt_dlp/extractor/odatv.py b/yt_dlp/extractor/odatv.py deleted file mode 100644 index 24ab939421..0000000000 --- a/yt_dlp/extractor/odatv.py +++ /dev/null @@ -1,47 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - NO_DEFAULT, - remove_start -) - - -class OdaTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?odatv\.com/(?:mob|vid)_video\.php\?.*\bid=(?P[^&]+)' - _TESTS = [{ - 'url': 'http://odatv.com/vid_video.php?id=8E388', - 'md5': 'dc61d052f205c9bf2da3545691485154', - 'info_dict': { - 'id': '8E388', - 'ext': 'mp4', - 'title': 'Artık Davutoğlu ile devam edemeyiz' - } - }, { - # mobile URL - 'url': 'http://odatv.com/mob_video.php?id=8E388', - 'only_matching': True, - }, { - # no video - 'url': 'http://odatv.com/mob_video.php?id=8E900', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - no_video = 'NO VIDEO!' in webpage - - video_url = self._search_regex( - r'mp4\s*:\s*(["\'])(?Phttp.+?)\1', webpage, 'video url', - default=None if no_video else NO_DEFAULT, group='url') - - if no_video: - raise ExtractorError('Video %s does not exist' % video_id, expected=True) - - return { - 'id': video_id, - 'url': video_url, - 'title': remove_start(self._og_search_title(webpage), 'Video: '), - 'thumbnail': self._og_search_thumbnail(webpage), - } diff --git a/yt_dlp/extractor/parlview.py b/yt_dlp/extractor/parlview.py index 0b547917c0..777b008895 100644 --- a/yt_dlp/extractor/parlview.py +++ b/yt_dlp/extractor/parlview.py @@ -8,7 +8,7 @@ class ParlviewIE(InfoExtractor): - + _WORKING = False _VALID_URL = r'https?://(?:www\.)?parlview\.aph\.gov\.au/(?:[^/]+)?\bvideoID=(?P\d{6})' _TESTS = [{ 'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=542661', diff --git a/yt_dlp/extractor/playstuff.py b/yt_dlp/extractor/playstuff.py deleted file mode 100644 index b424ba1872..0000000000 --- a/yt_dlp/extractor/playstuff.py +++ /dev/null @@ -1,63 +0,0 @@ -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - smuggle_url, - try_get, -) - - -class PlayStuffIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?play\.stuff\.co\.nz/details/(?P[^/?#&]+)' - _TESTS = [{ - 'url': 'https://play.stuff.co.nz/details/608778ac1de1c4001a3fa09a', - 'md5': 'c82d3669e5247c64bc382577843e5bd0', - 'info_dict': { - 'id': '6250584958001', - 'ext': 'mp4', - 'title': 'Episode 1: Rotorua/Mt Maunganui/Tauranga', - 'description': 'md5:c154bafb9f0dd02d01fd4100fb1c1913', - 'uploader_id': '6005208634001', - 'timestamp': 1619491027, - 'upload_date': '20210427', - }, - 'add_ie': ['BrightcoveNew'], - }, { - # geo restricted, bypassable - 'url': 'https://play.stuff.co.nz/details/_6155660351001', - 'only_matching': True, - }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s' - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - state = self._parse_json( - self._search_regex( - r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'state'), - video_id) - - account_id = try_get( - state, lambda x: x['configurations']['accountId'], - compat_str) or '6005208634001' - player_id = try_get( - state, lambda x: x['configurations']['playerId'], - compat_str) or 'default' - - entries = [] - for item_id, video in state['items'].items(): - if not isinstance(video, dict): - continue - asset_id = try_get( - video, lambda x: x['content']['attributes']['assetId'], - compat_str) - if not asset_id: - continue - entries.append(self.url_result( - smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, asset_id), - {'geo_countries': ['NZ']}), - 'BrightcoveNew', video_id)) - - return self.playlist_result(entries, video_id) diff --git a/yt_dlp/extractor/plutotv.py b/yt_dlp/extractor/plutotv.py index caffeb21df..5898d927c6 100644 --- a/yt_dlp/extractor/plutotv.py +++ b/yt_dlp/extractor/plutotv.py @@ -16,6 +16,7 @@ class PlutoTVIE(InfoExtractor): + _WORKING = False _VALID_URL = r'''(?x) https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand /(?Pmovies|series) diff --git a/yt_dlp/extractor/podomatic.py b/yt_dlp/extractor/podomatic.py index 985bfae9dd..37b68694b9 100644 --- a/yt_dlp/extractor/podomatic.py +++ b/yt_dlp/extractor/podomatic.py @@ -5,6 +5,7 @@ class PodomaticIE(InfoExtractor): + _WORKING = False IE_NAME = 'podomatic' _VALID_URL = r'''(?x) (?Phttps?):// diff --git a/yt_dlp/extractor/pornovoisines.py b/yt_dlp/extractor/pornovoisines.py index aa48da06b9..2e51b4f6b2 100644 --- a/yt_dlp/extractor/pornovoisines.py +++ b/yt_dlp/extractor/pornovoisines.py @@ -7,6 +7,7 @@ class PornoVoisinesIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P\d+)/(?P[^/.]+)' _TEST = { diff --git a/yt_dlp/extractor/pornoxo.py b/yt_dlp/extractor/pornoxo.py index 5104d8a49b..049feb4ece 100644 --- a/yt_dlp/extractor/pornoxo.py +++ b/yt_dlp/extractor/pornoxo.py @@ -5,6 +5,7 @@ class PornoXOIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P\d+)/(?P[^/]+)\.html' _TEST = { 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html', diff --git a/yt_dlp/extractor/projectveritas.py b/yt_dlp/extractor/projectveritas.py index 0e029ce8cd..daf14054c5 100644 --- a/yt_dlp/extractor/projectveritas.py +++ b/yt_dlp/extractor/projectveritas.py @@ -7,6 +7,7 @@ class ProjectVeritasIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?projectveritas\.com/(?Pnews|video)/(?P[^/?#]+)' _TESTS = [{ 'url': 'https://www.projectveritas.com/news/exclusive-inside-the-new-york-and-new-jersey-hospitals-battling-coronavirus/', diff --git a/yt_dlp/extractor/r7.py b/yt_dlp/extractor/r7.py index f067a0571b..36f0b52bd8 100644 --- a/yt_dlp/extractor/r7.py +++ b/yt_dlp/extractor/r7.py @@ -3,6 +3,8 @@ class R7IE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE _VALID_URL = r'''(?x) https?:// (?: @@ -86,6 +88,8 @@ def _real_extract(self, url): class R7ArticleIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE _VALID_URL = r'https?://(?:[a-zA-Z]+)\.r7\.com/(?:[^/]+/)+[^/?#&]+-(?P\d+)' _TEST = { 'url': 'http://tv.r7.com/record-play/balanco-geral/videos/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-16102015', diff --git a/yt_dlp/extractor/radiode.py b/yt_dlp/extractor/radiode.py index 32c36d5577..7262078251 100644 --- a/yt_dlp/extractor/radiode.py +++ b/yt_dlp/extractor/radiode.py @@ -2,6 +2,7 @@ class RadioDeIE(InfoExtractor): + _WORKING = False IE_NAME = 'radio.de' _VALID_URL = r'https?://(?P.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)' _TEST = { diff --git a/yt_dlp/extractor/radiojavan.py b/yt_dlp/extractor/radiojavan.py index 6a91394668..b3befaef90 100644 --- a/yt_dlp/extractor/radiojavan.py +++ b/yt_dlp/extractor/radiojavan.py @@ -11,6 +11,7 @@ class RadioJavanIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P[^/]+)/?' _TEST = { 'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam', diff --git a/yt_dlp/extractor/rbmaradio.py b/yt_dlp/extractor/rbmaradio.py deleted file mode 100644 index 86c63dbb7f..0000000000 --- a/yt_dlp/extractor/rbmaradio.py +++ /dev/null @@ -1,68 +0,0 @@ -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - clean_html, - int_or_none, - unified_timestamp, - update_url_query, -) - - -class RBMARadioIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:rbmaradio|redbullradio)\.com/shows/(?P[^/]+)/episodes/(?P[^/?#&]+)' - _TEST = { - 'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011', - 'md5': '6bc6f9bcb18994b4c983bc3bf4384d95', - 'info_dict': { - 'id': 'ford-lopatin-live-at-primavera-sound-2011', - 'ext': 'mp3', - 'title': 'Main Stage - Ford & Lopatin at Primavera Sound', - 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', - 'thumbnail': r're:^https?://.*\.jpg', - 'duration': 2452, - 'timestamp': 1307103164, - 'upload_date': '20110603', - }, - } - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - show_id = mobj.group('show_id') - episode_id = mobj.group('id') - - webpage = self._download_webpage(url, episode_id) - - episode = self._parse_json( - self._search_regex( - r'__INITIAL_STATE__\s*=\s*({.+?})\s*', - webpage, 'json data'), - episode_id)['episodes'][show_id][episode_id] - - title = episode['title'] - - show_title = episode.get('showTitle') - if show_title: - title = '%s - %s' % (show_title, title) - - formats = [{ - 'url': update_url_query(episode['audioURL'], query={'cbr': abr}), - 'format_id': compat_str(abr), - 'abr': abr, - 'vcodec': 'none', - } for abr in (96, 128, 192, 256)] - self._check_formats(formats, episode_id) - - description = clean_html(episode.get('longTeaser')) - thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape')) - duration = int_or_none(episode.get('duration')) - timestamp = unified_timestamp(episode.get('publishedAt')) - - return { - 'id': episode_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - } diff --git a/yt_dlp/extractor/rds.py b/yt_dlp/extractor/rds.py index 9a2e0d9851..1a1c6634e3 100644 --- a/yt_dlp/extractor/rds.py +++ b/yt_dlp/extractor/rds.py @@ -8,6 +8,7 @@ class RDSIE(InfoExtractor): + _WORKING = False IE_DESC = 'RDS.ca' _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P[^/]+)-\d+\.\d+' diff --git a/yt_dlp/extractor/redbee.py b/yt_dlp/extractor/redbee.py index b59b518b13..4d71133b3c 100644 --- a/yt_dlp/extractor/redbee.py +++ b/yt_dlp/extractor/redbee.py @@ -134,6 +134,7 @@ def _real_extract(self, url): class RTBFIE(RedBeeBaseIE): + _WORKING = False _VALID_URL = r'''(?x) https?://(?:www\.)?rtbf\.be/ (?: diff --git a/yt_dlp/extractor/regiotv.py b/yt_dlp/extractor/regiotv.py deleted file mode 100644 index edb6ae5bce..0000000000 --- a/yt_dlp/extractor/regiotv.py +++ /dev/null @@ -1,55 +0,0 @@ -from .common import InfoExtractor -from ..networking import Request -from ..utils import xpath_text, xpath_with_ns - - -class RegioTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P[0-9]+)' - _TESTS = [{ - 'url': 'http://www.regio-tv.de/video/395808.html', - 'info_dict': { - 'id': '395808', - 'ext': 'mp4', - 'title': 'Wir in Ludwigsburg', - 'description': 'Mit unseren zuckersüßen Adventskindern, außerdem besuchen wir die Abendsterne!', - } - }, { - 'url': 'http://www.regio-tv.de/video/395808', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - key = self._search_regex( - r'key\s*:\s*(["\'])(?P.+?)\1', webpage, 'key', group='key') - title = self._og_search_title(webpage) - - SOAP_TEMPLATE = '<{0} xmlns="http://v.telvi.de/">{1}' - - request = Request( - 'http://v.telvi.de/', - SOAP_TEMPLATE.format('GetHTML5VideoData', key).encode('utf-8')) - video_data = self._download_xml(request, video_id, 'Downloading video XML') - - NS_MAP = { - 'xsi': 'http://www.w3.org/2001/XMLSchema-instance', - 'soap': 'http://schemas.xmlsoap.org/soap/envelope/', - } - - video_url = xpath_text( - video_data, xpath_with_ns('.//video', NS_MAP), 'video url', fatal=True) - thumbnail = xpath_text( - video_data, xpath_with_ns('.//image', NS_MAP), 'thumbnail') - description = self._og_search_description( - webpage) or self._html_search_meta('description', webpage) - - return { - 'id': video_id, - 'url': video_url, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - } diff --git a/yt_dlp/extractor/rentv.py b/yt_dlp/extractor/rentv.py index fdde31704c..abb537cf3e 100644 --- a/yt_dlp/extractor/rentv.py +++ b/yt_dlp/extractor/rentv.py @@ -8,6 +8,7 @@ class RENTVIE(InfoExtractor): + _WORKING = False _VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P\d+)' _TESTS = [{ 'url': 'http://ren.tv/video/epizod/118577', @@ -59,6 +60,7 @@ def _real_extract(self, url): class RENTVArticleIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?ren\.tv/novosti/\d{4}-\d{2}-\d{2}/(?P[^/?#]+)' _TESTS = [{ 'url': 'http://ren.tv/novosti/2016-10-26/video-mikroavtobus-popavshiy-v-dtp-s-gruzovikami-v-podmoskove-prevratilsya-v', diff --git a/yt_dlp/extractor/restudy.py b/yt_dlp/extractor/restudy.py index 6d032564d3..f49262a650 100644 --- a/yt_dlp/extractor/restudy.py +++ b/yt_dlp/extractor/restudy.py @@ -2,6 +2,7 @@ class RestudyIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:(?:www|portal)\.)?restudy\.dk/video/[^/]+/id/(?P[0-9]+)' _TESTS = [{ 'url': 'https://www.restudy.dk/video/play/id/1637', diff --git a/yt_dlp/extractor/reuters.py b/yt_dlp/extractor/reuters.py index 6919425f3a..0a8f13b9f6 100644 --- a/yt_dlp/extractor/reuters.py +++ b/yt_dlp/extractor/reuters.py @@ -9,6 +9,7 @@ class ReutersIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?reuters\.com/.*?\?.*?videoId=(?P[0-9]+)' _TEST = { 'url': 'http://www.reuters.com/video/2016/05/20/san-francisco-police-chief-resigns?videoId=368575562', diff --git a/yt_dlp/extractor/rockstargames.py b/yt_dlp/extractor/rockstargames.py index c491aaf534..b0b92e642b 100644 --- a/yt_dlp/extractor/rockstargames.py +++ b/yt_dlp/extractor/rockstargames.py @@ -6,6 +6,7 @@ class RockstarGamesIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?rockstargames\.com/videos(?:/video/|#?/?\?.*\bvideo=)(?P\d+)' _TESTS = [{ 'url': 'https://www.rockstargames.com/videos/video/11544/', diff --git a/yt_dlp/extractor/rts.py b/yt_dlp/extractor/rts.py index 9f73d1811f..bce5cba82a 100644 --- a/yt_dlp/extractor/rts.py +++ b/yt_dlp/extractor/rts.py @@ -13,6 +13,7 @@ class RTSIE(SRGSSRIE): # XXX: Do not subclass from concrete IE + _WORKING = False IE_DESC = 'RTS.ch' _VALID_URL = r'rts:(?P\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P[0-9]+)-(?P.+?)\.html' diff --git a/yt_dlp/extractor/saitosan.py b/yt_dlp/extractor/saitosan.py index d2f60e92ff..a5f05e1d05 100644 --- a/yt_dlp/extractor/saitosan.py +++ b/yt_dlp/extractor/saitosan.py @@ -3,6 +3,7 @@ class SaitosanIE(InfoExtractor): + _WORKING = False IE_NAME = 'Saitosan' _VALID_URL = r'https?://(?:www\.)?saitosan\.net/bview.html\?id=(?P[0-9]+)' _TESTS = [{ diff --git a/yt_dlp/extractor/savefrom.py b/yt_dlp/extractor/savefrom.py deleted file mode 100644 index 9c9e74b6dd..0000000000 --- a/yt_dlp/extractor/savefrom.py +++ /dev/null @@ -1,30 +0,0 @@ -import os.path - -from .common import InfoExtractor - - -class SaveFromIE(InfoExtractor): - IE_NAME = 'savefrom.net' - _VALID_URL = r'https?://[^.]+\.savefrom\.net/\#url=(?P.*)$' - - _TEST = { - 'url': 'http://en.savefrom.net/#url=http://youtube.com/watch?v=UlVRAPW2WJY&utm_source=youtube.com&utm_medium=short_domains&utm_campaign=ssyoutube.com', - 'info_dict': { - 'id': 'UlVRAPW2WJY', - 'ext': 'mp4', - 'title': 'About Team Radical MMA | MMA Fighting', - 'upload_date': '20120816', - 'uploader': 'Howcast', - 'uploader_id': 'Howcast', - 'description': r're:(?s).* Hi, my name is Rene Dreifuss\. And I\'m here to show you some MMA.*', - }, - 'params': { - 'skip_download': True - } - } - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - video_id = os.path.splitext(url.split('/')[-1])[0] - - return self.url_result(mobj.group('url'), video_id=video_id) diff --git a/yt_dlp/extractor/seeker.py b/yt_dlp/extractor/seeker.py deleted file mode 100644 index 65eb16a09d..0000000000 --- a/yt_dlp/extractor/seeker.py +++ /dev/null @@ -1,55 +0,0 @@ -import re - -from .common import InfoExtractor -from ..utils import ( - get_element_by_class, - strip_or_none, -) - - -class SeekerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P.*)-(?P\d+)\.html' - _TESTS = [{ - 'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html', - 'md5': '897d44bbe0d8986a2ead96de565a92db', - 'info_dict': { - 'id': 'Elrn3gnY', - 'ext': 'mp4', - 'title': 'Should Trump Be Required To Release His Tax Returns?', - 'description': 'md5:41efa8cfa8d627841045eec7b018eb45', - 'timestamp': 1490090165, - 'upload_date': '20170321', - } - }, { - 'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html', - 'playlist': [ - { - 'md5': '0497b9f20495174be73ae136949707d2', - 'info_dict': { - 'id': 'FihYQ8AE', - 'ext': 'mp4', - 'title': 'The Pros & Cons Of Zoos', - 'description': 'md5:d88f99a8ea8e7d25e6ff77f271b1271c', - 'timestamp': 1490039133, - 'upload_date': '20170320', - }, - } - ], - 'info_dict': { - 'id': '1834116536', - 'title': 'After Gorilla Killing, Changes Ahead for Zoos', - 'description': 'The largest association of zoos and others are hoping to learn from recent incidents that led to the shooting deaths of a gorilla and two lions.', - }, - }] - - def _real_extract(self, url): - display_id, article_id = self._match_valid_url(url).groups() - webpage = self._download_webpage(url, display_id) - entries = [] - for jwp_id in re.findall(r'data-video-id="([a-zA-Z0-9]{8})"', webpage): - entries.append(self.url_result( - 'jwplatform:' + jwp_id, 'JWPlatform', jwp_id)) - return self.playlist_result( - entries, article_id, - self._og_search_title(webpage), - strip_or_none(get_element_by_class('subtitle__text', webpage)) or self._og_search_description(webpage)) diff --git a/yt_dlp/extractor/senalcolombia.py b/yt_dlp/extractor/senalcolombia.py index f3c066da77..b2f354faef 100644 --- a/yt_dlp/extractor/senalcolombia.py +++ b/yt_dlp/extractor/senalcolombia.py @@ -3,6 +3,7 @@ class SenalColombiaLiveIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?senalcolombia\.tv/(?Psenal-en-vivo)' _TESTS = [{ diff --git a/yt_dlp/extractor/sendtonews.py b/yt_dlp/extractor/sendtonews.py index 3600e2e740..1ecea71fcc 100644 --- a/yt_dlp/extractor/sendtonews.py +++ b/yt_dlp/extractor/sendtonews.py @@ -12,6 +12,7 @@ class SendtoNewsIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P[0-9A-Za-z-]+)' _TEST = { diff --git a/yt_dlp/extractor/sexu.py b/yt_dlp/extractor/sexu.py index 3117f81e38..989b63c721 100644 --- a/yt_dlp/extractor/sexu.py +++ b/yt_dlp/extractor/sexu.py @@ -2,6 +2,7 @@ class SexuIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P\d+)' _TEST = { 'url': 'http://sexu.com/961791/', diff --git a/yt_dlp/extractor/skylinewebcams.py b/yt_dlp/extractor/skylinewebcams.py index 4292bb2ae5..197407c18d 100644 --- a/yt_dlp/extractor/skylinewebcams.py +++ b/yt_dlp/extractor/skylinewebcams.py @@ -2,6 +2,7 @@ class SkylineWebcamsIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?skylinewebcams\.com/[^/]+/webcam/(?:[^/]+/)+(?P[^/]+)\.html' _TEST = { 'url': 'https://www.skylinewebcams.com/it/webcam/italia/lazio/roma/scalinata-piazza-di-spagna-barcaccia.html', diff --git a/yt_dlp/extractor/skynewsarabia.py b/yt_dlp/extractor/skynewsarabia.py index 6264b04bb3..867782778b 100644 --- a/yt_dlp/extractor/skynewsarabia.py +++ b/yt_dlp/extractor/skynewsarabia.py @@ -38,6 +38,7 @@ def _extract_video_info(self, video_data): class SkyNewsArabiaIE(SkyNewsArabiaBaseIE): + _WORKING = False IE_NAME = 'skynewsarabia:video' _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P[0-9]+)' _TEST = { @@ -64,6 +65,7 @@ def _real_extract(self, url): class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE): + _WORKING = False IE_NAME = 'skynewsarabia:article' _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P[0-9]+)' _TESTS = [{ diff --git a/yt_dlp/extractor/startrek.py b/yt_dlp/extractor/startrek.py index e92122f9b7..94efb589c6 100644 --- a/yt_dlp/extractor/startrek.py +++ b/yt_dlp/extractor/startrek.py @@ -3,6 +3,7 @@ class StarTrekIE(InfoExtractor): + _WORKING = False _VALID_URL = r'(?Phttps?://(?:intl|www)\.startrek\.com)/videos/(?P[^/]+)' _TESTS = [{ 'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room', diff --git a/yt_dlp/extractor/streamff.py b/yt_dlp/extractor/streamff.py deleted file mode 100644 index 93c42942c3..0000000000 --- a/yt_dlp/extractor/streamff.py +++ /dev/null @@ -1,30 +0,0 @@ -from .common import InfoExtractor -from ..utils import int_or_none, parse_iso8601 - - -class StreamFFIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?streamff\.com/v/(?P[a-zA-Z0-9]+)' - - _TESTS = [{ - 'url': 'https://streamff.com/v/55cc94', - 'md5': '8745a67bb5e5c570738efe7983826370', - 'info_dict': { - 'id': '55cc94', - 'ext': 'mp4', - 'title': '55cc94', - 'timestamp': 1634764643, - 'upload_date': '20211020', - 'view_count': int, - } - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - json_data = self._download_json(f'https://streamff.com/api/videos/{video_id}', video_id) - return { - 'id': video_id, - 'title': json_data.get('name') or video_id, - 'url': 'https://streamff.com/%s' % json_data['videoLink'], - 'view_count': int_or_none(json_data.get('views')), - 'timestamp': parse_iso8601(json_data.get('date')), - } diff --git a/yt_dlp/extractor/syfy.py b/yt_dlp/extractor/syfy.py index afcdbf7804..bd2d738423 100644 --- a/yt_dlp/extractor/syfy.py +++ b/yt_dlp/extractor/syfy.py @@ -6,6 +6,7 @@ class SyfyIE(AdobePassIE): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?syfy\.com/(?:[^/]+/)?videos/(?P[^/?#]+)' _TESTS = [{ 'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer', diff --git a/yt_dlp/extractor/tagesschau.py b/yt_dlp/extractor/tagesschau.py index e23b490b00..c69c13d0bb 100644 --- a/yt_dlp/extractor/tagesschau.py +++ b/yt_dlp/extractor/tagesschau.py @@ -12,6 +12,7 @@ class TagesschauIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P[^/]+/(?:[^/]+/)*?(?P[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html' _TESTS = [{ diff --git a/yt_dlp/extractor/tass.py b/yt_dlp/extractor/tass.py index 67e544a6a3..d4c5b41a71 100644 --- a/yt_dlp/extractor/tass.py +++ b/yt_dlp/extractor/tass.py @@ -8,6 +8,7 @@ class TassIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P\d+)' _TESTS = [ { diff --git a/yt_dlp/extractor/tdslifeway.py b/yt_dlp/extractor/tdslifeway.py deleted file mode 100644 index 3623a68c8c..0000000000 --- a/yt_dlp/extractor/tdslifeway.py +++ /dev/null @@ -1,31 +0,0 @@ -from .common import InfoExtractor - - -class TDSLifewayIE(InfoExtractor): - _VALID_URL = r'https?://tds\.lifeway\.com/v1/trainingdeliverysystem/courses/(?P\d+)/index\.html' - - _TEST = { - # From http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers - 'url': 'http://tds.lifeway.com/v1/trainingdeliverysystem/courses/3453494717001/index.html?externalRegistration=AssetId%7C34F466F1-78F3-4619-B2AB-A8EFFA55E9E9%21InstanceId%7C0%21UserId%7Caaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa&grouping=http%3A%2F%2Flifeway.com%2Fvideo%2F3453494717001&activity_id=http%3A%2F%2Flifeway.com%2Fvideo%2F3453494717001&content_endpoint=http%3A%2F%2Ftds.lifeway.com%2Fv1%2Ftrainingdeliverysystem%2FScormEngineInterface%2FTCAPI%2Fcontent%2F&actor=%7B%22name%22%3A%5B%22Guest%20Guest%22%5D%2C%22account%22%3A%5B%7B%22accountServiceHomePage%22%3A%22http%3A%2F%2Fscorm.lifeway.com%2F%22%2C%22accountName%22%3A%22aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa%22%7D%5D%2C%22objectType%22%3A%22Agent%22%7D&content_token=462a50b2-b6f9-4970-99b1-930882c499fb®istration=93d6ec8e-7f7b-4ed3-bbc8-a857913c0b2a&externalConfiguration=access%7CFREE%21adLength%7C-1%21assignOrgId%7C4AE36F78-299A-425D-91EF-E14A899B725F%21assignOrgParentId%7C%21courseId%7C%21isAnonymous%7Cfalse%21previewAsset%7Cfalse%21previewLength%7C-1%21previewMode%7Cfalse%21royalty%7CFREE%21sessionId%7C671422F9-8E79-48D4-9C2C-4EE6111EA1CD%21trackId%7C&auth=Basic%20OjhmZjk5MDBmLTBlYTMtNDJhYS04YjFlLWE4MWQ3NGNkOGRjYw%3D%3D&endpoint=http%3A%2F%2Ftds.lifeway.com%2Fv1%2Ftrainingdeliverysystem%2FScormEngineInterface%2FTCAPI%2F', - 'info_dict': { - 'id': '3453494717001', - 'ext': 'mp4', - 'title': 'The Gospel by Numbers', - 'thumbnail': r're:^https?://.*\.jpg', - 'upload_date': '20140410', - 'description': 'Coming soon from T4G 2014!', - 'uploader_id': '2034960640001', - 'timestamp': 1397145591, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['BrightcoveNew'], - } - - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/2034960640001/default_default/index.html?videoId=%s' - - def _real_extract(self, url): - brightcove_id = self._match_id(url) - return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/yt_dlp/extractor/teachable.py b/yt_dlp/extractor/teachable.py index 01906bda9d..5eac9aa3fd 100644 --- a/yt_dlp/extractor/teachable.py +++ b/yt_dlp/extractor/teachable.py @@ -99,6 +99,7 @@ def is_logged(webpage): class TeachableIE(TeachableBaseIE): + _WORKING = False _VALID_URL = r'''(?x) (?: %shttps?://(?P[^/]+)| diff --git a/yt_dlp/extractor/teachertube.py b/yt_dlp/extractor/teachertube.py index c3eec2784f..90a976297a 100644 --- a/yt_dlp/extractor/teachertube.py +++ b/yt_dlp/extractor/teachertube.py @@ -9,6 +9,7 @@ class TeacherTubeIE(InfoExtractor): + _WORKING = False IE_NAME = 'teachertube' IE_DESC = 'teachertube.com videos' @@ -87,6 +88,7 @@ def _real_extract(self, url): class TeacherTubeUserIE(InfoExtractor): + _WORKING = False IE_NAME = 'teachertube:user:collection' IE_DESC = 'teachertube.com user and collection videos' diff --git a/yt_dlp/extractor/teachingchannel.py b/yt_dlp/extractor/teachingchannel.py index 275f6d1f92..5791292a95 100644 --- a/yt_dlp/extractor/teachingchannel.py +++ b/yt_dlp/extractor/teachingchannel.py @@ -2,6 +2,7 @@ class TeachingChannelIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos?/(?P[^/?&#]+)' _TEST = { diff --git a/yt_dlp/extractor/tele5.py b/yt_dlp/extractor/tele5.py index 9260db2b44..72f67e4024 100644 --- a/yt_dlp/extractor/tele5.py +++ b/yt_dlp/extractor/tele5.py @@ -7,6 +7,7 @@ class Tele5IE(DPlayIE): # XXX: Do not subclass from concrete IE + _WORKING = False _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P[^/?#&]+)' _GEO_COUNTRIES = ['DE'] _TESTS = [{ diff --git a/yt_dlp/extractor/telemb.py b/yt_dlp/extractor/telemb.py index 3d29dace30..a71b14c27c 100644 --- a/yt_dlp/extractor/telemb.py +++ b/yt_dlp/extractor/telemb.py @@ -5,6 +5,7 @@ class TeleMBIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P.+?)_d_(?P\d+)\.html' _TESTS = [ { diff --git a/yt_dlp/extractor/telemundo.py b/yt_dlp/extractor/telemundo.py index 54e74a6c02..84b24dead8 100644 --- a/yt_dlp/extractor/telemundo.py +++ b/yt_dlp/extractor/telemundo.py @@ -4,7 +4,7 @@ class TelemundoIE(InfoExtractor): - + _WORKING = False _VALID_URL = r'https?:\/\/(?:www\.)?telemundo\.com\/.+?video\/[^\/]+(?Ptmvo\d{7})' _TESTS = [{ 'url': 'https://www.telemundo.com/noticias/noticias-telemundo-en-la-noche/empleo/video/esta-aplicacion-gratuita-esta-ayudando-los-latinos-encontrar-trabajo-en-estados-unidos-tmvo9829325', diff --git a/yt_dlp/extractor/teletask.py b/yt_dlp/extractor/teletask.py index a73dd68fba..fd831f580a 100644 --- a/yt_dlp/extractor/teletask.py +++ b/yt_dlp/extractor/teletask.py @@ -5,6 +5,7 @@ class TeleTaskIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P[0-9]+)' _TEST = { 'url': 'http://www.tele-task.de/archive/video/html5/26168/', diff --git a/yt_dlp/extractor/tonline.py b/yt_dlp/extractor/tonline.py index 7202826636..33b9a32e4e 100644 --- a/yt_dlp/extractor/tonline.py +++ b/yt_dlp/extractor/tonline.py @@ -3,6 +3,8 @@ class TOnlineIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE IE_NAME = 't-online.de' _VALID_URL = r'https?://(?:www\.)?t-online\.de/tv/(?:[^/]+/)*id_(?P\d+)' _TEST = { diff --git a/yt_dlp/extractor/tv2.py b/yt_dlp/extractor/tv2.py index f6b452dc80..7756aa3f58 100644 --- a/yt_dlp/extractor/tv2.py +++ b/yt_dlp/extractor/tv2.py @@ -161,6 +161,7 @@ def _real_extract(self, url): class KatsomoIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P\d+)' _TESTS = [{ 'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321', @@ -279,6 +280,7 @@ def _real_extract(self, url): class MTVUutisetArticleIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P\d+)' _TESTS = [{ 'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384', diff --git a/yt_dlp/extractor/tvn24.py b/yt_dlp/extractor/tvn24.py index 9c777c17d8..5276813155 100644 --- a/yt_dlp/extractor/tvn24.py +++ b/yt_dlp/extractor/tvn24.py @@ -7,6 +7,7 @@ class TVN24IE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P[^/]+)' _TESTS = [{ 'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html', diff --git a/yt_dlp/extractor/tvnoe.py b/yt_dlp/extractor/tvnoe.py index 712fbb2754..917c46bd1d 100644 --- a/yt_dlp/extractor/tvnoe.py +++ b/yt_dlp/extractor/tvnoe.py @@ -7,6 +7,7 @@ class TVNoeIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P[0-9]+)' _TEST = { 'url': 'http://www.tvnoe.cz/video/10362', diff --git a/yt_dlp/extractor/ukcolumn.py b/yt_dlp/extractor/ukcolumn.py index aade79f20e..f914613c09 100644 --- a/yt_dlp/extractor/ukcolumn.py +++ b/yt_dlp/extractor/ukcolumn.py @@ -9,6 +9,7 @@ class UkColumnIE(InfoExtractor): + _WORKING = False IE_NAME = 'ukcolumn' _VALID_URL = r'(?i)https?://(?:www\.)?ukcolumn\.org(/index\.php)?/(?:video|ukcolumn-news)/(?P[-a-z0-9]+)' diff --git a/yt_dlp/extractor/umg.py b/yt_dlp/extractor/umg.py index 3ffcb7364a..1da4ecdf85 100644 --- a/yt_dlp/extractor/umg.py +++ b/yt_dlp/extractor/umg.py @@ -7,6 +7,7 @@ class UMGDeIE(InfoExtractor): + _WORKING = False IE_NAME = 'umg:de' IE_DESC = 'Universal Music Deutschland' _VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/]+/videos/[^/?#]+-(?P\d+)' diff --git a/yt_dlp/extractor/unity.py b/yt_dlp/extractor/unity.py index d1b0ecbf38..6d8bc05939 100644 --- a/yt_dlp/extractor/unity.py +++ b/yt_dlp/extractor/unity.py @@ -3,6 +3,7 @@ class UnityIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?unity3d\.com/learn/tutorials/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://unity3d.com/learn/tutorials/topics/animation/animate-anything-mecanim', diff --git a/yt_dlp/extractor/urort.py b/yt_dlp/extractor/urort.py index debd2ba9ec..f14d7cce6a 100644 --- a/yt_dlp/extractor/urort.py +++ b/yt_dlp/extractor/urort.py @@ -5,6 +5,7 @@ class UrortIE(InfoExtractor): + _WORKING = False IE_DESC = 'NRK P3 Urørt' _VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/#!/Band/(?P[^/]+)$' diff --git a/yt_dlp/extractor/varzesh3.py b/yt_dlp/extractor/varzesh3.py index 2c13cbdc0b..07a2d5329a 100644 --- a/yt_dlp/extractor/varzesh3.py +++ b/yt_dlp/extractor/varzesh3.py @@ -7,6 +7,7 @@ class Varzesh3IE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?video\.varzesh3\.com/(?:[^/]+/)+(?P[^/]+)/?' _TESTS = [{ 'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/', diff --git a/yt_dlp/extractor/vesti.py b/yt_dlp/extractor/vesti.py index e9731a9415..3f2dddbe90 100644 --- a/yt_dlp/extractor/vesti.py +++ b/yt_dlp/extractor/vesti.py @@ -6,6 +6,7 @@ class VestiIE(InfoExtractor): + _WORKING = False IE_DESC = 'Вести.Ru' _VALID_URL = r'https?://(?:.+?\.)?vesti\.ru/(?P.+)' diff --git a/yt_dlp/extractor/videofyme.py b/yt_dlp/extractor/videofyme.py index 7354326881..f1f88c499a 100644 --- a/yt_dlp/extractor/videofyme.py +++ b/yt_dlp/extractor/videofyme.py @@ -6,6 +6,7 @@ class VideofyMeIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P\d+)(&|#|$)' IE_NAME = 'videofy.me' diff --git a/yt_dlp/extractor/viqeo.py b/yt_dlp/extractor/viqeo.py index 79b9f299a8..f0a7b5e443 100644 --- a/yt_dlp/extractor/viqeo.py +++ b/yt_dlp/extractor/viqeo.py @@ -7,6 +7,7 @@ class ViqeoIE(InfoExtractor): + _WORKING = False _VALID_URL = r'''(?x) (?: viqeo:| diff --git a/yt_dlp/extractor/voicy.py b/yt_dlp/extractor/voicy.py index 7438b49565..9ab97688a2 100644 --- a/yt_dlp/extractor/voicy.py +++ b/yt_dlp/extractor/voicy.py @@ -62,6 +62,7 @@ def _call_api(self, url, video_id, **kwargs): class VoicyIE(VoicyBaseIE): + _WORKING = False IE_NAME = 'voicy' _VALID_URL = r'https?://voicy\.jp/channel/(?P\d+)/(?P\d+)' ARTICLE_LIST_API_URL = 'https://vmw.api.voicy.jp/articles_list?channel_id=%s&pid=%s' @@ -88,6 +89,7 @@ def _real_extract(self, url): class VoicyChannelIE(VoicyBaseIE): + _WORKING = False IE_NAME = 'voicy:channel' _VALID_URL = r'https?://voicy\.jp/channel/(?P\d+)' PROGRAM_LIST_API_URL = 'https://vmw.api.voicy.jp/program_list/all?channel_id=%s&limit=20&public_type=3%s' diff --git a/yt_dlp/extractor/vtm.py b/yt_dlp/extractor/vtm.py index 6381fd311f..6db49c5b61 100644 --- a/yt_dlp/extractor/vtm.py +++ b/yt_dlp/extractor/vtm.py @@ -7,6 +7,7 @@ class VTMIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?vtm\.be/([^/?&#]+)~v(?P[0-9a-f]{8}(?:-[0-9a-f]{4}){3}-[0-9a-f]{12})' _TEST = { 'url': 'https://vtm.be/gast-vernielt-genkse-hotelkamer~ve7534523-279f-4b4d-a5c9-a33ffdbe23e1', diff --git a/yt_dlp/extractor/weiqitv.py b/yt_dlp/extractor/weiqitv.py index c9ff641542..89e4856ca1 100644 --- a/yt_dlp/extractor/weiqitv.py +++ b/yt_dlp/extractor/weiqitv.py @@ -2,6 +2,7 @@ class WeiqiTVIE(InfoExtractor): + _WORKING = False IE_DESC = 'WQTV' _VALID_URL = r'https?://(?:www\.)?weiqitv\.com/index/video_play\?videoId=(?P[A-Za-z0-9]+)' diff --git a/yt_dlp/extractor/xinpianchang.py b/yt_dlp/extractor/xinpianchang.py index 9b878de855..bd67e8b292 100644 --- a/yt_dlp/extractor/xinpianchang.py +++ b/yt_dlp/extractor/xinpianchang.py @@ -9,6 +9,7 @@ class XinpianchangIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://www\.xinpianchang\.com/(?P[^/]+?)(?:\D|$)' IE_NAME = 'xinpianchang' IE_DESC = 'xinpianchang.com' diff --git a/yt_dlp/extractor/xminus.py b/yt_dlp/extractor/xminus.py index 5f113810fd..37e31045c0 100644 --- a/yt_dlp/extractor/xminus.py +++ b/yt_dlp/extractor/xminus.py @@ -12,6 +12,7 @@ class XMinusIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P[0-9]+)' _TEST = { 'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html', diff --git a/yt_dlp/extractor/yapfiles.py b/yt_dlp/extractor/yapfiles.py index 19812bae00..d6024d912c 100644 --- a/yt_dlp/extractor/yapfiles.py +++ b/yt_dlp/extractor/yapfiles.py @@ -8,6 +8,7 @@ class YapFilesIE(InfoExtractor): + _WORKING = False _YAPFILES_URL = r'//(?:(?:www|api)\.)?yapfiles\.ru/get_player/*\?.*?\bv=(?P\w+)' _VALID_URL = r'https?:%s' % _YAPFILES_URL _EMBED_REGEX = [rf']+\bsrc=(["\'])(?P(?:https?:)?{_YAPFILES_URL}.*?)\1'] diff --git a/yt_dlp/extractor/yappy.py b/yt_dlp/extractor/yappy.py index 7b3d0cb81f..5ce647eeea 100644 --- a/yt_dlp/extractor/yappy.py +++ b/yt_dlp/extractor/yappy.py @@ -9,6 +9,7 @@ class YappyIE(InfoExtractor): + _WORKING = False _VALID_URL = r'https?://yappy\.media/video/(?P\w+)' _TESTS = [{ 'url': 'https://yappy.media/video/47fea6d8586f48d1a0cf96a7342aabd2', diff --git a/yt_dlp/extractor/zeenews.py b/yt_dlp/extractor/zeenews.py index 1616dbfbf7..e2cb1e7d68 100644 --- a/yt_dlp/extractor/zeenews.py +++ b/yt_dlp/extractor/zeenews.py @@ -3,6 +3,8 @@ class ZeeNewsIE(InfoExtractor): + _WORKING = False + _ENABLED = None # XXX: pass through to GenericIE _VALID_URL = r'https?://zeenews\.india\.com/[^#?]+/video/(?P[^#/?]+)/(?P\d+)' _TESTS = [ {