From cb480e390d85fb3a598c1b6d5eef3438ce729fc9 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Sat, 11 Nov 2023 13:53:59 -0600 Subject: [PATCH] [ie/thisav] Remove (#8346) Authored by: bashonly --- yt_dlp/extractor/_extractors.py | 1 - yt_dlp/extractor/thisav.py | 66 --------------------------------- yt_dlp/extractor/unsupported.py | 4 ++ 3 files changed, 4 insertions(+), 67 deletions(-) delete mode 100644 yt_dlp/extractor/thisav.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index cf6744487..b4d50e52b 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -2019,7 +2019,6 @@ from .thestar import TheStarIE from .thesun import TheSunIE from .theweatherchannel import TheWeatherChannelIE from .thisamericanlife import ThisAmericanLifeIE -from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE from .thisvid import ( ThisVidIE, diff --git a/yt_dlp/extractor/thisav.py b/yt_dlp/extractor/thisav.py deleted file mode 100644 index b1cd57d1f..000000000 --- a/yt_dlp/extractor/thisav.py +++ /dev/null @@ -1,66 +0,0 @@ -from .common import InfoExtractor -from ..utils import remove_end - - -class ThisAVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P[0-9]+)/.*' - _TESTS = [{ - # jwplayer - 'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html', - 'md5': '0480f1ef3932d901f0e0e719f188f19b', - 'info_dict': { - 'id': '47734', - 'ext': 'flv', - 'title': '高樹マリア - Just fit', - 'uploader': 'dj7970', - 'uploader_id': 'dj7970' - } - }, { - # html5 media - 'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html', - 'md5': 'ba90c076bd0f80203679e5b60bf523ee', - 'info_dict': { - 'id': '242352', - 'ext': 'mp4', - 'title': 'Nerdy 18yo Big Ass Tattoos and Glasses', - 'uploader': 'cybersluts', - 'uploader_id': 'cybersluts', - }, - }] - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - title = remove_end(self._html_extract_title(webpage), ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站') - video_url = self._html_search_regex( - r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None) - if video_url: - info_dict = { - 'formats': [{ - 'url': video_url, - }], - } - else: - entries = self._parse_html5_media_entries(url, webpage, video_id) - if entries: - info_dict = entries[0] - else: - info_dict = self._extract_jwplayer_data( - webpage, video_id, require_title=False) - uploader = self._html_search_regex( - r': ([^<]+)', - webpage, 'uploader name', fatal=False) - uploader_id = self._html_search_regex( - r': (?:[^<]+)', - webpage, 'uploader id', fatal=False) - - info_dict.update({ - 'id': video_id, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'title': title, - }) - - return info_dict diff --git a/yt_dlp/extractor/unsupported.py b/yt_dlp/extractor/unsupported.py index bbcbf3acb..d610baecb 100644 --- a/yt_dlp/extractor/unsupported.py +++ b/yt_dlp/extractor/unsupported.py @@ -164,11 +164,15 @@ class KnownPiracyIE(UnsupportedInfoExtractor): r'viewsb\.com', r'filemoon\.sx', r'hentai\.animestigma\.com', + r'thisav\.com', ) _TESTS = [{ 'url': 'http://dood.to/e/5s1wmbdacezb', 'only_matching': True, + }, { + 'url': 'https://thisav.com/en/terms', + 'only_matching': True, }] def _real_extract(self, url):