diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 17:37:42 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 17:37:42 +0000 |
commit | c7bab7c39fd51c0812f70020172766303191bc01 (patch) | |
tree | 56c05fbdd4fc47409d48ba318a4b621a7b0d299a /yt_dlp/extractor/thesun.py | |
parent | Initial commit. (diff) | |
download | yt-dlp-c7bab7c39fd51c0812f70020172766303191bc01.tar.xz yt-dlp-c7bab7c39fd51c0812f70020172766303191bc01.zip |
Adding upstream version 2023.03.04.upstream/2023.03.04upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/thesun.py')
-rw-r--r-- | yt_dlp/extractor/thesun.py | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/yt_dlp/extractor/thesun.py b/yt_dlp/extractor/thesun.py new file mode 100644 index 0000000..ba58482 --- /dev/null +++ b/yt_dlp/extractor/thesun.py @@ -0,0 +1,36 @@ +import re + +from .common import InfoExtractor +from ..utils import extract_attributes + + +class TheSunIE(InfoExtractor): + _VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/[^/]+/(?P<id>\d+)' + _TEST = { + 'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/', + 'info_dict': { + 'id': '2261604', + 'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf', + }, + 'playlist_count': 2, + } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' + + def _real_extract(self, url): + article_id = self._match_id(url) + + webpage = self._download_webpage(url, article_id) + + entries = [] + for video in re.findall( + r'<video[^>]+data-video-id-pending=[^>]+>', + webpage): + attrs = extract_attributes(video) + video_id = attrs['data-video-id-pending'] + account_id = attrs.get('data-account', '5067014667001') + entries.append(self.url_result( + self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), + 'BrightcoveNew', video_id)) + + return self.playlist_result( + entries, article_id, self._og_search_title(webpage, fatal=False)) |