0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-22 06:00:00 +00:00

[ie/mixch:archive] Fix extractor (#8761)

Closes #2373
Authored by: pzhlkj6612
This commit is contained in:
Mozi 2024-04-01 22:41:09 +00:00 committed by GitHub
parent 0284f1fee2
commit c59de48e2b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -1,5 +1,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import UserNotLive, traverse_obj from ..networking.exceptions import HTTPError
from ..utils import ExtractorError, UserNotLive, url_or_none
from ..utils.traversal import traverse_obj
class MixchIE(InfoExtractor): class MixchIE(InfoExtractor):
@ -60,22 +62,38 @@ class MixchArchiveIE(InfoExtractor):
'skip': 'paid video, no DRM. expires at Jan 23', 'skip': 'paid video, no DRM. expires at Jan 23',
'info_dict': { 'info_dict': {
'id': '421', 'id': '421',
'ext': 'mp4',
'title': '96NEKO SHOW TIME', 'title': '96NEKO SHOW TIME',
} }
}, {
'url': 'https://mixch.tv/archive/1213',
'skip': 'paid video, no DRM. expires at Dec 31, 2023',
'info_dict': {
'id': '1213',
'ext': 'mp4',
'title': '【特別トーク番組アーカイブス】Merm4id×燐舞曲 2nd LIVE「VERSUS」',
'release_date': '20231201',
'thumbnail': str,
}
}, {
'url': 'https://mixch.tv/archive/1214',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
html5_videos = self._parse_html5_media_entries( try:
url, webpage.replace('video-js', 'video'), video_id, 'hls') info_json = self._download_json(
if not html5_videos: f'https://mixch.tv/api-web/archive/{video_id}', video_id)['archive']
self.raise_login_required(method='cookies') except ExtractorError as e:
infodict = html5_videos[0] if isinstance(e.cause, HTTPError) and e.cause.status == 401:
infodict.update({ self.raise_login_required()
raise
return {
'id': video_id, 'id': video_id,
'title': self._html_search_regex(r'class="archive-title">(.+?)</', webpage, 'title') 'title': traverse_obj(info_json, ('title', {str})),
}) 'formats': self._extract_m3u8_formats(info_json['archiveURL'], video_id),
'thumbnail': traverse_obj(info_json, ('thumbnailURL', {url_or_none})),
return infodict }