fenix/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-03-09 23:40:08 +01:00
Code Issues Projects Releases Wiki Activity

[ie/altcensored] Fix categories

Browse Source 
Authored by: bashonly
This commit is contained in:
bashonly 2024-02-25 17:29:00 -06:00
parent 48cea66716
commit ac2066dbd0
No known key found for this signature in database
GPG Key ID: 783F096F253D15B0
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
yt_dlp/extractor/altcensored.py
View File

@ -4,6 +4,7 @@ from .archiveorg import ArchiveOrgIE
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
InAdvancePagedList, InAdvancePagedList,
clean_html,
int_or_none, int_or_none,
orderedSet, orderedSet,
str_to_int, str_to_int,
@ -32,13 +33,15 @@ class AltCensoredIE(InfoExtractor):
'duration': 926.09, 'duration': 926.09,
'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg', 'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
'view_count': int, 'view_count': int,
'categories': ['News & Politics'], # FIXME 'categories': ['News & Politics'],
} }
}] }]
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) webpage = self._download_webpage(url, video_id)
category = clean_html(self._html_search_regex(
r'<a href="/category/\d+">([^<]+)</a>', webpage, 'category', default=None))
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
@ -46,9 +49,7 @@ class AltCensoredIE(InfoExtractor):
'ie_key': ArchiveOrgIE.ie_key(), 'ie_key': ArchiveOrgIE.ie_key(),
'view_count': str_to_int(self._html_search_regex( 'view_count': str_to_int(self._html_search_regex(
r'YouTube Views:(?:\s|&nbsp;)*([\d,]+)', webpage, 'view count', default=None)), r'YouTube Views:(?:\s|&nbsp;)*([\d,]+)', webpage, 'view count', default=None)),
'categories': self._html_search_regex( 'categories': [category] if category else None,
r'<a href="/category/\d+">\s*\n?\s*([^<]+)</a>',
webpage, 'category', default='').split() or None,
} }