w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[youtube] Fix categories and improve tags extraction

Browse source
This commit is contained in:
Sergey M․ 2020-06-16 03:13:39 +07:00
parent ed604ce7bc
commit dbeafce5d5
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
youtube_dl/extractor/youtube.py
View file

@ -2356,17 +2356,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
m_cat_container = self._search_regex( m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
video_webpage, 'categories', default=None) video_webpage, 'categories', default=None)
category = None
if m_cat_container: if m_cat_container:
category = self._html_search_regex( category = self._html_search_regex(
r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
default=None) default=None)
if not category:
category = try_get(
microformat, lambda x: x['category'], compat_str)
video_categories = None if category is None else [category] video_categories = None if category is None else [category]
else:
video_categories = None
video_tags = [ video_tags = [
unescapeHTML(m.group('content')) unescapeHTML(m.group('content'))
for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
if not video_tags:
video_tags = try_get(video_details, lambda x: x['keywords'], list)
def _extract_count(count_name): def _extract_count(count_name):
return str_to_int(self._search_regex( return str_to_int(self._search_regex(