projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[youtube] Fix categories and improve tags extraction
[youtube-dl]
/
youtube_dl
/
extractor
/
drtuber.py
diff --git
a/youtube_dl/extractor/drtuber.py
b/youtube_dl/extractor/drtuber.py
index c88b3126b1676f11ee3696a2499e1f7a0a57d8b3..2baea585bf6b8882d5816052ca734b1f9dbc024c 100644
(file)
--- a/
youtube_dl/extractor/drtuber.py
+++ b/
youtube_dl/extractor/drtuber.py
@@
-4,7
+4,9
@@
import re
from .common import InfoExtractor
from ..utils import (
from .common import InfoExtractor
from ..utils import (
+ int_or_none,
NO_DEFAULT,
NO_DEFAULT,
+ parse_duration,
str_to_int,
)
str_to_int,
)
@@
-65,8
+67,13
@@
class DrTuberIE(InfoExtractor):
})
self._sort_formats(formats)
})
self._sort_formats(formats)
+ duration = int_or_none(video_data.get('duration')) or parse_duration(
+ video_data.get('duration_format'))
+
title = self._html_search_regex(
title = self._html_search_regex(
- (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
+ (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
+ r'<title>([^<]+)\s*@\s+DrTuber',
+ r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
webpage, 'title')
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
webpage, 'title')
@@
-101,4
+108,5
@@
class DrTuberIE(InfoExtractor):
'comment_count': comment_count,
'categories': categories,
'age_limit': self._rta_search(webpage),
'comment_count': comment_count,
'categories': categories,
'age_limit': self._rta_search(webpage),
+ 'duration': duration,
}
}