projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
d2d970d
)
[pornhub] Improve and simplify (closes #19135)
author
Sergey M․
<dstftw@gmail.com>
Tue, 5 Feb 2019 16:06:55 +0000
(23:06 +0700)
committer
Sergey M․
<dstftw@gmail.com>
Tue, 5 Feb 2019 16:09:24 +0000
(23:09 +0700)
youtube_dl/extractor/pornhub.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/pornhub.py
b/youtube_dl/extractor/pornhub.py
index 428324ef0b72366d4700372f826ad9c7c0fb9cb6..641083da7b4b0778a78e4f5af044202081a5af9c 100644
(file)
--- a/
youtube_dl/extractor/pornhub.py
+++ b/
youtube_dl/extractor/pornhub.py
@@
-302,17
+302,12
@@
class PornHubIE(PornHubBaseIE):
comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
- def
_get_items(class_name
):
+ def
extract_list(meta_key
):
div = self._search_regex(
div = self._search_regex(
- r'
<div class="' + class_name + '">([\S\s]+?)</div>',
-
webpage, class_name
, default=None)
+ r'
(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
+
% meta_key, webpage, meta_key
, default=None)
if div:
if div:
- return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)]
- else:
- return None
-
- categories = _get_items('categoriesWrapper')
- tags = _get_items('tagsWrapper')
+ return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
return {
'id': video_id,
return {
'id': video_id,
@@
-327,8
+322,8
@@
class PornHubIE(PornHubBaseIE):
'comment_count': comment_count,
'formats': formats,
'age_limit': 18,
'comment_count': comment_count,
'formats': formats,
'age_limit': 18,
- 'tags':
tags
,
- 'categories':
categories
,
+ 'tags':
extract_list('tags')
,
+ 'categories':
extract_list('categories')
,
'subtitles': subtitles,
}
'subtitles': subtitles,
}