R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

made requested changes

Browse Source
This commit is contained in:
JChris246 2019-02-02 16:33:54 -04:00 committed by GitHub
parent 54f503a83d
commit ee3a27d036
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/pornhub.py
View File

@ -159,14 +159,6 @@ class PornHubIE(PornHubBaseIE):
return str_to_int(self._search_regex( return str_to_int(self._search_regex(
pattern, webpage, '%s count' % name, fatal=False)) pattern, webpage, '%s count' % name, fatal=False))
@staticmethod
def _get_text(class_name, page):
div = re.findall(r'<div class="' + class_name + '">\s+[^\n]+\s+([^\n]+)', page)
if div:
return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div[0])]
else:
return []
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
host = mobj.group('host') or 'pornhub.com' host = mobj.group('host') or 'pornhub.com'
@ -310,8 +302,14 @@ class PornHubIE(PornHubBaseIE):
comment_count = self._extract_count( comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
categories = self._get_text("categoriesWrapper", webpage) def _get_text(class_name, page):
tags = self._get_text("tagsWrapper", webpage) div = re.search(
r'<div class="' + class_name + '">\s+[^\n]+\s+([^\n]+)\s+[^\n]+\s+</div>', page)
if div:
return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div.group(1))]
categories = _get_text('categoriesWrapper', webpage)
tags = _get_text('tagsWrapper', webpage)
return { return {
'id': video_id, 'id': video_id,