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

improved function to grab categories and tags

Browse Source
This commit is contained in:
JChris246 2019-02-02 15:20:14 -04:00 committed by GitHub
parent eb6f5ea0b0
commit 32f6c118cb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
youtube_dl/extractor/pornhub.py
View File

@ -159,10 +159,12 @@ 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))
def _get_text(self, str): def _get_text(self, str, page):
l = [] l = []
for a in re.finditer(r'<a href=[^>]+>([^<]+)', str): div = re.search(r'<div class="categoriesWrapper">\s+[^\n]+\s+([^\n]+)', page)
l.append(a.group(1)) if div:
for a in re.finditer(r'<a href=[^>]+>([^<]+)', div.group(1)):
l.append(a.group(1))
return l return l
def _real_extract(self, url): def _real_extract(self, url):
@ -308,17 +310,8 @@ 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')
div = re.search(r'<div class="categoriesWrapper">\s+[^\n]+\s+([^\n]+)', webpage) categories = self._get_text("categoriesWrapper", webpage)
if div: tags = self._get_text("tagsWrapper", webpage)
categories = self._get_text(div.group(1))
else:
categories = None
div = re.search(r'<div class="tagsWrapper">\s+Tags:&nbsp;\s+([^\n]+)', webpage)
if div:
tags = self._get_text(div.group(1))
else:
tags = None
return { return {
'id': video_id, 'id': video_id,