fenix/ytdl-nightly
1
0
Fork 0
mirror of https://github.com/ytdl-org/ytdl-nightly.git synced 2024-12-23 05:23:32 +01:00
Code Issues Packages Projects Releases Wiki Activity

[pornhub] Fix tags and categories extraction (closes #13720)

Browse Source
This commit is contained in:
JChris246 2019-02-04 13:33:54 -04:00 committed by Sergey M․
parent 48fb963b2f
commit d2d970d07e
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
youtube_dl/extractor/pornhub.py
View File

@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper
from ..utils import (
ExtractorError,
int_or_none,
js_to_json,
orderedSet,
remove_quotes,
str_to_int,
@ -303,14 +302,17 @@ class PornHubIE(PornHubBaseIE):
comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
page_params = self._parse_json(self._search_regex(
r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
webpage, 'page parameters', group='data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
tags = categories = None
if page_params:
tags = page_params.get('tags', '').split(',')
categories = page_params.get('categories', '').split(',')
def _get_items(class_name):
div = self._search_regex(
r'<div class="' + class_name + '">([\S\s]+?)</div>',
webpage, class_name, default=None)
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 {
'id': video_id,