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

pull/8/head
JChris246 6 years ago committed by Sergey M․
parent 48fb963b2f
commit d2d970d07e
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
js_to_json,
orderedSet, orderedSet,
remove_quotes, remove_quotes,
str_to_int, str_to_int,
@ -303,14 +302,17 @@ 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')
page_params = self._parse_json(self._search_regex( def _get_items(class_name):
r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', div = self._search_regex(
webpage, 'page parameters', group='data', default='{}'), r'<div class="' + class_name + '">([\S\s]+?)</div>',
video_id, transform_source=js_to_json, fatal=False) webpage, class_name, default=None)
tags = categories = None if div:
if page_params: return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)]
tags = page_params.get('tags', '').split(',') else:
categories = page_params.get('categories', '').split(',') return None
categories = _get_items('categoriesWrapper')
tags = _get_items('tagsWrapper')
return { return {
'id': video_id, 'id': video_id,

Loading…
Cancel
Save