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

made requested changes

Browse Source 
changed regex for categories
fixed parsing for tags
This commit is contained in:
JChris246 2019-02-02 14:46:18 -04:00 committed by GitHub
parent 300fc5a053
commit 77020f033b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/pornhub.py
View File

@ -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,
@ -303,17 +302,15 @@ 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(
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 = None
if page_params:
tags = page_params.get('tags', '').split(',')
categories = [] categories = []
for mobj in re.finditer(r'<a href=[^>]+Category[^>]*>([^<]+)', webpage): cat_div = re.search(r'<div class="categoriesWrapper">\s+Categories:&nbsp;\s+([^\n]+)', webpage)
categories.append(mobj.group(1)) for a in re.finditer(r'<a href=[^>]+Category[^>]*>([^<]+)', cat_div.group(1)):
categories.append(a.group(1))
tags = []
tag_div = re.search(r'<div class="tagsWrapper">\s+Tags:&nbsp;\s+([^\n]+)', webpage)
for a in re.finditer(r'<a href=[^>]+>([^<]+)', tag_div.group(1)):
tags.append(a.group(1))
return { return {
'id': video_id, 'id': video_id,