From 481d8ec6aa98eae62c82c8eff1f97e53dd99fd14 Mon Sep 17 00:00:00 2001
From: burnersauce <burnersauce@maildrop.cc>
Date: Sun, 23 Jul 2017 22:31:29 -0400
Subject: [PATCH] [pornhub] Correctly parse categories and tags (#13720)
---
youtube_dl/extractor/pornhub.py | 13 +++----------
1 file changed, 3 insertions(+), 10 deletions(-)
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index e032817f2..be0b4e902 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -197,16 +197,9 @@ class PornHubIE(InfoExtractor):
r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
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(',')
-
+ categories = re.findall(r"onclick=\"ga\('send', 'event', 'Watch Page', 'click', 'Category'\);\">([^<]+)<", webpage)
+ tags = re.findall(r'<a href="/video/search\?search=[^"]+">([^<]+)<', webpage)
+
return {
'id': video_id,
'url': video_url,