From 5dda1edef93d94c9a49672f905df0c49c75c5739 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Feb 2019 23:06:55 +0700 Subject: [PATCH] [pornhub] Improve and simplify (closes #19135) --- youtube_dl/extractor/pornhub.py | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 428324ef0..641083da7 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -302,17 +302,12 @@ class PornHubIE(PornHubBaseIE): comment_count = self._extract_count( r'All Comments\s*\(([\d,.]+)\)', webpage, 'comment') - def _get_items(class_name): + def extract_list(meta_key): div = self._search_regex( - r'
([\S\s]+?)
', - webpage, class_name, default=None) + r'(?s)]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)' + % meta_key, webpage, meta_key, default=None) if div: - return [a for a in re.findall(r']+>([^<]+)', div)] - else: - return None - - categories = _get_items('categoriesWrapper') - tags = _get_items('tagsWrapper') + return re.findall(r']+\bhref=[^>]+>([^<]+)', div) return { 'id': video_id, @@ -327,8 +322,8 @@ class PornHubIE(PornHubBaseIE): 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, - 'tags': tags, - 'categories': categories, + 'tags': extract_list('tags'), + 'categories': extract_list('categories'), 'subtitles': subtitles, }