from .common import InfoExtractor
from ..utils import (
- unified_strdate,
- str_to_int,
+ float_or_none,
int_or_none,
- parse_duration,
+ str_to_int,
+ unified_strdate,
)
webpage = self._download_webpage(mrss_url, video_id)
title = self._html_search_regex(
- [r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>',
- r'<h1[^>]*>([^<]+)</h1>',
- r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title')
+ [r'<h1[^>]*>([^<]+)</h1>',
+ r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+ r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+ webpage, 'title')
# Only a few videos have an description
mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
webpage, 'upload date', fatal=False))
uploader = self._html_search_regex(
- r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
+ r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
webpage, 'uploader', default='anonymous')
thumbnail = self._search_regex(
r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
webpage, 'thumbnail', fatal=False, group='thumbnail')
- duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
- webpage, 'duration', fatal=False))
+ duration = float_or_none(self._search_regex(
+ r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
+ webpage, 'duration', fatal=False, group='duration'))
- view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
- if view_count:
- view_count = str_to_int(view_count)
+ view_count = int_or_none(self._search_regex(
+ r'content=["\']User(?:View|Play)s:(\d+)',
+ webpage, 'view count', fatal=False))
mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
(like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)