class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
- _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+ _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
_TESTS = [
{
'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
- 'md5': '8281348b8d3c53d39fffb377d24eac4e',
'info_dict': {
'id': '1509445',
'ext': 'mp4',
},
{
'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
- 'md5': '4cbd8d56708ecb4fb4124c23e4acb81a',
'info_dict': {
'id': '2221348',
'ext': 'mp4',
'duration': 200,
'age_limit': 18,
}
- }
+ },
+ {
+ 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+ 'only_matching': True,
+ },
]
- def _real_extract(self,url):
+ def _real_extract(self, url):
def extract_video_url(webpage):
mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
if mp4 is None:
video_id = mobj.group('id')
seo = mobj.group('seo')
- mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
+ proto = mobj.group('proto')
+ mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
webpage = self._download_webpage(mrss_url, video_id)
title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
description = mobj.group(1) if mobj else None
upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
- webpage, 'upload date', fatal=False)
+ webpage, 'upload date', fatal=False)
if upload_date:
upload_date = unified_strdate(upload_date)
uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
- webpage, 'uploader id', default='anonymous')
+ webpage, 'uploader id', default='anonymous')
thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
- webpage, 'duration', fatal=False))
+ webpage, 'duration', fatal=False))
view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
if view_count: