X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..540fd68c40df72763aee5d75598675c45cfa9aba:/youtube_dl/extractor/xhamster.py?ds=sidebyside diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 4e8fbde..4527567 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -14,7 +14,7 @@ from ..utils import ( class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" - _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' + _VALID_URL = r'(?Phttps?)://(?:.+?\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' _TESTS = [ { 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', @@ -39,10 +39,14 @@ class XHamsterIE(InfoExtractor): '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'', webpage) if mp4 is None: @@ -57,7 +61,8 @@ class XHamsterIE(InfoExtractor): 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'(?P<title>.+?) - xHamster\.com', webpage, 'title') @@ -67,17 +72,17 @@ class XHamsterIE(InfoExtractor): 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']+>(?P[^<]+)', - webpage, 'uploader id', default='anonymous') + webpage, 'uploader id', default='anonymous') thumbnail = self._html_search_regex(r'', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._html_search_regex(r'Runtime: (\d+:\d+)', - webpage, 'duration', fatal=False)) + webpage, 'duration', fatal=False)) view_count = self._html_search_regex(r'Views: ([^<]+)', webpage, 'view count', fatal=False) if view_count: