from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( ExtractorError, unified_strdate, str_to_int, int_or_none, parse_duration, ) class XHamsterIE(InfoExtractor): _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', 'info_dict': { 'id': '1509445', 'ext': 'mp4', 'title': 'FemaleAgent Shy beauty takes the bait', 'upload_date': '20121014', 'uploader_id': 'Ruseful2011', 'duration': 893, 'age_limit': 18, } }, { 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', 'info_dict': { 'id': '2221348', 'ext': 'mp4', 'title': 'Britney Spears Sexy Booty', 'upload_date': '20130914', 'uploader_id': 'jojo747400', '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 extract_video_url(webpage, name): return self._search_regex( [r'''file\s*:\s*(?P["'])(?P.+?)(?P=q)''', r'''["'])(?P.+?)(?P=q)\s+class=["']mp4Thumb''', r''']+file=(?P["'])(?P.+?)(?P=q)[^>]*>'''], webpage, name, group='mp4') def is_hd(webpage): return '
(?P.+?) - xHamster\.com', webpage, 'title') # Only a few videos have an description mobj = re.search(r'Description: ([^<]+)', webpage) 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) if upload_date: upload_date = unified_strdate(upload_date) uploader_id = self._html_search_regex(r']+>(?P[^<]+)', webpage, 'uploader id', default='anonymous') thumbnail = self._search_regex( [r'''thumb\s*:\s*(?P["'])(?P.+?)(?P=q)''', r''']+poster=(?P["'])(?P.+?)(?P=q)[^>]*>'''], webpage, 'thumbnail', fatal=False, group='thumbnail') duration = parse_duration(self._html_search_regex(r'Runtime: (\d+:\d+)
', webpage, 'duration', fatal=False)) view_count = self._html_search_regex(r'Views: ([^<]+)', webpage, 'view count', fatal=False) if view_count: view_count = str_to_int(view_count) mobj = re.search(r"hint='(?P\d+) Likes / (?P\d+) Dislikes'", webpage) (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None) mobj = re.search(r'Comments \((?P\d+)\)', webpage) comment_count = mobj.group('commentcount') if mobj else 0 age_limit = self._rta_search(webpage) hd = is_hd(webpage) format_id = 'hd' if hd else 'sd' video_url = extract_video_url(webpage, format_id) formats = [{ 'url': video_url, 'format_id': 'hd' if hd else 'sd', 'preference': 1, }] if not hd: mrss_url = self._search_regex(r'\d+)' _TEST = { 'url': 'http://xhamster.com/xembed.php?video=3328539', 'info_dict': { 'id': '3328539', 'ext': 'mp4', 'title': 'Pen Masturbation', 'upload_date': '20140728', 'uploader_id': 'anonymous', 'duration': 5, 'age_limit': 18, } } @staticmethod def _extract_urls(webpage): return [url for _, url in re.findall( r']+?src=(["\'])(?P(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1', webpage)] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = self._search_regex( r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id, webpage, 'xhamster url') return self.url_result(video_url, 'XHamster')