1 from __future__ import unicode_literals
5 from .common import InfoExtractor
15 class XHamsterIE(InfoExtractor):
16 """Information Extractor for xHamster"""
17 _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
20 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
24 'title': 'FemaleAgent Shy beauty takes the bait',
25 'upload_date': '20121014',
26 'uploader_id': 'Ruseful2011',
32 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
36 'title': 'Britney Spears Sexy Booty',
37 'upload_date': '20130914',
38 'uploader_id': 'jojo747400',
44 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
48 'title': 'Amber slayed by the Knight',
49 'upload_date': '20131009',
50 'uploader_id': 'amberblank',
56 "url": "https://xhamster.com/movies/1444747/hotkinkyjo_amp_asian_girl_elbow_deep_anal_fisting_and_footing.html",
60 "title": "HOTKINKYJO & ASIAN GIRL ELBOW DEEP ANAL FISTING AND FOOTING",
61 "upload_date": "20120922",
62 "uploader_id": "alex1981",
69 def _real_extract(self, url):
70 def extract_video_url(webpage):
71 mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
73 raise ExtractorError('Unable to extract media URL')
78 return '<div class=\'icon iconHD\'' in webpage
80 mobj = re.match(self._VALID_URL, url)
82 video_id = mobj.group('id')
83 seo = mobj.group('seo')
84 proto = mobj.group('proto')
85 mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
86 webpage = self._download_webpage(mrss_url, video_id)
88 title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
90 # Only a few videos have an description
91 mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
92 description = mobj.group(1) if mobj else None
94 upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
95 webpage, 'upload date', fatal=False)
97 upload_date = unified_strdate(upload_date)
99 uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
100 webpage, 'uploader id', default='anonymous')
102 thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
104 duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
105 webpage, 'duration', fatal=False))
107 view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
109 view_count = str_to_int(view_count)
111 mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
112 (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
114 mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
115 comment_count = mobj.group('commentcount') if mobj else 0
117 age_limit = self._rta_search(webpage)
121 video_url = extract_video_url(webpage)
124 'format_id': 'hd' if hd else 'sd',
129 mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
130 webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
132 video_url = extract_video_url(webpage)
139 self._sort_formats(formats)
144 'description': description,
145 'upload_date': upload_date,
146 'uploader_id': uploader_id,
147 'thumbnail': thumbnail,
148 'duration': duration,
149 'view_count': view_count,
150 'like_count': int_or_none(like_count),
151 'dislike_count': int_or_none(dislike_count),
152 'comment_count': int_or_none(comment_count),
153 'age_limit': age_limit,