youtube_dl/extractor/xhamster.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     unified_strdate,
   9     str_to_int,
  10     int_or_none,
  11     parse_duration,
  12 )
  13
  14
  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(?:\?.*)?'
  18     _TESTS = [
  19         {
  20             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  21             'info_dict': {
  22                 'id': '1509445',
  23                 'ext': 'mp4',
  24                 'title': 'FemaleAgent Shy beauty takes the bait',
  25                 'upload_date': '20121014',
  26                 'uploader_id': 'Ruseful2011',
  27                 'duration': 893,
  28                 'age_limit': 18,
  29             }
  30         },
  31         {
  32             'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  33             'info_dict': {
  34                 'id': '2221348',
  35                 'ext': 'mp4',
  36                 'title': 'Britney Spears  Sexy Booty',
  37                 'upload_date': '20130914',
  38                 'uploader_id': 'jojo747400',
  39                 'duration': 200,
  40                 'age_limit': 18,
  41             }
  42         },
  43         {
  44             'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  45             'only_matching': True,
  46         },
  47     ]
  48
  49     def _real_extract(self, url):
  50         def extract_video_url(webpage):
  51             mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
  52             if mp4 is None:
  53                 raise ExtractorError('Unable to extract media URL')
  54             else:
  55                 return mp4.group(1)
  56
  57         def is_hd(webpage):
  58             return '<div class=\'icon iconHD\'' in webpage
  59
  60         mobj = re.match(self._VALID_URL, url)
  61
  62         video_id = mobj.group('id')
  63         seo = mobj.group('seo')
  64         proto = mobj.group('proto')
  65         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
  66         webpage = self._download_webpage(mrss_url, video_id)
  67
  68         title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
  69
  70         # Only a few videos have an description
  71         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  72         description = mobj.group(1) if mobj else None
  73
  74         upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
  75                                               webpage, 'upload date', fatal=False)
  76         if upload_date:
  77             upload_date = unified_strdate(upload_date)
  78
  79         uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  80                                               webpage, 'uploader id', default='anonymous')
  81
  82         thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
  83
  84         duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
  85                                                           webpage, 'duration', fatal=False))
  86
  87         view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
  88         if view_count:
  89             view_count = str_to_int(view_count)
  90
  91         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
  92         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
  93
  94         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
  95         comment_count = mobj.group('commentcount') if mobj else 0
  96
  97         age_limit = self._rta_search(webpage)
  98
  99         hd = is_hd(webpage)
 100
 101         video_url = extract_video_url(webpage)
 102         formats = [{
 103             'url': video_url,
 104             'format_id': 'hd' if hd else 'sd',
 105             'preference': 1,
 106         }]
 107
 108         if not hd:
 109             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 110             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 111             if is_hd(webpage):
 112                 video_url = extract_video_url(webpage)
 113                 formats.append({
 114                     'url': video_url,
 115                     'format_id': 'hd',
 116                     'preference': 2,
 117                 })
 118
 119         self._sort_formats(formats)
 120
 121         return {
 122             'id': video_id,
 123             'title': title,
 124             'description': description,
 125             'upload_date': upload_date,
 126             'uploader_id': uploader_id,
 127             'thumbnail': thumbnail,
 128             'duration': duration,
 129             'view_count': view_count,
 130             'like_count': int_or_none(like_count),
 131             'dislike_count': int_or_none(dislike_count),
 132             'comment_count': int_or_none(comment_count),
 133             'age_limit': age_limit,
 134             'formats': formats,
 135         }