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'http://(?:.+?\.)?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             'md5': '8281348b8d3c53d39fffb377d24eac4e',
  22             'info_dict': {
  23                 'id': '1509445',
  24                 'ext': 'mp4',
  25                 'title': 'FemaleAgent Shy beauty takes the bait',
  26                 'upload_date': '20121014',
  27                 'uploader_id': 'Ruseful2011',
  28                 'duration': 893,
  29                 'age_limit': 18,
  30             }
  31         },
  32         {
  33             'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  34             'md5': '4cbd8d56708ecb4fb4124c23e4acb81a',
  35             'info_dict': {
  36                 'id': '2221348',
  37                 'ext': 'mp4',
  38                 'title': 'Britney Spears  Sexy Booty',
  39                 'upload_date': '20130914',
  40                 'uploader_id': 'jojo747400',
  41                 'duration': 200,
  42                 'age_limit': 18,
  43             }
  44         }
  45     ]
  46
  47     def _real_extract(self,url):
  48         def extract_video_url(webpage):
  49             mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
  50             if mp4 is None:
  51                 raise ExtractorError('Unable to extract media URL')
  52             else:
  53                 return mp4.group(1)
  54
  55         def is_hd(webpage):
  56             return '<div class=\'icon iconHD\'' in webpage
  57
  58         mobj = re.match(self._VALID_URL, url)
  59
  60         video_id = mobj.group('id')
  61         seo = mobj.group('seo')
  62         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
  63         webpage = self._download_webpage(mrss_url, video_id)
  64
  65         title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
  66
  67         # Only a few videos have an description
  68         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  69         description = mobj.group(1) if mobj else None
  70
  71         upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
  72             webpage, 'upload date', fatal=False)
  73         if upload_date:
  74             upload_date = unified_strdate(upload_date)
  75
  76         uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  77             webpage, 'uploader id', default='anonymous')
  78
  79         thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
  80
  81         duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
  82             webpage, 'duration', fatal=False))
  83
  84         view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
  85         if view_count:
  86             view_count = str_to_int(view_count)
  87
  88         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
  89         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
  90
  91         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
  92         comment_count = mobj.group('commentcount') if mobj else 0
  93
  94         age_limit = self._rta_search(webpage)
  95
  96         hd = is_hd(webpage)
  97
  98         video_url = extract_video_url(webpage)
  99         formats = [{
 100             'url': video_url,
 101             'format_id': 'hd' if hd else 'sd',
 102             'preference': 1,
 103         }]
 104
 105         if not hd:
 106             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 107             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 108             if is_hd(webpage):
 109                 video_url = extract_video_url(webpage)
 110                 formats.append({
 111                     'url': video_url,
 112                     'format_id': 'hd',
 113                     'preference': 2,
 114                 })
 115
 116         self._sort_formats(formats)
 117
 118         return {
 119             'id': video_id,
 120             'title': title,
 121             'description': description,
 122             'upload_date': upload_date,
 123             'uploader_id': uploader_id,
 124             'thumbnail': thumbnail,
 125             'duration': duration,
 126             'view_count': view_count,
 127             'like_count': int_or_none(like_count),
 128             'dislike_count': int_or_none(dislike_count),
 129             'comment_count': int_or_none(comment_count),
 130             'age_limit': age_limit,
 131             'formats': formats,
 132         }