_ Git - youtube-dl/blob - 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     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
  17     _TESTS = [
  18         {
  19             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  20             'info_dict': {
  21                 'id': '1509445',
  22                 'ext': 'mp4',
  23                 'title': 'FemaleAgent Shy beauty takes the bait',
  24                 'upload_date': '20121014',
  25                 'uploader': 'Ruseful2011',
  26                 'duration': 893,
  27                 'age_limit': 18,
  28             }
  29         },
  30         {
  31             'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  32             'info_dict': {
  33                 'id': '2221348',
  34                 'ext': 'mp4',
  35                 'title': 'Britney Spears  Sexy Booty',
  36                 'upload_date': '20130914',
  37                 'uploader': 'jojo747400',
  38                 'duration': 200,
  39                 'age_limit': 18,
  40             }
  41         },
  42         {
  43             'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  44             'only_matching': True,
  45         },
  46     ]
  47
  48     def _real_extract(self, url):
  49         def extract_video_url(webpage, name):
  50             return self._search_regex(
  51                 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  52                  r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  53                  r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  54                 webpage, name, group='mp4')
  55
  56         def is_hd(webpage):
  57             return '<div class=\'icon iconHD\'' in webpage
  58
  59         mobj = re.match(self._VALID_URL, url)
  60
  61         video_id = mobj.group('id')
  62         seo = mobj.group('seo')
  63         proto = mobj.group('proto')
  64         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
  65         webpage = self._download_webpage(mrss_url, video_id)
  66
  67         title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
  68
  69         # Only a few videos have an description
  70         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  71         description = mobj.group(1) if mobj else None
  72
  73         upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
  74                                               webpage, 'upload date', fatal=False)
  75         if upload_date:
  76             upload_date = unified_strdate(upload_date)
  77
  78         uploader = self._html_search_regex(
  79             r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
  80             webpage, 'uploader', default='anonymous')
  81
  82         thumbnail = self._search_regex(
  83             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
  84              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
  85              webpage, 'thumbnail', fatal=False, group='thumbnail')
  86
  87         duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
  88                                                           webpage, 'duration', fatal=False))
  89
  90         view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
  91         if view_count:
  92             view_count = str_to_int(view_count)
  93
  94         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
  95         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
  96
  97         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
  98         comment_count = mobj.group('commentcount') if mobj else 0
  99
 100         age_limit = self._rta_search(webpage)
 101
 102         hd = is_hd(webpage)
 103
 104         format_id = 'hd' if hd else 'sd'
 105
 106         video_url = extract_video_url(webpage, format_id)
 107         formats = [{
 108             'url': video_url,
 109             'format_id': 'hd' if hd else 'sd',
 110             'preference': 1,
 111         }]
 112
 113         if not hd:
 114             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 115             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 116             if is_hd(webpage):
 117                 video_url = extract_video_url(webpage, 'hd')
 118                 formats.append({
 119                     'url': video_url,
 120                     'format_id': 'hd',
 121                     'preference': 2,
 122                 })
 123
 124         self._sort_formats(formats)
 125
 126         return {
 127             'id': video_id,
 128             'title': title,
 129             'description': description,
 130             'upload_date': upload_date,
 131             'uploader': uploader,
 132             'thumbnail': thumbnail,
 133             'duration': duration,
 134             'view_count': view_count,
 135             'like_count': int_or_none(like_count),
 136             'dislike_count': int_or_none(dislike_count),
 137             'comment_count': int_or_none(comment_count),
 138             'age_limit': age_limit,
 139             'formats': formats,
 140         }
 141
 142
 143 class XHamsterEmbedIE(InfoExtractor):
 144     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 145     _TEST = {
 146         'url': 'http://xhamster.com/xembed.php?video=3328539',
 147         'info_dict': {
 148             'id': '3328539',
 149             'ext': 'mp4',
 150             'title': 'Pen Masturbation',
 151             'upload_date': '20140728',
 152             'uploader_id': 'anonymous',
 153             'duration': 5,
 154             'age_limit': 18,
 155         }
 156     }
 157
 158     @staticmethod
 159     def _extract_urls(webpage):
 160         return [url for _, url in re.findall(
 161             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 162             webpage)]
 163
 164     def _real_extract(self, url):
 165         video_id = self._match_id(url)
 166
 167         webpage = self._download_webpage(url, video_id)
 168
 169         video_url = self._search_regex(
 170             r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
 171             webpage, 'xhamster url')
 172
 173         return self.url_result(video_url, 'XHamster')