_ 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     clean_html,
   8     dict_get,
   9     ExtractorError,
  10     int_or_none,
  11     parse_duration,
  12     unified_strdate,
  13 )
  14
  15
  16 class XHamsterIE(InfoExtractor):
  17     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
  18     _TESTS = [{
  19         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  20         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  21         'info_dict': {
  22             'id': '1509445',
  23             'ext': 'mp4',
  24             'title': 'FemaleAgent Shy beauty takes the bait',
  25             'upload_date': '20121014',
  26             'uploader': 'Ruseful2011',
  27             'duration': 893,
  28             'age_limit': 18,
  29             'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
  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': 'jojo747400',
  39             'duration': 200,
  40             'age_limit': 18,
  41             'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
  42         },
  43         'params': {
  44             'skip_download': True,
  45         },
  46     }, {
  47         # empty seo
  48         'url': 'http://xhamster.com/movies/5667973/.html',
  49         'info_dict': {
  50             'id': '5667973',
  51             'ext': 'mp4',
  52             'title': '....',
  53             'upload_date': '20160208',
  54             'uploader': 'parejafree',
  55             'duration': 72,
  56             'age_limit': 18,
  57             'categories': ['Amateur', 'Blowjobs'],
  58         },
  59         'params': {
  60             'skip_download': True,
  61         },
  62     }, {
  63         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  64         'only_matching': True,
  65     }, {
  66         # This video is visible for marcoalfa123456's friends only
  67         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  68         'only_matching': True,
  69     }]
  70
  71     def _real_extract(self, url):
  72         def extract_video_url(webpage, name):
  73             return self._search_regex(
  74                 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  75                  r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  76                  r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  77                 webpage, name, group='mp4')
  78
  79         def is_hd(webpage):
  80             return '<div class=\'icon iconHD\'' in webpage
  81
  82         mobj = re.match(self._VALID_URL, url)
  83
  84         video_id = mobj.group('id')
  85         seo = mobj.group('seo')
  86         proto = mobj.group('proto')
  87         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
  88         webpage = self._download_webpage(mrss_url, video_id)
  89
  90         error = self._html_search_regex(
  91             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
  92             webpage, 'error', default=None)
  93         if error:
  94             raise ExtractorError(error, expected=True)
  95
  96         title = self._html_search_regex(
  97             [r'<h1[^>]*>([^<]+)</h1>',
  98              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
  99              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 100             webpage, 'title')
 101
 102         # Only a few videos have an description
 103         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 104         description = mobj.group(1) if mobj else None
 105
 106         upload_date = unified_strdate(self._search_regex(
 107             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 108             webpage, 'upload date', fatal=False))
 109
 110         uploader = self._html_search_regex(
 111             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
 112             webpage, 'uploader', default='anonymous')
 113
 114         thumbnail = self._search_regex(
 115             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 116              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 117             webpage, 'thumbnail', fatal=False, group='thumbnail')
 118
 119         duration = parse_duration(self._search_regex(
 120             r'Runtime:\s*</span>\s*([\d:]+)', webpage,
 121             'duration', fatal=False))
 122
 123         view_count = int_or_none(self._search_regex(
 124             r'content=["\']User(?:View|Play)s:(\d+)',
 125             webpage, 'view count', fatal=False))
 126
 127         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
 128         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 129
 130         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 131         comment_count = mobj.group('commentcount') if mobj else 0
 132
 133         age_limit = self._rta_search(webpage)
 134
 135         hd = is_hd(webpage)
 136
 137         format_id = 'hd' if hd else 'sd'
 138
 139         video_url = extract_video_url(webpage, format_id)
 140         formats = [{
 141             'url': video_url,
 142             'format_id': 'hd' if hd else 'sd',
 143             'preference': 1,
 144         }]
 145
 146         if not hd:
 147             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 148             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 149             if is_hd(webpage):
 150                 video_url = extract_video_url(webpage, 'hd')
 151                 formats.append({
 152                     'url': video_url,
 153                     'format_id': 'hd',
 154                     'preference': 2,
 155                 })
 156
 157         self._sort_formats(formats)
 158
 159         categories_html = self._search_regex(
 160             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 161             'categories', default=None)
 162         categories = [clean_html(category) for category in re.findall(
 163             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 164
 165         return {
 166             'id': video_id,
 167             'title': title,
 168             'description': description,
 169             'upload_date': upload_date,
 170             'uploader': uploader,
 171             'thumbnail': thumbnail,
 172             'duration': duration,
 173             'view_count': view_count,
 174             'like_count': int_or_none(like_count),
 175             'dislike_count': int_or_none(dislike_count),
 176             'comment_count': int_or_none(comment_count),
 177             'age_limit': age_limit,
 178             'categories': categories,
 179             'formats': formats,
 180         }
 181
 182
 183 class XHamsterEmbedIE(InfoExtractor):
 184     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 185     _TEST = {
 186         'url': 'http://xhamster.com/xembed.php?video=3328539',
 187         'info_dict': {
 188             'id': '3328539',
 189             'ext': 'mp4',
 190             'title': 'Pen Masturbation',
 191             'upload_date': '20140728',
 192             'uploader_id': 'anonymous',
 193             'duration': 5,
 194             'age_limit': 18,
 195         }
 196     }
 197
 198     @staticmethod
 199     def _extract_urls(webpage):
 200         return [url for _, url in re.findall(
 201             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 202             webpage)]
 203
 204     def _real_extract(self, url):
 205         video_id = self._match_id(url)
 206
 207         webpage = self._download_webpage(url, video_id)
 208
 209         video_url = self._search_regex(
 210             r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
 211             webpage, 'xhamster url', default=None)
 212
 213         if not video_url:
 214             vars = self._parse_json(
 215                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 216                 video_id)
 217             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 218
 219         return self.url_result(video_url, 'XHamster')