yt_dlp/extractor/youporn.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     extract_attributes,
   6     int_or_none,
   7     merge_dicts,
   8     str_to_int,
   9     unified_strdate,
  10     url_or_none,
  11 )
  12
  13
  14 class YouPornIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
  16     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)']
  17     _TESTS = [{
  18         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  19         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
  20         'info_dict': {
  21             'id': '505835',
  22             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
  23             'ext': 'mp4',
  24             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  25             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  26             'thumbnail': r're:^https?://.*\.jpg$',
  27             'duration': 210,
  28             'uploader': 'Ask Dan And Jennifer',
  29             'upload_date': '20101217',
  30             'average_rating': int,
  31             'view_count': int,
  32             'categories': list,
  33             'tags': list,
  34             'age_limit': 18,
  35         },
  36         'skip': 'This video has been disabled',
  37     }, {
  38         # Unknown uploader
  39         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  40         'info_dict': {
  41             'id': '561726',
  42             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  43             'ext': 'mp4',
  44             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  45             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  46             'thumbnail': r're:^https?://.*\.jpg$',
  47             'uploader': 'Unknown',
  48             'upload_date': '20110418',
  49             'average_rating': int,
  50             'view_count': int,
  51             'categories': list,
  52             'tags': list,
  53             'age_limit': 18,
  54         },
  55         'params': {
  56             'skip_download': True,
  57         },
  58         'skip': '404',
  59     }, {
  60         'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  61         'only_matching': True,
  62     }, {
  63         'url': 'http://www.youporn.com/watch/505835',
  64         'only_matching': True,
  65     }, {
  66         'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
  67         'only_matching': True,
  68     }, {
  69         'url': 'https://www.youporn.com/watch/16290308/tinderspecial-trailer1/',
  70         'info_dict': {
  71             'id': '16290308',
  72             'age_limit': 18,
  73             'categories': [],
  74             'description': 'md5:00ea70f642f431c379763c17c2f396bc',
  75             'display_id': 'tinderspecial-trailer1',
  76             'duration': 298.0,
  77             'ext': 'mp4',
  78             'upload_date': '20201123',
  79             'uploader': 'Ersties',
  80             'tags': [],
  81             'thumbnail': 'https://fi1.ypncdn.com/202011/23/16290308/original/8/tinderspecial-trailer1-8(m=eaAaaEPbaaaa).jpg',
  82             'timestamp': 1606089600,
  83             'title': 'Tinder In Real Life',
  84             'view_count': int,
  85         }
  86     }]
  87
  88     def _real_extract(self, url):
  89         mobj = self._match_valid_url(url)
  90         video_id = mobj.group('id')
  91         display_id = mobj.group('display_id') or video_id
  92
  93         definitions = self._download_json(
  94             'https://www.youporn.com/api/video/media_definitions/%s/' % video_id,
  95             display_id)
  96
  97         formats = []
  98         for definition in definitions:
  99             if not isinstance(definition, dict):
 100                 continue
 101             video_url = url_or_none(definition.get('videoUrl'))
 102             if not video_url:
 103                 continue
 104             f = {
 105                 'url': video_url,
 106                 'filesize': int_or_none(definition.get('videoSize')),
 107             }
 108             height = int_or_none(definition.get('quality'))
 109             # Video URL's path looks like this:
 110             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 111             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 112             #  /videos/201703/11/109285532/1080P_4000K_109285532.mp4
 113             # We will benefit from it by extracting some metadata
 114             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
 115             if mobj:
 116                 if not height:
 117                     height = int(mobj.group('height'))
 118                 bitrate = int(mobj.group('bitrate'))
 119                 f.update({
 120                     'format_id': '%dp-%dk' % (height, bitrate),
 121                     'tbr': bitrate,
 122                 })
 123             f['height'] = height
 124             formats.append(f)
 125
 126         webpage = self._download_webpage(
 127             'http://www.youporn.com/watch/%s' % video_id, display_id,
 128             headers={'Cookie': 'age_verified=1'})
 129
 130         title = self._html_search_regex(
 131             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
 132             webpage, 'title', default=None) or self._og_search_title(
 133             webpage, default=None) or self._html_search_meta(
 134             'title', webpage, fatal=True)
 135
 136         description = self._html_search_regex(
 137             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
 138             webpage, 'description',
 139             default=None) or self._og_search_description(
 140             webpage, default=None)
 141         thumbnail = self._search_regex(
 142             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 143             webpage, 'thumbnail', fatal=False, group='thumbnail')
 144         duration = int_or_none(self._html_search_meta(
 145             'video:duration', webpage, 'duration', fatal=False))
 146
 147         uploader = self._html_search_regex(
 148             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 149             webpage, 'uploader', fatal=False)
 150         upload_date = unified_strdate(self._html_search_regex(
 151             (r'UPLOADED:\s*<span>([^<]+)',
 152              r'Date\s+[Aa]dded:\s*<span>([^<]+)',
 153              r'''(?s)<div[^>]+class=["']videoInfo(?:Date|Time)\b[^>]*>(.+?)</div>''',
 154              r'(?s)<label\b[^>]*>Uploaded[^<]*</label>\s*<span\b[^>]*>(.+?)</span>'),
 155             webpage, 'upload date', fatal=False))
 156
 157         age_limit = self._rta_search(webpage)
 158
 159         view_count = None
 160         views = self._search_regex(
 161             r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
 162             'views', default=None)
 163         if views:
 164             view_count = str_to_int(extract_attributes(views).get('data-value'))
 165         comment_count = str_to_int(self._search_regex(
 166             r'>All [Cc]omments? \(([\d,.]+)\)',
 167             webpage, 'comment count', default=None))
 168
 169         def extract_tag_box(regex, title):
 170             tag_box = self._search_regex(regex, webpage, title, default=None)
 171             if not tag_box:
 172                 return []
 173             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 174
 175         categories = extract_tag_box(
 176             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 177         tags = extract_tag_box(
 178             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 179             'tags')
 180
 181         data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False)
 182         return merge_dicts(data, {
 183             'id': video_id,
 184             'display_id': display_id,
 185             'title': title,
 186             'description': description,
 187             'thumbnail': thumbnail,
 188             'duration': duration,
 189             'uploader': uploader,
 190             'upload_date': upload_date,
 191             'view_count': view_count,
 192             'comment_count': comment_count,
 193             'categories': categories,
 194             'tags': tags,
 195             'age_limit': age_limit,
 196             'formats': formats,
 197         })