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