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