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     traverse_obj,
  10     unified_strdate,
  11     url_or_none,
  12 )
  13
  14
  15 class YouPornIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
  17     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)']
  18     _TESTS = [{
  19         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  20         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
  21         'info_dict': {
  22             'id': '505835',
  23             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
  24             'ext': 'mp4',
  25             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  26             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'duration': 210,
  29             'uploader': 'Ask Dan And Jennifer',
  30             'upload_date': '20101217',
  31             'average_rating': int,
  32             'view_count': int,
  33             'categories': list,
  34             'tags': list,
  35             'age_limit': 18,
  36         },
  37         'skip': 'This video has been disabled',
  38     }, {
  39         # Unknown uploader
  40         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  41         'info_dict': {
  42             'id': '561726',
  43             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  44             'ext': 'mp4',
  45             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  46             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  47             'thumbnail': r're:^https?://.*\.jpg$',
  48             'uploader': 'Unknown',
  49             'upload_date': '20110418',
  50             'average_rating': int,
  51             'view_count': int,
  52             'categories': list,
  53             'tags': list,
  54             'age_limit': 18,
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59         'skip': '404',
  60     }, {
  61         'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  62         'only_matching': True,
  63     }, {
  64         'url': 'http://www.youporn.com/watch/505835',
  65         'only_matching': True,
  66     }, {
  67         'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
  68         'only_matching': True,
  69     }, {
  70         'url': 'https://www.youporn.com/watch/16290308/tinderspecial-trailer1/',
  71         'info_dict': {
  72             'id': '16290308',
  73             'age_limit': 18,
  74             'categories': [],
  75             'description': str,  # TODO: detect/remove SEO spam description in ytdl backport
  76             'display_id': 'tinderspecial-trailer1',
  77             'duration': 298.0,
  78             'ext': 'mp4',
  79             'upload_date': '20201123',
  80             'uploader': 'Ersties',
  81             'tags': [],
  82             'thumbnail': r're:https://.+\.jpg',
  83             'timestamp': 1606147564,
  84             'title': 'Tinder In Real Life',
  85             'view_count': int,
  86         }
  87     }]
  88
  89     def _real_extract(self, url):
  90         video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
  91         self._set_cookie('.youporn.com', 'age_verified', '1')
  92         webpage = self._download_webpage(f'https://www.youporn.com/watch/{video_id}', video_id)
  93         definitions = self._search_json(r'\bplayervars\s*:', webpage, 'player vars', video_id)['mediaDefinitions']
  94
  95         def get_format_data(data, stream_type):
  96             info_url = traverse_obj(data, (lambda _, v: v['format'] == stream_type, 'videoUrl', {url_or_none}, any))
  97             if not info_url:
  98                 return []
  99             return traverse_obj(
 100                 self._download_json(info_url, video_id, f'Downloading {stream_type} info JSON', fatal=False),
 101                 lambda _, v: v['format'] == stream_type and url_or_none(v['videoUrl']))
 102
 103         formats = []
 104         # Try to extract only the actual master m3u8 first, avoiding the duplicate single resolution "master" m3u8s
 105         for hls_url in traverse_obj(get_format_data(definitions, 'hls'), (
 106                 lambda _, v: not isinstance(v['defaultQuality'], bool), 'videoUrl'), (..., 'videoUrl')):
 107             formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls'))
 108
 109         for definition in get_format_data(definitions, 'mp4'):
 110             f = traverse_obj(definition, {
 111                 'url': 'videoUrl',
 112                 'filesize': ('videoSize', {int_or_none})
 113             })
 114             height = int_or_none(definition.get('quality'))
 115             # Video URL's path looks like this:
 116             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 117             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 118             #  /videos/201703/11/109285532/1080P_4000K_109285532.mp4
 119             # We will benefit from it by extracting some metadata
 120             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', definition['videoUrl'])
 121             if mobj:
 122                 if not height:
 123                     height = int(mobj.group('height'))
 124                 bitrate = int(mobj.group('bitrate'))
 125                 f.update({
 126                     'format_id': '%dp-%dk' % (height, bitrate),
 127                     'tbr': bitrate,
 128                 })
 129             f['height'] = height
 130             formats.append(f)
 131
 132         title = self._html_search_regex(
 133             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
 134             webpage, 'title', default=None) or self._og_search_title(
 135             webpage, default=None) or self._html_search_meta(
 136             'title', webpage, fatal=True)
 137
 138         description = self._html_search_regex(
 139             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
 140             webpage, 'description',
 141             default=None) or self._og_search_description(
 142             webpage, default=None)
 143         thumbnail = self._search_regex(
 144             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 145             webpage, 'thumbnail', fatal=False, group='thumbnail')
 146         duration = int_or_none(self._html_search_meta(
 147             'video:duration', webpage, 'duration', fatal=False))
 148
 149         uploader = self._html_search_regex(
 150             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 151             webpage, 'uploader', fatal=False)
 152         upload_date = unified_strdate(self._html_search_regex(
 153             (r'UPLOADED:\s*<span>([^<]+)',
 154              r'Date\s+[Aa]dded:\s*<span>([^<]+)',
 155              r'''(?s)<div[^>]+class=["']videoInfo(?:Date|Time)\b[^>]*>(.+?)</div>''',
 156              r'(?s)<label\b[^>]*>Uploaded[^<]*</label>\s*<span\b[^>]*>(.+?)</span>'),
 157             webpage, 'upload date', fatal=False))
 158
 159         age_limit = self._rta_search(webpage)
 160
 161         view_count = None
 162         views = self._search_regex(
 163             r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
 164             'views', default=None)
 165         if views:
 166             view_count = str_to_int(extract_attributes(views).get('data-value'))
 167         comment_count = str_to_int(self._search_regex(
 168             r'>All [Cc]omments? \(([\d,.]+)\)',
 169             webpage, 'comment count', default=None))
 170
 171         def extract_tag_box(regex, title):
 172             tag_box = self._search_regex(regex, webpage, title, default=None)
 173             if not tag_box:
 174                 return []
 175             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 176
 177         categories = extract_tag_box(
 178             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 179         tags = extract_tag_box(
 180             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 181             'tags')
 182
 183         data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False)
 184         data.pop('url', None)
 185         return merge_dicts(data, {
 186             'id': video_id,
 187             'display_id': display_id,
 188             'title': title,
 189             'description': description,
 190             'thumbnail': thumbnail,
 191             'duration': duration,
 192             'uploader': uploader,
 193             'upload_date': upload_date,
 194             'view_count': view_count,
 195             'comment_count': comment_count,
 196             'categories': categories,
 197             'tags': tags,
 198             'age_limit': age_limit,
 199             'formats': formats,
 200         })