yt_dlp/extractor/youporn.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     str_to_int,
   9     unescapeHTML,
  10     unified_strdate,
  11     url_or_none,
  12 )
  13 from ..aes import aes_decrypt_text
  14
  15
  16 class YouPornIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
  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$',
  28             'duration': 210,
  29             'uploader': 'Ask Dan And Jennifer',
  30             'upload_date': '20101217',
  31             'average_rating': int,
  32             'view_count': int,
  33             'categories': list,
  34             'tags': list,
  35             'age_limit': 18,
  36         },
  37     }, {
  38         # Unknown uploader
  39         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  40         'info_dict': {
  41             'id': '561726',
  42             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  43             'ext': 'mp4',
  44             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  45             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  46             'thumbnail': r're:^https?://.*\.jpg$',
  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
  70     @staticmethod
  71     def _extract_urls(webpage):
  72         return re.findall(
  73             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
  74             webpage)
  75
  76     def _real_extract(self, url):
  77         mobj = re.match(self._VALID_URL, url)
  78         video_id = mobj.group('id')
  79         display_id = mobj.group('display_id') or video_id
  80
  81         webpage = self._download_webpage(
  82             'http://www.youporn.com/watch/%s' % video_id, display_id,
  83             headers={'Cookie': 'age_verified=1'})
  84
  85         title = self._html_search_regex(
  86             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
  87             webpage, 'title', default=None) or self._og_search_title(
  88             webpage, default=None) or self._html_search_meta(
  89             'title', webpage, fatal=True)
  90
  91         links = []
  92
  93         # Main source
  94         definitions = self._parse_json(
  95             self._search_regex(
  96                 r'mediaDefinition\s*[=:]\s*(\[.+?\])\s*[;,]', webpage,
  97                 'media definitions', default='[]'),
  98             video_id, fatal=False)
  99         if definitions:
 100             for definition in definitions:
 101                 if not isinstance(definition, dict):
 102                     continue
 103                 video_url = url_or_none(definition.get('videoUrl'))
 104                 if video_url:
 105                     links.append(video_url)
 106
 107         # Fallback #1, this also contains extra low quality 180p format
 108         for _, link in re.findall(r'<a[^>]+href=(["\'])(http(?:(?!\1).)+\.mp4(?:(?!\1).)*)\1[^>]+title=["\']Download [Vv]ideo', webpage):
 109             links.append(link)
 110
 111         # Fallback #2 (unavailable as at 22.06.2017)
 112         sources = self._search_regex(
 113             r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
 114         if sources:
 115             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
 116                 links.append(link)
 117
 118         # Fallback #3 (unavailable as at 22.06.2017)
 119         for _, link in re.findall(
 120                 r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
 121             links.append(link)
 122
 123         # Fallback #4, encrypted links (unavailable as at 22.06.2017)
 124         for _, encrypted_link in re.findall(
 125                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
 126             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
 127
 128         formats = []
 129         for video_url in set(unescapeHTML(link) for link in links):
 130             f = {
 131                 'url': video_url,
 132             }
 133             # Video URL's path looks like this:
 134             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 135             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 136             #  /videos/201703/11/109285532/1080P_4000K_109285532.mp4
 137             # We will benefit from it by extracting some metadata
 138             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
 139             if mobj:
 140                 height = int(mobj.group('height'))
 141                 bitrate = int(mobj.group('bitrate'))
 142                 f.update({
 143                     'format_id': '%dp-%dk' % (height, bitrate),
 144                     'height': height,
 145                     'tbr': bitrate,
 146                 })
 147             formats.append(f)
 148         self._sort_formats(formats)
 149
 150         description = self._html_search_regex(
 151             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
 152             webpage, 'description',
 153             default=None) or self._og_search_description(
 154             webpage, default=None)
 155         thumbnail = self._search_regex(
 156             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 157             webpage, 'thumbnail', fatal=False, group='thumbnail')
 158         duration = int_or_none(self._html_search_meta(
 159             'video:duration', webpage, 'duration', fatal=False))
 160
 161         uploader = self._html_search_regex(
 162             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 163             webpage, 'uploader', fatal=False)
 164         upload_date = unified_strdate(self._html_search_regex(
 165             [r'UPLOADED:\s*<span>([^<]+)',
 166              r'Date\s+[Aa]dded:\s*<span>([^<]+)',
 167              r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
 168             webpage, 'upload date', fatal=False))
 169
 170         age_limit = self._rta_search(webpage)
 171
 172         average_rating = int_or_none(self._search_regex(
 173             r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 174             webpage, 'average rating', fatal=False))
 175
 176         view_count = str_to_int(self._search_regex(
 177             r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
 178             webpage, 'view count', fatal=False, group='count'))
 179         comment_count = str_to_int(self._search_regex(
 180             r'>All [Cc]omments? \(([\d,.]+)\)',
 181             webpage, 'comment count', default=None))
 182
 183         def extract_tag_box(regex, title):
 184             tag_box = self._search_regex(regex, webpage, title, default=None)
 185             if not tag_box:
 186                 return []
 187             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 188
 189         categories = extract_tag_box(
 190             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 191         tags = extract_tag_box(
 192             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 193             'tags')
 194
 195         return {
 196             'id': video_id,
 197             'display_id': display_id,
 198             'title': title,
 199             'description': description,
 200             'thumbnail': thumbnail,
 201             'duration': duration,
 202             'uploader': uploader,
 203             'upload_date': upload_date,
 204             'average_rating': average_rating,
 205             'view_count': view_count,
 206             'comment_count': comment_count,
 207             'categories': categories,
 208             'tags': tags,
 209             'age_limit': age_limit,
 210             'formats': formats,
 211         }