youtube_dl/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     sanitized_Request,
   9     str_to_int,
  10     unescapeHTML,
  11     unified_strdate,
  12     url_or_none,
  13 )
  14 from ..aes import aes_decrypt_text
  15
  16
  17 class YouPornIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
  19     _TESTS = [{
  20         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  21         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
  22         'info_dict': {
  23             'id': '505835',
  24             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
  25             'ext': 'mp4',
  26             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  27             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29             'uploader': 'Ask Dan And Jennifer',
  30             'upload_date': '20101217',
  31             'average_rating': int,
  32             'view_count': int,
  33             'comment_count': int,
  34             'categories': list,
  35             'tags': list,
  36             'age_limit': 18,
  37         },
  38     }, {
  39         # Unknown uploader
  40         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  41         'info_dict': {
  42             'id': '561726',
  43             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  44             'ext': 'mp4',
  45             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  46             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  47             'thumbnail': r're:^https?://.*\.jpg$',
  48             'uploader': 'Unknown',
  49             'upload_date': '20110418',
  50             'average_rating': int,
  51             'view_count': int,
  52             'comment_count': int,
  53             'categories': list,
  54             'tags': list,
  55             'age_limit': 18,
  56         },
  57         'params': {
  58             'skip_download': True,
  59         },
  60     }]
  61
  62     def _real_extract(self, url):
  63         mobj = re.match(self._VALID_URL, url)
  64         video_id = mobj.group('id')
  65         display_id = mobj.group('display_id')
  66
  67         request = sanitized_Request(url)
  68         request.add_header('Cookie', 'age_verified=1')
  69         webpage = self._download_webpage(request, display_id)
  70
  71         title = self._html_search_regex(
  72             r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
  73             webpage, 'title', default=None) or self._og_search_title(
  74             webpage, default=None) or self._html_search_meta(
  75             'title', webpage, fatal=True)
  76
  77         links = []
  78
  79         # Main source
  80         definitions = self._parse_json(
  81             self._search_regex(
  82                 r'mediaDefinition\s*=\s*(\[.+?\]);', webpage,
  83                 'media definitions', default='[]'),
  84             video_id, fatal=False)
  85         if definitions:
  86             for definition in definitions:
  87                 if not isinstance(definition, dict):
  88                     continue
  89                 video_url = url_or_none(definition.get('videoUrl'))
  90                 if video_url:
  91                     links.append(video_url)
  92
  93         # Fallback #1, this also contains extra low quality 180p format
  94         for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
  95             links.append(link)
  96
  97         # Fallback #2 (unavailable as at 22.06.2017)
  98         sources = self._search_regex(
  99             r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
 100         if sources:
 101             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
 102                 links.append(link)
 103
 104         # Fallback #3 (unavailable as at 22.06.2017)
 105         for _, link in re.findall(
 106                 r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
 107             links.append(link)
 108
 109         # Fallback #4, encrypted links (unavailable as at 22.06.2017)
 110         for _, encrypted_link in re.findall(
 111                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
 112             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
 113
 114         formats = []
 115         for video_url in set(unescapeHTML(link) for link in links):
 116             f = {
 117                 'url': video_url,
 118             }
 119             # Video URL's path looks like this:
 120             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 121             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 122             # We will benefit from it by extracting some metadata
 123             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
 124             if mobj:
 125                 height = int(mobj.group('height'))
 126                 bitrate = int(mobj.group('bitrate'))
 127                 f.update({
 128                     'format_id': '%dp-%dk' % (height, bitrate),
 129                     'height': height,
 130                     'tbr': bitrate,
 131                 })
 132             formats.append(f)
 133         self._sort_formats(formats)
 134
 135         description = self._html_search_regex(
 136             r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
 137             webpage, 'description',
 138             default=None) or self._og_search_description(
 139             webpage, default=None)
 140         thumbnail = self._search_regex(
 141             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 142             webpage, 'thumbnail', fatal=False, group='thumbnail')
 143
 144         uploader = self._html_search_regex(
 145             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 146             webpage, 'uploader', fatal=False)
 147         upload_date = unified_strdate(self._html_search_regex(
 148             [r'Date\s+[Aa]dded:\s*<span>([^<]+)',
 149              r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
 150             webpage, 'upload date', fatal=False))
 151
 152         age_limit = self._rta_search(webpage)
 153
 154         average_rating = int_or_none(self._search_regex(
 155             r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 156             webpage, 'average rating', fatal=False))
 157
 158         view_count = str_to_int(self._search_regex(
 159             r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
 160             webpage, 'view count', fatal=False, group='count'))
 161         comment_count = str_to_int(self._search_regex(
 162             r'>All [Cc]omments? \(([\d,.]+)\)',
 163             webpage, 'comment count', fatal=False))
 164
 165         def extract_tag_box(regex, title):
 166             tag_box = self._search_regex(regex, webpage, title, default=None)
 167             if not tag_box:
 168                 return []
 169             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 170
 171         categories = extract_tag_box(
 172             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 173         tags = extract_tag_box(
 174             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 175             'tags')
 176
 177         return {
 178             'id': video_id,
 179             'display_id': display_id,
 180             'title': title,
 181             'description': description,
 182             'thumbnail': thumbnail,
 183             'uploader': uploader,
 184             'upload_date': upload_date,
 185             'average_rating': average_rating,
 186             'view_count': view_count,
 187             'comment_count': comment_count,
 188             'categories': categories,
 189             'tags': tags,
 190             'age_limit': age_limit,
 191             'formats': formats,
 192         }