_ Git - youtube-dl/blob - youtube_dl/extractor/youporn.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_request
   7 from ..utils import (
   8     int_or_none,
   9     str_to_int,
  10     unescapeHTML,
  11     unified_strdate,
  12 )
  13 from ..aes import aes_decrypt_text
  14
  15
  16 class YouPornIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?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': '71ec5fcfddacf80f495efa8b6a8d9a89',
  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': 're:^https?://.*\.jpg$',
  28             'uploader': 'Ask Dan And Jennifer',
  29             'upload_date': '20101221',
  30             'average_rating': int,
  31             'view_count': int,
  32             'categories': list,
  33             'tags': list,
  34             'age_limit': 18,
  35         },
  36     }, {
  37         # Anonymous User uploader
  38         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  39         'info_dict': {
  40             'id': '561726',
  41             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  42             'ext': 'mp4',
  43             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  44             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  45             'thumbnail': 're:^https?://.*\.jpg$',
  46             'uploader': 'Anonymous User',
  47             'upload_date': '20111125',
  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     }]
  58
  59     def _real_extract(self, url):
  60         mobj = re.match(self._VALID_URL, url)
  61         video_id = mobj.group('id')
  62         display_id = mobj.group('display_id')
  63
  64         request = compat_urllib_request.Request(url)
  65         request.add_header('Cookie', 'age_verified=1')
  66         webpage = self._download_webpage(request, display_id)
  67
  68         title = self._search_regex(
  69             [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
  70              r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
  71             webpage, 'title', group='title')
  72
  73         links = []
  74
  75         sources = self._search_regex(
  76             r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
  77         if sources:
  78             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
  79                 links.append(link)
  80
  81         # Fallback #1
  82         for _, link in re.findall(
  83                 r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
  84             links.append(link)
  85
  86         # Fallback #2, this also contains extra low quality 180p format
  87         for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
  88             links.append(link)
  89
  90         # Fallback #3, encrypted links
  91         for _, encrypted_link in re.findall(
  92                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
  93             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
  94
  95         formats = []
  96         for video_url in set(unescapeHTML(link) for link in links):
  97             f = {
  98                 'url': video_url,
  99             }
 100             # Video URL's path looks like this:
 101             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 102             # We will benefit from it by extracting some metadata
 103             mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
 104             if mobj:
 105                 height = int(mobj.group('height'))
 106                 bitrate = int(mobj.group('bitrate'))
 107                 f.update({
 108                     'format_id': '%dp-%dk' % (height, bitrate),
 109                     'height': height,
 110                     'tbr': bitrate,
 111                 })
 112             formats.append(f)
 113         self._sort_formats(formats)
 114
 115         description = self._html_search_regex(
 116             r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
 117             webpage, 'description', default=None)
 118         thumbnail = self._search_regex(
 119             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 120             webpage, 'thumbnail', fatal=False, group='thumbnail')
 121
 122         uploader = self._html_search_regex(
 123             r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
 124             webpage, 'uploader', fatal=False)
 125         upload_date = unified_strdate(self._html_search_regex(
 126             r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
 127             webpage, 'upload date', fatal=False))
 128
 129         age_limit = self._rta_search(webpage)
 130
 131         average_rating = int_or_none(self._search_regex(
 132             r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 133             webpage, 'average rating', fatal=False))
 134
 135         view_count = str_to_int(self._search_regex(
 136             r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
 137             webpage, 'view count', fatal=False))
 138
 139         def extract_tag_box(title):
 140             tag_box = self._search_regex(
 141                 (r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*'
 142                  '<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title),
 143                 webpage, '%s tag box' % title, default=None)
 144             if not tag_box:
 145                 return []
 146             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 147
 148         categories = extract_tag_box('Category')
 149         tags = extract_tag_box('Tags')
 150
 151         return {
 152             'id': video_id,
 153             'display_id': display_id,
 154             'title': title,
 155             'description': description,
 156             'thumbnail': thumbnail,
 157             'uploader': uploader,
 158             'upload_date': upload_date,
 159             'average_rating': average_rating,
 160             'view_count': view_count,
 161             'categories': categories,
 162             'tags': tags,
 163             'age_limit': age_limit,
 164             'formats': formats,
 165         }