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 )
  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': '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$',
  28             'uploader': 'Ask Dan And Jennifer',
  29             'upload_date': '20101221',
  30             'average_rating': int,
  31             'view_count': int,
  32             'comment_count': int,
  33             'categories': list,
  34             'tags': list,
  35             'age_limit': 18,
  36         },
  37     }, {
  38         # Unknown uploader
  39         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
  40         'info_dict': {
  41             'id': '561726',
  42             'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
  43             'ext': 'mp4',
  44             'title': 'Big Tits Awesome Brunette On amazing webcam show',
  45             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
  46             'thumbnail': r're:^https?://.*\.jpg$',
  47             'uploader': 'Unknown',
  48             'upload_date': '20111125',
  49             'average_rating': int,
  50             'view_count': int,
  51             'comment_count': int,
  52             'categories': list,
  53             'tags': list,
  54             'age_limit': 18,
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59     }]
  60
  61     def _real_extract(self, url):
  62         mobj = re.match(self._VALID_URL, url)
  63         video_id = mobj.group('id')
  64         display_id = mobj.group('display_id')
  65
  66         request = sanitized_Request(url)
  67         request.add_header('Cookie', 'age_verified=1')
  68         webpage = self._download_webpage(request, display_id)
  69
  70         title = self._search_regex(
  71             [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
  72              r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
  73             webpage, 'title', group='title')
  74
  75         links = []
  76
  77         sources = self._search_regex(
  78             r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
  79         if sources:
  80             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
  81                 links.append(link)
  82
  83         # Fallback #1
  84         for _, link in re.findall(
  85                 r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
  86             links.append(link)
  87
  88         # Fallback #2, this also contains extra low quality 180p format
  89         for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
  90             links.append(link)
  91
  92         # Fallback #3, encrypted links
  93         for _, encrypted_link in re.findall(
  94                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
  95             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
  96
  97         formats = []
  98         for video_url in set(unescapeHTML(link) for link in links):
  99             f = {
 100                 'url': video_url,
 101             }
 102             # Video URL's path looks like this:
 103             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 104             #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
 105             # We will benefit from it by extracting some metadata
 106             mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
 107             if mobj:
 108                 height = int(mobj.group('height'))
 109                 bitrate = int(mobj.group('bitrate'))
 110                 f.update({
 111                     'format_id': '%dp-%dk' % (height, bitrate),
 112                     'height': height,
 113                     'tbr': bitrate,
 114                 })
 115             formats.append(f)
 116         self._sort_formats(formats)
 117
 118         description = self._og_search_description(webpage, default=None)
 119         thumbnail = self._search_regex(
 120             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
 121             webpage, 'thumbnail', fatal=False, group='thumbnail')
 122
 123         uploader = self._html_search_regex(
 124             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
 125             webpage, 'uploader', fatal=False)
 126         upload_date = unified_strdate(self._html_search_regex(
 127             r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
 128             webpage, 'upload date', fatal=False))
 129
 130         age_limit = self._rta_search(webpage)
 131
 132         average_rating = int_or_none(self._search_regex(
 133             r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 134             webpage, 'average rating', fatal=False))
 135
 136         view_count = str_to_int(self._search_regex(
 137             r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
 138             webpage, 'view count', fatal=False, group='count'))
 139         comment_count = str_to_int(self._search_regex(
 140             r'>All [Cc]omments? \(([\d,.]+)\)',
 141             webpage, 'comment count', fatal=False))
 142
 143         def extract_tag_box(regex, title):
 144             tag_box = self._search_regex(regex, webpage, title, default=None)
 145             if not tag_box:
 146                 return []
 147             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 148
 149         categories = extract_tag_box(
 150             r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
 151         tags = extract_tag_box(
 152             r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
 153             'tags')
 154
 155         return {
 156             'id': video_id,
 157             'display_id': display_id,
 158             'title': title,
 159             'description': description,
 160             'thumbnail': thumbnail,
 161             'uploader': uploader,
 162             'upload_date': upload_date,
 163             'average_rating': average_rating,
 164             'view_count': view_count,
 165             'comment_count': comment_count,
 166             'categories': categories,
 167             'tags': tags,
 168             'age_limit': age_limit,
 169             'formats': formats,
 170         }