_ 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     _TEST = {
  19         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  20         'info_dict': {
  21             'id': '505835',
  22             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
  23             'ext': 'mp4',
  24             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  25             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  26             'thumbnail': 're:^https?://.*\.jpg$',
  27             'uploader': 'Ask Dan And Jennifer',
  28             'upload_date': '20101221',
  29             'average_rating': int,
  30             'view_count': int,
  31             'categories': list,
  32             'tags': list,
  33             'age_limit': 18,
  34         }
  35     }
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40         display_id = mobj.group('display_id')
  41
  42         request = compat_urllib_request.Request(url)
  43         request.add_header('Cookie', 'age_verified=1')
  44         webpage = self._download_webpage(request, display_id)
  45
  46         title = self._search_regex(
  47             [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
  48              r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
  49             webpage, 'title', group='title')
  50
  51         links = []
  52
  53         sources = self._search_regex(
  54             r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
  55         if sources:
  56             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
  57                 links.append(link)
  58
  59         # Fallback #1
  60         for _, link in re.findall(
  61                 r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
  62             links.append(link)
  63
  64         # Fallback #2, this also contains extra low quality 180p format
  65         for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
  66             links.append(link)
  67
  68         # Fallback #3, encrypted links
  69         for _, encrypted_link in re.findall(
  70                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
  71             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
  72
  73         formats = []
  74         for video_url in set(unescapeHTML(link) for link in links):
  75             f = {
  76                 'url': video_url,
  77             }
  78             # Video URL's path looks like this:
  79             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
  80             # We will benefit from it by extracting some metadata
  81             mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
  82             if mobj:
  83                 height = int(mobj.group('height'))
  84                 bitrate = int(mobj.group('bitrate'))
  85                 f.update({
  86                     'format_id': '%dp-%dk' % (height, bitrate),
  87                     'height': height,
  88                     'tbr': bitrate,
  89                 })
  90             formats.append(f)
  91         self._sort_formats(formats)
  92
  93         description = self._html_search_regex(
  94             r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
  95             webpage, 'description', default=None)
  96         thumbnail = self._search_regex(
  97             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
  98             webpage, 'thumbnail', fatal=False, group='thumbnail')
  99
 100         uploader = self._search_regex(
 101             r'<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>\s*<a[^>]+href="[^"]*">([^<]+)</a>',
 102             webpage, 'uploader', fatal=False)
 103         upload_date = unified_strdate(self._html_search_regex(
 104             r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
 105             webpage, 'upload date', fatal=False))
 106
 107         age_limit = self._rta_search(webpage)
 108
 109         average_rating = int_or_none(self._search_regex(
 110             r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
 111             webpage, 'average rating', fatal=False))
 112
 113         view_count = str_to_int(self._search_regex(
 114             r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
 115             webpage, 'view count', fatal=False))
 116
 117         def extract_tag_box(title):
 118             tag_box = self._search_regex(
 119                 (r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*'
 120                  '<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title),
 121                 webpage, '%s tag box' % title, default=None)
 122             if not tag_box:
 123                 return []
 124             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 125
 126         categories = extract_tag_box('Category')
 127         tags = extract_tag_box('Tags')
 128
 129         return {
 130             'id': video_id,
 131             'display_id': display_id,
 132             'title': title,
 133             'description': description,
 134             'thumbnail': thumbnail,
 135             'uploader': uploader,
 136             'upload_date': upload_date,
 137             'average_rating': average_rating,
 138             'view_count': view_count,
 139             'categories': categories,
 140             'tags': tags,
 141             'age_limit': age_limit,
 142             'formats': formats,
 143         }