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

   1 from __future__ import unicode_literals
   2
   3
   4 import json
   5 import re
   6 import sys
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     compat_urllib_parse_urlparse,
  11     compat_urllib_request,
  12
  13     ExtractorError,
  14     unescapeHTML,
  15     unified_strdate,
  16 )
  17 from ..aes import (
  18     aes_decrypt_text
  19 )
  20
  21
  22 class YouPornIE(InfoExtractor):
  23     _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
  24     _TEST = {
  25         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  26         'info_dict': {
  27             'id': '505835',
  28             'ext': 'mp4',
  29             'upload_date': '20101221',
  30             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  31             'uploader': 'Ask Dan And Jennifer',
  32             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  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('videoid')
  40         url = mobj.group('proto') + 'www.' + mobj.group('url')
  41
  42         req = compat_urllib_request.Request(url)
  43         req.add_header('Cookie', 'age_verified=1')
  44         webpage = self._download_webpage(req, video_id)
  45         age_limit = self._rta_search(webpage)
  46
  47         # Get JSON parameters
  48         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters')
  49         try:
  50             params = json.loads(json_params)
  51         except:
  52             raise ExtractorError(u'Invalid JSON')
  53
  54         self.report_extraction(video_id)
  55         try:
  56             video_title = params['title']
  57             upload_date = unified_strdate(params['release_date_f'])
  58             video_description = params['description']
  59             video_uploader = params['submitted_by']
  60             thumbnail = params['thumbnails'][0]['image']
  61         except KeyError:
  62             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  63
  64         # Get all of the links from the page
  65         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  66         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  67                                                 webpage, 'download list').strip()
  68         LINK_RE = r'<a href="([^"]+)">'
  69         links = re.findall(LINK_RE, download_list_html)
  70
  71         # Get all encrypted links
  72         encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
  73         for encrypted_link in encrypted_links:
  74             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
  75             links.append(link)
  76
  77         formats = []
  78         for link in links:
  79             # A link looks like this:
  80             # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
  81             # A path looks like this:
  82             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
  83             video_url = unescapeHTML(link)
  84             path = compat_urllib_parse_urlparse(video_url).path
  85             format_parts = path.split('/')[4].split('_')[:2]
  86
  87             dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
  88
  89             resolution = format_parts[0]
  90             height = int(resolution[:-len('p')])
  91             bitrate = int(format_parts[1][:-len('k')])
  92             format = '-'.join(format_parts) + '-' + dn
  93
  94             formats.append({
  95                 'url': video_url,
  96                 'format': format,
  97                 'format_id': format,
  98                 'height': height,
  99                 'tbr': bitrate,
 100                 'resolution': resolution,
 101             })
 102
 103         self._sort_formats(formats)
 104
 105         if not formats:
 106             raise ExtractorError(u'ERROR: no known formats available for video')
 107
 108         return {
 109             'id': video_id,
 110             'uploader': video_uploader,
 111             'upload_date': upload_date,
 112             'title': video_title,
 113             'thumbnail': thumbnail,
 114             'description': video_description,
 115             'age_limit': age_limit,
 116             'formats': formats,
 117         }