youtube_dl/extractor/youporn.py

   1 import json
   2 import os
   3 import re
   4 import sys
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10
  11     ExtractorError,
  12     unescapeHTML,
  13     unified_strdate,
  14 )
  15 from ..aes import (
  16     aes_decrypt_text
  17 )
  18
  19 class YouPornIE(InfoExtractor):
  20     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
  21     _TEST = {
  22         u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  23         u'file': u'505835.mp4',
  24         u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
  25         u'info_dict': {
  26             u"upload_date": u"20101221",
  27             u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
  28             u"uploader": u"Ask Dan And Jennifer",
  29             u"title": u"Sex Ed: Is It Safe To Masturbate Daily?",
  30             u"age_limit": 18,
  31         }
  32     }
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         video_id = mobj.group('videoid')
  37         url = 'http://www.' + mobj.group('url')
  38
  39         req = compat_urllib_request.Request(url)
  40         req.add_header('Cookie', 'age_verified=1')
  41         webpage = self._download_webpage(req, video_id)
  42         age_limit = self._rta_search(webpage)
  43
  44         # Get JSON parameters
  45         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
  46         try:
  47             params = json.loads(json_params)
  48         except:
  49             raise ExtractorError(u'Invalid JSON')
  50
  51         self.report_extraction(video_id)
  52         try:
  53             video_title = params['title']
  54             upload_date = unified_strdate(params['release_date_f'])
  55             video_description = params['description']
  56             video_uploader = params['submitted_by']
  57             thumbnail = params['thumbnails'][0]['image']
  58         except KeyError:
  59             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  60
  61         # Get all of the links from the page
  62         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  63         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  64             webpage, u'download list').strip()
  65         LINK_RE = r'<a href="([^"]+)">'
  66         links = re.findall(LINK_RE, download_list_html)
  67
  68         # Get all encrypted links
  69         encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
  70         for encrypted_link in encrypted_links:
  71             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
  72             links.append(link)
  73
  74         if not links:
  75             raise ExtractorError(u'ERROR: no known formats available for video')
  76
  77         formats = []
  78         for link in links:
  79
  80             # A link looks like this:
  81             # 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
  82             # A path looks like this:
  83             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
  84             video_url = unescapeHTML(link)
  85             path = compat_urllib_parse_urlparse(video_url).path
  86             extension = os.path.splitext(path)[1][1:]
  87             format = path.split('/')[4].split('_')[:2]
  88
  89             # size = format[0]
  90             # bitrate = format[1]
  91             format = "-".join(format)
  92             # title = u'%s-%s-%s' % (video_title, size, bitrate)
  93
  94             formats.append({
  95                 'url': video_url,
  96                 'ext': extension,
  97                 'format': format,
  98                 'format_id': format,
  99             })
 100
 101         # Sort and remove doubles
 102         formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
 103         for i in range(len(formats)-1,0,-1):
 104             if formats[i]['format_id'] == formats[i-1]['format_id']:
 105                 del formats[i]
 106
 107         return {
 108             'id': video_id,
 109             'uploader': video_uploader,
 110             'upload_date': upload_date,
 111             'title': video_title,
 112             'thumbnail': thumbnail,
 113             'description': video_description,
 114             'age_limit': age_limit,
 115             'formats': formats,
 116         }