Raphaël G. Git Repositories - youtubedl/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         'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
  27         'info_dict': {
  28             'id': '505835',
  29             'ext': 'mp4',
  30             'upload_date': '20101221',
  31             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
  32             'uploader': 'Ask Dan And Jennifer',
  33             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  34             'age_limit': 18,
  35         }
  36     }
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         video_id = mobj.group('videoid')
  41         url = mobj.group('proto') + 'www.' + mobj.group('url')
  42
  43         req = compat_urllib_request.Request(url)
  44         req.add_header('Cookie', 'age_verified=1')
  45         webpage = self._download_webpage(req, video_id)
  46         age_limit = self._rta_search(webpage)
  47
  48         # Get JSON parameters
  49         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters')
  50         try:
  51             params = json.loads(json_params)
  52         except:
  53             raise ExtractorError(u'Invalid JSON')
  54
  55         self.report_extraction(video_id)
  56         try:
  57             video_title = params['title']
  58             upload_date = unified_strdate(params['release_date_f'])
  59             video_description = params['description']
  60             video_uploader = params['submitted_by']
  61             thumbnail = params['thumbnails'][0]['image']
  62         except KeyError:
  63             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  64
  65         # Get all of the links from the page
  66         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  67         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  68             webpage, 'download list').strip()
  69         LINK_RE = r'<a href="([^"]+)">'
  70         links = re.findall(LINK_RE, download_list_html)
  71
  72         # Get all encrypted links
  73         encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
  74         for encrypted_link in encrypted_links:
  75             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
  76             links.append(link)
  77
  78         formats = []
  79         for link in links:
  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             format_parts = path.split('/')[4].split('_')[:2]
  87
  88             dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
  89
  90             resolution = format_parts[0]
  91             height = int(resolution[:-len('p')])
  92             bitrate = int(format_parts[1][:-len('k')])
  93             format = '-'.join(format_parts) + '-' + dn
  94
  95             formats.append({
  96                 'url': video_url,
  97                 'format': format,
  98                 'format_id': format,
  99                 'height': height,
 100                 'tbr': bitrate,
 101                 'resolution': resolution,
 102             })
 103
 104         self._sort_formats(formats)
 105
 106         if not formats:
 107             raise ExtractorError(u'ERROR: no known formats available for video')
 108
 109         return {
 110             'id': video_id,
 111             'uploader': video_uploader,
 112             'upload_date': upload_date,
 113             'title': video_title,
 114             'thumbnail': thumbnail,
 115             'description': video_description,
 116             'age_limit': age_limit,
 117             'formats': formats,
 118         }