_ Git - youtube-dl/blob - 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_str,
   9     compat_urllib_parse_urlparse,
  10     compat_urllib_request,
  11
  12     ExtractorError,
  13     unescapeHTML,
  14     unified_strdate,
  15 )
  16 from ..aes import (
  17     aes_decrypt_text
  18 )
  19
  20 class YouPornIE(InfoExtractor):
  21     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
  22     _TEST = {
  23         u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  24         u'file': u'505835.mp4',
  25         u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
  26         u'info_dict': {
  27             u"upload_date": u"20101221",
  28             u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
  29             u"uploader": u"Ask Dan And Jennifer",
  30             u"title": u"Sex Ed: Is It Safe To Masturbate Daily?"
  31         }
  32     }
  33
  34     def _print_formats(self, formats):
  35         """Print all available formats"""
  36         print(u'Available formats:')
  37         print(u'ext\t\tformat')
  38         print(u'---------------------------------')
  39         for format in formats:
  40             print(u'%s\t\t%s'  % (format['ext'], format['format']))
  41
  42     def _specific(self, req_format, formats):
  43         for x in formats:
  44             if x["format"] == req_format:
  45                 return x
  46         return None
  47
  48     def _real_extract(self, url):
  49         mobj = re.match(self._VALID_URL, url)
  50         video_id = mobj.group('videoid')
  51
  52         req = compat_urllib_request.Request(url)
  53         req.add_header('Cookie', 'age_verified=1')
  54         webpage = self._download_webpage(req, video_id)
  55
  56         # Get JSON parameters
  57         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
  58         try:
  59             params = json.loads(json_params)
  60         except:
  61             raise ExtractorError(u'Invalid JSON')
  62
  63         self.report_extraction(video_id)
  64         try:
  65             video_title = params['title']
  66             upload_date = unified_strdate(params['release_date_f'])
  67             video_description = params['description']
  68             video_uploader = params['submitted_by']
  69             thumbnail = params['thumbnails'][0]['image']
  70         except KeyError:
  71             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  72
  73         # Get all of the formats available
  74         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  75         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  76             webpage, u'download list').strip()
  77
  78         # Get all of the links from the page
  79         LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
  80         links = re.findall(LINK_RE, download_list_html)
  81
  82         # Get link of hd video
  83         encrypted_video_url = self._html_search_regex(
  84             r'var encrypted(?:Quality[0-9]+)?URL = \'(?P<encrypted_video_url>[a-zA-Z0-9+/]+={0,2})\';',
  85             webpage, u'encrypted_video_url')
  86         video_url = aes_decrypt_text(encrypted_video_url, video_title, 32)
  87         print(video_url)
  88         assert isinstance(video_url, compat_str)
  89         if video_url.split('/')[6].split('_')[0] == u'720p': # only add if 720p to avoid duplicates
  90             links = [video_url] + links
  91
  92         if not links:
  93             raise ExtractorError(u'ERROR: no known formats available for video')
  94
  95         self.to_screen(u'Links found: %d' % len(links))
  96
  97         formats = []
  98         for link in links:
  99
 100             # A link looks like this:
 101             # 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
 102             # A path looks like this:
 103             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
 104             video_url = unescapeHTML( link )
 105             path = compat_urllib_parse_urlparse( video_url ).path
 106             extension = os.path.splitext( path )[1][1:]
 107             format = path.split('/')[4].split('_')[:2]
 108             # size = format[0]
 109             # bitrate = format[1]
 110             format = "-".join( format )
 111             # title = u'%s-%s-%s' % (video_title, size, bitrate)
 112
 113             formats.append({
 114                 'id': video_id,
 115                 'url': video_url,
 116                 'uploader': video_uploader,
 117                 'upload_date': upload_date,
 118                 'title': video_title,
 119                 'ext': extension,
 120                 'format': format,
 121                 'thumbnail': thumbnail,
 122                 'description': video_description
 123             })
 124
 125         if self._downloader.params.get('listformats', None):
 126             self._print_formats(formats)
 127             return
 128
 129         req_format = self._downloader.params.get('format', 'best')
 130         self.to_screen(u'Format: %s' % req_format)
 131
 132         if req_format is None or req_format == 'best':
 133             return [formats[0]]
 134         elif req_format == 'worst':
 135             return [formats[-1]]
 136         elif req_format in ('-1', 'all'):
 137             return formats
 138         else:
 139             format = self._specific( req_format, formats )
 140             if format is None:
 141                 raise ExtractorError(u'Requested format not available')
 142             return [format]