Raphaël G. Git Repositories - youtubedl/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_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?://)?(?:\w+\.)?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         }
  31     }
  32
  33     def _print_formats(self, formats):
  34         """Print all available formats"""
  35         print(u'Available formats:')
  36         print(u'ext\t\tformat')
  37         print(u'---------------------------------')
  38         for format in formats:
  39             print(u'%s\t\t%s'  % (format['ext'], format['format']))
  40
  41     def _specific(self, req_format, formats):
  42         for x in formats:
  43             if x["format"] == req_format:
  44                 return x
  45         return None
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_id = mobj.group('videoid')
  50
  51         req = compat_urllib_request.Request(url)
  52         req.add_header('Cookie', 'age_verified=1')
  53         webpage = self._download_webpage(req, video_id)
  54
  55         # Get JSON parameters
  56         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
  57         try:
  58             params = json.loads(json_params)
  59         except:
  60             raise ExtractorError(u'Invalid JSON')
  61
  62         self.report_extraction(video_id)
  63         try:
  64             video_title = params['title']
  65             upload_date = unified_strdate(params['release_date_f'])
  66             video_description = params['description']
  67             video_uploader = params['submitted_by']
  68             thumbnail = params['thumbnails'][0]['image']
  69         except KeyError:
  70             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  71
  72         # Get all of the formats available
  73         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  74         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  75             webpage, u'download list').strip()
  76
  77         # Get all of the links from the page
  78         LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
  79         links = re.findall(LINK_RE, download_list_html)
  80
  81         # Get link of hd video if available
  82         mobj = re.search(r'var encryptedQuality720URL = \'(?P<encrypted_video_url>[a-zA-Z0-9+/]+={0,2})\';', webpage)
  83         if mobj != None:
  84             encrypted_video_url = mobj.group(u'encrypted_video_url')
  85             video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf-8')
  86             links = [video_url] + links
  87
  88         if not links:
  89             raise ExtractorError(u'ERROR: no known formats available for video')
  90
  91         self.to_screen(u'Links found: %d' % len(links))
  92
  93         formats = []
  94         for link in links:
  95
  96             # A link looks like this:
  97             # 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
  98             # A path looks like this:
  99             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
 100             video_url = unescapeHTML( link )
 101             path = compat_urllib_parse_urlparse( video_url ).path
 102             extension = os.path.splitext( path )[1][1:]
 103             format = path.split('/')[4].split('_')[:2]
 104             # size = format[0]
 105             # bitrate = format[1]
 106             format = "-".join( format )
 107             # title = u'%s-%s-%s' % (video_title, size, bitrate)
 108
 109             formats.append({
 110                 'id': video_id,
 111                 'url': video_url,
 112                 'uploader': video_uploader,
 113                 'upload_date': upload_date,
 114                 'title': video_title,
 115                 'ext': extension,
 116                 'format': format,
 117                 'thumbnail': thumbnail,
 118                 'description': video_description
 119             })
 120
 121         if self._downloader.params.get('listformats', None):
 122             self._print_formats(formats)
 123             return
 124
 125         req_format = self._downloader.params.get('format', 'best')
 126         self.to_screen(u'Format: %s' % req_format)
 127
 128         if req_format is None or req_format == 'best':
 129             return [formats[0]]
 130         elif req_format == 'worst':
 131             return [formats[-1]]
 132         elif req_format in ('-1', 'all'):
 133             return formats
 134         else:
 135             format = self._specific( req_format, formats )
 136             if format is None:
 137                 raise ExtractorError(u'Requested format not available')
 138             return [format]