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
  16
  17 class YouPornIE(InfoExtractor):
  18     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
  19     _TEST = {
  20         u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  21         u'file': u'505835.mp4',
  22         u'md5': u'c37ddbaaa39058c76a7e86c6813423c1',
  23         u'info_dict': {
  24             u"upload_date": u"20101221",
  25             u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
  26             u"uploader": u"Ask Dan And Jennifer",
  27             u"title": u"Sex Ed: Is It Safe To Masturbate Daily?"
  28         }
  29     }
  30
  31     def _print_formats(self, formats):
  32         """Print all available formats"""
  33         print(u'Available formats:')
  34         print(u'ext\t\tformat')
  35         print(u'---------------------------------')
  36         for format in formats:
  37             print(u'%s\t\t%s'  % (format['ext'], format['format']))
  38
  39     def _specific(self, req_format, formats):
  40         for x in formats:
  41             if x["format"] == req_format:
  42                 return x
  43         return None
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         video_id = mobj.group('videoid')
  48
  49         req = compat_urllib_request.Request(url)
  50         req.add_header('Cookie', 'age_verified=1')
  51         webpage = self._download_webpage(req, video_id)
  52
  53         # Get JSON parameters
  54         json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
  55         try:
  56             params = json.loads(json_params)
  57         except:
  58             raise ExtractorError(u'Invalid JSON')
  59
  60         self.report_extraction(video_id)
  61         try:
  62             video_title = params['title']
  63             upload_date = unified_strdate(params['release_date_f'])
  64             video_description = params['description']
  65             video_uploader = params['submitted_by']
  66             thumbnail = params['thumbnails'][0]['image']
  67         except KeyError:
  68             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
  69
  70         # Get all of the formats available
  71         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
  72         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
  73             webpage, u'download list').strip()
  74
  75         # Get all of the links from the page
  76         LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
  77         links = re.findall(LINK_RE, download_list_html)
  78         if(len(links) == 0):
  79             raise ExtractorError(u'ERROR: no known formats available for video')
  80
  81         self.to_screen(u'Links found: %d' % len(links))
  82
  83         formats = []
  84         for link in links:
  85
  86             # A link looks like this:
  87             # 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
  88             # A path looks like this:
  89             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
  90             video_url = unescapeHTML( link )
  91             path = compat_urllib_parse_urlparse( video_url ).path
  92             extension = os.path.splitext( path )[1][1:]
  93             format = path.split('/')[4].split('_')[:2]
  94             # size = format[0]
  95             # bitrate = format[1]
  96             format = "-".join( format )
  97             # title = u'%s-%s-%s' % (video_title, size, bitrate)
  98
  99             formats.append({
 100                 'id': video_id,
 101                 'url': video_url,
 102                 'uploader': video_uploader,
 103                 'upload_date': upload_date,
 104                 'title': video_title,
 105                 'ext': extension,
 106                 'format': format,
 107                 'thumbnail': thumbnail,
 108                 'description': video_description
 109             })
 110
 111         if self._downloader.params.get('listformats', None):
 112             self._print_formats(formats)
 113             return
 114
 115         req_format = self._downloader.params.get('format', None)
 116         self.to_screen(u'Format: %s' % req_format)
 117
 118         if req_format is None or req_format == 'best':
 119             return [formats[0]]
 120         elif req_format == 'worst':
 121             return [formats[-1]]
 122         elif req_format in ('-1', 'all'):
 123             return formats
 124         else:
 125             format = self._specific( req_format, formats )
 126             if format is None:
 127                 raise ExtractorError(u'Requested format not available')
 128             return [format]