youtube_dl/extractor/moviefap.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import str_to_int
   7
   8
   9 class MovieFapIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<name>[a-z-_]+)'
  11     _TESTS = [{
  12         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
  13         'md5': 'fa56683e291fc80635907168a743c9ad',
  14         'info_dict': {
  15             'id': 'e5da0d3edce5404418f5',
  16             'ext': 'flv',
  17             'title': 'Jeune Couple Russe',
  18             'description': 'Amateur',
  19             'thumbnail': 'http://pic.moviefap.com/thumbs/e5/949-18l.jpg',
  20             'uploader_id': 'whiskeyjar',
  21             'display_id': 'jeune-couple-russe'
  22         }
  23     }, {
  24         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
  25         'md5': '26624b4e2523051b550067d547615906',
  26         'info_dict': {
  27             'id': 'be9867c9416c19f54a4a',
  28             'ext': 'mp4',
  29             'title': 'Experienced MILF Amazing Handjob',
  30             'description': 'Experienced MILF giving an Amazing Handjob',
  31             'thumbnail': 'http://img.moviefap.com/a16:9w990r/thumbs/be/322032-20l.jpg',
  32             'uploader_id': 'darvinfred06',
  33             'display_id': 'experienced-milf-amazing-handjob'
  34         }
  35     }]
  36
  37     @staticmethod
  38     def __get_thumbnail_data(xml):
  39
  40         """
  41         Constructs a list of video thumbnails from timeline preview images.
  42         :param xml: the information XML document to parse
  43         """
  44
  45         timeline = xml.find('timeline')
  46         if timeline is None:
  47             # not all videos have the data - ah well
  48             return []
  49
  50         # get the required information from the XML
  51         width = str_to_int(timeline.find('imageWidth').text)
  52         height = str_to_int(timeline.find('imageHeight').text)
  53         first = str_to_int(timeline.find('imageFirst').text)
  54         last = str_to_int(timeline.find('imageLast').text)
  55         pattern = timeline.find('imagePattern').text
  56
  57         # generate the list of thumbnail information dicts
  58         thumbnails = []
  59         for i in range(first, last + 1):
  60             thumbnails.append({
  61                 'url': pattern.replace('#', str(i)),
  62                 'width': width,
  63                 'height': height
  64             })
  65         return thumbnails
  66
  67     def _real_extract(self, url):
  68
  69         # find the video ID
  70         video_id = self._match_id(url)
  71
  72         # retrieve the page HTML
  73         webpage = self._download_webpage(url, video_id)
  74
  75         # find the URL of the XML document detailing video download URLs
  76         info_url = self._html_search_regex(r'flashvars\.config = escape\("(.+?)"', webpage, 'player parameters')
  77
  78         # download that XML
  79         xml = self._download_xml(info_url, video_id)
  80
  81         # create dictionary of properties we know so far, or can find easily
  82         info = {
  83             'id': video_id,
  84             'title': self._html_search_regex(r'<div id="view_title"><h1>(.*?)</h1>', webpage, 'title'),
  85             'display_id': re.compile(self._VALID_URL).match(url).group('name'),
  86             'thumbnails': self.__get_thumbnail_data(xml),
  87             'thumbnail': xml.find('startThumb').text,
  88             'description': self._html_search_regex(r'name="description" value="(.*?)"', webpage, 'description'),
  89             'uploader_id': self._html_search_regex(r'name="username" value="(.*?)"', webpage, 'uploader_id'),
  90             'view_count': str_to_int(self._html_search_regex(r'<br>Views <strong>([0-9]+)</strong>', webpage, 'view_count')),
  91             'average_rating': float(self._html_search_regex(r'Current Rating<br> <strong>(.*?)</strong>', webpage, 'average_rating')),
  92             'comment_count': str_to_int(self._html_search_regex(r'<span id="comCount">([0-9]+)</span>', webpage, 'comment_count')),
  93             'age_limit': 18,
  94             'webpage_url': self._html_search_regex(r'name="link" value="(.*?)"', webpage, 'webpage_url'),
  95             'categories': self._html_search_regex(r'</div>\s*(.*?)\s*<br>', webpage, 'categories').split(', ')
  96         }
  97
  98         # find and add the format
  99         if xml.find('videoConfig') is not None:
 100             info['ext'] = xml.find('videoConfig').find('type').text
 101         else:
 102             info['ext'] = 'flv'  # guess...
 103
 104         # work out the video URL(s)
 105         if xml.find('videoLink') is not None:
 106             # single format available
 107             info['url'] = xml.find('videoLink').text
 108         else:
 109             # multiple formats available
 110             info['formats'] = []
 111
 112             # N.B. formats are already in ascending order of quality
 113             for item in xml.find('quality').findall('item'):
 114                 info['formats'].append({
 115                     'url': item.find('videoLink').text,
 116                     'resolution': item.find('res').text  # 480p etc.
 117                 })
 118
 119         return info