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