_ 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 from ..compat import compat_str
  11
  12
  13 class MovieFapIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<name>[a-z-_]+)'
  15     _TESTS = [{
  16         # normal, multi-format video
  17         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
  18         'md5': '26624b4e2523051b550067d547615906',
  19         'info_dict': {
  20             'id': 'be9867c9416c19f54a4a',
  21             'ext': 'mp4',
  22             'title': 'Experienced MILF Amazing Handjob',
  23             'description': 'Experienced MILF giving an Amazing Handjob',
  24             'thumbnail': 'http://img.moviefap.com/a16:9w990r/thumbs/be/322032-20l.jpg',
  25             'uploader_id': 'darvinfred06',
  26             'display_id': 'experienced-milf-amazing-handjob',
  27             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing']
  28         }
  29     }, {
  30         # quirky single-format case where the extension is given as fid, but the video is really an flv
  31         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
  32         'md5': 'fa56683e291fc80635907168a743c9ad',
  33         'info_dict': {
  34             'id': 'e5da0d3edce5404418f5',
  35             'ext': 'flv',
  36             'title': 'Jeune Couple Russe',
  37             'description': 'Amateur',
  38             'thumbnail': 'http://pic.moviefap.com/thumbs/e5/949-18l.jpg',
  39             'uploader_id': 'whiskeyjar',
  40             'display_id': 'jeune-couple-russe',
  41             'categories': ['Amateur', 'Teen']
  42         }
  43     }]
  44
  45     @staticmethod
  46     def __get_thumbnail_data(xml):
  47
  48         """
  49         Constructs a list of video thumbnails from timeline preview images.
  50         :param xml: the information XML document to parse
  51         """
  52
  53         timeline = xml.find('timeline')
  54         if timeline is None:
  55             # not all videos have the data - ah well
  56             return []
  57
  58         # get the required information from the XML
  59         width = str_to_int(timeline.find('imageWidth').text)
  60         height = str_to_int(timeline.find('imageHeight').text)
  61         first = str_to_int(timeline.find('imageFirst').text)
  62         last = str_to_int(timeline.find('imageLast').text)
  63         pattern = timeline.find('imagePattern').text
  64
  65         # generate the list of thumbnail information dicts
  66         thumbnails = []
  67         for i in range(first, last + 1):
  68             thumbnails.append({
  69                 'url': pattern.replace('#', compat_str(i)),
  70                 'width': width,
  71                 'height': height
  72             })
  73         return thumbnails
  74
  75     def _real_extract(self, url):
  76
  77         video_id = self._match_id(url)
  78         webpage = self._download_webpage(url, video_id)
  79
  80         # find and retrieve the XML document detailing video download URLs
  81         info_url = self._html_search_regex( \
  82                 r'flashvars\.config = escape\("(.+?)"', webpage, 'player parameters')
  83         xml = self._download_xml(info_url, video_id)
  84
  85         # find the video container
  86         if xml.find('videoConfig') is not None:
  87             ext = xml.find('videoConfig').find('type').text
  88         else:
  89             ext = 'flv'  # guess...
  90
  91         # work out the video URL(s)
  92         formats = []
  93         if xml.find('videoLink') is not None:
  94             # single format available
  95             formats.append({
  96                 'url': xpath_text(xml, 'videoLink', 'url', True),
  97                 'ext': ext
  98             })
  99         else:
 100             # multiple formats available
 101             for item in xml.find('quality').findall('item'):
 102                 resolution = xpath_text(item, 'res', 'resolution', True)  # 480p etc.
 103                 formats.append({
 104                     'url': xpath_text(item, 'videoLink', 'url', True),
 105                     'ext': ext,
 106                     'resolution': resolution,
 107                     'height': int(re.findall(r'\d+', resolution)[0])
 108                 })
 109
 110             self._sort_formats(formats)
 111
 112         return {
 113             'id': video_id,
 114             'formats': formats,
 115             'title': self._html_search_regex( \
 116                     r'<div id="view_title"><h1>(.*?)</h1>', webpage, 'title'),
 117             'display_id': re.compile(self._VALID_URL).match(url).group('name'),
 118             'thumbnails': self.__get_thumbnail_data(xml),
 119             'thumbnail': xpath_text(xml, 'startThumb', 'thumbnail'),
 120             'description': self._html_search_regex( \
 121                     r'name="description" value="(.*?)"', webpage, 'description', fatal=False),
 122             'uploader_id': self._html_search_regex( \
 123                     r'name="username" value="(.*?)"', webpage, 'uploader_id', fatal=False),
 124             'view_count': str_to_int(self._html_search_regex( \
 125                     r'<br>Views <strong>([0-9]+)</strong>', webpage, 'view_count, fatal=False')),
 126             'average_rating': float(self._html_search_regex( \
 127                     r'Current Rating<br> <strong>(.*?)</strong>', webpage, 'average_rating', fatal=False)),
 128             'comment_count': str_to_int(self._html_search_regex( \
 129                     r'<span id="comCount">([0-9]+)</span>', webpage, 'comment_count', fatal=False)),
 130             'age_limit': 18,
 131             'webpage_url': self._html_search_regex( \
 132                     r'name="link" value="(.*?)"', webpage, 'webpage_url', fatal=False),
 133             'categories': self._html_search_regex( \
 134                     r'</div>\s*(.*?)\s*<br>', webpage, 'categories', fatal=False).split(', ')
 135         }