youtube_dl/extractor/motherless.py

   1 from __future__ import unicode_literals
   2
   3 import datetime
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     unified_strdate,
  10 )
  11
  12
  13 class MotherlessIE(InfoExtractor):
  14     _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P<id>[A-Z0-9]+)'
  15     _TESTS = [
  16         {
  17             'url': 'http://motherless.com/AC3FFE1',
  18             'md5': '5527fef81d2e529215dad3c2d744a7d9',
  19             'info_dict': {
  20                 'id': 'AC3FFE1',
  21                 'ext': 'flv',
  22                 'title': 'Fucked in the ass while playing PS3',
  23                 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
  24                 'upload_date': '20100913',
  25                 'uploader_id': 'famouslyfuckedup',
  26                 'thumbnail': 're:http://.*\.jpg',
  27                 'age_limit': 18,
  28             }
  29         },
  30         {
  31             'url': 'http://motherless.com/532291B',
  32             'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
  33             'info_dict': {
  34                 'id': '532291B',
  35                 'ext': 'mp4',
  36                 'title': 'Amazing girl playing the omegle game, PERFECT!',
  37                 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
  38                 'upload_date': '20140622',
  39                 'uploader_id': 'Sulivana7x',
  40                 'thumbnail': 're:http://.*\.jpg',
  41                 'age_limit': 18,
  42             }
  43         }
  44     ]
  45
  46     def _real_extract(self,url):
  47         mobj = re.match(self._VALID_URL, url)
  48         video_id = mobj.group('id')
  49
  50         webpage = self._download_webpage(url, video_id)
  51
  52         title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
  53
  54         video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url')
  55         age_limit = self._rta_search(webpage)
  56
  57         view_count = self._html_search_regex(r'<strong>Views</strong>\s+([^<]+)<', webpage, 'view_count')
  58
  59         upload_date = self._html_search_regex(r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload_date')
  60         if 'Ago' in upload_date:
  61             days = int(re.search(r'([0-9]+)', upload_date).group(1))
  62             upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
  63         else:
  64             upload_date = unified_strdate(upload_date)
  65
  66         like_count = self._html_search_regex(r'<strong>Favorited</strong>\s+([^<]+)<', webpage, 'like_count')
  67
  68         comment_count = webpage.count('class="media-comment-contents"')
  69         uploader_id = self._html_search_regex(r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id')
  70
  71         categories = self._html_search_meta('keywords', webpage)
  72         if categories:
  73             categories = [cat.strip() for cat in categories.split(',')]
  74
  75         return {
  76             'id': video_id,
  77             'title': title,
  78             'upload_date': upload_date,
  79             'uploader_id': uploader_id,
  80             'thumbnail': self._og_search_thumbnail(webpage),
  81             'categories': categories,
  82             'view_count': int_or_none(view_count.replace(',', '')),
  83             'like_count': int_or_none(like_count.replace(',', '')),
  84             'comment_count': comment_count,
  85             'age_limit': age_limit,
  86             'url': video_url,
  87         }