_ Git - youtube-dl/blob - 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 str_to_int
   8
   9
  10 class MotherlessIE(InfoExtractor):
  11     """Information Extractor for Motherless"""
  12     _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P<id>[A-Z0-9]+)'
  13     _TESTS = [
  14         {
  15             'url': 'http://motherless.com/AC3FFE1',
  16             'md5': '5527fef81d2e529215dad3c2d744a7d9',
  17             'info_dict': {
  18                 'id': 'AC3FFE1',
  19                 'ext': 'flv',
  20                 'title': 'Fucked in the ass while playing PS3',
  21                 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
  22                 'upload_date': '20100913',
  23                 'uploader_id': 'famouslyfuckedup',
  24                 'thumbnail': 'http://thumbs.motherlessmedia.com/thumbs/AC3FFE1.jpg',
  25                 'age_limit': 18,
  26             }
  27         },
  28         {
  29             'url': 'http://motherless.com/532291B',
  30             'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
  31             'info_dict': {
  32                 'id': '532291B',
  33                 'ext': 'mp4',
  34                 'title': 'Amazing girl playing the omegle game, PERFECT!',
  35                 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
  36                 'upload_date': '20140622',
  37                 'uploader_id': 'Sulivana7x',
  38                 'thumbnail': 'http://thumbs.motherlessmedia.com/thumbs/532291B.jpg',
  39                 'age_limit': 18,
  40             }
  41         }
  42     ]
  43
  44     def _real_extract(self,url):
  45         mobj = re.match(self._VALID_URL, url)
  46         video_id = mobj.group('id')
  47
  48         webpage = self._download_webpage(url, video_id)
  49
  50         title = self._html_search_regex(r'<title>(?P<title>.+?) - MOTHERLESS.COM</title>', webpage, 'title')
  51         video_url = self._search_regex(r"__fileurl = '(?P<video_url>[^']+)'", webpage, 'video_url')
  52         thumbnail = self._og_search_thumbnail(webpage)
  53         age_limit = self._rta_search(webpage)  # Hint: it's 18 ;)
  54         view_count = str_to_int(self._html_search_regex(r'<strong>Views</strong>(.+?)</h2>', webpage,
  55                                                         'view_count', flags=re.DOTALL))
  56
  57         like_count = str_to_int(self._html_search_regex(r'<strong>Favorited</strong>(.+?)</h2>', webpage,
  58                                                         'like_count', flags=re.DOTALL))
  59         comment_count = webpage.count('class="media-comment-contents"')
  60         uploader_id = self._html_search_regex(r'<div class="thumb-member-username">.*?<a [^>]*>(.+?)</a>',
  61                                               webpage, 'uploader_id', flags=re.DOTALL)
  62
  63         categories = self._html_search_meta('keywords', webpage)
  64         if categories is not None:
  65             categories = [cat.strip() for cat in categories.split(',')]
  66
  67         upload_date = self._html_search_regex(r'<strong>Uploaded</strong>(.+?)</h2>', webpage,
  68                                               'upload_date', flags=re.DOTALL)
  69         mobj = re.search(r'(\d+) days? ago', upload_date, re.I)
  70         if mobj is not None:
  71             upload_date = datetime.datetime.now() - datetime.timedelta(days=int(mobj.group(1)))
  72         else:
  73             mobj = re.search(r'(\w+) (\d+)\w* (\d+)', upload_date, re.I)
  74             if mobj is not None:
  75                 upload_date = datetime.datetime.strptime('%s %s %s' % mobj.groups(), '%b %d %Y').date()
  76             else:
  77                 upload_date = None
  78         if upload_date is not None:
  79             upload_date = upload_date.strftime('%Y%m%d')
  80
  81         return {
  82             'id': video_id,
  83             'title': title,
  84             'upload_date': upload_date,
  85             'uploader_id': uploader_id,
  86             'thumbnail': thumbnail,
  87             'categories': categories,
  88             'view_count': view_count,
  89             'like_count': like_count,
  90             'comment_count': comment_count,
  91             'age_limit': age_limit,
  92             'url': video_url,
  93         }