_ 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 (
   8     ExtractorError,
   9     str_to_int,
  10     unified_strdate,
  11 )
  12
  13
  14 class MotherlessIE(InfoExtractor):
  15     _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
  16     _TESTS = [
  17         {
  18             'url': 'http://motherless.com/AC3FFE1',
  19             'md5': '310f62e325a9fafe64f68c0bccb6e75f',
  20             'info_dict': {
  21                 'id': 'AC3FFE1',
  22                 'ext': 'mp4',
  23                 'title': 'Fucked in the ass while playing PS3',
  24                 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
  25                 'upload_date': '20100913',
  26                 'uploader_id': 'famouslyfuckedup',
  27                 'thumbnail': 're:http://.*\.jpg',
  28                 'age_limit': 18,
  29             }
  30         },
  31         {
  32             'url': 'http://motherless.com/532291B',
  33             'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
  34             'info_dict': {
  35                 'id': '532291B',
  36                 'ext': 'mp4',
  37                 'title': 'Amazing girl playing the omegle game, PERFECT!',
  38                 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
  39                 'upload_date': '20140622',
  40                 'uploader_id': 'Sulivana7x',
  41                 'thumbnail': 're:http://.*\.jpg',
  42                 'age_limit': 18,
  43             }
  44         },
  45         {
  46             'url': 'http://motherless.com/g/cosplay/633979F',
  47             'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
  48             'info_dict': {
  49                 'id': '633979F',
  50                 'ext': 'mp4',
  51                 'title': 'Turtlette',
  52                 'categories': ['superheroine heroine  superher'],
  53                 'upload_date': '20140827',
  54                 'uploader_id': 'shade0230',
  55                 'thumbnail': 're:http://.*\.jpg',
  56                 'age_limit': 18,
  57             }
  58         },
  59         {
  60             # no keywords
  61             'url': 'http://motherless.com/8B4BBC1',
  62             'only_matching': True,
  63         }
  64     ]
  65
  66     def _real_extract(self, url):
  67         video_id = self._match_id(url)
  68         webpage = self._download_webpage(url, video_id)
  69
  70         if any(p in webpage for p in (
  71                 '<title>404 - MOTHERLESS.COM<',
  72                 ">The page you're looking for cannot be found.<")):
  73             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  74
  75         title = self._html_search_regex(
  76             r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
  77         video_url = self._html_search_regex(
  78             r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL')
  79         age_limit = self._rta_search(webpage)
  80         view_count = str_to_int(self._html_search_regex(
  81             r'<strong>Views</strong>\s+([^<]+)<',
  82             webpage, 'view count', fatal=False))
  83         like_count = str_to_int(self._html_search_regex(
  84             r'<strong>Favorited</strong>\s+([^<]+)<',
  85             webpage, 'like count', fatal=False))
  86
  87         upload_date = self._html_search_regex(
  88             r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
  89         if 'Ago' in upload_date:
  90             days = int(re.search(r'([0-9]+)', upload_date).group(1))
  91             upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
  92         else:
  93             upload_date = unified_strdate(upload_date)
  94
  95         comment_count = webpage.count('class="media-comment-contents"')
  96         uploader_id = self._html_search_regex(
  97             r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
  98             webpage, 'uploader_id')
  99
 100         categories = self._html_search_meta('keywords', webpage, default=None)
 101         if categories:
 102             categories = [cat.strip() for cat in categories.split(',')]
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'upload_date': upload_date,
 108             'uploader_id': uploader_id,
 109             'thumbnail': self._og_search_thumbnail(webpage),
 110             'categories': categories,
 111             'view_count': view_count,
 112             'like_count': like_count,
 113             'comment_count': comment_count,
 114             'age_limit': age_limit,
 115             'url': video_url,
 116         }