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