_ 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 ..compat import compat_urlparse
   8 from ..utils import (
   9     ExtractorError,
  10     InAdvancePagedList,
  11     orderedSet,
  12     str_to_int,
  13     unified_strdate,
  14 )
  15
  16
  17 class MotherlessIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
  19     _TESTS = [{
  20         'url': 'http://motherless.com/AC3FFE1',
  21         'md5': '310f62e325a9fafe64f68c0bccb6e75f',
  22         'info_dict': {
  23             'id': 'AC3FFE1',
  24             'ext': 'mp4',
  25             'title': 'Fucked in the ass while playing PS3',
  26             'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
  27             'upload_date': '20100913',
  28             'uploader_id': 'famouslyfuckedup',
  29             'thumbnail': r're:https?://.*\.jpg',
  30             'age_limit': 18,
  31         }
  32     }, {
  33         'url': 'http://motherless.com/532291B',
  34         'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
  35         'info_dict': {
  36             'id': '532291B',
  37             'ext': 'mp4',
  38             'title': 'Amazing girl playing the omegle game, PERFECT!',
  39             'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
  40                            'game', 'hairy'],
  41             'upload_date': '20140622',
  42             'uploader_id': 'Sulivana7x',
  43             'thumbnail': r're:https?://.*\.jpg',
  44             'age_limit': 18,
  45         },
  46         'skip': '404',
  47     }, {
  48         'url': 'http://motherless.com/g/cosplay/633979F',
  49         'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
  50         'info_dict': {
  51             'id': '633979F',
  52             'ext': 'mp4',
  53             'title': 'Turtlette',
  54             'categories': ['superheroine heroine  superher'],
  55             'upload_date': '20140827',
  56             'uploader_id': 'shade0230',
  57             'thumbnail': r're:https?://.*\.jpg',
  58             'age_limit': 18,
  59         }
  60     }, {
  61         # no keywords
  62         'url': 'http://motherless.com/8B4BBC1',
  63         'only_matching': True,
  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         if '>The content you are trying to view is for friends only.' in webpage:
  76             raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
  77
  78         title = self._html_search_regex(
  79             (r'(?s)<div[^>]+\bclass=["\']media-meta-title[^>]+>(.+?)</div>',
  80              r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title')
  81         video_url = (self._html_search_regex(
  82             (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
  83              r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
  84             webpage, 'video URL', default=None, group='url')
  85             or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
  86         age_limit = self._rta_search(webpage)
  87         view_count = str_to_int(self._html_search_regex(
  88             (r'>(\d+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'),
  89             webpage, 'view count', fatal=False))
  90         like_count = str_to_int(self._html_search_regex(
  91             (r'>(\d+)\s+Favorites<', r'<strong>Favorited</strong>\s+([^<]+)<'),
  92             webpage, 'like count', fatal=False))
  93
  94         upload_date = self._html_search_regex(
  95             (r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<',
  96              r'<strong>Uploaded</strong>\s+([^<]+)<'), webpage, 'upload date')
  97         if 'Ago' in upload_date:
  98             days = int(re.search(r'([0-9]+)', upload_date).group(1))
  99             upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
 100         else:
 101             upload_date = unified_strdate(upload_date)
 102
 103         comment_count = webpage.count('class="media-comment-contents"')
 104         uploader_id = self._html_search_regex(
 105             r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
 106             webpage, 'uploader_id')
 107
 108         categories = self._html_search_meta('keywords', webpage, default=None)
 109         if categories:
 110             categories = [cat.strip() for cat in categories.split(',')]
 111
 112         return {
 113             'id': video_id,
 114             'title': title,
 115             'upload_date': upload_date,
 116             'uploader_id': uploader_id,
 117             'thumbnail': self._og_search_thumbnail(webpage),
 118             'categories': categories,
 119             'view_count': view_count,
 120             'like_count': like_count,
 121             'comment_count': comment_count,
 122             'age_limit': age_limit,
 123             'url': video_url,
 124         }
 125
 126
 127 class MotherlessGroupIE(InfoExtractor):
 128     _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
 129     _TESTS = [{
 130         'url': 'http://motherless.com/g/movie_scenes',
 131         'info_dict': {
 132             'id': 'movie_scenes',
 133             'title': 'Movie Scenes',
 134             'description': 'Hot and sexy scenes from "regular" movies... '
 135                            'Beautiful actresses fully nude... A looot of '
 136                            'skin! :)Enjoy!',
 137         },
 138         'playlist_mincount': 662,
 139     }, {
 140         'url': 'http://motherless.com/gv/sex_must_be_funny',
 141         'info_dict': {
 142             'id': 'sex_must_be_funny',
 143             'title': 'Sex must be funny',
 144             'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
 145                            'any kind!'
 146         },
 147         'playlist_mincount': 9,
 148     }]
 149
 150     @classmethod
 151     def suitable(cls, url):
 152         return (False if MotherlessIE.suitable(url)
 153                 else super(MotherlessGroupIE, cls).suitable(url))
 154
 155     def _extract_entries(self, webpage, base):
 156         entries = []
 157         for mobj in re.finditer(
 158                 r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
 159                 webpage):
 160             video_url = compat_urlparse.urljoin(base, mobj.group('href'))
 161             if not MotherlessIE.suitable(video_url):
 162                 continue
 163             video_id = MotherlessIE._match_id(video_url)
 164             title = mobj.group('title')
 165             entries.append(self.url_result(
 166                 video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
 167                 video_title=title))
 168         # Alternative fallback
 169         if not entries:
 170             entries = [
 171                 self.url_result(
 172                     compat_urlparse.urljoin(base, '/' + entry_id),
 173                     ie=MotherlessIE.ie_key(), video_id=entry_id)
 174                 for entry_id in orderedSet(re.findall(
 175                     r'data-codename=["\']([A-Z0-9]+)', webpage))]
 176         return entries
 177
 178     def _real_extract(self, url):
 179         group_id = self._match_id(url)
 180         page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
 181         webpage = self._download_webpage(page_url, group_id)
 182         title = self._search_regex(
 183             r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
 184         description = self._html_search_meta(
 185             'description', webpage, fatal=False)
 186         page_count = self._int(self._search_regex(
 187             r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
 188             webpage, 'page_count'), 'page_count')
 189         PAGE_SIZE = 80
 190
 191         def _get_page(idx):
 192             webpage = self._download_webpage(
 193                 page_url, group_id, query={'page': idx + 1},
 194                 note='Downloading page %d/%d' % (idx + 1, page_count)
 195             )
 196             for entry in self._extract_entries(webpage, url):
 197                 yield entry
 198
 199         playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 200
 201         return {
 202             '_type': 'playlist',
 203             'id': group_id,
 204             'title': title,
 205             'description': description,
 206             'entries': playlist
 207         }