yt_dlp/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         # see https://motherless.com/videos/recent for recent videos with
  66         # uploaded date in "ago" format
  67         'url': 'https://motherless.com/3C3E2CF',
  68         'info_dict': {
  69             'id': '3C3E2CF',
  70             'ext': 'mp4',
  71             'title': 'a/ Hot Teens',
  72             'categories': list,
  73             'upload_date': '20210104',
  74             'uploader_id': 'yonbiw',
  75             'thumbnail': r're:https?://.*\.jpg',
  76             'age_limit': 18,
  77         },
  78         'params': {
  79             'skip_download': True,
  80         },
  81     }]
  82
  83     def _real_extract(self, url):
  84         video_id = self._match_id(url)
  85         webpage = self._download_webpage(url, video_id)
  86
  87         if any(p in webpage for p in (
  88                 '<title>404 - MOTHERLESS.COM<',
  89                 ">The page you're looking for cannot be found.<")):
  90             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  91
  92         if '>The content you are trying to view is for friends only.' in webpage:
  93             raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
  94
  95         title = self._html_search_regex(
  96             (r'(?s)<div[^>]+\bclass=["\']media-meta-title[^>]+>(.+?)</div>',
  97              r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title')
  98         video_url = (self._html_search_regex(
  99             (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
 100              r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
 101             webpage, 'video URL', default=None, group='url')
 102             or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
 103         age_limit = self._rta_search(webpage)
 104         view_count = str_to_int(self._html_search_regex(
 105             (r'>([\d,.]+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'),
 106             webpage, 'view count', fatal=False))
 107         like_count = str_to_int(self._html_search_regex(
 108             (r'>([\d,.]+)\s+Favorites<',
 109              r'<strong>Favorited</strong>\s+([^<]+)<'),
 110             webpage, 'like count', fatal=False))
 111
 112         upload_date = unified_strdate(self._search_regex(
 113             r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<', webpage,
 114             'upload date', default=None))
 115         if not upload_date:
 116             uploaded_ago = self._search_regex(
 117                 r'>\s*(\d+[hd])\s+[aA]go\b', webpage, 'uploaded ago',
 118                 default=None)
 119             if uploaded_ago:
 120                 delta = int(uploaded_ago[:-1])
 121                 _AGO_UNITS = {
 122                     'h': 'hours',
 123                     'd': 'days',
 124                 }
 125                 kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
 126                 upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
 127
 128         comment_count = webpage.count('class="media-comment-contents"')
 129         uploader_id = self._html_search_regex(
 130             (r'"media-meta-member">\s+<a href="/m/([^"]+)"',
 131              r'<span\b[^>]+\bclass="username">([^<]+)</span>'),
 132             webpage, 'uploader_id', fatal=False)
 133         categories = self._html_search_meta('keywords', webpage, default=None)
 134         if categories:
 135             categories = [cat.strip() for cat in categories.split(',')]
 136
 137         return {
 138             'id': video_id,
 139             'title': title,
 140             'upload_date': upload_date,
 141             'uploader_id': uploader_id,
 142             'thumbnail': self._og_search_thumbnail(webpage),
 143             'categories': categories,
 144             'view_count': view_count,
 145             'like_count': like_count,
 146             'comment_count': comment_count,
 147             'age_limit': age_limit,
 148             'url': video_url,
 149         }
 150
 151
 152 class MotherlessGroupIE(InfoExtractor):
 153     _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
 154     _TESTS = [{
 155         'url': 'http://motherless.com/g/movie_scenes',
 156         'info_dict': {
 157             'id': 'movie_scenes',
 158             'title': 'Movie Scenes',
 159             'description': 'Hot and sexy scenes from "regular" movies... '
 160                            'Beautiful actresses fully nude... A looot of '
 161                            'skin! :)Enjoy!',
 162         },
 163         'playlist_mincount': 662,
 164     }, {
 165         'url': 'http://motherless.com/gv/sex_must_be_funny',
 166         'info_dict': {
 167             'id': 'sex_must_be_funny',
 168             'title': 'Sex must be funny',
 169             'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
 170                            'any kind!'
 171         },
 172         'playlist_mincount': 0,
 173         'expected_warnings': [
 174             'This group has no videos.',
 175         ]
 176     }, {
 177         'url': 'https://motherless.com/g/beautiful_cock',
 178         'info_dict': {
 179             'id': 'beautiful_cock',
 180             'title': 'Beautiful Cock',
 181             'description': 'Group for lovely cocks yours, mine, a friends anything human',
 182         },
 183         'playlist_mincount': 2500,
 184     }]
 185
 186     @classmethod
 187     def suitable(cls, url):
 188         return (False if MotherlessIE.suitable(url)
 189                 else super(MotherlessGroupIE, cls).suitable(url))
 190
 191     def _extract_entries(self, webpage, base):
 192         entries = []
 193         for mobj in re.finditer(
 194                 r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
 195                 webpage):
 196             video_url = compat_urlparse.urljoin(base, mobj.group('href'))
 197             if not MotherlessIE.suitable(video_url):
 198                 continue
 199             video_id = MotherlessIE._match_id(video_url)
 200             title = mobj.group('title')
 201             entries.append(self.url_result(
 202                 video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
 203                 video_title=title))
 204         # Alternative fallback
 205         if not entries:
 206             entries = [
 207                 self.url_result(
 208                     compat_urlparse.urljoin(base, '/' + entry_id),
 209                     ie=MotherlessIE.ie_key(), video_id=entry_id)
 210                 for entry_id in orderedSet(re.findall(
 211                     r'data-codename=["\']([A-Z0-9]+)', webpage))]
 212         return entries
 213
 214     def _real_extract(self, url):
 215         group_id = self._match_id(url)
 216         page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
 217         webpage = self._download_webpage(page_url, group_id)
 218         title = self._search_regex(
 219             r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
 220         description = self._html_search_meta(
 221             'description', webpage, fatal=False)
 222         page_count = self._int(self._search_regex(
 223             r'(\d+)</(?:a|span)><(?:a|span)[^>]+rel="next">',
 224             webpage, 'page_count', default=0), 'page_count')
 225         if not page_count:
 226             message = self._search_regex(
 227                 r'class="error-page"[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*',
 228                 webpage, 'error_msg', default=None) or 'This group has no videos.'
 229             self.report_warning(message, group_id)
 230         PAGE_SIZE = 80
 231
 232         def _get_page(idx):
 233             if not page_count:
 234                 return
 235             webpage = self._download_webpage(
 236                 page_url, group_id, query={'page': idx + 1},
 237                 note='Downloading page %d/%d' % (idx + 1, page_count)
 238             )
 239             for entry in self._extract_entries(webpage, url):
 240                 yield entry
 241
 242         playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 243
 244         return {
 245             '_type': 'playlist',
 246             'id': group_id,
 247             'title': title,
 248             'description': description,
 249             'entries': playlist
 250         }