yt_dlp/extractor/spankbang.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9     merge_dicts,
  10     parse_duration,
  11     parse_resolution,
  12     str_to_int,
  13     url_or_none,
  14     urlencode_postdata,
  15     urljoin,
  16 )
  17
  18
  19 class SpankBangIE(InfoExtractor):
  20     _VALID_URL = r'''(?x)
  21                     https?://
  22                         (?:[^/]+\.)?spankbang\.com/
  23                         (?:
  24                             (?P<id>[\da-z]+)/(?:video|play|embed)\b|
  25                             [\da-z]+-(?P<id_2>[\da-z]+)/playlist/[^/?#&]+
  26                         )
  27                     '''
  28     _TESTS = [{
  29         'url': 'https://spankbang.com/56b3d/video/the+slut+maker+hmv',
  30         'md5': '2D13903DE4ECC7895B5D55930741650A',
  31         'info_dict': {
  32             'id': '56b3d',
  33             'ext': 'mp4',
  34             'title': 'The Slut Maker HMV',
  35             'description': 'Girls getting converted into cock slaves.',
  36             'thumbnail': r're:^https?://.*\.jpg$',
  37             'uploader': 'Mindself',
  38             'uploader_id': 'mindself',
  39             'timestamp': 1617109572,
  40             'upload_date': '20210330',
  41             'age_limit': 18,
  42         }
  43     }, {
  44         # 480p only
  45         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  46         'only_matching': True,
  47     }, {
  48         # no uploader
  49         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  50         'only_matching': True,
  51     }, {
  52         # mobile page
  53         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  54         'only_matching': True,
  55     }, {
  56         # 4k
  57         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
  58         'only_matching': True,
  59     }, {
  60         'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
  61         'only_matching': True,
  62     }, {
  63         'url': 'https://m.spankbang.com/3vvn/play',
  64         'only_matching': True,
  65     }, {
  66         'url': 'https://spankbang.com/2y3td/embed/',
  67         'only_matching': True,
  68     }, {
  69         'url': 'https://spankbang.com/2v7ik-7ecbgu/playlist/latina+booty',
  70         'only_matching': True,
  71     }]
  72
  73     def _real_extract(self, url):
  74         mobj = self._match_valid_url(url)
  75         video_id = mobj.group('id') or mobj.group('id_2')
  76         webpage = self._download_webpage(
  77             url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
  78             video_id, headers={'Cookie': 'country=US'})
  79
  80         if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
  81             raise ExtractorError(
  82                 'Video %s is not available' % video_id, expected=True)
  83
  84         formats = []
  85
  86         def extract_format(format_id, format_url):
  87             f_url = url_or_none(format_url)
  88             if not f_url:
  89                 return
  90             f = parse_resolution(format_id)
  91             ext = determine_ext(f_url)
  92             if format_id.startswith('m3u8') or ext == 'm3u8':
  93                 formats.extend(self._extract_m3u8_formats(
  94                     f_url, video_id, 'mp4', entry_protocol='m3u8_native',
  95                     m3u8_id='hls', fatal=False))
  96             elif format_id.startswith('mpd') or ext == 'mpd':
  97                 formats.extend(self._extract_mpd_formats(
  98                     f_url, video_id, mpd_id='dash', fatal=False))
  99             elif ext == 'mp4' or f.get('width') or f.get('height'):
 100                 f.update({
 101                     'url': f_url,
 102                     'format_id': format_id,
 103                 })
 104                 formats.append(f)
 105
 106         STREAM_URL_PREFIX = 'stream_url_'
 107
 108         for mobj in re.finditer(
 109                 r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
 110                 % STREAM_URL_PREFIX, webpage):
 111             extract_format(mobj.group('id', 'url'))
 112
 113         if not formats:
 114             stream_key = self._search_regex(
 115                 r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
 116                 webpage, 'stream key', group='value')
 117
 118             stream = self._download_json(
 119                 'https://spankbang.com/api/videos/stream', video_id,
 120                 'Downloading stream JSON', data=urlencode_postdata({
 121                     'id': stream_key,
 122                     'data': 0,
 123                 }), headers={
 124                     'Referer': url,
 125                     'X-Requested-With': 'XMLHttpRequest',
 126                 })
 127
 128             for format_id, format_url in stream.items():
 129                 if format_url and isinstance(format_url, list):
 130                     format_url = format_url[0]
 131                 extract_format(format_id, format_url)
 132
 133         self._sort_formats(formats)
 134
 135         info = self._search_json_ld(webpage, video_id, default={})
 136
 137         title = self._html_search_regex(
 138             r'(?s)<h1[^>]+\btitle=["\']([^"]+)["\']>', webpage, 'title', default=None)
 139         description = self._search_regex(
 140             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
 141             webpage, 'description', default=None)
 142         thumbnail = self._og_search_thumbnail(webpage, default=None)
 143         uploader = self._html_search_regex(
 144             r'<svg[^>]+\bclass="(?:[^"]*?user[^"]*?)">.*?</svg>([^<]+)', webpage, 'uploader', default=None)
 145         uploader_id = self._html_search_regex(
 146             r'<a[^>]+href="/profile/([^"]+)"', webpage, 'uploader_id', default=None)
 147         duration = parse_duration(self._search_regex(
 148             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
 149             webpage, 'duration', default=None))
 150         view_count = str_to_int(self._search_regex(
 151             r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
 152
 153         age_limit = self._rta_search(webpage)
 154
 155         return merge_dicts({
 156             'id': video_id,
 157             'title': title or video_id,
 158             'description': description,
 159             'thumbnail': thumbnail,
 160             'uploader': uploader,
 161             'uploader_id': uploader_id,
 162             'duration': duration,
 163             'view_count': view_count,
 164             'formats': formats,
 165             'age_limit': age_limit,
 166         }, info
 167         )
 168
 169
 170 class SpankBangPlaylistIE(InfoExtractor):
 171     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/(?P<display_id>[^/]+)'
 172     _TEST = {
 173         'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
 174         'info_dict': {
 175             'id': 'ug0k',
 176             'title': 'Big Ass Titties',
 177         },
 178         'playlist_mincount': 40,
 179     }
 180
 181     def _real_extract(self, url):
 182         mobj = self._match_valid_url(url)
 183         playlist_id = mobj.group('id')
 184         display_id = mobj.group('display_id')
 185
 186         webpage = self._download_webpage(
 187             url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
 188
 189         entries = [self.url_result(
 190             urljoin(url, mobj.group('path')),
 191             ie=SpankBangIE.ie_key(), video_id=mobj.group('id'))
 192             for mobj in re.finditer(
 193                 r'<a[^>]+\bhref=(["\'])(?P<path>/?[\da-z]+-(?P<id>[\da-z]+)/playlist/%s(?:(?!\1).)*)\1'
 194                 % re.escape(display_id), webpage)]
 195
 196         title = self._html_search_regex(
 197             r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
 198             fatal=False)
 199
 200         return self.playlist_result(entries, playlist_id, title)