yt_dlp/extractor/spankbang.py

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