youtube_dl/extractor/spankbang.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     orderedSet,
   9     parse_duration,
  10     parse_resolution,
  11     str_to_int,
  12     url_or_none,
  13     urlencode_postdata,
  14 )
  15
  16
  17 class SpankBangIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
  19     _TESTS = [{
  20         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
  21         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  22         'info_dict': {
  23             'id': '3vvn',
  24             'ext': 'mp4',
  25             'title': 'fantasy solo',
  26             'description': 'dillion harper masturbates on a bed',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'uploader': 'silly2587',
  29             'age_limit': 18,
  30         }
  31     }, {
  32         # 480p only
  33         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  34         'only_matching': True,
  35     }, {
  36         # no uploader
  37         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  38         'only_matching': True,
  39     }, {
  40         # mobile page
  41         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  42         'only_matching': True,
  43     }, {
  44         # 4k
  45         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
  46         'only_matching': True,
  47     }, {
  48         'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
  49         'only_matching': True,
  50     }, {
  51         'url': 'https://m.spankbang.com/3vvn/play',
  52         'only_matching': True,
  53     }, {
  54         'url': 'https://spankbang.com/2y3td/embed/',
  55         'only_matching': True,
  56     }]
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url)
  60         webpage = self._download_webpage(
  61             url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
  62             video_id, headers={'Cookie': 'country=US'})
  63
  64         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
  65             raise ExtractorError(
  66                 'Video %s is not available' % video_id, expected=True)
  67
  68         formats = []
  69
  70         def extract_format(format_id, format_url):
  71             f_url = url_or_none(format_url)
  72             if not f_url:
  73                 return
  74             f = parse_resolution(format_id)
  75             f.update({
  76                 'url': f_url,
  77                 'format_id': format_id,
  78             })
  79             formats.append(f)
  80
  81         STREAM_URL_PREFIX = 'stream_url_'
  82
  83         for mobj in re.finditer(
  84                 r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
  85                 % STREAM_URL_PREFIX, webpage):
  86             extract_format(mobj.group('id', 'url'))
  87
  88         if not formats:
  89             stream_key = self._search_regex(
  90                 r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  91                 webpage, 'stream key', group='value')
  92
  93             sb_csrf_session = self._get_cookies(
  94                 'https://spankbang.com')['sb_csrf_session'].value
  95
  96             stream = self._download_json(
  97                 'https://spankbang.com/api/videos/stream', video_id,
  98                 'Downloading stream JSON', data=urlencode_postdata({
  99                     'id': stream_key,
 100                     'data': 0,
 101                     'sb_csrf_session': sb_csrf_session,
 102                 }), headers={
 103                     'Referer': url,
 104                     'X-CSRFToken': sb_csrf_session,
 105                 })
 106
 107             for format_id, format_url in stream.items():
 108                 if format_id.startswith(STREAM_URL_PREFIX):
 109                     extract_format(
 110                         format_id[len(STREAM_URL_PREFIX):], format_url)
 111
 112         self._sort_formats(formats)
 113
 114         title = self._html_search_regex(
 115             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
 116         description = self._search_regex(
 117             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
 118             webpage, 'description', fatal=False)
 119         thumbnail = self._og_search_thumbnail(webpage)
 120         uploader = self._search_regex(
 121             r'class="user"[^>]*><img[^>]+>([^<]+)',
 122             webpage, 'uploader', default=None)
 123         duration = parse_duration(self._search_regex(
 124             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
 125             webpage, 'duration', fatal=False))
 126         view_count = str_to_int(self._search_regex(
 127             r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
 128
 129         age_limit = self._rta_search(webpage)
 130
 131         return {
 132             'id': video_id,
 133             'title': title,
 134             'description': description,
 135             'thumbnail': thumbnail,
 136             'uploader': uploader,
 137             'duration': duration,
 138             'view_count': view_count,
 139             'formats': formats,
 140             'age_limit': age_limit,
 141         }
 142
 143
 144 class SpankBangPlaylistIE(InfoExtractor):
 145     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
 146     _TEST = {
 147         'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
 148         'info_dict': {
 149             'id': 'ug0k',
 150             'title': 'Big Ass Titties',
 151         },
 152         'playlist_mincount': 50,
 153     }
 154
 155     def _real_extract(self, url):
 156         playlist_id = self._match_id(url)
 157
 158         webpage = self._download_webpage(
 159             url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
 160
 161         entries = [self.url_result(
 162             'https://spankbang.com/%s/video' % video_id,
 163             ie=SpankBangIE.ie_key(), video_id=video_id)
 164             for video_id in orderedSet(re.findall(
 165                 r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
 166
 167         title = self._html_search_regex(
 168             r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
 169             fatal=False)
 170
 171         return self.playlist_result(entries, playlist_id, title)