Raphaël G. Git Repositories - youtubedl/blob - 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     merge_dicts,
   9     orderedSet,
  10     parse_duration,
  11     parse_resolution,
  12     str_to_int,
  13     url_or_none,
  14     urlencode_postdata,
  15 )
  16
  17
  18 class SpankBangIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
  20     _TESTS = [{
  21         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
  22         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  23         'info_dict': {
  24             'id': '3vvn',
  25             'ext': 'mp4',
  26             'title': 'fantasy solo',
  27             'description': 'dillion harper masturbates on a bed',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29             'uploader': 'silly2587',
  30             'timestamp': 1422571989,
  31             'upload_date': '20150129',
  32             'age_limit': 18,
  33         }
  34     }, {
  35         # 480p only
  36         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  37         'only_matching': True,
  38     }, {
  39         # no uploader
  40         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  41         'only_matching': True,
  42     }, {
  43         # mobile page
  44         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  45         'only_matching': True,
  46     }, {
  47         # 4k
  48         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
  49         'only_matching': True,
  50     }, {
  51         'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
  52         'only_matching': True,
  53     }, {
  54         'url': 'https://m.spankbang.com/3vvn/play',
  55         'only_matching': True,
  56     }, {
  57         'url': 'https://spankbang.com/2y3td/embed/',
  58         'only_matching': True,
  59     }]
  60
  61     def _real_extract(self, url):
  62         video_id = self._match_id(url)
  63         webpage = self._download_webpage(
  64             url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
  65             video_id, headers={'Cookie': 'country=US'})
  66
  67         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
  68             raise ExtractorError(
  69                 'Video %s is not available' % video_id, expected=True)
  70
  71         formats = []
  72
  73         def extract_format(format_id, format_url):
  74             f_url = url_or_none(format_url)
  75             if not f_url:
  76                 return
  77             f = parse_resolution(format_id)
  78             f.update({
  79                 'url': f_url,
  80                 'format_id': format_id,
  81             })
  82             formats.append(f)
  83
  84         STREAM_URL_PREFIX = 'stream_url_'
  85
  86         for mobj in re.finditer(
  87                 r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
  88                 % STREAM_URL_PREFIX, webpage):
  89             extract_format(mobj.group('id', 'url'))
  90
  91         if not formats:
  92             stream_key = self._search_regex(
  93                 r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  94                 webpage, 'stream key', group='value')
  95
  96             sb_csrf_session = self._get_cookies(
  97                 'https://spankbang.com')['sb_csrf_session'].value
  98
  99             stream = self._download_json(
 100                 'https://spankbang.com/api/videos/stream', video_id,
 101                 'Downloading stream JSON', data=urlencode_postdata({
 102                     'id': stream_key,
 103                     'data': 0,
 104                     'sb_csrf_session': sb_csrf_session,
 105                 }), headers={
 106                     'Referer': url,
 107                     'X-CSRFToken': sb_csrf_session,
 108                 })
 109
 110             for format_id, format_url in stream.items():
 111                 if format_id.startswith(STREAM_URL_PREFIX):
 112                     if format_url and isinstance(format_url, list):
 113                         format_url = format_url[0]
 114                     extract_format(
 115                         format_id[len(STREAM_URL_PREFIX):], format_url)
 116
 117         self._sort_formats(formats)
 118
 119         info = self._search_json_ld(webpage, video_id, default={})
 120
 121         title = self._html_search_regex(
 122             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)
 123         description = self._search_regex(
 124             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
 125             webpage, 'description', default=None)
 126         thumbnail = self._og_search_thumbnail(webpage, default=None)
 127         uploader = self._html_search_regex(
 128             (r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
 129              r'class="user"[^>]*><img[^>]+>([^<]+)'),
 130             webpage, 'uploader', default=None)
 131         duration = parse_duration(self._search_regex(
 132             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
 133             webpage, 'duration', default=None))
 134         view_count = str_to_int(self._search_regex(
 135             r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
 136
 137         age_limit = self._rta_search(webpage)
 138
 139         return merge_dicts({
 140             'id': video_id,
 141             'title': title or video_id,
 142             'description': description,
 143             'thumbnail': thumbnail,
 144             'uploader': uploader,
 145             'duration': duration,
 146             'view_count': view_count,
 147             'formats': formats,
 148             'age_limit': age_limit,
 149         }, info
 150         )
 151
 152
 153 class SpankBangPlaylistIE(InfoExtractor):
 154     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
 155     _TEST = {
 156         'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
 157         'info_dict': {
 158             'id': 'ug0k',
 159             'title': 'Big Ass Titties',
 160         },
 161         'playlist_mincount': 50,
 162     }
 163
 164     def _real_extract(self, url):
 165         playlist_id = self._match_id(url)
 166
 167         webpage = self._download_webpage(
 168             url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
 169
 170         entries = [self.url_result(
 171             'https://spankbang.com/%s/video' % video_id,
 172             ie=SpankBangIE.ie_key(), video_id=video_id)
 173             for video_id in orderedSet(re.findall(
 174                 r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
 175
 176         title = self._html_search_regex(
 177             r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
 178             fatal=False)
 179
 180         return self.playlist_result(entries, playlist_id, title)