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