youtube_dlc/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': 'http://spankbang.com/3vvn/video/fantasy+solo',
  30         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  31         'info_dict': {
  32             'id': '3vvn',
  33             'ext': 'mp4',
  34             'title': 'fantasy solo',
  35             'description': 'dillion harper masturbates on a bed',
  36             'thumbnail': r're:^https?://.*\.jpg$',
  37             'uploader': 'silly2587',
  38             'timestamp': 1422571989,
  39             'upload_date': '20150129',
  40             'age_limit': 18,
  41         }
  42     }, {
  43         # 480p only
  44         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  45         'only_matching': True,
  46     }, {
  47         # no uploader
  48         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  49         'only_matching': True,
  50     }, {
  51         # mobile page
  52         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  53         'only_matching': True,
  54     }, {
  55         # 4k
  56         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
  57         'only_matching': True,
  58     }, {
  59         'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
  60         'only_matching': True,
  61     }, {
  62         'url': 'https://m.spankbang.com/3vvn/play',
  63         'only_matching': True,
  64     }, {
  65         'url': 'https://spankbang.com/2y3td/embed/',
  66         'only_matching': True,
  67     }, {
  68         'url': 'https://spankbang.com/2v7ik-7ecbgu/playlist/latina+booty',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         video_id = mobj.group('id') or mobj.group('id_2')
  75         webpage = self._download_webpage(
  76             url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
  77             video_id, headers={'Cookie': 'country=US'})
  78
  79         if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
  80             raise ExtractorError(
  81                 'Video %s is not available' % video_id, expected=True)
  82
  83         formats = []
  84
  85         def extract_format(format_id, format_url):
  86             f_url = url_or_none(format_url)
  87             if not f_url:
  88                 return
  89             f = parse_resolution(format_id)
  90             ext = determine_ext(f_url)
  91             if format_id.startswith('m3u8') or ext == 'm3u8':
  92                 formats.extend(self._extract_m3u8_formats(
  93                     f_url, video_id, 'mp4', entry_protocol='m3u8_native',
  94                     m3u8_id='hls', fatal=False))
  95             elif format_id.startswith('mpd') or ext == 'mpd':
  96                 formats.extend(self._extract_mpd_formats(
  97                     f_url, video_id, mpd_id='dash', fatal=False))
  98             elif ext == 'mp4' or f.get('width') or f.get('height'):
  99                 f.update({
 100                     'url': f_url,
 101                     'format_id': format_id,
 102                 })
 103                 formats.append(f)
 104
 105         STREAM_URL_PREFIX = 'stream_url_'
 106
 107         for mobj in re.finditer(
 108                 r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
 109                 % STREAM_URL_PREFIX, 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         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
 133
 134         info = self._search_json_ld(webpage, video_id, default={})
 135
 136         title = self._html_search_regex(
 137             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)
 138         description = self._search_regex(
 139             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
 140             webpage, 'description', default=None)
 141         thumbnail = self._og_search_thumbnail(webpage, default=None)
 142         uploader = self._html_search_regex(
 143             (r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
 144              r'class="user"[^>]*><img[^>]+>([^<]+)'),
 145             webpage, 'uploader', default=None)
 146         duration = parse_duration(self._search_regex(
 147             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
 148             webpage, 'duration', default=None))
 149         view_count = str_to_int(self._search_regex(
 150             r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
 151
 152         age_limit = self._rta_search(webpage)
 153
 154         return merge_dicts({
 155             'id': video_id,
 156             'title': title or video_id,
 157             'description': description,
 158             'thumbnail': thumbnail,
 159             'uploader': uploader,
 160             'duration': duration,
 161             'view_count': view_count,
 162             'formats': formats,
 163             'age_limit': age_limit,
 164         }, info
 165         )
 166
 167
 168 class SpankBangPlaylistIE(InfoExtractor):
 169     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/(?P<display_id>[^/]+)'
 170     _TEST = {
 171         'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
 172         'info_dict': {
 173             'id': 'ug0k',
 174             'title': 'Big Ass Titties',
 175         },
 176         'playlist_mincount': 40,
 177     }
 178
 179     def _real_extract(self, url):
 180         mobj = re.match(self._VALID_URL, url)
 181         playlist_id = mobj.group('id')
 182         display_id = mobj.group('display_id')
 183
 184         webpage = self._download_webpage(
 185             url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
 186
 187         entries = [self.url_result(
 188             urljoin(url, mobj.group('path')),
 189             ie=SpankBangIE.ie_key(), video_id=mobj.group('id'))
 190             for mobj in re.finditer(
 191                 r'<a[^>]+\bhref=(["\'])(?P<path>/?[\da-z]+-(?P<id>[\da-z]+)/playlist/%s(?:(?!\1).)*)\1'
 192                 % re.escape(display_id), webpage)]
 193
 194         title = self._html_search_regex(
 195             r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
 196             fatal=False)
 197
 198         return self.playlist_result(entries, playlist_id, title)