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     determine_ext,
   8     ExtractorError,
   9     merge_dicts,
  10     orderedSet,
  11     parse_duration,
  12     parse_resolution,
  13     str_to_int,
  14     url_or_none,
  15     urlencode_postdata,
  16 )
  17
  18
  19 class SpankBangIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
  21     _TESTS = [{
  22         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
  23         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  24         'info_dict': {
  25             'id': '3vvn',
  26             'ext': 'mp4',
  27             'title': 'fantasy solo',
  28             'description': 'dillion harper masturbates on a bed',
  29             'thumbnail': r're:^https?://.*\.jpg$',
  30             'uploader': 'silly2587',
  31             'timestamp': 1422571989,
  32             'upload_date': '20150129',
  33             'age_limit': 18,
  34         }
  35     }, {
  36         # 480p only
  37         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  38         'only_matching': True,
  39     }, {
  40         # no uploader
  41         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  42         'only_matching': True,
  43     }, {
  44         # mobile page
  45         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  46         'only_matching': True,
  47     }, {
  48         # 4k
  49         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
  50         'only_matching': True,
  51     }, {
  52         'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
  53         'only_matching': True,
  54     }, {
  55         'url': 'https://m.spankbang.com/3vvn/play',
  56         'only_matching': True,
  57     }, {
  58         'url': 'https://spankbang.com/2y3td/embed/',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         video_id = self._match_id(url)
  64         webpage = self._download_webpage(
  65             url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
  66             video_id, headers={'Cookie': 'country=US'})
  67
  68         if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
  69             raise ExtractorError(
  70                 'Video %s is not available' % video_id, expected=True)
  71
  72         formats = []
  73
  74         def extract_format(format_id, format_url):
  75             f_url = url_or_none(format_url)
  76             if not f_url:
  77                 return
  78             f = parse_resolution(format_id)
  79             ext = determine_ext(f_url)
  80             if format_id.startswith('m3u8') or ext == 'm3u8':
  81                 formats.extend(self._extract_m3u8_formats(
  82                     f_url, video_id, 'mp4', entry_protocol='m3u8_native',
  83                     m3u8_id='hls', fatal=False))
  84             elif format_id.startswith('mpd') or ext == 'mpd':
  85                 formats.extend(self._extract_mpd_formats(
  86                     f_url, video_id, mpd_id='dash', fatal=False))
  87             elif ext == 'mp4' or f.get('width') or f.get('height'):
  88                 f.update({
  89                     'url': f_url,
  90                     'format_id': format_id,
  91                 })
  92                 formats.append(f)
  93
  94         STREAM_URL_PREFIX = 'stream_url_'
  95
  96         for mobj in re.finditer(
  97                 r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
  98                 % STREAM_URL_PREFIX, webpage):
  99             extract_format(mobj.group('id', 'url'))
 100
 101         if not formats:
 102             stream_key = self._search_regex(
 103                 r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
 104                 webpage, 'stream key', group='value')
 105
 106             stream = self._download_json(
 107                 'https://spankbang.com/api/videos/stream', video_id,
 108                 'Downloading stream JSON', data=urlencode_postdata({
 109                     'id': stream_key,
 110                     'data': 0,
 111                 }), headers={
 112                     'Referer': url,
 113                     'X-Requested-With': 'XMLHttpRequest',
 114                 })
 115
 116             for format_id, format_url in stream.items():
 117                 if format_url and isinstance(format_url, list):
 118                     format_url = format_url[0]
 119                 extract_format(format_id, format_url)
 120
 121         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
 122
 123         info = self._search_json_ld(webpage, video_id, default={})
 124
 125         title = self._html_search_regex(
 126             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)
 127         description = self._search_regex(
 128             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
 129             webpage, 'description', default=None)
 130         thumbnail = self._og_search_thumbnail(webpage, default=None)
 131         uploader = self._html_search_regex(
 132             (r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
 133              r'class="user"[^>]*><img[^>]+>([^<]+)'),
 134             webpage, 'uploader', default=None)
 135         duration = parse_duration(self._search_regex(
 136             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
 137             webpage, 'duration', default=None))
 138         view_count = str_to_int(self._search_regex(
 139             r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
 140
 141         age_limit = self._rta_search(webpage)
 142
 143         return merge_dicts({
 144             'id': video_id,
 145             'title': title or video_id,
 146             'description': description,
 147             'thumbnail': thumbnail,
 148             'uploader': uploader,
 149             'duration': duration,
 150             'view_count': view_count,
 151             'formats': formats,
 152             'age_limit': age_limit,
 153         }, info
 154         )
 155
 156
 157 class SpankBangPlaylistIE(InfoExtractor):
 158     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
 159     _TEST = {
 160         'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
 161         'info_dict': {
 162             'id': 'ug0k',
 163             'title': 'Big Ass Titties',
 164         },
 165         'playlist_mincount': 50,
 166     }
 167
 168     def _real_extract(self, url):
 169         playlist_id = self._match_id(url)
 170
 171         webpage = self._download_webpage(
 172             url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
 173
 174         entries = [self.url_result(
 175             'https://spankbang.com/%s/video' % video_id,
 176             ie=SpankBangIE.ie_key(), video_id=video_id)
 177             for video_id in orderedSet(re.findall(
 178                 r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
 179
 180         title = self._html_search_regex(
 181             r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
 182             fatal=False)
 183
 184         return self.playlist_result(entries, playlist_id, title)