]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/spankbang.py
3 from .common
import InfoExtractor
17 class SpankBangIE(InfoExtractor
):
20 (?:[^/]+\.)?spankbang\.com/
22 (?P<id>[\da-z]+)/(?:video|play|embed)\b|
23 [\da-z]+-(?P<id_2>[\da-z]+)/playlist/[^/?#&]+
27 'url': 'https://spankbang.com/56b3d/video/the+slut+maker+hmv',
28 'md5': '2D13903DE4ECC7895B5D55930741650A',
32 'title': 'The Slut Maker HMV',
33 'description': 'Girls getting converted into cock slaves.',
34 'thumbnail': r
're:^https?://.*\.jpg$',
35 'uploader': 'Mindself',
36 'uploader_id': 'mindself',
37 'timestamp': 1617109572,
38 'upload_date': '20210330',
43 'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
44 'only_matching': True,
47 'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
48 'only_matching': True,
51 'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
52 'only_matching': True,
55 'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
56 'only_matching': True,
58 'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
59 'only_matching': True,
61 'url': 'https://m.spankbang.com/3vvn/play',
62 'only_matching': True,
64 'url': 'https://spankbang.com/2y3td/embed/',
65 'only_matching': True,
67 'url': 'https://spankbang.com/2v7ik-7ecbgu/playlist/latina+booty',
68 'only_matching': True,
71 def _real_extract(self
, url
):
72 mobj
= self
._match
_valid
_url
(url
)
73 video_id
= mobj
.group('id') or mobj
.group('id_2')
74 webpage
= self
._download
_webpage
(
75 url
.replace('/%s/embed' % video_id
, '/%s/video' % video_id
),
76 video_id
, headers
={'Cookie': 'country=US'}
)
78 if re
.search(r
'<[^>]+\b(?:id|class)=["\']video_removed
', webpage):
80 'Video
%s is not available
' % video_id, expected=True)
84 def extract_format(format_id, format_url):
85 f_url = url_or_none(format_url)
88 f = parse_resolution(format_id)
89 ext = determine_ext(f_url)
90 if format_id.startswith('m3u8
') or ext == 'm3u8
':
91 formats.extend(self._extract_m3u8_formats(
92 f_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
93 m3u8_id='hls
', fatal=False))
94 elif format_id.startswith('mpd
') or ext == 'mpd
':
95 formats.extend(self._extract_mpd_formats(
96 f_url, video_id, mpd_id='dash
', fatal=False))
97 elif ext == 'mp4
' or f.get('width
') or f.get('height
'):
100 'format_id
': format_id,
104 STREAM_URL_PREFIX = 'stream_url_
'
106 for mobj in re.finditer(
107 r'%s(?P
<id>[^\s
=]+)\s
*=\s
*(["\'])(?P<url>(?:(?!\2).)+)\2'
108 % STREAM_URL_PREFIX, webpage):
109 extract_format(mobj.group('id', 'url'))
112 stream_key = self._search_regex(
113 r'data-streamkey\s*=\s*(["\'])(?P
<value
>(?
:(?
!\
1).)+)\
1',
114 webpage, 'stream key
', group='value
')
116 stream = self._download_json(
117 'https
://spankbang
.com
/api
/videos
/stream
', video_id,
118 'Downloading stream JSON
', data=urlencode_postdata({
123 'X
-Requested
-With
': 'XMLHttpRequest
',
126 for format_id, format_url in stream.items():
127 if format_url and isinstance(format_url, list):
128 format_url = format_url[0]
129 extract_format(format_id, format_url)
131 self._sort_formats(formats)
133 info = self._search_json_ld(webpage, video_id, default={})
135 title = self._html_search_regex(
136 r'(?s
)<h1
[^
>]+\btitle
=["\']([^"]+)["\']>', webpage, 'title', default=None)
137 description = self._search_regex(
138 r'<div[^>]+\bclass=["\']bottom
[^
>]+>\s
*<p
>[^
<]*</p
>\s
*<p
>([^
<]+)',
139 webpage, 'description
', default=None)
140 thumbnail = self._og_search_thumbnail(webpage, default=None)
141 uploader = self._html_search_regex(
142 r'<svg
[^
>]+\bclass
="(?:[^"]*?user
[^
"]*?)">.*?
</svg
>([^
<]+)', webpage, 'uploader
', default=None)
143 uploader_id = self._html_search_regex(
144 r'<a
[^
>]+href
="/profile/([^"]+)"', webpage, 'uploader_id', default=None)
145 duration = parse_duration(self._search_regex(
146 r'<div[^>]+\bclass=["\']right_side
[^
>]+>\s
*<span
>([^
<]+)',
147 webpage, 'duration
', default=None))
148 view_count = str_to_int(self._search_regex(
149 r'([\d
,.]+)\s
+plays
', webpage, 'view count
', default=None))
151 age_limit = self._rta_search(webpage)
155 'title
': title or video_id,
156 'description
': description,
157 'thumbnail
': thumbnail,
158 'uploader
': uploader,
159 'uploader_id
': uploader_id,
160 'duration
': duration,
161 'view_count
': view_count,
163 'age_limit
': age_limit,
168 class SpankBangPlaylistIE(InfoExtractor):
169 _VALID_URL = r'https?
://(?
:[^
/]+\
.)?spankbang\
.com
/(?P
<id>[\da
-z
]+)/playlist
/(?P
<display_id
>[^
/]+)'
171 'url
': 'https
://spankbang
.com
/ug0k
/playlist
/big
+ass
+titties
',
174 'title
': 'Big Ass Titties
',
176 'playlist_mincount
': 40,
179 def _real_extract(self, url):
180 mobj = self._match_valid_url(url)
181 playlist_id = mobj.group('id')
182 display_id = mobj.group('display_id
')
184 webpage = self._download_webpage(
185 url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
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)]
194 title = self._html_search_regex(
195 r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
198 return self.playlist_result(entries, playlist_id, title)