2015-04-05 15:50:21 -04:00
|
|
|
import re
|
|
|
|
|
2015-04-06 11:24:17 -04:00
|
|
|
from .common import InfoExtractor
|
2018-03-02 11:39:20 -05:00
|
|
|
from ..utils import (
|
|
|
|
ExtractorError,
|
2024-05-26 15:27:21 -04:00
|
|
|
determine_ext,
|
2019-07-13 13:21:39 -04:00
|
|
|
merge_dicts,
|
2018-03-02 11:39:20 -05:00
|
|
|
parse_duration,
|
|
|
|
parse_resolution,
|
|
|
|
str_to_int,
|
2019-03-02 18:25:45 -05:00
|
|
|
url_or_none,
|
|
|
|
urlencode_postdata,
|
2021-01-01 07:26:37 -05:00
|
|
|
urljoin,
|
2018-03-02 11:39:20 -05:00
|
|
|
)
|
2015-04-06 11:24:17 -04:00
|
|
|
|
|
|
|
|
2015-04-05 15:50:21 -04:00
|
|
|
class SpankBangIE(InfoExtractor):
|
2021-01-01 07:26:37 -05:00
|
|
|
_VALID_URL = r'''(?x)
|
|
|
|
https?://
|
|
|
|
(?:[^/]+\.)?spankbang\.com/
|
|
|
|
(?:
|
|
|
|
(?P<id>[\da-z]+)/(?:video|play|embed)\b|
|
|
|
|
[\da-z]+-(?P<id_2>[\da-z]+)/playlist/[^/?#&]+
|
|
|
|
)
|
|
|
|
'''
|
2016-02-05 11:16:56 -05:00
|
|
|
_TESTS = [{
|
2021-09-23 21:06:30 -04:00
|
|
|
'url': 'https://spankbang.com/56b3d/video/the+slut+maker+hmv',
|
|
|
|
'md5': '2D13903DE4ECC7895B5D55930741650A',
|
2015-04-06 11:24:17 -04:00
|
|
|
'info_dict': {
|
2021-09-23 21:06:30 -04:00
|
|
|
'id': '56b3d',
|
2015-04-06 11:24:17 -04:00
|
|
|
'ext': 'mp4',
|
2021-09-23 21:06:30 -04:00
|
|
|
'title': 'The Slut Maker HMV',
|
|
|
|
'description': 'Girls getting converted into cock slaves.',
|
2017-01-02 07:08:07 -05:00
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2021-09-23 21:06:30 -04:00
|
|
|
'uploader': 'Mindself',
|
|
|
|
'uploader_id': 'mindself',
|
|
|
|
'timestamp': 1617109572,
|
|
|
|
'upload_date': '20210330',
|
2015-04-06 11:24:17 -04:00
|
|
|
'age_limit': 18,
|
2024-06-11 19:09:58 -04:00
|
|
|
},
|
2016-02-05 11:16:56 -05:00
|
|
|
}, {
|
|
|
|
# 480p only
|
|
|
|
'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
|
|
|
|
'only_matching': True,
|
2017-02-20 12:54:43 -05:00
|
|
|
}, {
|
|
|
|
# no uploader
|
|
|
|
'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
|
|
|
|
'only_matching': True,
|
2017-11-16 13:05:04 -05:00
|
|
|
}, {
|
|
|
|
# mobile page
|
|
|
|
'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
|
|
|
|
'only_matching': True,
|
2018-03-02 11:39:20 -05:00
|
|
|
}, {
|
|
|
|
# 4k
|
|
|
|
'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
|
|
|
|
'only_matching': True,
|
2019-02-07 11:57:58 -05:00
|
|
|
}, {
|
|
|
|
'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
|
|
|
|
'only_matching': True,
|
|
|
|
}, {
|
|
|
|
'url': 'https://m.spankbang.com/3vvn/play',
|
|
|
|
'only_matching': True,
|
|
|
|
}, {
|
|
|
|
'url': 'https://spankbang.com/2y3td/embed/',
|
|
|
|
'only_matching': True,
|
2021-01-01 07:26:37 -05:00
|
|
|
}, {
|
|
|
|
'url': 'https://spankbang.com/2v7ik-7ecbgu/playlist/latina+booty',
|
|
|
|
'only_matching': True,
|
2016-02-05 11:16:56 -05:00
|
|
|
}]
|
2015-04-05 15:50:21 -04:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2021-08-18 21:41:24 -04:00
|
|
|
mobj = self._match_valid_url(url)
|
2021-01-01 07:26:37 -05:00
|
|
|
video_id = mobj.group('id') or mobj.group('id_2')
|
2024-11-16 14:48:47 -05:00
|
|
|
country = self.get_param('geo_bypass_country') or 'US'
|
|
|
|
self._set_cookie('.spankbang.com', 'country', country.upper())
|
2019-02-07 11:57:58 -05:00
|
|
|
webpage = self._download_webpage(
|
2024-06-11 19:09:58 -04:00
|
|
|
url.replace(f'/{video_id}/embed', f'/{video_id}/video'),
|
2024-11-16 14:48:47 -05:00
|
|
|
video_id, impersonate=True)
|
2015-04-05 15:50:21 -04:00
|
|
|
|
2019-12-31 10:18:01 -05:00
|
|
|
if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
|
2017-10-31 12:05:25 -04:00
|
|
|
raise ExtractorError(
|
2024-06-11 19:09:58 -04:00
|
|
|
f'Video {video_id} is not available', expected=True)
|
2017-10-31 12:05:25 -04:00
|
|
|
|
2018-03-02 11:39:20 -05:00
|
|
|
formats = []
|
2019-03-02 18:25:45 -05:00
|
|
|
|
|
|
|
def extract_format(format_id, format_url):
|
|
|
|
f_url = url_or_none(format_url)
|
|
|
|
if not f_url:
|
|
|
|
return
|
2018-03-02 11:39:20 -05:00
|
|
|
f = parse_resolution(format_id)
|
2019-12-31 10:16:39 -05:00
|
|
|
ext = determine_ext(f_url)
|
|
|
|
if format_id.startswith('m3u8') or ext == 'm3u8':
|
|
|
|
formats.extend(self._extract_m3u8_formats(
|
|
|
|
f_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
|
|
|
m3u8_id='hls', fatal=False))
|
|
|
|
elif format_id.startswith('mpd') or ext == 'mpd':
|
|
|
|
formats.extend(self._extract_mpd_formats(
|
|
|
|
f_url, video_id, mpd_id='dash', fatal=False))
|
|
|
|
elif ext == 'mp4' or f.get('width') or f.get('height'):
|
|
|
|
f.update({
|
|
|
|
'url': f_url,
|
|
|
|
'format_id': format_id,
|
|
|
|
})
|
|
|
|
formats.append(f)
|
2019-03-02 18:25:45 -05:00
|
|
|
|
|
|
|
STREAM_URL_PREFIX = 'stream_url_'
|
|
|
|
|
|
|
|
for mobj in re.finditer(
|
2024-06-11 19:09:58 -04:00
|
|
|
rf'{STREAM_URL_PREFIX}(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2', webpage):
|
2019-03-02 18:25:45 -05:00
|
|
|
extract_format(mobj.group('id', 'url'))
|
|
|
|
|
|
|
|
if not formats:
|
|
|
|
stream_key = self._search_regex(
|
|
|
|
r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
|
|
|
|
webpage, 'stream key', group='value')
|
|
|
|
|
|
|
|
stream = self._download_json(
|
|
|
|
'https://spankbang.com/api/videos/stream', video_id,
|
|
|
|
'Downloading stream JSON', data=urlencode_postdata({
|
|
|
|
'id': stream_key,
|
|
|
|
'data': 0,
|
|
|
|
}), headers={
|
|
|
|
'Referer': url,
|
2019-12-31 10:16:39 -05:00
|
|
|
'X-Requested-With': 'XMLHttpRequest',
|
2019-03-02 18:25:45 -05:00
|
|
|
})
|
|
|
|
|
|
|
|
for format_id, format_url in stream.items():
|
2019-12-31 10:16:39 -05:00
|
|
|
if format_url and isinstance(format_url, list):
|
|
|
|
format_url = format_url[0]
|
|
|
|
extract_format(format_id, format_url)
|
2019-03-02 18:25:45 -05:00
|
|
|
|
2019-07-13 13:21:39 -04:00
|
|
|
info = self._search_json_ld(webpage, video_id, default={})
|
|
|
|
|
2015-04-06 11:24:17 -04:00
|
|
|
title = self._html_search_regex(
|
2021-09-23 21:06:30 -04:00
|
|
|
r'(?s)<h1[^>]+\btitle=["\']([^"]+)["\']>', webpage, 'title', default=None)
|
2018-03-02 11:39:20 -05:00
|
|
|
description = self._search_regex(
|
|
|
|
r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
|
2019-07-13 13:21:39 -04:00
|
|
|
webpage, 'description', default=None)
|
|
|
|
thumbnail = self._og_search_thumbnail(webpage, default=None)
|
|
|
|
uploader = self._html_search_regex(
|
2021-09-23 21:06:30 -04:00
|
|
|
r'<svg[^>]+\bclass="(?:[^"]*?user[^"]*?)">.*?</svg>([^<]+)', webpage, 'uploader', default=None)
|
|
|
|
uploader_id = self._html_search_regex(
|
|
|
|
r'<a[^>]+href="/profile/([^"]+)"', webpage, 'uploader_id', default=None)
|
2018-03-02 11:39:20 -05:00
|
|
|
duration = parse_duration(self._search_regex(
|
|
|
|
r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
|
2019-07-13 13:21:39 -04:00
|
|
|
webpage, 'duration', default=None))
|
2018-03-02 11:39:20 -05:00
|
|
|
view_count = str_to_int(self._search_regex(
|
2019-07-13 13:21:39 -04:00
|
|
|
r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
|
2015-04-06 11:24:17 -04:00
|
|
|
|
|
|
|
age_limit = self._rta_search(webpage)
|
2015-04-05 15:50:21 -04:00
|
|
|
|
2019-07-13 13:21:39 -04:00
|
|
|
return merge_dicts({
|
2015-04-06 11:24:17 -04:00
|
|
|
'id': video_id,
|
2019-07-13 13:21:39 -04:00
|
|
|
'title': title or video_id,
|
2015-04-06 11:24:17 -04:00
|
|
|
'description': description,
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
'uploader': uploader,
|
2021-09-23 21:06:30 -04:00
|
|
|
'uploader_id': uploader_id,
|
2018-03-02 11:39:20 -05:00
|
|
|
'duration': duration,
|
|
|
|
'view_count': view_count,
|
2015-04-06 11:24:17 -04:00
|
|
|
'formats': formats,
|
|
|
|
'age_limit': age_limit,
|
2024-06-11 19:09:58 -04:00
|
|
|
}, info,
|
2019-07-13 13:21:39 -04:00
|
|
|
)
|
2019-02-07 12:09:50 -05:00
|
|
|
|
|
|
|
|
|
|
|
class SpankBangPlaylistIE(InfoExtractor):
|
2021-01-01 07:26:37 -05:00
|
|
|
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/(?P<display_id>[^/]+)'
|
2019-02-07 12:09:50 -05:00
|
|
|
_TEST = {
|
|
|
|
'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'ug0k',
|
|
|
|
'title': 'Big Ass Titties',
|
|
|
|
},
|
2021-01-01 07:26:37 -05:00
|
|
|
'playlist_mincount': 40,
|
2019-02-07 12:09:50 -05:00
|
|
|
}
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2021-08-18 21:41:24 -04:00
|
|
|
mobj = self._match_valid_url(url)
|
2021-01-01 07:26:37 -05:00
|
|
|
playlist_id = mobj.group('id')
|
2019-02-07 12:09:50 -05:00
|
|
|
|
|
|
|
webpage = self._download_webpage(
|
|
|
|
url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
|
|
|
|
|
|
|
|
entries = [self.url_result(
|
2021-01-01 07:26:37 -05:00
|
|
|
urljoin(url, mobj.group('path')),
|
|
|
|
ie=SpankBangIE.ie_key(), video_id=mobj.group('id'))
|
|
|
|
for mobj in re.finditer(
|
2022-12-29 03:08:22 -05:00
|
|
|
r'<a[^>]+\bhref=(["\'])(?P<path>/?[\da-z]+-(?P<id>[\da-z]+)/playlist/[^"\'](?:(?!\1).)*)\1',
|
|
|
|
webpage)]
|
2019-02-07 12:09:50 -05:00
|
|
|
|
|
|
|
title = self._html_search_regex(
|
2022-12-29 03:08:22 -05:00
|
|
|
r'<em>([^<]+)</em>\s+playlist\s*<', webpage, 'playlist title',
|
2019-02-07 12:09:50 -05:00
|
|
|
fatal=False)
|
|
|
|
|
|
|
|
return self.playlist_result(entries, playlist_id, title)
|