yt-dlp/youtube_dl/extractor/spankbang.py

137 lines
4.5 KiB
Python
Raw Normal View History

2015-04-05 19:50:21 +00:00
from __future__ import unicode_literals
import re
2015-04-06 15:24:17 +00:00
from .common import InfoExtractor
from ..utils import (
ExtractorError,
orderedSet,
parse_duration,
parse_resolution,
str_to_int,
)
2015-04-06 15:24:17 +00:00
2015-04-05 19:50:21 +00:00
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
_TESTS = [{
2015-04-06 15:24:17 +00:00
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
'info_dict': {
'id': '3vvn',
'ext': 'mp4',
'title': 'fantasy solo',
'description': 'dillion harper masturbates on a bed',
'thumbnail': r're:^https?://.*\.jpg$',
2015-04-06 15:24:17 +00:00
'uploader': 'silly2587',
'age_limit': 18,
2015-04-05 20:57:59 +00:00
}
}, {
# 480p only
'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
'only_matching': True,
}, {
# no uploader
'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
'only_matching': True,
}, {
# mobile page
'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
'only_matching': True,
}, {
# 4k
'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
'only_matching': True,
2019-02-07 16:57:58 +00:00
}, {
'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,
}]
2015-04-05 19:50:21 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
2019-02-07 16:57:58 +00:00
webpage = self._download_webpage(
url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
video_id, headers={'Cookie': 'country=US'})
2015-04-05 19:50:21 +00:00
if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
raise ExtractorError(
'Video %s is not available' % video_id, expected=True)
formats = []
for mobj in re.finditer(
r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
webpage):
format_id, format_url = mobj.group('id', 'url')
f = parse_resolution(format_id)
f.update({
'url': format_url,
'format_id': format_id,
})
formats.append(f)
2015-04-06 15:24:17 +00:00
self._sort_formats(formats)
title = self._html_search_regex(
r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
description = self._search_regex(
r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
webpage, 'description', fatal=False)
2015-04-06 15:24:17 +00:00
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'class="user"[^>]*><img[^>]+>([^<]+)',
webpage, 'uploader', default=None)
duration = parse_duration(self._search_regex(
r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
2015-04-06 15:24:17 +00:00
age_limit = self._rta_search(webpage)
2015-04-05 19:50:21 +00:00
return {
2015-04-06 15:24:17 +00:00
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
2015-04-06 15:24:17 +00:00
'formats': formats,
'age_limit': age_limit,
2015-04-05 19:50:21 +00:00
}
class SpankBangPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
_TEST = {
'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
'info_dict': {
'id': 'ug0k',
'title': 'Big Ass Titties',
},
'playlist_mincount': 50,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(
url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
entries = [self.url_result(
'https://spankbang.com/%s/video' % video_id,
ie=SpankBangIE.ie_key(), video_id=video_id)
for video_id in orderedSet(re.findall(
r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
title = self._html_search_regex(
r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
fatal=False)
return self.playlist_result(entries, playlist_id, title)