youtube-dl/youtube_dl/extractor/spankbang.py

77 lines
2.6 KiB
Python
Raw Normal View History

2015-04-06 04:50:21 +09:00
from __future__ import unicode_literals
import re
2015-04-07 00:24:17 +09:00
from .common import InfoExtractor
from ..utils import ExtractorError
2015-04-07 00:24:17 +09:00
2015-04-06 04:50:21 +09:00
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
_TESTS = [{
2015-04-07 00:24:17 +09:00
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
'info_dict': {
'id': '3vvn',
'ext': 'mp4',
'title': 'fantasy solo',
'description': 'Watch fantasy solo free HD porn video - 05 minutes - Babe,Masturbation,Solo,Toy - dillion harper masturbates on a bed free adult movies sexy clips.',
'thumbnail': r're:^https?://.*\.jpg$',
2015-04-07 00:24:17 +09:00
'uploader': 'silly2587',
'age_limit': 18,
2015-04-06 05:57:59 +09:00
}
}, {
# 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,
}]
2015-04-06 04:50:21 +09:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
raise ExtractorError(
'Video %s is not available' % video_id, expected=True)
2015-04-07 00:24:17 +09:00
stream_key = self._html_search_regex(
r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
webpage, 'stream key')
formats = [{
'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
'ext': 'mp4',
'format_id': '%sp' % height,
'height': int(height),
} for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
2016-02-06 01:16:40 +09:00
self._check_formats(formats, video_id)
2015-04-07 00:24:17 +09:00
self._sort_formats(formats)
title = self._html_search_regex(
r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
description = self._og_search_description(webpage)
2015-04-07 00:24:17 +09:00
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'class="user"[^>]*><img[^>]+>([^<]+)',
webpage, 'uploader', default=None)
2015-04-07 00:24:17 +09:00
age_limit = self._rta_search(webpage)
2015-04-06 04:50:21 +09:00
return {
2015-04-07 00:24:17 +09:00
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'formats': formats,
'age_limit': age_limit,
2015-04-06 04:50:21 +09:00
}