1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-18 16:26:23 +00:00
youtube-dl/youtube_dl/extractor/spankbang.py

64 lines
2.1 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
2015-04-05 19:50:21 +00:00
class SpankBangIE(InfoExtractor):
2015-04-06 15:24:17 +00:00
_VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
_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': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
'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,
}]
2015-04-05 19:50:21 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2015-04-06 15:24:17 +00:00
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)]
2016-02-05 16:16:40 +00:00
self._check_formats(formats, video_id)
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._og_search_description(webpage)
2015-04-06 15:24:17 +00:00
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'class="user"[^>]*><img[^>]+>([^<]+)',
2015-04-06 15:24:17 +00:00
webpage, 'uploader', fatal=False)
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,
'formats': formats,
'age_limit': age_limit,
2015-04-05 19:50:21 +00:00
}