1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 12:38:05 +01:00
youtube-dl/youtube_dl/extractor/mofosex.py

54 lines
1.6 KiB
Python
Raw Normal View History

2014-08-27 01:03:31 +02:00
from __future__ import unicode_literals
2013-10-28 18:18:58 +01:00
import os
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
2013-10-28 18:18:58 +01:00
compat_urllib_parse_urlparse,
compat_urllib_request,
)
2014-08-27 01:03:31 +02:00
2013-10-28 18:18:58 +01:00
class MofosexIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
2013-10-28 18:18:58 +01:00
_TEST = {
2014-08-27 01:03:31 +02:00
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
'info_dict': {
'id': '5018',
'ext': 'mp4',
'title': 'Japanese Teen Music Video',
'age_limit': 18,
2013-10-28 18:18:58 +01:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2013-10-28 18:18:58 +01:00
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
2014-08-27 01:03:31 +02:00
video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
2013-10-28 18:18:58 +01:00
format = path.split('/')[5].split('_')[:2]
format = "-".join(format)
2013-10-28 18:18:58 +01:00
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'title': video_title,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': age_limit,
}