1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-27 12:35:52 +01:00
youtube-dl/youtube_dl/extractor/hentaistigma.py

43 lines
1.2 KiB
Python
Raw Normal View History

2014-05-13 10:10:59 +02:00
from __future__ import unicode_literals
2014-05-12 12:58:07 +02:00
import re
from .common import InfoExtractor
2014-05-13 10:10:59 +02:00
2014-05-12 12:58:07 +02:00
class HentaiStigmaIE(InfoExtractor):
2014-05-13 10:10:59 +02:00
_VALID_URL = r'^https?://hentai\.animestigma\.com/(?P<id>[^/]+)'
2014-05-12 12:58:07 +02:00
_TEST = {
2014-05-13 10:10:59 +02:00
'url': 'http://hentai.animestigma.com/inyouchuu-etsu-bonus/',
'md5': '4e3d07422a68a4cc363d8f57c8bf0d23',
'info_dict': {
'id': 'inyouchuu-etsu-bonus',
'ext': 'mp4',
"title": "Inyouchuu Etsu Bonus",
"age_limit": 18,
2014-05-12 12:58:07 +02:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-05-13 10:10:59 +02:00
video_id = mobj.group('id')
2014-05-12 12:58:07 +02:00
webpage = self._download_webpage(url, video_id)
2014-05-13 10:10:59 +02:00
title = self._html_search_regex(
r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
webpage, 'title')
wrap_url = self._html_search_regex(
r'<iframe src="([^"]+mp4)"', webpage, 'wrapper url')
2014-05-12 12:58:07 +02:00
wrap_webpage = self._download_webpage(wrap_url, video_id)
2014-05-13 10:10:59 +02:00
video_url = self._html_search_regex(
r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url')
2014-05-12 12:58:07 +02:00
2014-05-13 10:10:59 +02:00
return {
'id': video_id,
'url': video_url,
'title': title,
'age_limit': 18,
}