youtube-dl/youtube_dl/extractor/ku6.py

33 lines
992 B
Python
Raw Permalink Normal View History

2014-05-31 04:15:59 +00:00
from __future__ import unicode_literals
2014-06-07 13:46:33 +00:00
2014-05-31 04:15:59 +00:00
from .common import InfoExtractor
2014-06-07 13:46:33 +00:00
2014-05-31 04:15:59 +00:00
class Ku6IE(InfoExtractor):
_VALID_URL = r'https?://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
2014-05-31 04:15:59 +00:00
_TEST = {
'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
2014-06-07 13:46:33 +00:00
'md5': '01203549b9efbb45f4b87d55bdea1ed1',
2014-05-31 04:15:59 +00:00
'info_dict': {
'id': 'JG-8yS14xzBr4bCn1pu0xw',
'ext': 'f4v',
2014-06-07 13:46:33 +00:00
'title': 'techniques test',
2014-05-31 04:15:59 +00:00
}
}
def _real_extract(self, url):
2014-10-27 01:32:44 +00:00
video_id = self._match_id(url)
2014-05-31 04:15:59 +00:00
webpage = self._download_webpage(url, video_id)
2014-10-27 01:32:44 +00:00
title = self._html_search_regex(
r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
2014-06-07 13:46:33 +00:00
dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
2014-05-31 04:15:59 +00:00
jsonData = self._download_json(dataUrl, video_id)
downloadUrl = jsonData['data']['f']
return {
'id': video_id,
'title': title,
'url': downloadUrl
}