yt-dlp/yt_dlp/extractor/ku6.py

31 lines
957 B
Python
Raw Normal View History

2014-05-31 06:15:59 +02:00
from .common import InfoExtractor
2014-06-07 15:46:33 +02:00
2014-05-31 06:15:59 +02:00
class Ku6IE(InfoExtractor):
_VALID_URL = r'https?://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
2014-05-31 06:15:59 +02:00
_TEST = {
'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
2014-06-07 15:46:33 +02:00
'md5': '01203549b9efbb45f4b87d55bdea1ed1',
2014-05-31 06:15:59 +02:00
'info_dict': {
'id': 'JG-8yS14xzBr4bCn1pu0xw',
'ext': 'f4v',
2014-06-07 15:46:33 +02:00
'title': 'techniques test',
},
2014-05-31 06:15:59 +02:00
}
def _real_extract(self, url):
2014-10-27 02:32:44 +01:00
video_id = self._match_id(url)
2014-05-31 06:15:59 +02:00
webpage = self._download_webpage(url, video_id)
2014-10-27 02:32:44 +01:00
title = self._html_search_regex(
r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
data_url = f'http://v.ku6.com/fetchVideo4Player/{video_id}.html'
json_data = self._download_json(data_url, video_id)
download_url = json_data['data']['f']
2014-05-31 06:15:59 +02:00
return {
'id': video_id,
'title': title,
'url': download_url,
2014-05-31 06:15:59 +02:00
}