1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-23 03:45:39 +08:00
youtube-dl/youtube_dl/extractor/c56.py
2014-01-07 10:19:15 +01:00

41 lines
1.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class C56IE(InfoExtractor):
_VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
IE_NAME = '56.com'
_TEST = {
'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
'file': '93440716.flv',
'md5': 'e59995ac63d0457783ea05f93f12a866',
'info_dict': {
'title': '网事知多少 第32期车怒',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
text_id = mobj.group('textid')
info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
text_id, 'Downloading video info')
info = json.loads(info_page)['info']
formats = [{
'format_id': f['type'],
'filesize': int(f['filesize']),
'url': f['url']
} for f in info['rfiles']]
self._sort_formats(formats)
return {
'id': info['vid'],
'title': info['Subject'],
'formats': formats,
'thumbnail': info.get('bimg') or info.get('img'),
}