yt-dlp/youtube_dl/extractor/c56.py

41 lines
1.2 KiB
Python
Raw Normal View History

# coding: utf-8
2014-01-07 10:19:15 +01:00
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
2014-01-07 10:19:15 +01:00
class C56IE(InfoExtractor):
_VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
2014-01-07 10:19:15 +01:00
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,
2014-01-07 10:19:15 +01:00
text_id, 'Downloading video info')
info = json.loads(info_page)['info']
2014-01-07 10:19:15 +01:00
formats = [{
'format_id': f['type'],
'filesize': int(f['filesize']),
'url': f['url']
} for f in info['rfiles']]
self._sort_formats(formats)
2014-01-07 10:19:15 +01:00
return {
'id': info['vid'],
'title': info['Subject'],
'formats': formats,
'thumbnail': info.get('bimg') or info.get('img'),
}