[c56] Modernize and add duration extraction

This commit is contained in:
Sergey M․ 2014-04-03 19:53:11 +07:00
parent bec1fad223
commit 4a419b8851
1 changed files with 18 additions and 11 deletions

View File

@ -2,39 +2,46 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
class C56IE(InfoExtractor): class C56IE(InfoExtractor):
_VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)' _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
IE_NAME = '56.com' IE_NAME = '56.com'
_TEST = { _TEST = {
'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html', 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
'file': '93440716.flv',
'md5': 'e59995ac63d0457783ea05f93f12a866', 'md5': 'e59995ac63d0457783ea05f93f12a866',
'info_dict': { 'info_dict': {
'id': '93440716',
'ext': 'flv',
'title': '网事知多少 第32期车怒', 'title': '网事知多少 第32期车怒',
'duration': 283.813,
}, },
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
text_id = mobj.group('textid') text_id = mobj.group('textid')
info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
text_id, 'Downloading video info') page = self._download_json(
info = json.loads(info_page)['info'] 'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
formats = [{
info = page['info']
formats = [
{
'format_id': f['type'], 'format_id': f['type'],
'filesize': int(f['filesize']), 'filesize': int(f['filesize']),
'url': f['url'] 'url': f['url']
} for f in info['rfiles']] } for f in info['rfiles']
]
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': info['vid'], 'id': info['vid'],
'title': info['Subject'], 'title': info['Subject'],
'duration': int(info['duration']) / 1000.0,
'formats': formats, 'formats': formats,
'thumbnail': info.get('bimg') or info.get('img'), 'thumbnail': info.get('bimg') or info.get('img'),
} }