1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-15 01:01:23 +01:00
youtube-dl/youtube_dl/extractor/baidu.py

57 lines
1.9 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2016-01-02 14:36:35 +01:00
from ..utils import unescapeHTML
class BaiduVideoIE(InfoExtractor):
2015-07-10 18:49:59 +02:00
IE_DESC = '百度视频'
_VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
'info_dict': {
'id': '1069',
2015-10-30 13:56:21 +01:00
'title': '中华小当家 TV版国语',
2016-01-02 14:36:35 +01:00
'description': 'md5:51be07afe461cf99fa61231421b5397c',
},
'playlist_count': 52,
}, {
'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
'info_dict': {
'id': '11595',
'title': 're:^奔跑吧兄弟',
'description': 'md5:1bf88bad6d850930f542d51547c089b8',
},
2015-10-30 13:56:21 +01:00
'playlist_mincount': 12,
}]
2016-01-02 14:44:49 +01:00
def _call_api(self, path, category, playlist_id, note):
return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
path, category, playlist_id), playlist_id, note)
2015-10-30 13:56:21 +01:00
def _real_extract(self, url):
2015-10-30 13:56:21 +01:00
category, playlist_id = re.match(self._VALID_URL, url).groups()
if category == 'show':
2015-10-30 13:56:21 +01:00
category = 'tvshow'
if category == 'tv':
category = 'tvplay'
2016-01-02 14:44:49 +01:00
playlist_detail = self._call_api(
'xqinfo', category, playlist_id, 'Download playlist JSON metadata')
2015-10-30 13:56:21 +01:00
playlist_title = playlist_detail['title']
2016-01-02 14:36:35 +01:00
playlist_description = unescapeHTML(playlist_detail.get('intro'))
2016-01-02 14:44:49 +01:00
episodes_detail = self._call_api(
'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
2016-01-02 14:46:40 +01:00
entries = [self.url_result(
episode['url'], video_title=episode['title']
) for episode in episodes_detail['videos']]
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)