]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/baidu.py
[dailymotion] Error spelling
[youtube-dl] / youtube_dl / extractor / baidu.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_urlparse
8
9
10 class BaiduVideoIE(InfoExtractor):
11     IE_DESC = '百度视频'
12     _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
13     _TESTS = [{
14         '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',
15         'info_dict': {
16             'id': '1069',
17             'title': '中华小当家 TV版 (全52集)',
18             'description': 'md5:395a419e41215e531c857bb037bbaf80',
19         },
20         'playlist_count': 52,
21     }, {
22         'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
23         'info_dict': {
24             'id': '11595',
25             'title': 're:^奔跑吧兄弟',
26             'description': 'md5:1bf88bad6d850930f542d51547c089b8',
27         },
28         'playlist_mincount': 3,
29     }]
30
31     def _real_extract(self, url):
32         mobj = re.match(self._VALID_URL, url)
33         playlist_id = mobj.group('id')
34         category = category2 = mobj.group('type')
35         if category == 'show':
36             category2 = 'tvshow'
37
38         webpage = self._download_webpage(url, playlist_id)
39
40         playlist_title = self._html_search_regex(
41             r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
42             'playlist title', group='title')
43         playlist_description = self._html_search_regex(
44             r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
45             playlist_id, 'playlist description')
46
47         site = self._html_search_regex(
48             r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
49             'primary provider site')
50         api_result = self._download_json(
51             'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
52                 category, category2, playlist_id, site),
53             playlist_id, 'Get playlist links')
54
55         entries = []
56         for episode in api_result[0]['episodes']:
57             episode_id = '%s_%s' % (playlist_id, episode['episode'])
58
59             redirect_page = self._download_webpage(
60                 compat_urlparse.urljoin(url, episode['url']), episode_id,
61                 note='Download Baidu redirect page')
62             real_url = self._html_search_regex(
63                 r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
64
65             entries.append(self.url_result(
66                 real_url, video_title=episode['single_title']))
67
68         return self.playlist_result(
69             entries, playlist_id, playlist_title, playlist_description)