0b26ad32d28b5e84498f2ff4cf85c0ab66dc28bd
[youtube-dl] / youtube_dl / extractor / cntv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import compat_urllib_request
6
7 class CntvIE(InfoExtractor):
8     IE_NAME = 'cntv'
9     IE_DESC = '央视网'
10     _VALID_URL = r'''(?x)
11         (?:
12             http://(?:ent|tv|sports|english|chunwan)\.(?:cntv|cctv)\.(?:com|cn)/
13             (?:
14                 (?:video|special)/(?:[_A-Za-z0-9]+)|(?P<year>\d+)/(?P<month>\d+)/(?P<day>\d+)
15             )
16         )
17         /(?P<id>[A-Za-z0-9]+)(index)?(?:\.shtml|)
18     '''
19
20     _TESTS = [{
21         'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
22         'md5': 'd0f8c3e043fe43534517ed47c831fd4e',
23         'info_dict': {
24             'id': '5ecdbeab623f4973b40ff25f18b174e8',
25             'ext': 'flv',
26             'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕(快讯)',
27             'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95',
28             'uploader': 'songjunjie'
29         }
30     },{
31         'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
32         'md5': '3bde627de65b6bad064f3e67ec9e71a1',
33         'info_dict': {
34             'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
35             'ext': 'flv',
36             'title': '[赛车]“车王”舒马赫恢复情况成谜(快讯)',
37             'description': '2月4日,蒙特泽莫罗透露了关于“车王”舒马赫恢复情况,但情况是否属实遭到了质疑。',
38             'uploader': 'shujun'
39         }
40     },{
41         'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml',
42         'md5': 'f37a56d5f16647eae24c3e618f8d23a2',
43         'info_dict': {
44             'id': '4bb9bb4db7a6471ba85fdeda5af0381e',
45             'ext': 'flv',
46             'title': 'NHnews008 ANNUAL POLITICAL SEASON',
47             'description': 'Four Comprehensives',
48             'uploader': 'zhangyunlei'
49         }
50     },{
51         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
52         'md5': '37ad2407b5f28336ddf26aacea570ee5',
53         'info_dict': {
54             'id': '45336758dd474ef39dc6887f115e0375',
55             'ext': 'flv',
56             'title': '《爱国之恋》中国梦新歌展播  综艺视频精切',
57             'description': 'md5:856836ae2660f000e458ead597b1e2bd',
58             'uploader': 'baiyuqing'
59         }
60     },{
61         'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44',
62         'md5': 'd7188ecc2a2f8447c70023895724c31c',
63         'info_dict': {
64             'id': 'e0210d949f113ddfb38d31f00a4e5c44',
65             'ext': 'flv',
66             'title': '《传奇故事》 20150409 金钱“魔术”(下)',
67             'description': '本期节目主要内容:     2014年10月23日凌晨,浙江余杭警方出动2000多名警力,一举摧毁1040阳光工程传销组织,抓获65名涉嫌传销的组织头目,教育遣返400多名参与传销人员。',
68             'uploader': '陆银凯'
69         }
70     }]
71
72     def _real_extract(self, url):
73         video_id = self._match_id(url)
74         webpage = self._download_webpage(url, video_id)
75
76         video_id_regex = [r'var guid[ ="]+([a-zA-Z0-9]+)"',
77                     r'"videoCenterId"[ ,"]+([a-zA-Z0-9]+)"',
78                     r'"changePlayer\(\'([a-zA-Z0-9]+)\'\)\"']
79         video_id = self._search_regex(video_id_regex, webpage, 'video_id', default=None)
80
81         if video_id is None:
82             video_id = self._match_id(url)
83
84         # refer to youku.py
85         def retrieve_data(req_url, note):
86             req = compat_urllib_request.Request(req_url)
87
88             cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
89             if cn_verification_proxy:
90                 req.add_header('Ytdl-request-proxy', cn_verification_proxy)
91
92             raw_data = self._download_json(req, video_id, note=note)
93             return raw_data
94
95         get_info_url = \
96             'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do' + \
97             '?pid=%s' % video_id + \
98             '&tz=-8' + \
99             '&from=000tv' + \
100             '&url=%s' % url + \
101             '&idl=32' + \
102             '&idlr=32' + \
103             '&modifyed=false'
104
105         data = retrieve_data(
106             get_info_url,
107             'Downloading JSON metadata')
108
109         title = data.get('title')
110         uploader = data.get('editer_name')
111         hls_url = data.get('hls_url')
112         formats = self._extract_m3u8_formats(hls_url, video_id, 'flv')
113         self._sort_formats(formats)
114
115         description = self._html_search_meta('description', webpage)
116
117         return {
118             'id': video_id,
119             'title': title,
120             'uploader': uploader,
121             'formats': formats,
122             'description': description,
123         }