庭审公开网 刷刷刷

如需使用只需编辑range()范围

 1 # -*- coding: UTF-8 -*-
 2 '''
 3 Created on 2017年9月6日
 4 @author: leilei
 5 '''
 6 import urllib2
 7 videoids=[]
 8 print "获取视频个数..."
 9 for i in range(1,50):#需要修改
10     pageurl = 'http://tingshen.court.gov.cn/court/cases?courtCode=1384&page=%d' % i
11     o = urllib2.urlopen(pageurl)
12     jsonstr = o.read().replace("null","None").replace("false","False")
13     jsondata = eval(jsonstr)
14     cases = jsondata['data']
15     for c in cases:
16         vid = c['videoId']
17         if vid not in videoids:
18             videoids.append(vid)
19 
20 print "共有视频%d个" % len(videoids)
21 def shua(url,id):
22     print "视频id:%d" % id
23     try:
24         op = urllib2.urlopen(url,timeout = 2)
25         count = int(op.read())
26     except Exception as e:
27         print '正在重试...'
28         count = -1
29     finally:
30         if count<1500:
31             if count != -1:
32                 print count
33             shua(url,id)
34     
35 for v in videoids:
36     counturl = 'http://click.videoincloud.com/count?videoid=%d' % v
37     shua(counturl,v)
38 print "done"

 

posted @ 2017-09-06 19:22  Jerory  阅读(183)  评论(0)  编辑  收藏  举报