对于已经成功的1000页,也要修改。为了以后代码执行的工作量小点!进行切割:

代码:【并不完善,需要手工修改一下!】

 1 '''
 2 核心思想,就是通过不同的id号进行查找。不想要的,移除掉!
 3 '''
 4 
 5 import json
 6 def makes():
 7     i = 24999#截取后面的
 8     # i = 49999# 截取前面的
 9     cve_num0_file = open('D:/1hos/cvebase_ifo.json', "r")
10     cvesum = json.load(cve_num0_file)
11     # print(cvesum[i]['id'])
12     # while i > 25000:#截取前面的
13     while i > 0:#截取后面的
14         print(cvesum[i]['id'])
15         if int(cvesum[i]['id']) < 25000:
16             # cvesum[i].remove
17             del cvesum[i]
18         i -= 1#截取前面的
19         # i += 1#截取后面的
20 
21     # with open('D:/1swqcve/cve_num1.json', "w+") as json_file:
22     #     json_str = json.dumps(cve_num1_context, indent=4)
23     #     json_file.write(json_str)
24     #     json_file.close()
25     #     print('\n************已经成功复制在cve_num1的内容************\n')
26     # print(cvesum)
27     with open('D:/1hos/cvebase_ifo4.json', "w") as json_file:
28         json_str = json.dumps(cvesum, indent=4)
29         json_file.write(json_str)
30         json_file.close()
31     # with open('D:/1swqcve/cve_num2.json', "w") as json_file:
32     #     json_str = json.dumps(cvesum, indent=4)
33     #     json_file.write(json_str)
34     #     json_file.close()
35     # with open('D:/1swqcve/cve_num3.json', "w") as json_file:
36     #     json_str = json.dumps(cvesum, indent=4)
37     #     json_file.write(json_str)
38     #     json_file.close()
39     # with open('D:/1swqcve/cve_num4.json', "w") as json_file:
40     #     json_str = json.dumps(cvesum, indent=4)
41     #     json_file.write(json_str)
42     #     json_file.close()
43     # print("成功将cve编号写入4个json文件!\n")
44 if __name__=="__main__":
45     makes()

 清理CVE编号:

找出分界线下标:

 

 取出前500页【25000个】

成功代码:

 1 '''
 2 核心思想,就是通过不同的id号进行查找。不想要的,移除掉!
 3 '''
 4 
 5 import json
 6 def makes():
 7     # i = 0#截取后面的
 8     i = 49999# 截取前面的
 9     cve_num0_file = open('D:/1hos/cve_num0.json', "r")
10     cvesum = json.load(cve_num0_file)
11     print(cvesum[24999])
12     # while i > 25000:#截取前面的
13     while i > 24999:#截取后面的
14         print(i)
15         del cvesum[i]
16         i -= 1
17     #     print(cvesum[i]['id'])
18     #     if int(cvesum[i]['id']) < 25000:
19     #         # cvesum[i].remove
20 
21     #     i -= 1#截取前面的
22     #     # i += 1#截取后面的
23 
24     # with open('D:/1swqcve/cve_num1.json', "w+") as json_file:
25     #     json_str = json.dumps(cve_num1_context, indent=4)
26     #     json_file.write(json_str)
27     #     json_file.close()
28     #     print('\n************已经成功复制在cve_num1的内容************\n')
29     # print(cvesum)
30     with open('D:/1hos/cve_num1.json', "w") as json_file:
31         json_str = json.dumps(cvesum, indent=4)
32         json_file.write(json_str)
33         json_file.close()
34     # with open('D:/1swqcve/cve_num2.json', "w") as json_file:
35     #     json_str = json.dumps(cvesum, indent=4)
36     #     json_file.write(json_str)
37     #     json_file.close()
38     # with open('D:/1swqcve/cve_num3.json', "w") as json_file:
39     #     json_str = json.dumps(cvesum, indent=4)
40     #     json_file.write(json_str)
41     #     json_file.close()
42     # with open('D:/1swqcve/cve_num4.json', "w") as json_file:
43     #     json_str = json.dumps(cvesum, indent=4)
44     #     json_file.write(json_str)
45     #     json_file.close()
46     # print("成功将cve编号写入4个json文件!\n")
47 if __name__=="__main__":
48     makes()

 

 截取后面的:【需要手动删除一个信息!】

代码:

 1 '''
 2 核心思想,就是通过不同的id号进行查找。不想要的,移除掉!
 3 '''
 4 
 5 import json
 6 def makes():
 7     # i = 0#截取后面的
 8     i = 24999# 截取前面的
 9     cve_num0_file = open('D:/1hos/cve_num0.json', "r")
10     cvesum = json.load(cve_num0_file)
11     print(cvesum[24999])
12     # while i > 25000:#截取前面的
13     while i > 0:#截取后面的
14         print(i)
15         del cvesum[i]
16         i -= 1
17     #     print(cvesum[i]['id'])
18     #     if int(cvesum[i]['id']) < 25000:
19     #         # cvesum[i].remove
20 
21     #     i -= 1#截取前面的
22     #     # i += 1#截取后面的
23 
24     # with open('D:/1swqcve/cve_num1.json', "w+") as json_file:
25     #     json_str = json.dumps(cve_num1_context, indent=4)
26     #     json_file.write(json_str)
27     #     json_file.close()
28     #     print('\n************已经成功复制在cve_num1的内容************\n')
29     # print(cvesum)
30     with open('D:/1hos/cve_num8.json', "w") as json_file:
31         json_str = json.dumps(cvesum, indent=4)
32         json_file.write(json_str)
33         json_file.close()
34     # with open('D:/1swqcve/cve_num2.json', "w") as json_file:
35     #     json_str = json.dumps(cvesum, indent=4)
36     #     json_file.write(json_str)
37     #     json_file.close()
38     # with open('D:/1swqcve/cve_num3.json', "w") as json_file:
39     #     json_str = json.dumps(cvesum, indent=4)
40     #     json_file.write(json_str)
41     #     json_file.close()
42     # with open('D:/1swqcve/cve_num4.json', "w") as json_file:
43     #     json_str = json.dumps(cvesum, indent=4)
44     #     json_file.write(json_str)
45     #     json_file.close()
46     # print("成功将cve编号写入4个json文件!\n")
47 if __name__=="__main__":
48     makes()

 

结果:

需要手动删除一个,其他一切都好!

posted @ 2020-04-04 14:44  努力变胖-HWP  阅读(151)  评论(1编辑  收藏  举报