文件对比

#coding:utf-8
#!/usr/bin/python
#import codec
import os

f_out1 = open(‘C:/Users/l/Desktop/g/log_analyse/result1.txt’,‘w’)#规则有没测到的
f_out2 = open(‘C:/Users/l/Desktop/g/log_analyse/result2.txt’,‘w’)#测试没有在规则中的
with open(‘C:/Users/l/Desktop/g/gui/dns100w.csv’,‘r’) as f:#标准规则文件
list1=[]
for line1 in f.readlines():
line1=line1.strip(’\n’)
b=line1.split(’,’)
#print(b[3])
list1.append(b[3])

f1=open(‘C:/Users/l/Desktop/g/gui/email_dic/email_hitlog.txt’)#测试获取的关键字集
list2=[]
for line2 in f1.readlines():
line2=line2.strip(’\n’)
#print(line2)
list2.append(line2)
‘’’
for s in list1:
if list2.count(s)==0:
f_out1.write(s)
f_out1.write(’\n’)

for t in list2:
if list1.count(t)==0:
f_out2.write(t)
f_out2.write(’\n’)
‘’’
list3 = set(list2).difference(set(list1))#规则有没测到的
list4 = set(list1).difference(set(list2))#测到没有在规则中的

f_out1.write(’\n’.join(list3))
f_out2.write(’\n’.join(list4))

f1.close()
f_out1.close()
f_out2.close()