从txt中提取子域名

Posted 2021-03-05 zuoxiaolongzzz

import re

DOMAIN =[]

f = open(‘test.txt‘,‘r‘,encoding=‘UTF-8‘)
w = open(‘domain.txt‘,‘w‘)
for data in f.readlines():
    domain = re.findall(r"w+.+baidu.com", data)
    for i in domain:
    	if i not in DOMAIN:
    		DOMAIN.append(i)
    domain = re.findall(r"w+.+w+.+baidu.com", data) 
    for i in domain:
    	if i not in DOMAIN:
    		DOMAIN.append(i)
    domain = re.findall(r"w+.+w+.+w+.+baidu.com", data)
    for i in domain:
    	if i not in DOMAIN:
    		DOMAIN.append(i)
for i in DOMAIN:
	w.write(str(i)+‘
‘)
w.close()

　　丑是丑了点，懒得改了