读取txt中冒号、过滤url中的网址

import re

with open(‘software.txt’,‘r’,encoding=‘utf-8’) as file:
software = file.readlines()
list3 = []
for i in software:
software = i.strip(’\n’)
list3.append(software)
list5 = []
for i in list3:
list4 = i.split(’、’)
list5 += list4
list1 = list(set(list5))
print(’、’.join(list1))

with open(‘weburl.txt’,‘r’,encoding=‘utf-8’) as file1:
str1 = file1.read()
pattern = r’.\w*.com.cn|.\w*.net.cn|.\w*.com|.\w*.cn|.\w*.group|.\w*.tv’
match = re.findall(pattern,str1)
list1 =[]
for i in match:
if i not in list1:
list1.append(i)
for i in list1:
print(’*’+i)