# -*- coding: utf-8 -*-
# author :HXM
from lxml import etree
import requests
import re
from fake_useragent import UserAgent
def page():
ua=UserAgent()
url=input("请输入代理网页:")
#https://proxy.horocn.com/day-free-proxy/e8ZG.html
headers={'User-Agent' : ua.random}
response=requests.get(url,headers=headers)
if response.status_code==200:
datas=response.text
pattern=re.compile('.*?<br />(.*?)#.*?<br />',re.S)#re.S表示换行匹配,不受行数限制,python常用pattern来封装表达式规则,极大方便了调用
result=re.findall(pattern,datas)
print(type(result))
for results in result:
with open ("ip.txt","a",encoding="utf-8") as f:
f.write("{}\n".format(results))
return None
page()