python网络爬虫——正则获取ip

python网络爬虫，几行代码就可以搞定

1.请求网页，获取数据

#请求网络
def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:63.0) Gecko/20100101 Firefox/63.0')
    
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

2.正则匹配Ip值  ，匹配规则为   (?:(?:[0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5]))

#正则匹配ip值(?:(?:[0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5]))
def get_iplist(html):
     p = r'(?:(?:[0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5]))'
     iplist = re.findall(p,html)

     for each in iplist:
         print(each)

3.全部代码，打印输出

import urllib.request
import re

#请求网络
def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:63.0) Gecko/20100101 Firefox/63.0')
    
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

#正则匹配ip值(?:(?:[0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5]))
def get_iplist(html):
     p = r'(?:(?:[0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5]))'
     iplist = re.findall(p,html)

     for each in iplist:
         print(each)
    

if __name__ == '__main__':
  url = 'http://www.xicidaili.com/'
  get_iplist(open_url(url))

输出结果：

python刚入门，有点意思。

有兴趣一起讨论，欢迎加入我的Java与Android逆向开发交流QQ群，一起学习编码。