爬取IP

import urllib.request
import re

def url_open(url):
    req = urllib.request.Request(url,headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36 LBBROWSER'})
    response =urllib.request.urlopen(url)
    html = response.read().decode('utf-8')
    return html

def get_img(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)
        '''
        filename = each.split('/')[-1]
        urllib.request.urlretrieve(each,filename,None)'''

if __name__ == '__main__':
    url = 'http://www.proxy360.cn/default.aspx'
    get_img(url_open(url))
    

 

转载于:https://www.cnblogs.com/themost/p/6748524.html