requests+正则表达式爬取ip

#requests+正则表达式爬取ip
#findall方法，如果表达式中包含有子组，则会把子组单独返回出来，如果有多个子组，则会组合成元祖
import requests
import re
def get_ip(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 = requests.get(url,headers=headers)
    pattern= re.compile(r'(?:(?:[0-1]{0,1}d{0,1}d|2[0-4]d|25[0-5]).){3}(?:[0-1]{0,1}d{0,1}d|2[0-4]d|25[0-5]).*s*.*(?:d+)')
    result = re.findall(pattern,response.text)
    #print(result)
    return result

def make_iplist(iplist,result):

    for ip in result:
        ip = re.sub(r'</td>s*.*<td>',':',ip)
        iplist.append(ip)
    return iplist

def main(num):

    iplist = []
    for i in range(1,num):
        url = 'http://www.xicidaili.com/nt/'
        url =url + str(num)
        #print(url)
        result = get_ip(url)
        iplist = make_iplist(iplist,result)

    for j in iplist:
        print(j)
if __name__ == '__main__':
    num=int(input('请输入要抓取的页数：'))
    main(num)