python代理爬取存入csv文件

爬取高匿代理

from urllib import request
import re
import time

f = open('西1.csv','w',encoding='GBK')
headers = {
'Cookie':' _free_proxy_session=BAh7B0kiD3Nlc3Npb25faWQGOgZFVEkiJTJjNTgwNDE4OTYyNTJiNjlmMmU2NDFhZWEwZjExMjFjBjsAVEkiEF9jc3JmX3Rva2VuBjsARkkiMVd4THYybCtNcW1yZmJFckpWUDJFdnNzam5hUCtuMGJLNEg0UFUzdE1XWTA9BjsARg%3D%3D--a43f95e415d8ee53f36f90941dbab43b1503d84b',
'User-Agent':' Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36',
}
url = 'http://www.xicidaili.com/nn/{}'
end = int(input('你想爬几页的代理呢'))
for pag in range(1,end+1):
    fullurl = url.format(pag)
    res = request.Request(fullurl,headers=headers)
    response = request.urlopen(res)
    html = response.read().decode('utf-8')
    # print(html)
    list_rule = re.compile(r'<tr.*?</tr>',re.S)
    list = list_rule.findall(html)
    # print(list)
    for td in list:
        iplist_rule = re.compile(r'<td>(.*?)</td>',re.S)
        iplist = iplist_rule.findall(td)
        # print(iplist)
        for ip_a in iplist:
            a_rule = re.compile(r'>(.*?)<',re.S)
            address = a_rule.findall(ip_a)
            for ip_address in address:
                iplist[2]=(ip_address)
                f.write(','.join(iplist) + '
')
    print('第{}页下载完成'.format(pag))
    time.sleep(5)
f.close()