构建ip池

from lxml import etree
from fake_useragent import UserAgent
import time
import json
import requests
import csv

def check_ip(li):
    headers={
        'User-Agent': UserAgent().random
            }  
    ip_ok=[]
    for l in li:
        try:
            
            response=requests.get('https://xa.anjuke.com/sale/weiyangq/?from=navigation',proxies=l,timeout=0.1)
            if response.status_code==200:
                ip_ok.append(l)
        except Exception as e:
            print(e)
        
    return ip_ok
li=[]
for i in range(150,170):
    print("==========正在爬取第{}页===========".format(i))
    url='https://www.kuaidaili.com/free/inha/{}/'.format(i)
    headers={
        'User-Agent': UserAgent().random
            }  
    
    
    page_text=requests.get(url=url,headers=headers).text
    tree=etree.HTML(page_text)
    div_list=tree.xpath('//*[@id="list"]/table//tr')
    
    for div in div_list:
        proxies_dict={}
        try:
            ip=div.xpath('./td/text()')[0]+":"+div.xpath('./td/text()')[1]
            type=div.xpath('./td/text()')[3]
            proxies_dict[type]=ip
            if len(proxies_dict)!=0:
                print(proxies_dict)
                li.append(proxies_dict)
        except:pass
        
    time.sleep(1)
print("ip数量：",len(li))
ok_ip=check_ip(li)
print("ok的ip:",ok_ip)
print("数目:",len(ok_ip))