#爬取某代理网站的ip并且校检是否可以用

# 爬取某代理网站的ip并且校检是否可以用
import requests
import re
# 获取ip
def get_ip(page):
    if page==1:
        url='https://www.kuaidaili.com/free/fps/'
    else:
        url=f'https://www.kuaidaili.com/free/fps/{page}'
    headers={
        'user-agent':
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0'
    }
    res=requests.get(url,headers=headers)
    content=res.text
    con=re.findall("const fpsList = (.*)",content)
    if con==[]:
        del con
    else:
        data=con[0]
        data=data.split('[')[1].split(']')[0]
        data=eval(data)
        data=data[0]
        ip=data['ip']
        port=data['port']
        chick(ip,port)
# 对ip进行校检
def chick(ip,port):
    try:
        dic={'http':f"{ip}:{port}"}
        res = requests.get(url="http://www.hao123.com", timeout=2, proxies=dic,verify=False)
        if res.status_code==200:
            print('有效')
            print(ip)
            save_ip(ip , port)
        else:
            print('无效')
            return False
    except Exception as e:
        print(e)
        return False
# 保存ip和prot
def save_ip(ip,prot):
    print(ip)
    with open('ip.txt','a') as f:
        f.write(ip+':'+prot+'\n')
if __name__ == '__main__':
    for page in range(1,6181):
        get_ip(page)