import parsel
import requests
import time


def chik_ip(proxies_list):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    can_ip=[]
    for proxies in proxies_list:
         try:
            respon=requests.get(url='http://www.baidu.com',headers=headers,proxies={'http://':proxies},timeout=1)
            if respon.status_code==200:
                print(f"{proxies}可用")
                can_ip.append(proxies)
         except Exception as e:
                return False

    return  can_ip

def ipinfo():
    proxies_list = []
    start_time=time.time()
    for i in range(6):
        page=i+1
        print(f"正在爬取第{page}页{'#*#'*30}")
        url=f'https://www.kuaidaili.com/free/inha/{page}/'
        headers={
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
        }
        res=requests.get(url,headers=headers)
        data = res.text
        html = parsel.Selector(data)  # 实例化
        resp = html.xpath('//*[@id="list"]/table/tbody/tr')
        time.sleep(0.5)
        for i in resp:
            proxies_dict={}
            http_type = i.xpath('./td[4]/text()').extract_first()
            ip_num = i.xpath('./td[1]/text()').extract_first()
            port_num = i.xpath('./td[2]/text()').extract_first()

            proxies_dict[http_type]=ip_num+':'+port_num
            print(proxies_dict)

            time.sleep(0.5)
            proxies_list.append(proxies_dict[http_type])
        print(f"第{page}爬取完毕{'*+*'*30}")
    print(proxies_list,)

    print('获取到的代理IP数量是:',len(proxies_list),"个")

    end_time=time.time()
    now_time=end_time-start_time
    print(f"用时{now_time}秒")
    return proxies_list

def write_text(can_ip):
    w = open('./i_p.text', 'w')
    for i, item in enumerate(can_ip):
        w.write(item + '\n')
    w.close()


def run():
    s_ip=ipinfo()
    c_ip=chik_ip(s_ip)
    write_text(c_ip)


run()