进程池获取代理和检测代理

import requests
from lxml import etree
import multiprocessing
#获取代理函数
def get_all_proxy(queue):
    url = 'http://www.xicidaili.com/nn/1'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
    }
    response = requests.get(url,headers=headers)

    html = response.text
    html = etree.HTML(html)

    ip_list = html.xpath('//table[@id="ip_list"]/tr/td[2]/text()')
    d_list = html.xpath('//table[@id="ip_list"]/tr/td[3]/text()')
    # print(ip_list,d_list)

    for i in range(0,len(ip_list)):
        proxy = 'http://' + ip_list[i] + ':' + d_list[i]
        # print(proxy)

        # print(porxy_list)
        queue.put(proxy)
# with open('xicidaili.html','wb') as f:
#     f.write(response.content)
#检测代理函数
def check_all_proxy(proxy):
        # print(proxy)
    try:
        url = 'http://fanyi.baidu.com/sug'
        porxy_dict = {
            'http':proxy
        }
        try:
            response = requests.get(url,proxies=porxy_dict,timeout=3)
            if response.status_code == 200:
                print(proxy)
                # with open('ip.txt', 'a') as f:
                #     f.write(proxy+'\n')
                return proxy

            else:
                print('不可用'*20)
                return proxy
        except:
            return None
    except Exception as e:
        print(e)
#进程池
if __name__ == '__main__':
    import time
    start_time = time.time()
    # 创建队列
    q = multiprocessing.Queue()
    # pool 进程池中, 要用的是下面的这个queue
    # 获取所有代理
    p = multiprocessing.Process(target=get_all_proxy, args=(q,))
    # 执行
    p.start()
    # proxy_list = get_all_proxy()
    # 检测代理的可用性

    pool = multiprocessing.Pool(50)
    result_list = []
    while True:
        try:
            proxy_str = q.get(timeout=5)
            # print('人头送到这里了', proxy_str)
        except:
            break
        # print('apply_async 之前')
        # proxy_and_queue = [proxy_str, result_q]
        proxy_res = pool.apply_async(check_all_proxy, (proxy_str,))
        result_list.append(proxy_res)
    # valid_proxy_list = check_all_proxy(proxy_list)

    valid_proxy_list = []
    for proxy_res in result_list:
        result = proxy_res.get()
        if result is None:
            pass
        else:
            valid_proxy_list.append(result)
            # print(result)

    print('All proxy we can get:')
    print(valid_proxy_list)
    pool.close()
    pool.join()
    p.join()
  • 2
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值