zoukankan      html  css  js  c++  java
  • 获取免费代理

    # -*- coding=utf8 -*-
    
    import urllib2
    import re
    import time
    import random
    import socket
    import threading
    from user_agents import agents
    import sys
    
    reload(sys)
    sys.setdefaultencoding('utf8')
    
    # 抓取代理IP
    ip_totle = []
    for page in range(1,10):
        # url = 'http://ip84.com/dlgn/' + str(page)
        url='http://www.xicidaili.com/nn/'+str(page) #西刺代理
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64)"}
        # proxy_handler = urllib2.ProxyHandler({'http': 'http://'})
        # opener = urllib2.build_opener(proxy_handler)
        # urllib2.install_opener(opener)
        request = urllib2.Request(url=url, headers=headers)
        response = urllib2.urlopen(request)
        content = response.read().decode('utf-8')
        print('get page', page)
        pattern = re.compile('<td>(d.*?)</td>')  # 截取<td>与</td>之间第一个数为数字的内容
        ip_page = re.findall(pattern, str(content))
        ip_totle.extend(ip_page)
        time.sleep(random.choice(range(3, 5)))
    # 打印抓取内容
    print('代理IP地址     ', '	', '端口', '	', '速度', '	', '验证时间')
    for i in range(0, len(ip_totle), 4):
        print(ip_totle[i], '    ', '	', ip_totle[i + 1], '	', ip_totle[i + 2], '	', ip_totle[i + 3])
    # 整理代理IP格式
    proxys = []
    for i in range(0, len(ip_totle), 4):
        proxy_host = ip_totle[i] + ':' + ip_totle[i + 1]
        proxy_temp = {"http": proxy_host}
        proxys.append(proxy_temp)
    
    proxy_ip = open('proxy_ip.txt', 'w')  # 新建一个储存有效IP的文档
    lock = threading.Lock()  # 建立一个锁
    
    
    # 验证代理IP有效性的方法
    def test(i):
        socket.setdefaulttimeout(5)  # 设置全局超时时间
        url = "http://www.dianping.com/shop/21143491"  # 打算爬取的网址
        try:
            headers = {
                'Host': 'www.dianping.com',
                'User-Agent': random.choice(agents),
            }
            proxy_support = urllib2.ProxyHandler(proxys[i])
            opener = urllib2.build_opener(proxy_support)
            # opener.addheaders = [("User-Agent", "Mozilla/5.0 (Windows NT 10.0; WOW64)")]
            urllib2.install_opener(opener)
            request = urllib2.Request(url=url, headers=headers)
            response = urllib2.urlopen(request)
            content = response.read().decode('utf-8')
            lock.acquire()  # 获得锁
            print(proxys[i], 'is OK')
            proxy_ip.write('%s
    ' % str(proxys[i]))  # 写入该代理IP
            lock.release()  # 释放锁
        except Exception as e:
            lock.acquire()
            print(proxys[i], e)
            lock.release()
    
    
    # 单线程验证
    # for i in range(len(proxys)):
    #     test(i)
    # 多线程验证
    threads = []
    for i in range(len(proxys)):
        thread = threading.Thread(target=test, args=[i])
        threads.append(thread)
        thread.start()
    # 阻塞主进程,等待所有子线程结束
    for thread in threads:
        thread.join()
    
    proxy_ip.close()  # 关闭文件
    
  • 相关阅读:
    n个数字相加
    爬取编程常用词汇,保存为Excel
    Python对 Excel 的常用操作
    Python对Redis增删改查
    Python对MySql增删改查
    Python对MongoDB增删改查
    MySql事务的简单使用
    Python-判断回文
    Pyhton 连接数据库
    PyCharm设置完自动上传,却不会自动上传任何内容
  • 原文地址:https://www.cnblogs.com/shangpolu/p/7975973.html
Copyright © 2011-2022 走看看