zoukankan      html  css  js  c++  java
  • 获取免费IP--代码--转

    #! /usr/bin/env python3
    from urllib import request
    import random
    import time
    import lxml
    import re



    user_agent_list = [
    'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
    'Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3',
    'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
    'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
    'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
    'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
    'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0',
    'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
    ]

    count = 0

    def Get_proxy_ip():
    headers = {
    'Host': 'www.xicidaili.com',
    'User-Agent':'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
    'Accept': r'application/json, text/javascript, */*; q=0.01',
    'Referer': r'http://www.xicidaili.com/',
    }
    req = request.Request(r'http://www.xicidaili.com/nn/', headers=headers)
    response = request.urlopen(req)
    html = response.read().decode('utf-8')
    proxy_list = []
    ip_list = re.findall(r'd+.d+.d+.d+',html)
    port_list = re.findall(r'<td>d+</td>',html)
    for i in range(len(ip_list)):
    ip = ip_list[i]
    port = re.sub(r'<td>|</td>', '', port_list[i])
    proxy = '%s:%s' %(ip,port)
    proxy_list.append(proxy)
    return proxy_list

    def Proxy_read(proxy_list, user_agent_list, i):
    proxy_ip = proxy_list[i]
    print('当前代理ip:%s'%proxy_ip)
    user_agent = random.choice(user_agent_list)
    print('当前代理user_agent:%s'%user_agent)
    sleep_time = random.randint(1,3)
    print('等待时间:%s s' %sleep_time)
    time.sleep(sleep_time)
    print('开始获取')
    headers = {
    'Host': 's9-im-notify.csdn.net',
    'Origin':'http://blog.csdn.net',
    'User-Agent': user_agent,
    'Accept': r'application/json, text/javascript, */*; q=0.01',
    'Referer': r'http://blog.csdn.net/u010620031/article/details/51068703',
    }

    proxy_support = request.ProxyHandler({'http':proxy_ip})
    opener = request.build_opener(proxy_support)
    request.install_opener(opener)

    req = request.Request(r'http://blog.csdn.net/u010620031/article/details/51068703',headers=headers)
    try:
    html = request.urlopen(req).read().decode('utf-8')
    except Exception as e:
    print('******打开失败!******')
    else:
    global count
    count +=1
    print('OK!总计成功%s次!'%count)

    if __name__ == '__main__':
    proxy_list = Get_proxy_ip()
    for i in range(100):
    Proxy_read(proxy_list, user_agent_list, i)

    代理网站

    https://link.jianshu.com?t=http://www.cz88.net/proxy/
    https://link.jianshu.com?t=http://www.66ip.cn/index.html 
    https://link.jianshu.com?t=http://www.xicidaili.com/
    https://link.jianshu.com?t=http://www.coobobo.com/
    https://link.jianshu.com?t=http://www.kuaidaili.com/
    https://link.jianshu.com?t=http://www.proxy360.cn/default.aspx
    https://link.jianshu.com?t=http://ip.zdaye.com/
    https://link.jianshu.com?t=https://www.us-proxy.org/
    https://link.jianshu.com?t=http://www.nianshao.me/
    https://link.jianshu.com?t=http://www.goubanjia.com/
    https://link.jianshu.com?t=http://www.iphai.com/
    https://link.jianshu.com?t=http://www.meiridaili.com/
    https://link.jianshu.com?t=http://www.swei360.com/free/
    https://link.jianshu.com?t=http://www.89ip.cn/
    https://link.jianshu.com?t=http://www.ip3366.net/
    https://link.jianshu.com?t=http://www.mimiip.com/
    https://link.jianshu.com?t=http://daili.wy96.com/page1.asp
    https://link.jianshu.com?t=http://ip.qiaodm.com/free/index.html
    https://link.jianshu.com?t=http://www.ip181.com/
    https://link.jianshu.com?t=http://www.httpsdaili.com/free.asp
    https://link.jianshu.com?t=http://proxy.mimvp.com/free.php
    https://link.jianshu.com?t=http://www.httpdaili.com/mfdl/
    https://link.jianshu.com?t=http://www.mayidaili.com/free
    https://link.jianshu.com?t=http://www.fengyunip.com/free/china-high.html
    https://link.jianshu.com?t=http://www.kxdaili.com/dailiip.html
    https://link.jianshu.com?t=http://www.xdaili.cn/freeproxy
    https://link.jianshu.com?t=http://www.superfastip.com/welcome/getips
    https://link.jianshu.com?t=http://www.chinabaike.com/t/10475/2016/0530/5239251.html

    纯真
    66免费代理网
    西刺免费代理IP
    酷伯伯HTTP代理
    快代理
    proxy360.cn
    站大爷
    Free Proxy List
    年少
    全网代理IP
    IP海
    每日代理
    360代理IP
    流年免费HTTP代理IP 24小时自助提取系统
    云代理
    秘密代理IP
    迷惘网络IP代理
    敲代码 免费代理IP网
    代理IP检测平台,100免费代理IP
    瑶瑶代理IP
    米扑代理
    httpdaili
    蚂蚁代理
    风云代理IP
    开心代理
    讯代理
    急速IP

  • 相关阅读:
    linux系统常用命令
    oracle resetlog与noresetlog的作用(转载)
    RMAN备份之非归档模式下的备份
    查看oracle锁及解决办法
    夫夷以近,则游者众,险以远,则至者少!
    (转)一个10年程序员职业发展、总结和困境
    在myeclipse中写sql语句的细节问题
    myeclipse查询mysql出来的汉字是乱码
    如何将DB2的数据库转换到mySQL中?
    笔记本建立wifi热点的实用详细步骤
  • 原文地址:https://www.cnblogs.com/jamnoble/p/10920047.html
Copyright © 2011-2022 走看看