python简单构建可用IP代理池 python简单构建可用IP代理池

以下为简单示例：

import requestsimport reimport telnetliburl='http://www.66ip.cn/nmtq.php?getnum=100000&isp=0&anonymoustype=4&start=&ports=&export=&ipaddress=&area=2&proxytype=0&api=66ip'header = {'User-agent':'xxxxxxxxxxx','Connection':'close'}page_text = requests.get(url=url,headers=header).text#用于匹配ip:port的正则表达式p = r'(?:((?:\d|[1-9]\d|1\d{2}|2[0-5][0-5])\.(?:\d|[1-9]\d|1\d{2}|2[0-5][0-5])\.(?:\d|[1-9]\d|1\d{2}|2[0-5][0-5])\.(?:\d|[1-9]\d|1\d{2}|2[0-5][0-5]))\D+?(6[0-5]{2}[0-3][0-5]|[1-5]\d{4}|[1-9]\d{1,3}|[0-9]))'#匹配出所有的ip与端口，放入列表iplist = re.findall(p,page_text)# 判断爬取的代理ip是否可用for i in iplist:ip = i[0]+':'+i[1]+'\n'try:# 使用代理ip访问指定网站，能访问说明代理可用# requests.get('http://www.baidu.com', proxies={"http": ip})# 使用telnet测试代理是否可用telnetlib.Telnet(i[0], port=i[1], timeout=3)except:print('connect failed')else:print(ip)with open('ip.txt', 'a+', encoding='utf-8') as fp:fp.write(ip)