免费代理采集-多线程验证

1、采集地址：http://www.xicidaili.com/nn/
2、根据实际需求修改验证地址
3、免费代理稳定性不可靠，在使用中可增加重试，切换代理

# coding: utf-8
import urllib2
from bs4 import BeautifulSoup
import urllib
import socket
import threading


User_Agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0'
header = {}
header['User-Agent'] = User_Agent


def getProxyIp():
    proxy = []
    for i in range(1, 60):
        try:
            url = 'http://www.xicidaili.com/nn/' + str(i)
            req = urllib2.Request(url, headers=header)
            res = urllib2.urlopen(req).read()
            soup = BeautifulSoup(res, 'html5lib')
            ips = soup.findAll('tr')
            for x in range(1, len(ips)):
                ip = ips[x]
                tds = ip.findAll("td")
                ip_temp = tds[1].contents[0] + "\t" + tds[2].contents[0]+"\t"+tds[5].contents[0]
                proxy.append(ip_temp)
        except:
            continue
    return proxy


f = open("ip.txt", "w")


def validateIp(proxy):
    url = "http://ip.chinaz.com/getip.aspx"
    socket.setdefaulttimeout(3)
    for i in range(0, len(proxy)):
        try:
            ip = proxy[i].strip().split("\t")
            proxy_host = ip[2]+"://" + ip[0] + ":" + ip[1]
            proxy_temp = {ip[2]: proxy_host}
            res = urllib.urlopen(url, proxies=proxy_temp).read()
            f.write(proxy[i] + '\n')
            print proxy[i]
        except Exception, e:
            continue
    f.close()


lock = threading.Lock()


def validateIpThread():
    threads = []
    for i in range(len(proxy)):
        thread = threading.Thread(target=validateIp2, args=[i])
        threads.append(thread)
        thread.start()
    for thread in threads:
        thread.join()
    f.close()


def validateIp2(i):
    socket.setdefaulttimeout(5)
    # 验证地址
    url = "http://www.biquge.com.tw/17_17281/7647045.html"
    try:
        ip = proxy[i].strip().split("\t")
        proxy_host = "http://" + ip[0] + ":" + ip[1]
        proxy_temp = {"http": proxy_host}
        proxy_support = urllib2.ProxyHandler(proxy_temp)
        opener = urllib2.build_opener(proxy_support)
        opener.addheaders = [("User-Agent", "Mozilla/5.0 (Windows NT 10.0; WOW64)")]
        urllib2.install_opener(opener)
        res = urllib2.urlopen(url).read()
        if (len(res) < 10000):
            raise RuntimeError('return error')
        lock.acquire()
        print(proxy[i], 'is OK')
        f.write('%s\n' % str(proxy[i]))
        lock.release()
    except Exception as e:
        lock.acquire()
        print(proxy[i], e)
        lock.release()


if __name__ == '__main__':
    proxy = getProxyIp()
    # validateIp(proxy)
    validateIpThread()

下载链接：https://download.csdn.net/download/u012795120/10508293