抓取http://www.proxy.com.ru

#!/usr/bin/env python
#coding:utf-8
#BLOG: blog.linuxeye.com import urllib2 import re import threading import time import MySQLdb rawProxyList = [] checkedProxyList = [] #抓取代理网站 targets = [] for i in xrange(1,42): target = r"http://www.proxy.com.ru/list_%d.html" % i targets.append(target) #抓取代理服务器正则 p = re.compile(r'''<tr><b><td>(\d+)</td><td>(.+?)</td><td>(\d+)</td><td>(.+?)</td><td>(.+?)</td></b></tr>''') #获取代理的类 class ProxyGet(threading.Thread): def __init__(self,target): threading.Thread.__init__(self) self.target = target def getProxy(self): print "代理服务器目标网站： " + self.target req = urllib2.urlopen(self.target) result = req.read() #print chardet.detect(result) matchs = p.findall(result) # print matchs for row in matchs: ip=row[1] port =row[2] addr = row[4].decode("cp936").encode("utf-8") proxy = [ip,port,addr] print proxy rawProxyList.append(proxy) def run(self): self.getProxy() #检验代理的类 class ProxyCheck(threading.Thread): def __init__(self,proxyList): threading.Thread.__init__(self) self.proxyList = proxyList self.timeout = 5 self.testUrl = "http://www.baidu.com/" self.testStr 

转载于:https://www.cnblogs.com/qsjmobilesec/p/4564805.html