后端开发|Python教程
Python,抓取IP
后端开发-Python教程
这里以抓取 .ru 站点的代理服务器为例，代码如下：
socket vc源码,vscode能不能自动补全,ubuntu网络端口,jar包需要tomcat,社交软件爬虫,达内php讲师,seo关键词推广网站建设,网站签到插件lzw
#!/usr/bin/env python#coding:utf-8import urllib2import reimport threadingimport timeimport MySQLdbrawProxyList = []checkedProxyList = []#抓取代理网站targets = []for i in xrange(1,42): target = r".ru/list_%d.html" % i targets.append(target)#抓取代理服务器正则p = pile(r\
| (\d+) | (.+?) | (\d+) | (.+?) | (.+?) |
\)#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 = "/" self.testStr = "030173" def checkProxy(self): cookies = urllib2.HTTPCookieProcessor() for proxy in self.proxyList: proxyHandler = urllib2.ProxyHandler({"http" : rhttp://%s:%s %(proxy[0],proxy[1])}) #print rhttp://%s:%s %(proxy[0],proxy[1]) opener = urllib2.build_opener(cookies,proxyHandler) opener.addheaders = [(User-agent, Mozilla/5.0 (Windows NT 6.2; WOW64; rv:22.0) Gecko/0101 Firefox/22.0)] #urllib2.install_opener(opener) t1 = time.time() try: #req = urllib2.urlopen("", timeout=self.timeout) req = opener.open(self.testUrl, timeout=self.timeout) #print "urlopen is ok...." result = req.read() #print "read html...." timeused = time.time() - t1 pos = result.find(self.testStr) #print "pos is %s" %pos if pos > 1:checkedProxyList.append((proxy[0],proxy[1],proxy[2],timeused))#print "ok ip: %s %s %s %s" %(proxy[0],proxy[1],proxy[2],timeused) else:continue except Exception,e: #print e.message continue def run(self): self.checkProxy()if __name__ == "__main__": getThreads = [] checkThreads = []#对每个目标网站开启一个线程负责抓取代理for i in range(len(targets)): t = ProxyGet(targets[i]) getThreads.append(t)for i in range(len(getThreads)): getThreads[i].start()for i in range(len(getThreads)): getThreads[i].join()print .*10+"总共抓取了%s个代理" %len(rawProxyList) +.*10#开启20个线程负责校验，将抓取到的代理分成20份，每个线程校验一份for i in range(20): t = ProxyCheck(rawProxyList[((len(rawProxyList)+19)/20) * i:((len(rawProxyList)+19)/20) * (i+1)]) checkThreads.append(t)for i in range(len(checkThreads)): checkThreads[i].start()for i in range(len(checkThreads)): checkThreads[i].join()print .*10+"总共有%s个代理通过校验" %len(checkedProxyList) +.*10#插入数据库，表结构自己创建，四个字段ip,port,speed,addressdef db_insert(insert_list): try: conn = MySQLdb.connect(host="localhost", user="root", passwd="admin",db="m_common",charset=utf8) cursor = conn.cursor() cursor.execute(delete from proxy) cursor.execute(alter table proxy AUTO_INCREMENT=1) cursor.executemany("INSERT INTO proxy(ip,port,speed,address) VALUES (%s,%s,%s,%s)",insert_list) mit() cursor.close() conn.close() except MySQLdb.Error,e: print "Mysql Error %d: %s" % (e.args[0], e.args[1])#代理排序持久化proxy_ok = []f= open("proxy_list.txt",w+)for proxy in sorted(checkedProxyList,cmp=lambda x,y:cmp(x[3],y[3])): if proxy[3] < 8: #print "checked proxy is: %s:%s\t%s\t%s" %(proxy[0],proxy[1],proxy[2],proxy[3]) proxy_ok.append((proxy[0],proxy[1],proxy[3],proxy[2])) f.write("%s:%s\t%s\t%s\n"%(proxy[0],proxy[1],proxy[2],proxy[3]))f.close()db_insert(proxy_ok)
信用卡活动查询网站源码,ubuntu修改机器名字,tomcat拒绝服务配置,爬虫JS逆向,好的php学习外包,快照seolzw
测试：
装饰公司网站源码下载,vscode编写html的插件,ubuntu alsa,tomcat运行多个项目,数组 sqlite,日本 网页设计,gbk的网站 utf8的数据库,阿里云怎么登陆服务器,js 弹窗插件 iframe,前端操作数据库 框架设计,爬虫老李,php 跳过,seo微信群,springboot事物代码,织梦调用商品标签,asp网站防注入代码,网页粒子效果怎么做的,dashboard 模板,电子商务后台模板,手机页面禁止滚动,成本管理系统v2.0,有趣php程序lzw
python proxy.py
结果如下：
[61.58.94.179, 8088, \xe5\x8f\xb0\xe6\xb9\xbe\xe7\x9c\x81 \xe5\x8f\xb0\xe6\xb9\xbe\xe5\xae\xbd\xe9\xa2\x91\xe9\x80\x9a\xe8\xae\xaf\xe9\xa1\xbe\xe9\x97\xae\xe8\x82\xa1\xe4\xbb\xbd\xe6\x9c\x89\xe9\x99\x90\xe5\x85\xac\xe5\x8f\xb8][200.84.116.99, 9064, \xe5\xa7\x94\xe5\x86\x85\xe7\x91\x9e\xe6\x8b\x89 ][183.223.204.8, 8123, \xe5\x9b\x9b\xe5\xb7\x9d\xe7\x9c\x81\xe8\x87\xaa\xe8\xb4\xa1\xe5\xb8\x82 \xe7\xa7\xbb\xe5\x8a\xa8]..........总共抓取了1921个代理....................总共有524个代理通过校验..........# more proxy_list.txt202.106.169.142:80 北京市 联通ADSL 0.291432857513111.13.136.59:80 北京市 移动 0.297957897186111.13.136.56:80 北京市 移动 0.373070955276111.206.81.248:80 北京市 联通 0.403017997742111.13.136.58:80 北京市 移动 0.414332151413124.202.217.134:8118 北京市 电信通 0.416817903519124.202.183.218:8118 北京市 电信通 0.426618099213120.132.71.232:80 北京市 联通 0.44020009040861.232.6.164:8081 北京市 铁通 0.469615936279118.144.96.253:80 北京市 电信通 0.485229969025203.192.10.66:80 北京市 新华社 0.51485991478124.202.182.22:8118 北京市 电信通 0.553130865097
数据库：
mysql> select * from m_common.proxy limit 10;
+----------+-----------------+------+----------+----------------------+---------------------+| proxy_id | ip | port | speed | address | create_time |+----------+-----------------+------+----------+----------------------+---------------------+| 1 | 202.106.169.142 | 80 | 0.291433 | 北京市 联通ADSL | -02-26 11:29:24 || 2 | 111.13.136.59 | 80 | 0.297958 | 北京市 移动 | -02-26 11:29:24 || 3 | 111.13.136.56 | 80 | 0.373071 | 北京市 移动 | -02-26 11:29:24 || 4 | 111.206.81.248 | 80 | 0.403018 | 北京市 联通 | -02-26 11:29:24 || 5 | 111.13.136.58 | 80 | 0.414332 | 北京市 移动 | -02-26 11:29:24 || 6 | 124.202.217.134 | 8118 | 0.416818 | 北京市 电信通 | -02-26 11:29:24 || 7 | 124.202.183.218 | 8118 | 0.426618 | 北京市 电信通 | -02-26 11:29:24 || 8 | 120.132.71.232 | 80 | 0.4402 | 北京市 联通 | -02-26 11:29:24 || 9 | 61.232.6.164 | 8081 | 0.469616 | 北京市 铁通 | -02-26 11:29:24 || 10 | 118.144.96.253 | 80 | 0.48523 | 北京市 电信通 | -02-26 11:29:24 |+----------+-----------------+------+----------+----------------------+---------------------+10 rows in set (0.00 sec)
