Python制作刷网页流量工具


            准备

必须环境：

Python3



开始

先实现一个简单的版本，直接上代码：







import urllib.request

import urllib.error

#创建get方法

def get(url):

 code=urllib.request.urlopen(url).code

 return code

if __name__ == '__main__':

#设置一些基本属性

 url = "http://shua.zwyuanma.com"

 user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.63 Safari/537.36"

 headers = {'User-Agent':user_agent}

 req = urllib.request.Request(url, headers=headers)

 #记录次数

 i = 1

 while 1: 

   code = get(url)

   print('访问:'+str(code))

   i = i+1







简单粗暴，刷的只是 pv,ip 没变，容易被搜索引擎发现，下面我们来改进一下



增加代理功能

给 get 方法添加以下代码：







random_proxy = random.choice(proxies)

proxy_support = urllib.request.ProxyHandler({"http":random_proxy})

opener = urllib.request.build_opener(proxy_support)

urllib.request.install_opener(opener)









修改一下主方法：







if __name__ == '__main__':

 url = "http://shua.zwyuanma.com"

 #添加代理列表，可以自行去百度获取

 proxies = ["124.88.67.22:80","124.88.67.82:80","124.88.67.81:80","124.88.67.31:80","124.88.67.19:80","58.23.16.240:80"]

 user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.63 Safari/537.36"

 headers = {'User-Agent':user_agent}

 req = urllib.request.Request(url, headers=headers)

 i = 1

 while 1:

   #添加参数

   code = get(url,proxies)

   print('第'+str(i)+'次代理访问:'+str(code))

   i = i+1









这样差不多了，不过有个 bug ，如果页面打不开了或者代理失效了，程序就自动结束了，接下来我们添加异常处理功能



异常处理

定义 mail 方法 ，用来发邮件提醒





def mail(txt):

 _user = "你的账号"

 _pwd = "你的密码"

 _to = "收件账号"

 msg = MIMEText(txt, 'plain', 'utf-8')

 #标题

 msg["Subject"] = "代理失效！"

 msg["From"] = _user

 msg["To"] = _to



 try:

   #这里我用的qq邮箱

   s = smtplib.SMTP_SSL("smtp.qq.com", 465)

   s.login(_user, _pwd)

   s.sendmail(_user, _to, msg.as_string())

   s.quit()

   print("Success!")



 except smtplib.SMTPException as e:

   print("Falied,%s" % e)









然后我们修改一下主方法：







if __name__ == '__main__':

 url = "http://shua.zwyuanma.com"

 proxies = ["124.88.67.22:80","124.88.67.82:80","124.88.67.81:80","124.88.67.31:80","124.88.67.19:80","58.23.16.240:80"]

 user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.63 Safari/537.36"

 headers = {'User-Agent':user_agent}

 req = urllib.request.Request(url, headers=headers)

 i = 1

 while 1:

   try:

     code = get(url,proxies)

     print('第'+str(i)+'次代理访问:'+str(code))

     i = i+1

   except urllib.error.HTTPError as e:

     print(e.code)

      #添加mail方法

     mail(e.code)

   except urllib.error.URLError as err:

     print(err.reason)

      #添加mail方法

     mail(err.reason)









完成！



结语

代码只有短短的 50 行，程序还可以改进：



例如：代理列表自动获取，添加界面,扩展下多线程等等

最后给再给大家分享一个其他小伙伴的作品





import urllib2

import timeit

import thread 

import time

i = 0

mylock = thread.allocate_lock()

def test(no,r):

  global i

  url = 'http://blog.csdn.net'

  for j in range(1,r):

    req=urllib2.Request(url) 

    req.add_header("User-Agent","Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)") 

    file = urllib2.urlopen(req)

    print file.getcode();

    mylock.acquire()

    i+=1

    mylock.release()  

    print i;

  thread.exit_thread()



def fast():

    thread.start_new_thread(test,(1,50))

    thread.start_new_thread(test,(2,50)) 



fast()

time.sleep(15)







经测试，超过两个线程以上服务器就会出现503错误，所以2个线程刚好