一、需求背景
网站刷票时，经常会遇到限制一个ip只能投票一次的限制，为此需要使用代理ip
二、脚本如下：
1、Proxy_http.py使用代理ip发送httpr的get和post请求
#coding:utf-8
import urllib2,urllib,time,socket,random,Proxy_ip,Useragent
def Visitpage(proxyip,url):
socket.setdefaulttimeout(6)
proxy_support = urllib2.ProxyHandler({'http':proxyip})
user_agent = random.choice(Useragent.user_agents)
opener = urllib2.build_opener(proxy_support,urllib2.HTTPHandler)
urllib2.install_opener(opener)
try:
request = urllib2.Request(url)
request.add_header('Referer','http://www.baidu.com')
request.add_header('User-Agent',user_agent)
html = urllib2.urlopen(request).read()
print html
time.sleep(random.randint(60,180))
except urllib2.URLError,e:
print 'URLError! The bad proxy is %s' %proxyip
except urllib2.HTTPError,e:
print 'HTTPError! The bad proxy is %s' %proxyip
except:
print 'Unknown Errors! The bad proxy is %s ' %proxyip
def Clicklikebutton(proxyip,url,data):
socket.setdefaulttimeout(6)
proxy_support = urllib2.ProxyHandler({'http':proxyip})
user_agent = random.choice(Useragent.user_agents)
opener = urllib2.build_opener(proxy_support,urllib2.HTTPHandler)
try:
request = urllib2.Request(url)
request.add_header('Referer','http://www.baidu.com')
request.add_header('User-Agent',user_agent)
data = urllib.urlencode(data)
resp = opener.open(request, data)
print resp.read()
time.sleep(random.randint(60,180))
except urllib2.URLError,e:
print 'URLError! The bad proxy is %s' %proxyip
except urllib2.HTTPError,e:
print 'HTTPError! The bad proxy is %s' %proxyip
except:
print 'Unknown Errors! The bad proxy is %s ' %proxyip
def main():
for i in range(len(Proxy_ip.iplist)):
proxyip = Proxy_ip.iplist[i]
i += 1
print proxyip
for m in range(random.randint(2,4)):
Clicklikebutton(proxyip,'你的post请求地址',{你的post请求参数})
if __name__ == "__main__":
main()
2、Useragent.py文件为agent库
#!/usr/bin/python
#-*- coding:utf-8 -*-
user_agents = [
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60'
'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50'
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50'
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0'
'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10'
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2'
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36'
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11'
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16'
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50'
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50'
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0'
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)'
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.75 Safari/537.36'
]
3、Proxy_ip.py为读取代理ip文件
#coding:utf-8
iplist = []
datafile = file( "E:\\monkey_test\\http\\1222-1.txt", "r" )
for line in datafile.readlines():
line = line.strip('\n')
iplist.append(line)
4、代理ip的获取
可在以下网站获取http://www.xicidaili.com/（可自行开发脚本爬取网站的ip，容易被封，脚本在此不提供）
也可以购买http://www.daxiangdaili.com/