#!/usr/bin/python
#-*- coding:utf-8 -*-
'''
此脚本主要实现网页的点击量，除了实现次功能点外，还有三个知识点：
1、随机获取代理ip，通过代理ip访问指定站点，其目的是防止ip被封
2、访问一个页面后，随机休息几秒，再访问，其目的是防止网站前面有4-7层过滤设备拦截
3、修改http的user agent字段，有些网站和4-7层设备会检查
'''
import urllib2,re,time,urllib,random,user_agents
PROXYIPURL = 'http://www.goodips.com/?ip=&port=&dengji=&adr=%E7%94%B5%E4%BF%A1&checktime=&sleep=1%E7%A7%92%E5%86%85&cunhuo=48%E5%B0%8F%E6%97%B6%E4%BB%A5%E4%B8%8A&px='
class getProxyIP:
# 从网页抓去代理ip ，并整理格式
def getProxyHtml(self):
# 抓去代理 ip页面的代码
page = urllib.urlopen(PROXYIPURL)
html = page.read()
#print html
return html
def ipPortRe(self):
# 从页面代码中取出代理 ip和端口
html = self.getProxyHtml()
#ip_re = re.compile(r'(((2[0-4]d|25[0-5]|[01]?dd?).){3}(2[0-4]d|25[0-5]|[01]?dd?))')
ip_re = re.compile(r'(d{1,3}.d{1,3}.d{1,3}.d{1,3}).+
.+>(d{1,5})<')
ip_port = re.findall(ip_re,html)
return ip_port
def proxyIP(self):
# 格式化输出代理 ip和端口
ip_port = self.ipPortRe()
# 将代理 ip整理成['221.238.28.158:8081', '183.62.62.188:9999']格式
proxyIP = []
for i in range(0,len(ip_port)):
proxyIP.append(':'.join(ip_port[i]))
# 将代理 ip整理成[{'http': 'http://221.238.28.158:8081'}, {'http': 'http://183.62.62.188:9999'}]格式
proxy_list = []
for i in range(0,len(proxyIP)):
a0 = 'http://%s'%proxyIP[i]
a1 = {'http':'%s'%a0}
proxy_list.append(a1)
return proxy_list
def getHtml(url):
p = getProxyIP()
proxy_list = p.proxyIP()
proxy_ip =random.choice(proxy_list) #在proxy_list中随机取一个ip
print proxy_ip
proxy_support = urllib2.ProxyHandler(proxy_ip)
opener = urllib2.build_opener(proxy_support,urllib2.HTTPHandler)
urllib2.install_opener(opener)
request = urllib2.Request(url)
user_agent = random.choice(user_agents.user_agents) #在user_agents中随机取一个做user_agent
request.add_header('User-Agent',user_agent) #修改user-Agent字段
print user_agent
html = urllib2.urlopen(request).read()
print proxy_ip
return proxy_ip
URLS = ['http://www.x'x'xxw.net/study.asp?vip=',
'http://www.x'x'x'x'x'x.com/?fromuid=16',
]
count_True,count_False,count= 0,0,0
while True:
for url in URLS:
count +=1
try:
proxy_ip=getHtml(url)
except urllib2.URLError:
#print 'URLError! The bad proxy is %s' %proxy_ip
count_False += 1
except urllib2.HTTPError:
#print 'HTTPError! The bad proxy is %s' %proxy_ip
count_False += 1
except:
#print 'Unknown Errors! The bad proxy is %s ' %proxy_ip
count_False += 1
randomTime = random.uniform(1,3) #取1-10之间的随机浮点数
time.sleep(randomTime) #随机等待时间
print '%d Eroors,%d ok,总数 %d' %(count_False,count - count_False,count)
1 #!/usr/bin/python
2 #-*- coding:utf-8 -*-
3 '''
4 Created on 2013-7-14
5
6 @author: Administrator
7 '''
8
9 user_agents = [
10 'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
11 'Opera/9.25 (Windows NT 5.1; U; en)',
12 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
13 'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
14 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
15 'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9'
16 ]
View Code