Python使用代理抓取网站图片(多线程)
本文导语: 一、功能说明:1. 多线程方式抓取代理服务器,并多线程验证代理服务器ps 代理服务器是从http://www.cnproxy.com/ (测试只选择了8个页面)抓取2. 抓取一个网站的图片地址,多线程随机取一个代理服务器下载图片二、实现代码 代...
一、功能说明:
1. 多线程方式抓取代理服务器,并多线程验证代理服务器
ps 代理服务器是从http://www.cnproxy.com/ (测试只选择了8个页面)抓取
2. 抓取一个网站的图片地址,多线程随机取一个代理服务器下载图片
二、实现代码
#!/usr/bin/env python
#coding:utf-8
import urllib2
import re
import threading
import time
import random
rawProxyList = []
checkedProxyList = []
imgurl_list = []
#抓取代理网站
portdicts ={'v':"3",'m':"4",'a':"2",'l':"9",'q':"0",'b':"5",'i':"7",'w':"6",'r':"8",'c':"1"}
targets = []
for i in xrange(1,9):
target = r"http://www.cnproxy.com/proxy%d.html" % i
targets.append(target)
#print targets
#抓取代理服务器正则
p = re.compile(r'''(.+?)document.write(":"+(.+?))(.+?).+?(.+?)''')
#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)
for row in matchs:
ip=row[0]
port =row[1]
port = map(lambda x:portdicts[x],port.split('+'))
port = ''.join(port)
agent = row[2]
addr = row[3].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 = "030173"
def checkProxy(self):
cookies = urllib2.HTTPCookieProcessor()
for proxy in self.proxyList:
proxyHandler = urllib2.ProxyHandler({"http" : r'http://%s:%s' %(proxy[0],proxy[1])})
#print r'http://%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/20100101 Firefox/22.0')]
#urllib2.install_opener(opener)
t1 = time.time()
try:
#req = urllib2.urlopen("http://www.baidu.com", 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()
#获取图片地址函数
def imgurlList(url_home):
global imgurl_list
home_page = urllib2.urlopen(url_home)
url_re = re.compile(r'
pic_re = re.compile(r'