一个简单的Python网络爬虫(抓图),针对某论坛.

 #coding:utf-8
 import urllib2
 import re
 import threading

 #图片下载
 def loadImg(addr,x,y,artName):
     data = urllib2.urlopen(addr).read()
     f = open(artName.decode("utf-8")+str(y)+'.jpg', 'wb')
     f.write(data)
     f.close()

 #具体帖子页面解析,得到图片链接地址,并使用loadImg下载 artName为帖子名
 def getImgLink(html,x,artName):
     relink = '<img src=".*" file="(.*)" width=".*" id=".*" alt=".*.jpg" />'
     cinfo = re.findall(relink,html)
     y = 0
     for lin in cinfo:
         imgAddr =  'http://www.xxx.com/'+lin
         print "LoadImg:"+str(x),imgAddr+'\n'
         t = threading.Thread(target=loadImg(imgAddr,x,y,artName)) #使用threading 多线程下载
         t.start()
         y = y+1

 #论坛版块页面解析,得到具体帖子链接
 def getArticleLink(html,page):
     relink = '<a href="(viewthread\.php\?tid=.*3D.*)">(.*)</a>'
     cinfo = re.findall(relink,html)
     x = 1
     for lin in cinfo:
         #print lin,'\n'
         url="http://www.xxx.com/"+lin[0]
         headers={"User-Agent":"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1"}
         req = urllib2.Request(url,headers=headers)
         response= urllib2.urlopen(req)
         html = response.read()
         getImgLink(html,x,lin[1])
         x = x+1

 start = 1 #起始页
 end = 100 #终止页
 for page in range(end):
     url="http://www.xxx.com/forumdisplay.php?fid=19&page="+str(page+start)
     headers={"User-Agent":"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1"}
     req = urllib2.Request(url,headers=headers)
     response= urllib2.urlopen(req)
     html = response.read()
     print'Start'
     getArticleLink(html,page)