简单的网络爬虫代码

import urllib.request
import re
import os
import urllib
def getHtml(url):
      page = urllib.request.urlopen(url)
      html = page.read()
      return html.decode('UTF-8')
 
def getImg(html):
     reg = r'src="(.+?\.jpg)" pic_ext'
     imgre = re.compile(reg)
     imglist = imgre.findall(html)
     x = 0
     path = 'D:\\test'  
    
     if not os.path.isdir(path):  
         os.makedirs(path)  
     paths = path+'\\'    
 
     for imgurl in imglist:  
         urllib.request.urlretrieve(imgurl,'{}{}.jpg'.format(paths,x)) 
         x = x + 1  
     return imglist
html = getHtml("http://tieba.baidu.com/p/2460150866")
print (getImg(html))