python写的的简单的爬虫小程序

import re

import urllib

def getHtml(url):

page=urllib.urlopen(url)

html=page.read()

return html

def getpic(html):

s=r‘src="(.*?\.jpg)" pic_ext‘

piclist=re.findall(s,html)

x=0

for imgurl in piclist:

urllib.urlretrieve(imgurl,‘%d.jpg‘%x)

x=x+1

html=getHtml(‘http://tieba.baidu.com/p/3216903619‘)

getpic(html)