复制代码 代码如下:

-- coding: utf-8 --

import re
import urllib
def getHtml(url):

找出给出网页的源码

page = urllib.urlopen(url)
html = page.read()
return html

def getImg(html):

正则

reg = r'src="(.*?\.jpg)"'

编译正则

imgre = re.compile(reg)

找出图片地址

imglist = re.findall(imgre,html)

循环遍历

x = 0
for i in imglist:
urllib.urlretrieve(i,'%s.jpg' % x)
x+=1
html = getHtml(r'http://www.renren.com/')
getImg(html)