#!/usr/bin/python
#-*- coidng:UTF-8-*-
'''
Created on 2015-1-19
@author: huangpeng03
'''
#coding=utf-8
import urllib
import re
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
def getImg(html):
reg = r'src="(.+?\.jpg)" pic_ext'
imgre = re.compile(reg)
imglist = re.findall(imgre,html)
x = 0
for imgurl in imglist:
urllib.urlretrieve(imgurl,'%s.jpg' % x)
x+=1
html = getHtml("http://tieba.baidu.com/p/2460150866")
print getImg(html)
默认下载路径是工程目录
.+? 是懒惰模式匹配 .+的意思是.至少含有一个,加个问号表示匹配成功一次后就不往后走了