Python爬虫第一篇

#!/usr/bin/env python
#coding=utf-8
#http://tieba.baidu.com/p/3296647141
import re
import urllib

def get_content(url):
    '''doc.'''
    html=urllib.urlopen(url)
    content=html.read()
    html.close()

    return content
def get_images(info):
    """get images 
    """
    regex=r'class="BDE_Image" pic_type="0" width="(.+?)" height="(.+?)" src="(.+?\.jpg)"'
    pat=re.compile(regex)#moshi
    images_code=re.findall(pat,info)
    print images_code[2]
    i=0
    for image_url in images_code:
        print 'image_url:',image_url
        urllib.urlretrieve(image_url[2],'%d.jpg'%i)
        i+=1
    print 'count:',i

if __name__=='__main__':
    info=get_content('http://tieba.baidu.com/p/3296647141')
    get_images(info)