python图片小爬虫

标签：python   爬虫   

import re
import urllib
import os

def rename(name): 
    name = name + '.jpg'
    return name  

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)
    
    
    os.chdir("E:\\pic")  
    os.getcwd() 
    x=1
    for imgurl in imglist:
        img=urllib.urlopen(imgurl)
          
        
        name=str(x)  
        name = rename(name)  
        print(name) 
        x=x+1
        
        f=open(name,'wb')
        f.write(img.read()) 
        f.close()
 
 
 
    
html = getHtml("http://tieba.baidu.com/p/3553148164")
getImg(html)
print 'pic save!'



    

爬取的网页是  http://tieba.baidu.com/p/3553148164

图片保存在E盘pic文件夹下

爬取结果如下:

python图片小爬虫

标签：python   爬虫   

原文地址：http://blog.csdn.net/u013018721/article/details/43280425