python爬虫下载制定网址的图片

参看：http://www.cnblogs.com/fnng/p/3576154.html

点击(此处)折叠或打开

1. import urllib
   
2. import re
   
3. 
   
4. def getHtml(url):
   
5.     page = urllib.urlopen(url)
   
6.     html = page.read()
   
7.     return html
   
8. 
   
9. def getImg(html):
   
10.     reg = r'src="(.+?\.jpg)" pic_ext'
    
11.     imgre = re.compile(reg)
    
12.     imglist = re.findall(imgre,html)
    
13.     x = 0
    
14.     for imgurl in imglist:
    
15.         urllib.urlretrieve(imgurl,'%s.jpg' % x)
    
16.         x +=1
    
17. 
    
18. html = getHtml('http://tieba.baidu.com/p/2460150866')
    
19. print getImg(html)