python连续爬取多个网页的图片分别保存到不同的文件夹

Z时代
2024-01-10
分类：综合

python

作者:vpoet

mail:vpoet_sir@163.com

 1 #coding:utf-8
 2 import urllib
 3 import urllib2
 4 import re
 5 
 6 
 7 # 将正则表达式编译成Pattern对象
 8 rex=r'src="(http://imgsrc.baidu.com/forum/w%3D580.*?\.jpg)"';
 9 pages = ('1','2');
10 
11 for page in pages:
12     pageurl = "http://tieba.baidu.com/p/3710495592?pn="+page;
13     Response=urllib2.urlopen(pageurl);
14     Html=Response.read();
15     lists = re.findall(rex, Html);
16     lensofpage=len(lists);
17     print lensofpage;
18     
19     picname = 'pic' + page;
20     print picname;
21     x=1;
22     for picurl in lists:
23         urllib.urlretrieve(picurl,'C:\Users\Administrator\Desktop\%s\%s.jpg' % (picname,x));
24         print page+picurl;
25         x=x+1;
26 
27    
28    
29 print 'DownLoadPicOver'
30 # 图片存储路径:C:\Users\Administrator\Desktop\pic1
31         # C:\Users\Administrator\Desktop\pic2
32 #测试爬取网址:http://tieba.baidu.com/p/3710495592?pn=1
33 #         http://tieba.baidu.com/p/3710495592?pn=2