Python爬取贴吧图片都只能爬取第一页的,加了循环也不行,现在可以了。
#coding:utf-8
import urllib
import urllib2
import re
import os
# 将正则表达式编译成Pattern对象
rex=r'src="(http://imgsrc.baidu.com/forum/w%3D580.*?\.jpg)"';
root = "D:\\tupian\\"
for page in range(1,3):
pageurl = "http://tieba.baidu.com/p/3710495592?pn="+str(page);
Response=urllib2.urlopen(pageurl);
Html=Response.read();
lists = re.findall(rex, Html);
lensofpage=len(lists);
print lensofpage;
picname = 'pic' + str(page);
print picname;
x=1;
for picurl in lists:
if not os.path.exists(root+picname):
os.mkdir(root+picname)
urllib.urlretrieve(picurl,root+'%s\%s.jpg' % (picname,x));
#print str(page)+picurl;
print ".",
x=x+1;