python爬蟲教程之爬取百度貼吧並下載的樣本

測試url：http://tieba.baidu.com/p/27141123322?pn=
begin 1
end 4

代碼如下:

import string ,urllib2

def baidu_tieba(url,begin_page,end_page):
for i in range(begin_page, end_page+1):
sName = string.zfill(i,5)+ '.html'
print '正在下載第' + str(i) + '個網頁，並將其儲存為' + sName + '..........'
f = open (sName,'w+')
m = urllib2.urlopen(url + str(i)).read()
f.write(m)
f.close()

bdurl = str(raw_input('url： \n'))
begin_page = int(raw_input('begin :\n'))
end_page = int(raw_input('end : \n'))

baidu_tieba(bdurl,begin_page,end_page)

