python 网络爬虫

来源：互联网发布：工业怪兽知乎编辑：程序博客网时间：2024/04/30 12:52

# -*- coding: cp936 -*-import string,urllib2path = "G:/New Knowledge/practice/python/tmp/"def baidu_tieba(url,begin_page,end_page):    for i in range(begin_page,end_page+1):        Name = path+string.zfill(i,5)+'.html'#自动填充        print '下载'+str(i)+'个网页，并存为'+Name        f = open(Name,'w+')        data = urllib2.urlopen(url+str(i)).read()        f.write(data)        f.close()bdurl = raw_input(u'input url 去除最后的数字\n')begin_page = raw_input("begin page")end_page = raw_input("endpage")if not bdurl:    bdurl = 'http://tieba.baidu.com/p/2296017831?pn='if not begin_page:    begin_page = 1if not end_page:    end_page = 10baidu_tieba(bdurl,int(begin_page),int(end_page));

input url 去除最后的数字
http://tieba.baidu.com/p/301797825
begin page0
endpage9
下载1个网页，并存为00001.html
下载2个网页，并存为00002.html
下载3个网页，并存为00003.html
下载4个网页，并存为00004.html
下载5个网页，并存为00005.html
下载6个网页，并存为00006.html
下载7个网页，并存为00007.html
下载8个网页，并存为00008.html
下载9个网页，并存为00009.html
>>> ================================ RESTART ================================
>>>
input url 去除最后的数字

begin page
endpage
下载1个网页，并存为G:/New Knowledge/practice/python/tmp/00001.html
下载2个网页，并存为G:/New Knowledge/practice/python/tmp/00002.html
下载3个网页，并存为G:/New Knowledge/practice/python/tmp/00003.html
下载4个网页，并存为G:/New Knowledge/practice/python/tmp/00004.html
下载5个网页，并存为G:/New Knowledge/practice/python/tmp/00005.html
下载6个网页，并存为G:/New Knowledge/practice/python/tmp/00006.html
下载7个网页，并存为G:/New Knowledge/practice/python/tmp/00007.html
下载8个网页，并存为G:/New Knowledge/practice/python/tmp/00008.html
下载9个网页，并存为G:/New Knowledge/practice/python/tmp/00009.html
下载10个网页，并存为G:/New Knowledge/practice/python/tmp/00010.html

0 0