Python urllib 2を使用してCSDNブログリストをローカルにダウンロード

806 ワード

# -*- coding: utf-8 -*-
import string, urllib2

#   CSDN    
def load_csdn(url, page):
    name = string.zfill(page, 5) + '.html'
    print '    ' + str(page) + '   ,     ' + name

    f = open(name, 'w+')
    url = url + '/' + str(page)
    print url

    #       
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.101 Safari/537.36'
    }
    req = urllib2.Request(url = url,headers = headers)
    m = urllib2.urlopen(req).read()
    
    f.write(m)
    f.close()

# http://blog.csdn.net/Geek_ymv/article/list/2

url = str(raw_input(u'     :'))
page = int(raw_input(u'      :'))

#        
load_csdn(url, page)