#-*-coding:utf8-*-

 import requests

 import re

 import sys

 reload(sys)

 sys.setdefaultencoding("utf-8")

 class spider(object):

     def __init__(self):

         print "开始爬虫"

     def getsource(self,url):

         html = requests.get(url)

         return html.text

     def changepage(self,url,total_page):

         now_page = 1

         page_group = []

         for i in range(now_page,total_page+1):

             link = re.sub('(\d+)','%s'%i,url,re.S)

             page_group.append(link)

         return page_group

 if __name__ =='__main__':

     problem = []

     url = 'http://poj.org/problemlist?volume=1'

     pojspider = spider()

     all_link = pojspider.changepage(url,10)

     for link in all_link:

         print link

         htm = pojspider.getsource(link)

         problem = re.findall('href=problem?(.*?)</a>',htm,re.S)

         for i in problem:

             if i[0]=='?':

                 print i

                 f = open('info.txt','a')

                 f.writelines(i+'\n')

                 f.close()