AC自动机二之抓取南阳OJ题目列表 Python重写

代码像这样

__author__ = 'jtahstu'
import urllib2
import re
import sys
page=13
for i in xrange(1,page):
 url = 'http://acm.nyist.net/JudgeOnline/problemset.php?page='+str(i)
 headers = { 'User-Agent' : 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)' }
 try:
  request = urllib2.Request(url,headers = headers)
  response = urllib2.urlopen(request)
  content = response.read()
  # print content
  patten=re.compile('<TR.*?<TD>.*?<TD>(.*?)</TD>.*?<TD>(.*?)</TD>.*?probname tal.*?<a.*?">(.*?)</a>.*?<TD width="55" >(.*?) %</TD>.*?tal">\((.*?)/(.*?)\)</TD>',re.S)
  proList=re.findall(patten,content)
  # 0 题号
  # 1 难度
  # 2 标题
  # 3 AC率
  # 4 总AC次数
  # 5 总提交次数
  csv=open('naojproblem.csv','ab+')
  for res in proList:
   data='"'+res[0]+'","'+res[1]+'","'+res[2]+'","'+res[3]+'","'+res[4]+'","'+res[5]+'"'
   csv.write(data+"\r\n")
   print data
  csv.close()
 except urllib2.URLError, e:
    if hasattr(e,"code"):
        print e.code
    if hasattr(e,"reason"):
        print e.reason

去掉注释24行，生成csv格式文件，然后需要导入数据库，表结构如下

CREATE TABLE `nyojproblemlist` (
  `pid` int(11) NOT NULL,
  `difficult` int(11) DEFAULT NULL,
  `title` varchar(255) CHARACTER SET utf8 DEFAULT NULL,
  `ratio` int(11) DEFAULT NULL,
  `ac` int(11) DEFAULT NULL,
  `submit` int(11) DEFAULT NULL,
  PRIMARY KEY (`pid`)
) ENGINE=InnoDB DEFAULT CHARSET=latin1;

共有1141条数据，csv文件如下