php实现模拟登陆方正教务系统抓取课表(2)-木庄网络博客

　　　　这些东西在登陆的时候也是需要带上的，顺便贴出函数，顺便暴漏了博主的学校……皇家种地大学（主要是正则表达式的运用）

//登陆页面的隐藏字段　　

function getView(){
  $url = 'http://jw.hzau.edu.cn/default2.aspx';
  $result = curl_request($url);
  $pattern = '/<input type="hidden" name="__VIEWSTATE" value="(.*?)" \/>/is';
  preg_match_all($pattern, $result, $matches);
  $res[0] = $matches[1][0];
     
  return $res[0] ;
}
　　//返回教室查询页面的隐藏值
　　private function getViewJs($cookie,$xh){
　　　　$url = "http://jw.hzau.edu.cn/xxjsjy.aspx?xh={$xh}";
　　　　$result = curl_request($url,'',$cookie);
　　　　$pattern = '/<input type="hidden" name="__VIEWSTATE" value="(.*?)" \/>/is';
　　　　preg_match_all($pattern, $result, $matches);
　　　　$res[0] = $matches[1][0];
　　　　return $res[0] ;
　　}

　　4，cookie 的获取

function login($xh,$pwd){
    $url = 'http://jw.hzau.edu.cn/default2.aspx';
    $post['__VIEWSTATE'] = $this->getView();
    $post['txtUserName'] = $xh; //填写学号
    $post['TextBox2'] = $pwd; //填写密码
    $post['txtSecretCode'] = '';
    $post['lbLanguage'] = '';
    $post['hidPdrs'] = '';
    $post['hidsc'] = '';
    $post['RadioButtonList1'] = iconv('utf-8', 'gb2312', '学生');
    $post['Button1'] = iconv('utf-8', 'gb2312', '登录');
    $result = curl_request($url,$post,'', 1);
    return $result['cookie'];
  }

　　5，让我们来试试查课表的功能，格式有点乱额，大家凑合着看，我把课表转成了一个二维关联数组

//返回课表字符串
private function classresult($xh,$pwd){
    date_default_timezone_set("PRC"); //时区设置
    $classList = "";//声明课表变量
 
    $cookie = $this->login($xh,$pwd);
    $view = $this->getViewJs($cookie,$xh);//验证密码是否正确
 
    //如果密码正确
    if (!empty($view)) {
      $url = "http://jw.hzau.edu.cn/xskbcx.aspx?xh={$xh}";
      $result = curl_request($url,'',$cookie); //保存的cookies
      preg_match_all('/<table id="Table1"[\w\W]*?>([\w\W]*?)<\/table>/',$result,$out);
      $table = $out[0][0]; //获取整个课表
 
      preg_match_all('/<td [\w\W]*?>([\w\W]*?)<\/td>/',$table,$out);
      $td = $out[1];
      $length = count($td);
 
      //获得课程列表
      for ($i=0; $i < $length; $i++) {
        $td[$i] = str_replace("<br>", "", $td[$i]);
 
        $reg = "/{(.*)}/";
       
        if (!preg_match_all($reg, $td[$i], $matches)) {
          unset($td[$i]);
        }
      }
 
      $td = array_values($td); //将课程列表数组重新索引
      $tdLength = count($td);
      for ($i=0; $i < $tdLength; $i++) {
        $td[$i] = iconv('GB2312','UTF-8',$td[$i]);
      }
 
      //将课表转换成数组形式
      function converttoTable($table){
        $list = array(
          'sun' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          ),
          'mon' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          ),
          'tues' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          ),
          'wed' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          ),
          'thur' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          ),
          'fri' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          ),
          'sat' => array(
            '1,2' => '',
            '3,4' => '',
            '5,6' => '',
            '7,8' => '',
            '9,10' => ''
          )
        );
        $week = array("sun"=>"周日","mon"=>"周一","tues"=>"周二","wed"=>"周三","thur"=>"周四","fri"=>"周五","sat"=>"周六");
        $order = array('1,2','3,4','5,6','7,8','9,10');
        foreach ($table as $key => $value) {
          $class = $value;
          foreach ($week as $key => $weekDay) {
            $pos = strpos($class,$weekDay);
            // echo $pos;
            if ($pos) {
              $weekArrayDay = $key; //获取list数组中的第一维key
              foreach ($order as $key => $orderClass) {
                $pos = strpos($class,$orderClass);
                if ($pos) {
                  $weekArrayOrder = $orderClass; //获取该课程是第几节
                  break;
                }
              }
              break;
            }
          }
          $list[$weekArrayDay][$weekArrayOrder] = $class;
        }
        return $list;
      }
           
      //调用函数
      return converttoTable($td);
    }else{
      return 0;
    }
  }

　　6，再试试查询空教室的功能

//空教室查询结果
  public function roomresult(){
    $xh = ""; //设置学号
    $pwd = ""; //学号对应的密码
 
    $cookie = $this->login($xh,$pwd);
    $url = "http://jw.hzau.edu.cn/xs_main.aspx?xh={$xh}";
    $result = curl_request($url,'',$cookie); //保存的cookies
 
    $url="http://jw.hzau.edu.cn/xxjsjy.aspx?xh={$xh}";
    $post['Button2'] = iconv('utf-8', 'gb2312', '空教室查询');
    $post['__EVENTARGUMENT']='';
    $post['__EVENTTARGET']='';
    $post['__VIEWSTATE'] = $this->getViewJs($cookie,$xh);
    $post['ddlDsz'] = iconv('utf-8', 'gb2312', '单');
    $post['ddlSyXn'] = '2014-2015'; //学年
    $post['ddlSyxq'] = '1';
    $post['jslb'] = '';
    $post['xiaoq'] = '';
 
    $post['kssj']=$_GET['start']; //提交的开始查询时间 
    $post['sjd']=$_GET['class'];//提交的课程节次
 
    $post['xn']='2014-2015';//所在学年
    $post['xq']='2';//所在学期
    $post['xqj']='6';//当天星期几
    $post['dpDataGrid1:txtPageSize']=90;//每页显示条数
 
    $result = curl_request($url,$post,$cookie,0);
     
    preg_match_all('/<span[^>]+>[^>]+span>/',$result,$out);
    $tip = iconv('gb2312', 'utf-8', $out[0][3]);//获取页面前部的提示内容
    preg_match_all('/<table[\w\W]*?>([\w\W]*?)<\/table>/',$result,$out);
    $table = iconv('gb2312', 'utf-8', $out[0][0]); //获取查询列表
     
    $this->load->view("classroom",array('tip'=>$tip,'table'=>$table));
  }

　　总结起来就是这些了，每个学校的教务系统都不尽相同，这时我们可以借助火狐浏览器的 firebug 抓包，看看到底提交了哪些东西。

以上所述就是本文的全部内容了，希望大家能够喜欢。

更多相关Discuz论坛的内容来自木庄网络博客

标签：Discuz论坛

返回前面的内容