Maison >développement back-end >tutoriel php >以正方教务系统为例,用php模拟登陆抓取课表、空教室,抓取课表_PHP教程
课程格子和超级课程表这两个应用,想必大学生都很熟悉,使用自己的学号和教务系统的密码,就可以将自己的课表导入,随时随地都可以在手机上查看。
其实稍微了解一点php的话,我们也可以做一个类似这样的web 应用。
1,解决掉验证码
其实这是正方的一个小bug,当我们进入登陆界面时,浏览器会去请求服务器,服务器会生成一个验证码图片。如果我们不去请求这个图片,那么正方后台也不会生成相应的 验证码,于是这样我们就有了可乘之机,让我高兴会儿~这时,我们在不填写验证码的情况下,可以很流畅的进入。大家可以在自己的电脑上禁止访问验证码的地址,然后试试这 是不是真的~当然,这只对正方有效。
2,php 的curl 模拟登陆
这里直接贴一个脚本之家对 curl 的讲解吧 http://www.jb51.net/article/51299.htm
接下来就是相关代码了,相信很多人和我一样,只喜欢看例子,对于长篇大论的讲解,转头就走……不过这个习惯还是不好……废话不多说!
//模拟登陆 function curl_request($url,$post='',$cookie='', $returnCookie=0){ $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)'); curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1); curl_setopt($curl, CURLOPT_AUTOREFERER, 1); curl_setopt($curl, CURLOPT_REFERER, "这里一定要换成教务系统登陆的url"); //填写教务系统url if($post) { curl_setopt($curl, CURLOPT_POST, 1); curl_setopt($curl, CURLOPT_POSTFIELDS, http_build_query($post)); } if($cookie) { curl_setopt($curl, CURLOPT_COOKIE, $cookie); } curl_setopt($curl, CURLOPT_HEADER, $returnCookie); curl_setopt($curl, CURLOPT_TIMEOUT, 20); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); $data = curl_exec($curl); if (curl_errno($curl)) { return curl_error($curl); } curl_close($curl); if($returnCookie){ list($header, $body) = explode("\r\n\r\n", $data, 2); preg_match_all("/Set\-Cookie:([^;]*);/", $header, $matches); $info['cookie'] = substr($matches[1][0], 1); $info['content'] = $body; return $info; }else{ return $data; } }
3,教务系统登陆页面的隐藏字段
举个栗子
<input type="hidden" name="__VIEWSTATE" value="dDwyODE2NTM0OTg7Oz61eIbnKVojBioGYtg2vsy2SklwiA==">
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)
<br /> //登陆页面的隐藏字段<br /> 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);
$pattern = '//is';
preg_match_all($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。如果不成功,要看看自己该提交的东西post 上去了没有,如果再不成功,额……可以联系我 imzhongshan@126.com
就这些了,赶快去试试吧!