curl爬教务系统的数据解决思路

WBOY
Release: 2016-06-13 11:48:36
Original
769 people have browsed it

curl爬教务系统的数据
你好各位又来请教大家了,我现在又遇到这样的情况
代码是这样子的


header ( "content-Type: text/html; charset=utf-8" );
 require_once 'search.php';
// 第一步:提交数据,生成cookie,将cookie保存在临时目录下
$cookiejar = realpath ( 'cookie.txt' );
$id=$_GET['id'];
$password=$_GET['password'];
$year=$_GET['year'];
$term=$_GET['term'];
$ch = curl_init ();
$login_url = "http://211.67.32.51/default3.aspx";
$curlPost = "__VIEWSTATE=dDw5NTI3MzM0NTQ7dDw7bDxpPDE%2BO2k8NT47PjtsPHQ8O2w8aTw4PjtpPDExPjs%2BO2w8dDxwPDtwPGw8b25jbGljazs%2BO2w8d2luZG93LmNsb3NlKClcOzs%2BPj47Oz47dDxwPGw8VmlzaWJsZTs%2BO2w8bzxmPjs%2BPjs7Pjs%2BPjt0PHA8bDxWaXNpYmxlOz47bDxvPGY%2BOz4%2BOzs%2BOz4%2BO2w8aW1nREw7aW1nVEM7aW1nUU1NOz4%2BiyfPvg3FujyU8xX773LO%2FCbCuTw%3D&tbYHM=K061141026&tbPSW=100311&ddlSF=学生&imgDL.x=40&imgDL.y=7";
$curlPost = iconv("UTF-8", "GBK", $curlPost);
curl_setopt ( $ch, CURLOPT_URL, $login_url );
// 启用时会将头文件的信息作为数据流输出
curl_setopt ( $ch, CURLOPT_PROXY, 'jackdowosn.gnway.net:81');
curl_setopt ( $ch, CURLOPT_HEADER, 0 );
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/4");
curl_setopt($ch,CURLOPT_FOLLOWLOCATION,true);
curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, 1 );
curl_setopt ( $ch, CURLOPT_REFERER, 'http://211.67.32.51/' );
curl_setopt ( $ch, CURLOPT_POST, 1 );
curl_setopt ( $ch, CURLOPT_POSTFIELDS, $curlPost );
// 设置连接结束后保存cookie信息的文件
curl_setopt ( $ch, CURLOPT_COOKIEJAR, $cookiejar );
$data=curl_exec ( $ch );
//$data = mb_convert_encoding ( $data, "utf-8", "GBK" );
//echo '

'.$data.'';
$curlPost = "xh=K061141026";
$curlPost = iconv("UTF-8", "GBK", $curlPost);
curl_setopt ( $ch, CURLOPT_URL, "http://211.67.32.51/xscj.aspx?xh=K061141026" );
// 启用时会将头文件的信息作为数据流输出
curl_setopt ( $ch, CURLOPT_PROXY, 'jackdowosn.gnway.net:81');
curl_setopt ( $ch, CURLOPT_HEADER, 0 );
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/4");
curl_setopt($ch,CURLOPT_FOLLOWLOCATION,true);
curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, 1 );
curl_setopt ( $ch, CURLOPT_REFERER, 'http://211.67.32.51/' );
curl_setopt ( $ch, CURLOPT_POST, 0 );
curl_setopt ( $ch, CURLOPT_POSTFIELDS, $curlPost );
// 设置连接结束后保存cookie信息的文件
curl_setopt ( $ch, CURLOPT_COOKIEFILE, $cookiejar );
$data=curl_exec ( $ch );
$data = mb_convert_encoding ( $data, "utf-8", "GBK" );
preg_match_all ( '/\/i', $data, $matches );
//上面的模式修正符不能加s
//file_put_contents("d://value.txt",$matches[1][0]);
//echo var_dump($matches[1][0])."





";
//echo   $matches[1][0];
//echo ''.$data.'';
echo search3($id,$year, $term,$ch,$matches[1][0]);
?>


function search3($id,$year, $term, $ch,$value){
//$data=file_get_contents("d://value.txt");
curl_setopt ( $ch, CURLOPT_PROXY, 'jackdowosn.gnway.net:81');
$curlPost = "xh=K061141026&__VIEWSTATE=$value&Button2=按学年学期查询&ddlKCLX=必修&xn=2012-2013&xq=1";
$curlPost = iconv("UTF-8", "GBK", $curlPost);
curl_setopt ( $ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/4");
curl_setopt ( $ch, CURLOPT_FOLLOWLOCATION,true);
curl_setopt ( $ch, CURLOPT_URL, "http://211.67.32.51/xscj.aspx" );
curl_setopt ( $ch, CURLOPT_HEADER, 0);
curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, 1 );
curl_setopt ( $ch, CURLOPT_POST, 1 );
curl_setopt ( $ch, CURLOPT_REFERER, "http://211.67.32.51/xscj.aspx?xh=K061141026" );
curl_setopt ( $ch, CURLOPT_POSTFIELDS, $curlPost );
curl_setopt ( $ch, CURLOPT_COOKIEFILE, $cookiejar ); // 要回传cookie
$data = curl_exec ( $ch );
curl_close ( $ch );
$data = mb_convert_encoding ( $data, "utf-8", "GBK" );
/*preg_match_all ( '/\\s*\(.*?)\\s*\ (.*?)\/is', $data, $matches );
foreach ( $matches [1] as $key => $val )
$nav =$nav ."\n". $val . "---" . $matches [2] [$key];*/
return $data;
}


以上程序执行到search3时出现了,其他的都可正常返回数据。我问过一个前辈,他的回答是“我也不清楚喔。我有印象我们做正方系统遇到这种问题有可能是参数传错了,有可能是编码错了,也有可能没设置Referer这个参数”。请大家帮我看下问题出在哪里,有兴趣的可以帮我调试下,代理服务器都是真实可用的。下面是几个post参数和头信息

Related labels:
source:php.cn
Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Popular Tutorials
More>
Latest Downloads
More>
Web Effects
Website Source Code
Website Materials
Front End Template
About us Disclaimer Sitemap
php.cn:Public welfare online PHP training,Help PHP learners grow quickly!