使用PHP的CURL模拟POST采集开了viewstate的asp.net网页数据

用.NET做的网站如果做成POST提交方式,且开了viewstate的话，采集起来有点小繁琐,在此跟大家分享一下做法。

采的难点是必須先取得表單裏面的viewstate和datavalidtion兩個字段的值，並模擬POST給服務器，才能取到後面頁面的數據。由於回傳數據比較大，不能用默認的form/url-encode方法傳，要用傳文件的那個表單模式。主要代碼如下：

 /**
     QQ群:223494678
     函数:模拟post得到所有分页的页面信息
     参数:
         string $EVENTARGUMENT
         string $VIEWSTATE
         string $EVENTVALIDATION
         string $EVENTTARGET
     返回:
         string
 /**/
 function getn($EVENTARGUMENT = "", $VIEWSTATE = "", $EVENTVALIDATION = "", $EVENTTARGET = "pager"){
     $args = array();
     if($EVENTARGUMENT){
         $args = array(
             '__EVENTTARGET'=>$EVENTTARGET,
             '__EVENTARGUMENT'=>$EVENTARGUMENT,
             '__VIEWSTATE'=>$VIEWSTATE,
             '__EVENTVALIDATION'=>$EVENTVALIDATION,
             '__VIEWSTATEENCRYPTED'=>'',
             'search$txtFundName='=>'',
             'search$txtFundManger'=>'',
             'search$ddlFoundationDateOperater'=>'1',
             'search$txtFoundationDate'=>'',
             'search$dltFundType$ctl01$chkFundType'=>'on',
             'search$dltFundType$ctl01$chklFundChildType$0'=>'on',
             'search$dltFundType$ctl01$chklFundChildType$1'=>'on',
             'search$dltFundType$ctl01$chklFundChildType$2'=>'on',
             'search$dltFundType$ctl01$chklFundChildType$3'=>'on',
             'search$dltFundType$ctl01$chklFundChildType$4'=>'on',
             'search$chklFundStatus$0'=>'on',
             'search$ddlFundOrg'=>'0',
             'search$txtFundOrgName'=>'',
             'search$ddlStatisticDateOperater'=>'1',
             'search$txtStatisticDate'=>'',
             'search$radlStatisticMode'=>'1'
         );
     }

     $user_agent = "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.79 Safari/535.11";

     $ch = curl_init();
     curl_setopt($ch, CURLOPT_URL, 'http://???/default.aspx');
     curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);// 设为TRUE让结果不要直接输出
     curl_setopt($ch, CURLOPT_VERBOSE, TRUE);
     curl_setopt($ch, CURLOPT_AUTOREFERER, TRUE);
     curl_setopt($ch, CURLOPT_FAILONERROR, TRUE);
     curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE);
     curl_setopt($ch, CURLOPT_HEADER, TRUE);
     curl_setopt($ch, CURLINFO_HEADER_OUT, TRUE);

     curl_setopt($ch, CURLOPT_HTTPHEADER, array(
     'Accept:text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Accept-Language:zh-CN,zh;q=0.8',
     'Connection: Keep-Alive',
     'Cache-Control:max-age=0',
     'Referer:http://???/default.aspx',
     'Expect:'
     ));

     curl_setopt($ch, CURLOPT_POST, true); //启用POST提交
     curl_setopt($ch, CURLOPT_POSTFIELDS, $args); //设置POST提交的字符串
     curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);//HTTP请求User-Agent:头

     $document = curl_exec($ch); //执行预定义的CURL
     return $document;
 }

 /**
     QQ群:223494678
     函数:根据模拟post所得的页面信息，提取所需post的数据和分页，最后分解需要的html
     返回:
         string
 /**/
 function getHtml(){
     global $html;
     $first = getn();
     preg_match('/<font color="black"><b>(\d+?)<\/b><\/font> 页<\/span>/is', $first, $matches);
     $total = $matches[1];
     preg_match('/<table id="dltData".+?<!-- AspNetPager/is', $first, $matches);
     $html .= str_replace('<!-- AspNetPager', '', $matches[0]);
     $VIEWSTATE = "";
     $EVENTVALIDATION = "";
     preg_match('/<input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="(.+?)"/is', $first, $matches);
     $VIEWSTATE = $matches[1];
     preg_match('/<input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION" value="(.+?)"/is', $first, $matches);
     $EVENTVALIDATION = $matches[1];
     for($i = 2; $i <= $total; $i++){
         sleep(1);
         $EVENTARGUMENT = $i;
         $result = getn($EVENTARGUMENT, $VIEWSTATE, $EVENTVALIDATION);
         preg_match('/<table id="dltData".+?<!-- AspNetPager/is', $result, $matches);
         $html .= str_replace('<!-- AspNetPager', '', $matches[0]);
         $VIEWSTATE = "";
         $EVENTVALIDATION = "";
         preg_match('/<input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="(.+?)"/is', $result, $matches);
         $VIEWSTATE = $matches[1];
         preg_match('/<input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION" value="(.+?)"/is', $result, $matches);
         $EVENTVALIDATION = $matches[1];
     }
     return $html;
 }

getHtml是採集入口文件，裏面先取每一頁的數據，並提取頁碼等數據，然後循環採集後面的數據，getn是採集函數，主要是CURL模擬POST了