想下载“http://kaoshi.edu.sina.com.cn/collegedb/index.php?_action=more&show=more_score&provid=6&wl=2&collegeid=10001”里的分数线表格(不止这一个网站,是想批量下载)
就是collegeid=后面的10001 10002 10003 ……
然后用excl整理一下。但是发现在迅雷里批量添加下载地址后下载下来的是index.php一个文件,而且里面的分数线表格没有被下载,各位大虾怎么做啊??

解决方案 »

  1.   

    我查看源码,分数线框有如下源码
    //加载各省录取分数线function getCollegeScore(collegeid, provid, wl, num, pv){ $('#collegeScoreBody').html('<tr><td colspan="8">数据载入中...</td></tr>'); switch(wl) { case '1' : $('#wlinfo').html('文科分数线'); break; case '2': $('#wlinfo').html('理科分数线'); break; case '3': $('#wlinfo').html('综合分数线'); break; } num = (typeof (num) == "undefined") ? 0 : num; $.getJSON("http://kaoshi.edu.sina.com.cn/iframe/i_collegescore.php",{ '_action' : 'collegescore', 'provid' : provid, 'collegeid' : collegeid, 'wl' : wl, 'num' :num}, function(data){ if (typeof (data) != "undefined" && data != '') { var html = ''; var bgcolor; for(var i=0; i<data.length; i++) { var row = data[i]; if (!parseInt(row.score_min)) { row.score_min = '--'; } if (!parseInt(row.score_max)) { row.score_max = '--'; } if (!parseInt(row.score_avg)) { row.score_avg = '--'; } if (!parseInt(row.score_td)) { row.score_td = '--'; } if (!parseInt(row.plan)) { row.plan = '--'; } row.batch = arr_batch[row.batch]; bgcolor = (i%2) ? '#f0ffec' : '#FFF'; //html += '<tr><td>'+row.syear+'</td><td>'+row.score_min+'</td><td>' + row.score_max + '</td><td>'+row.score_avg+'</td><td>'+row.score_td+'</td><td>'+row.plan+'</td><td>'+row.batch+'</td></tr>';                    //去掉最低分 html += '<tr><td>'+row.syear+'</td><td>' + row.score_max + '</td><td>'+row.score_avg+'</td><td>'+row.score_td+'</td><td>'+row.plan+'</td><td>'+row.batch+'</td></tr>'; } $('#collegeScoreBody').html(html); if (pv == 1) { statPV(); } } else { $('#collegeScoreBody').html('<tr><td colspan="8">暂无数据</td></tr>'); } });}
      

  2.   

    这是模板页面... 估计数据是通过ajax加载的.所以要找到目标页面再采集
      

  3.   

    //加载各省录取分数线
    function getCollegeScore(collegeid, provid, wl, num, pv)
    {
        $('#collegeScoreBody').html('<tr><td colspan="8">数据载入中...</td></tr>');
        switch(wl)
        {
            case '1' :
                $('#wlinfo').html('文科分数线');
                break;
            case '2':
                $('#wlinfo').html('理科分数线');
                break;
            case '3':
                $('#wlinfo').html('综合分数线');
                break;
        }
        num = (typeof (num) == "undefined") ? 0 : num;
        $.getJSON("http://kaoshi.edu.sina.com.cn/iframe/i_collegescore.php",{
            '_action' : 'collegescore',
            'provid' : provid,
            'collegeid' : collegeid,
            'wl' : wl,
            'num' :num},
            function(data){
                if (typeof (data) != "undefined" && data != '') {
                    var html = '';
                    var bgcolor;
                    for(var i=0; i<data.length; i++) {
                        var row = data[i];
                        if (!parseInt(row.score_min)) {
                            row.score_min = '--';
                        }
                        if (!parseInt(row.score_max)) {
                            row.score_max = '--';
                        }
                        if (!parseInt(row.score_avg)) {
                            row.score_avg = '--';
                        }
                        if (!parseInt(row.score_td)) {
                            row.score_td = '--';
                        }
                        if (!parseInt(row.plan)) {
                            row.plan = '--';
                        }
                        row.batch = arr_batch[row.batch];
                        bgcolor = (i%2) ? '#f0ffec' : '#FFF';
                        //html += '<tr><td>'+row.syear+'</td><td>'+row.score_min+'</td><td>' + row.score_max + '</td><td>'+row.score_avg+'</td><td>'+row.score_td+'</td><td>'+row.plan+'</td><td>'+row.batch+'</td></tr>';
                        //去掉最低分
                        html += '<tr><td>'+row.syear+'</td><td>' + row.score_max + '</td><td>'+row.score_avg+'</td><td>'+row.score_td+'</td><td>'+row.plan+'</td><td>'+row.batch+'</td></tr>';
                    }
                    $('#collegeScoreBody').html(html);
                    if (pv == 1)
                    {
                        statPV();
                    }
                } else {
                    $('#collegeScoreBody').html('<tr><td colspan="8">暂无数据</td></tr>');
                }
            });
    }
      

  4.   

    这不是向这个地址请求json吗,   $.getJSON("http://kaoshi.edu.sina.com.cn/iframe/i_collegescore.php",{
            '_action' : 'collegescore',
            'provid' : provid,
            'collegeid' : collegeid,
            'wl' : wl,
            'num' :num},getCollegeScore(collegeid, user_provid, 2);provid是user_provid,wl是2,num传0就行了,user_provid 北京的传6,其他的你看看那个选择省份的js是去哪里拉的省份编号。GET请求json就完事了。
    GET http://kaoshi.edu.sina.com.cn/iframe/i_collegescore.php?_action=collegescore&provid=4&collegeid=10001&wl=2&num=0 HTTP/1.1
    Host: kaoshi.edu.sina.com.cn
    Connection: keep-alive
    Referer: http://kaoshi.edu.sina.com.cn/collegedb/index.php?_action=more&show=more_score&provid=6&wl=2&collegeid=10001
    X-Requested-With: XMLHttpRequest
    User-Agent: Mozilla/5.0 (Windows NT 5.1) AppleWebKit/534.30 (KHTML, like Gecko) Chrome/12.0.742.100  Safari/534.30 TaoBrowser/1.1
    Accept: application/json, text/javascript, */*
    Accept-Encoding: gzip,deflate,sdch
    Accept-Language: zh-CN,zh;q=0.8
    Accept-Charset: GBK,utf-8;q=0.7,*;q=0.3
    Cookie: BEFORE_GOSSO_REFERER=1; U_TRS1=00000032.6d7ae54.4fdde257.de1a6ef3; UOR=www.baidu.com,ishare.iask.sina.com.cn,; SINAGLOBAL=00000063.a0ba132c.4fdde25a.bcd5f136; SGUP=0; U_TRS2=000000fb.1d295300.4fe3c996.3075e599; USRMDE1=usrmdinst34_80; USRMDE2=usrmdinst77_8088; Apache=00000095.3955d44.4fe3c998.863453c9; ULV=1244392248151:7:7:1:00000095.3955d44.4fe3c998.863453c9:1244550632357; usrmd=usrmdins636; vjlast=1244441357.1244392246.10; _s_upa=4; vjuids=-4a1e16f17.121be7c28f8.0.5c292a58
    HTTP/1.1 200 OK
    Date: Fri, 22 Jun 2012 01:33:52 GMT
    Server: Apache
    Expires: Mon,26Jul199705:00:00GMT
    Cache-Control: no-cache,must-revalidate
    Pragma: no-cache
    DPOOL_HEADER: 10.44.6.34
    Content-Length: 2451
    Connection: close
    Content-Type: text/html; charset=gb2312[{"id":"10945","collegeid":"10001","provid":"4","syear":"2011","wl":"2","plan":"15","score_min":"667.00","score_avg":"678.00","score_td":"0.00","score_max":"690.00","batch":"11"},{"id":"9471","collegeid":"10001","provid":"4","syear":"2010","wl":"2","plan":"28","score_min":"0.00","score_avg":"676.00","score_td":"0.00","score_max":"693.00","batch":"11"},{"id":"7429","collegeid":"10001","provid":"4","syear":"2009","wl":"2","plan":"38","score_min":"660.00","score_avg":"678.00","score_td":"0.00","score_max":"692.00","batch":"11"},{"id":"5141","collegeid":"10001","provid":"4","syear":"2008","wl":"2","plan":"34","score_min":"652.00","score_avg":"675.00","score_td":"0.00","score_max":"706.00","batch":"11"},{"id":"5140","collegeid":"10001","provid":"4","syear":"2008","wl":"2","plan":"3","score_min":"665.00","score_avg":"677.00","score_td":"0.00","score_max":"684.00","batch":"01"},{"id":"2315","collegeid":"10001","provid":"4","syear":"2007","wl":"2","plan":"39","score_min":"566.00","score_avg":"649.00","score_td":"0.00","score_max":"680.00","batch":"11"},{"id":"4710","collegeid":"10001","provid":"4","syear":"2007","wl":"2","plan":"3","score_min":"637.00","score_avg":"649.00","score_td":"0.00","score_max":"659.00","batch":"01"},{"id":"4680","collegeid":"10001","provid":"4","syear":"2006","wl":"2","plan":"38","score_min":"587.00","score_avg":"670.00","score_td":"0.00","score_max":"697.00","batch":"11"},{"id":"789","collegeid":"10001","provid":"4","syear":"2006","wl":"2","plan":"3","score_min":"652.00","score_avg":"657.00","score_td":"0.00","score_max":"665.00","batch":"01"},{"id":"2","collegeid":"10001","provid":"4","syear":"2005","wl":"2","plan":"62","score_min":"568.00","score_avg":"657.00","score_td":"0.00","score_max":"689.00","batch":"11"},{"id":"4142","collegeid":"10001","provid":"4","syear":"2004","wl":"2","plan":"0","score_min":"675.00","score_avg":"0.00","score_td":"0.00","score_max":"0.00","batch":"00"},{"id":"3690","collegeid":"10001","provid":"4","syear":"2003","wl":"2","plan":"0","score_min":"630.00","score_avg":"0.00","score_td":"0.00","score_max":"0.00","batch":"00"},{"id":"3350","collegeid":"10001","provid":"4","syear":"2002","wl":"2","plan":"0","score_min":"672.00","score_avg":"0.00","score_td":"0.00","score_max":"0.00","batch":"00"},{"id":"2942","collegeid":"10001","provid":"4","syear":"2001","wl":"2","plan":"0","score_min":"0.00","score_avg":"655.00","score_td":"0.00","score_max":"0.00","batch":"00"}]
      

  5.   

    最终实验了一下,wl是0,1,2,代表文科,理科,综合,num统一传0,provid是省份id,你自己翻js看哪里获得的,collegeid和provid类似,你自己找它哪里来的,反正我看了一些都是10001