中国知网爬取问题（1）

按顺序在浏览器上访问可以得到正确的页面，但在spider中使用时却得不到。。。

1 http://200.96.97.90/grid2008/request/search.aspx?PageName=ASP.brief_libraryresult_aspx&DBViewType=FullText&DbPrefix=SCDB

2http://200.96.97.90/grid2008/DataCenter/DoGridTable.aspx?action=gridtablepage&turnpage=1&dbcode=&isselectorder=&prio=true&viewtype=&itype=0&showtype=&returnid=&pagemode=3&recordsperpage=1&dbcatalog=%E4%B8%AD%E5%9B%BD%E5%AD%A6%E6%9C%AF%E6%96%87%E7%8C%AE%E7%BD%91%E7%BB%9C%E5%87%BA%E7%89%88%E6%80%BB%E5%BA%93&dbprefix=SCDB&pagename=ASP.brief_libraryresult_aspx&queryid=0

 

3
http://200.96.97.90/kcms/detail/detail.aspx?filename=JCHX201111001019&dbname=CPFD2012&dbcode=CPFD

 

在spider上时会有如下的跳转

[DEBUG] ctx@2 execute http request: GET http://200.96.97.90/grid2008/brief/detailj.aspx?filename=ZGDN201109001107&dbname=CPFD2012&dbcode=CPFD&uid=aDNXbjV5WHRVd25SbXIwNEorbDVpOW9lNUROanFxN1ZMYmxvdzN5b2UzOU5mZjZB  <--[usearch worker 1] HttpStepExecutor.java(initRequestProducer:189)-->
[DEBUG] Redirect requested to location '/kns55/loginid.aspx?p=detail%2fdetail.aspx%3ffilename%3dZGDN201109001107%26dbname%3dCPFD2012%26dbcode%3dCPFD&uid=aUM1a0dBNlQzcTRUVFgxakpDeGwwY003YUkxdURaYmdhTGZhWThFWTFrMmxoZTFM'  <--[I/O dispatcher 3] MyRedirectStrategy.java(getLocationURI:87)-->
[DEBUG] Redirect requested to location '/kns55/detail/2fdetail.aspx/3ffilename/3dZGDN201109001107/26dbname/3dCPFD2012/26dbcode/3dCPFD'  <--[I/O dispatcher 3] MyRedirectStrategy.java(getLocationURI:87)-->
[DEBUG] Redirect requested to location '/Kns55/error.aspx?err=Error+Message%3a%e6%96%87%e4%bb%b6%e2%80%9c%2fkns55%2fdetail%2f2fdetail.aspx%e2%80%9d%e4%b8%8d%e5%ad%98%e5%9c%a8%e3%80%82'  <--[I/O dispatcher 3] MyRedirectStrategy.java(getLocationURI:87)

附

知网spider配置文件

 

{
    adapterId: 20,
    adapterName: '知网。会议论文',
    adapterType: "http",
    recordPerpage:10,
  proxy:{
  host:'115.239.234.44',
  port: "808",
  user:'',
  password:''
 },
    fieldMaps:[{
        name: 'chtitle',
        description:'中文标题',
        searchable: true,
        fieldId: 1
    },{
        name: 'entitle',
        description:'英文标题',
        searchable: true,
        fieldId: 2
    },{
        name: 'cajurl',
        description:'caj下载',
        searchable: true,
        fieldId: 3
    },{
        name: 'pdfurl',
        description:'pdf下载',
        searchable: true,
        fieldId: 4
    },{
        name: 'chauthors',
        description:'中文作者',
        searchable: true,
        fieldId: 5
    },{
        name: 'enauthors',
        description:'英文作者',
        searchable: true,
        fieldId: 6
    },{
        name: 'institution',
        description:'机构',
        searchable: true,
        fieldId: 7
    },{
        name: 'chabstract',
        description:'中文摘要',
        searchable: true,
        fieldId: 8
    },{
     name: 'enabstract',
        description:'英文摘要',
        searchable: false,
        fieldId: 9
    },{
     name: 'chkeyword',
        description:'中文关键词',
        searchable: false,
        fieldId: 10
    },{
     name: 'enkeyword',
        description:'英文关键词',
        searchable: false,
        fieldId: 11
   },{
     name: 'jname',
        description:'会议录名称',
        searchable: false,
        fieldId: 12
   },{
     name: 'meetingname',
        description:'会议名称',
        searchable: false,
        fieldId: 13
   },{
     name: 'meetingtime',
        description:'会议时间',
        searchable: false,
        fieldId: 14
   },{
     name: 'meetingplace',
        description:'会议地址',
        searchable: false,
        fieldId: 15
   },{
     name: 'classnumber',
        description:'分类号',
        searchable: false,
        fieldId: 16
   },{
     name: 'hostunit',
        description:'主办单位',
        searchable: false,
        fieldId: 17
   },{
     name: 'url',
        description:'详情地址',
        searchable: false,
        fieldId: 18
   },{
     name: 'detail',
        description:'详情地址',
        searchable: false,
        fieldId: 10001
   }],
prepareSteps:[{
  url: 'http://200.96.97.90/grid2008/request/search.aspx?PageName=ASP.brief_libraryresult_aspx&DBViewType=FullText&DbPrefix=SCDB',
  method: 'GET',
  reqCharset: 'utf-8',
  respCharset: 'utf-8',
  containingRecords: false,
 
 }
   ],

    fetchSteps:[
    {
        url: 'http://200.96.97.90/grid2008/DataCenter/DoGridTable.aspx?action=gridtablepage&turnpage=1&dbcode=&isselectorder=&prio=true&viewtype=&itype=0&showtype=&returnid=&pagemode=3&recordsperpage=1&dbcatalog=%E4%B8%AD%E5%9B%BD%E5%AD%A6%E6%9C%AF%E6%96%87%E7%8C%AE%E7%BD%91%E7%BB%9C%E5%87%BA%E7%89%88%E6%80%BB%E5%BA%93&dbprefix=SCDB&pagename=ASP.brief_libraryresult_aspx&queryid=0',
        method: 'GET',
        reqCharset: 'UTF-8',
        respCharset: 'UTF-8',
        containingRecords: true,
         reqParameters:[
         {
            type: 'page',
   paramKey: 'curpage',
   startIndex: '1',
   saveTo: 'GET',
   encode:false
        }]
        }],
   
    rsFormat:{
        
        hitExpr:{
            startTag: '',
            endTag: '$end',
            includeStartTag: false,
            includeEndTag: false,       
            script:'relVat="51504882"',
             maxValueLength: 64,
            escapeHtml: true
        },
        rsAreaExpr: {
            startTag: '下载频次</td>',
            endTag: '</table>',
            includeStartTag: false,
            includeEndTag: false,
             maxValueLength: 100000
        },
        recAreaExpr:{
            loopType: 'tag',
            startTag: '<input type=checkbox',
            endTag: 'οnclick="checkMark(this)"',
            includeStartTag: false,
            includeEndTag: false
     
        },
        fieldExprs:[{
            fieldId: 'detail',
      startTag: 'value="',
            endTag:'"',
            includeStartTag: false,
            includeEndTag: false,
            script:'retVal="http://200.96.97.90/grid2008/brief/detailj.aspx?filename="+(retVal.split("!"))[1]+"&dbname="+(retVal.split("!"))[0]+"&dbcode=CPFD&uid=aDNXbjV5WHRVd25SbXIwNEorbDVpOW9lNUROanFxN1ZMYmxvdzN5b2UzOU5mZjZB"',
            escapeHtml: true,
             maxValueLength: 10000
         },{
         fieldId: 'url',
      startTag: 'value="',
            endTag:'"',
            includeStartTag: false,
            includeEndTag: false,
            script:'retVal="http://200.96.97.90/grid2008/brief/detailj.aspx?filename="+(retVal.split("!"))[1]+"&dbname="+(retVal.split("!"))[0]+"&dbcode=CPFD&uid=aDNXbjV5WHRVd25SbXIwNEorbDVpOW9lNUROanFxN1ZMYmxvdzN5b2UzOU5mZjZB"',
            escapeHtml: true,
             maxValueLength: 10000
     }]
   },
     detailSteps:[{
   url: '$URL',
   method: 'GET',
   reqCharset: 'utf-8',
   respCharset: 'utf-8',
        respParameters:[{
            paramKey: 'dt_chtitle',
            startTag: ' id="chTitle">',
            endTag: '</span>',
            escapeHtml: true
        },{
            paramKey: 'dt_entitle',
            startTag: 'id="enTitle">',
                 escapeHtml: true,
            endTag: '</span>'
           
        },{
            paramKey: 'dt_cajurl',
           startTag: '<a target="_blank" href="&#xA;',
            endTag: '">',
               escapeHtml: true,
            maxValueLength: 4000
        },{
            paramKey: 'dt_pdfurl',
             startTag: '<a target="_blank" href="&#xA;',
             endTag: '">',
                escapeHtml: true,
              maxValueLength: 4000
        },{
            paramKey: 'dt_chauthors',
            startTag: '【作者】',
            endTag: '</p>',
               escapeHtml: true,
                maxValueLength: 4000
           
        },{
            paramKey: 'dt_enauthors',
            startTag: ' 【Author】',
            endTag: '</p>',
                   escapeHtml: true,
                maxValueLength: 4000
        },{
            paramKey: 'dt_institution',
            startTag: '【机构】',
              endTag: '</p>',
                     escapeHtml: true,
                maxValueLength: 4000
        },{
            paramKey: 'dt_chabstract',
            startTag: '【摘要】',
            endTag: '</span>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_enabstract',
            startTag: ' 【Abstract】',
            endTag: '</span>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_chkeyword',
            startTag: '【关键词】',
            endTag: '</span>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_enkeyword',
            startTag: ' 【Key words】',
            endTag: '</span>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_jname',
            startTag: ' 【会议录名称】',
            endTag: '</li>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_meetingname',
            startTag: ' 【会议名称】',
            endTag: '</li>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_meetingtime',
            startTag: '【会议时间】',
            endTag: '</li>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_meetingplace',
            startTag: '【会议地点】',
            endTag: '</li>',
             escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_classnumber',
            startTag: '【分类号】',
            endTag: '</li>',
                 escapeHtml: true,
                maxValueLength: 40000
        },{
            paramKey: 'dt_hostunit',
            startTag: '【主办单位】',
            endTag: '</li>',
                 escapeHtml: true,
                maxValueLength: 40000
        }]
       }]
    }
    
}