<%
...
@LANGUAGE="JSCRIPT" CODEPAGE="936"
%>
<!-- METADATA NAME="Microsoft ActiveX Data Objects 2.5 Library"
TYPE="TypeLib" UUID="{00000205-0000-0010-8000-00AA006D2EA4}" -->
<% ...
//打开数据库
try
{
var strConnectionString = "Provider=Microsoft.Jet.OLEDB.4.0;Data Source=" + Server.MapPath("#db.mdb");
var objConnection = Server.CreateObject("ADODB.Connection");
objConnection.Open(strConnectionString);
}
catch(e)
{
Response.Write(e.description);
Response.End();
}
%>
< script language ="jscript" runat ="server" > ...
//远程获取数据
function GetData()
...{
var xHttp = new ActiveXObject("microsoft.xmlhttp");
xHttp.open("POST","http://www.chinamp.org/mppro2.php",false);
xHttp.send();
return(xHttp.responseText);
}
//利用正则表达式提取符合条件的链接
function GetLinks(str)
...{
var re = new RegExp("<a[^<>]+?>((.| )*?)</a>", "gi");
var a = str.match(re); //第一次搜索 for(var i=0;i<a.length;i++)
...{
var t1,t2;
var temp;
var r = /qy.php?id=(d+)/ig;
if(!r.test(a[i]))continue;
temp = a[i].match(/qy.php?id=(d+)/ig);
t1 = RegExp.$1;
temp = a[i].match(/<font[^<>]+?color="#000000">(.*?)</font>/ig);
t2 = RegExp.$1;
if(t1 == t2)continue;
SaveArticle(t1,t2,GetContent(t1));
}
}
//通过提取的链接获取ID,并通过这个ID取抓取相应的文章
function GetContent(id)
{
var xHttp = new ActiveXObject("microsoft.xmlhttp");
xHttp.open("POST","http://www.chinamp.org/qy.php?id=" + id,false);
xHttp.send();
var str = xHttp.responseText;
var re = new RegExp("<span[^<>]+?style="font-size:10.8pt">(.*?)</span>", "gi");
var a = str.match(re);
return(RegExp.$1);
}
//入库
function SaveArticle(oldID,Title,Content)
...{
var oRst = Server.CreateObject("ADODB.Recordset");
var sQuery;
sQuery = "SELECT oldID,Title,Content FROM Articles"
oRst.Open(sQuery,objConnection,adOpenStatic,adLockPessimistic);
oRst.AddNew();
oRst("oldID") = oldID;
oRst("Title") = Title;
oRst("Content") = Content;
oRst.Update();
oRst.Close();
Response.Write(Title + "抓取成功" + "<br/>");
}
</ script >
< HTML >
< HEAD >
< TITLE > 抓取文章 </ TITLE >
< meta http-equiv ="Content-Type" content ="text/html; charset=gb2312" ></ HEAD >
< BODY >
<% = GetLinks(GetData()) %>
</ BODY >
</ HTML >
<!-- METADATA NAME="Microsoft ActiveX Data Objects 2.5 Library"
TYPE="TypeLib" UUID="{00000205-0000-0010-8000-00AA006D2EA4}" -->
<% ...
//打开数据库
try
{
var strConnectionString = "Provider=Microsoft.Jet.OLEDB.4.0;Data Source=" + Server.MapPath("#db.mdb");
var objConnection = Server.CreateObject("ADODB.Connection");
objConnection.Open(strConnectionString);
}
catch(e)
{
Response.Write(e.description);
Response.End();
}
%>
< script language ="jscript" runat ="server" > ...
//远程获取数据
function GetData()
...{
var xHttp = new ActiveXObject("microsoft.xmlhttp");
xHttp.open("POST","http://www.chinamp.org/mppro2.php",false);
xHttp.send();
return(xHttp.responseText);
}
//利用正则表达式提取符合条件的链接
function GetLinks(str)
...{
var re = new RegExp("<a[^<>]+?>((.| )*?)</a>", "gi");
var a = str.match(re); //第一次搜索 for(var i=0;i<a.length;i++)
...{
var t1,t2;
var temp;
var r = /qy.php?id=(d+)/ig;
if(!r.test(a[i]))continue;
temp = a[i].match(/qy.php?id=(d+)/ig);
t1 = RegExp.$1;
temp = a[i].match(/<font[^<>]+?color="#000000">(.*?)</font>/ig);
t2 = RegExp.$1;
if(t1 == t2)continue;
SaveArticle(t1,t2,GetContent(t1));
}
}
//通过提取的链接获取ID,并通过这个ID取抓取相应的文章
function GetContent(id)
{
var xHttp = new ActiveXObject("microsoft.xmlhttp");
xHttp.open("POST","http://www.chinamp.org/qy.php?id=" + id,false);
xHttp.send();
var str = xHttp.responseText;
var re = new RegExp("<span[^<>]+?style="font-size:10.8pt">(.*?)</span>", "gi");
var a = str.match(re);
return(RegExp.$1);
}
//入库
function SaveArticle(oldID,Title,Content)
...{
var oRst = Server.CreateObject("ADODB.Recordset");
var sQuery;
sQuery = "SELECT oldID,Title,Content FROM Articles"
oRst.Open(sQuery,objConnection,adOpenStatic,adLockPessimistic);
oRst.AddNew();
oRst("oldID") = oldID;
oRst("Title") = Title;
oRst("Content") = Content;
oRst.Update();
oRst.Close();
Response.Write(Title + "抓取成功" + "<br/>");
}
</ script >
< HTML >
< HEAD >
< TITLE > 抓取文章 </ TITLE >
< meta http-equiv ="Content-Type" content ="text/html; charset=gb2312" ></ HEAD >
< BODY >
<% = GetLinks(GetData()) %>
</ BODY >
</ HTML >