<script type="text/javascript"> google_ad_client = "pub-8800625213955058"; /* 336x280, 创建于 07-11-21 */ google_ad_slot = "0989131976"; google_ad_width = 336; google_ad_height = 280; // </script> <script type="text/javascript" src="http://pagead2.googlesyndication.com/pagead/show_ads.js"> </script> 此搜索引擎适于在一个中等规模的局域网中使用,由于找到的网页存在数据库中,不仅可以索静态的HTML页面,可以搜索php、asp等动态页面。对于一个拥有5万个网页的系统(使用PII-400作为服务器),搜索响应时间在2-10秒左右,完全可以满足要求,由于Java、MySQL、PHP都是跨平台的软件,所以此搜索引擎不仅可以工作在Windows服务器上,而且也可以工作在Linux等其他系统中。 一、建立搜索引擎需要的数据库和数据表。 首先建立数据库: c:/mysql/bin/> mysqladmin -uroot -pmypasswd create Spider 然后建立数据库中的表结构 c:/mysql/bin/> mysql -uroot -pmypasswd Spider < Spider.mysql 其中Spider.mysql为一个文本文件,其内容如下:
CREATE TABLE link (
Id int(10) unsigned NOT NULL auto_increment,
Url varchar(120) NOT NULL,
Class tinyint(3) unsigned NOT NULL default 0 ,
IsSearchLink tinyint(3) unsigned default 0,
PRIMARY KEY (Url),
UNIQUE Id (Id),
KEY Url (Url),
KEY Class (Class)
);
# 本局域网的初始主页地址,搜索蜘蛛从此网址开始搜索所有其他网页 INSERT INTO link VALUES( '1', 'HTTP://102.211.69.1/', '0', '0'); # 数据表 webpagelocal 用来存放下载的所有的网页
CREATE TABLE webpagelocal (
Id int(10) unsigned NOT NULL auto_increment,
Url varchar(120) NOT NULL,
Content text NOT NULL,
PRIMARY KEY (Url),
UNIQUE Id (Id),
KEY Url (Url)
);
# 数据表 webpagefindfast
# 用MakeFast.php从表webpagelocal中提取512字节的检索信息存放其中
CREATE TABLE webpagefindfast (
Id int(10) unsigned NOT NULL,
Url varchar(120) NOT NULL,
Title varchar(64),
Content blob,
PRIMARY KEY (Url),
KEY Url (Url),
KEY Title (Title)
);
二、以下为搜索网页和下载网页至本地数据库的Java程序LinkToDB.java,它也是此搜索引擎的核心和基础
/***************************** LinkToDB.java ***********************************
*
* 对URL中的http链接进行分析,将相对路径转换为绝对路径,排序方式输出结果到数据库
*
* 如果分析得到的URL是Link表中唯一的,就将其内容下载到表 WebPageLocal 中。
*
********************************************************************************
/
import java.io.*;
import java.util.*;
import java.net.*;
import java.lang.String;
import java.sql.*;
import java.text.*;
class Counter {
private int i = 1;
int read() { return i; }
void increment() { i ; }
}
public class LinkToDB {
String UrlHost = "";
String UrlFile = "";
String UrlPath = "";
static String StartWith = null;
boolean outsideTag = true; //判断是否在标记之中
static char[] buffer = new char[4096]; // 缓冲区:用于保存从 URL 读的数据
InputStreamReader read = null;
BufferedReader reader = null;
URLConnection uc = null;
private URL url = null;
private StreamTokenizer st;
private TreeMap counts = new TreeMap();//以排序方式保存找到的链接
LinkToDB(String myurl,String StartOnly){
try {
StartWith = StartOnly;
if(StartOnly!=null) { if(!myurl.startsWith(StartOnly)) return; }//只搜索此网站
url = new URL(myurl);
UrlHost = url.getHost();
UrlHost = UrlHost.toUpperCase();
UrlFile = url.getFile();
int v=UrlFile.lastIndexOf("/");
if(v!=-1) UrlPath = UrlFile.substring(0,v);
System.out.println("分析文件:" myurl);
int uclength=200000;
int ucError=0;
try{
uc = url.openConnection();
uc.setUseCaches(false);
uc.connect();
}
catch(IOException io) { ucError=1; System.out.println("打不开待分析网页:" myu
rl); }
if(ucError!=1){
uclength = uc.getContentLength();
if (uclength<200000) {
try{ read = new InputStreamReader(url.openStream()); }
catch(IOException io) {System.out.println("流打开错误:" myurl);}
}
else System.out.println("文件太大,不分析");
}
if(read!=null){
reader=new BufferedReader(read);
if(reader!=null){
st = new StreamTokenizer(reader);
st.resetSyntax(); // 重置语法表
st.wordChars(0,255); // 令牌范围为全部字符
st.ordinaryChar('<'); // HTML标记两边的分割符
st.ordinaryChar('>');
}
}
}
catch(MalformedURLException e){ System.out.println("Malformed URL String!");}
}
void cleanup() {
try { read.close(); }
catch(IOException e) { System.out.println("流关闭错误"); }
}
void countWords() {
try {
while(st.nextToken()!=StreamTokenizer.TT_EOF) {
String s0="";
String s_NoCase="";
switch(st.ttype) {
case '<': //入标记字段
outsideTag=false;
continue; //countWords();
case '>': //出标记字段
outsideTag=true;
continue; //countWords();
case StreamTokenizer.TT_EOL: s0 = new String("EOL"); break;
case StreamTokenizer.TT_WORD: if(!outsideTag) s0 = st.sval; /*已经是字符
串*/ break;
default: s0 = "";// s0 = String.valueOf((char)st.ttype);/*单一字符*/
}
if(outsideTag) continue;//出了标记区域(<a >)
String s = "";
s_NoCase = s0.trim();
s0=s_NoCase.toUpperCase();
if(s0.startsWith("A ")||s0.startsWith("AREA ")||s0.startsWith("FRAME ")||s0.s
tartsWith("IFRAME ")){ //以这些开始的都是超级链接
int HREF_POS = -1;
if(s0.startsWith("FRAME ")||s0.startsWith("IFRAME ")) {
HREF_POS = s0.indexOf("SRC=");
s0 = s0.substring(HREF_POS 4).trim();
s_NoCase=s_NoCase.substring(HREF_POS 4).trim();
}
else {
HREF_POS=s0.indexOf("HREF=");
s0=s0.substring(HREF_POS 5).trim();
s_NoCase=s_NoCase.substring(HREF_POS 5).trim();
}
if(HREF_POS!=-1) {
if(s0.startsWith("/""))
{s0=s0.substring(1);s_NoCase=s_NoCase.substring(1);}
int QUOTE=s0.indexOf("/"");
if(QUOTE!=-1)
{s0=s0.substring(0,QUOTE).trim();s_NoCase=s_NoCase.substring(0,QUOTE).trim
();}
int SPACE=s0.indexOf(" ");
if(SPACE!=-1)
{s0=s0.substring(0,SPACE).trim();s_NoCase=s_NoCase.substring(0,SPACE).trim
();}
if(s0.endsWith("/""))
{s0=s0.substring(0,s0.length()-1);s_NoCase=s_NoCase.substring(0,s_NoCase.l
ength()-1);}
if(s0.indexOf("'")!=-1||s0.indexOf("JAVASCRIPT:")!=-1||s0.indexOf("..")!=-1
)
{s0="";s_NoCase="";} //有这些符号,认为非合法链接;两点表示上一目录,而我
只想向下级查找
if ( !s0.startsWith("FTP://") &&//以下后缀或前缀通常非网页格式
!s0.startsWith("FTP://") &&
!s0.startsWith("MAILTO:") &&
!s0.endsWith(".SWF") &&
!s0.startsWith("../")) //因../表示上一目录,通常只需考虑本级和下N级目录
s=s0;
if (!s.startsWith("HTTP://")&&!s.equals("")) {s=UrlHost UrlPath "/" s;s_No
Case=UrlHost UrlPath "/" s_NoCase;}
else if(s.startsWith("/")) {s=UrlHost s;s_NoCase=UrlHost s_NoCase;}
if(s.startsWith("HTTP://")) {s=s.substring(7);s_NoCase=s_NoCase.substring(
7);}
int JinHao=s.indexOf("#"); //如果含有"#"号,表示有效的链接是此前的部分
if(JinHao!=-1) {s=s.substring(0,JinHao).trim();s_NoCase=s_NoCase.substring(
0,JinHao).trim();}
int H=-1; //以下将/./转换为/
for(int m=0;m<4;m ){
H=s.indexOf("/./");
if(H!=-1) {s=s.substring(0,H) s.substring(H 2);s_NoCase=s_NoCase.substring
(0,H) s_NoCase.substring(H 2);}
}
int TwoXG=-1; //以下将//转换为/
for(int m=0;m<5;m ){
TwoXG=s.indexOf("//");
if(TwoXG!=-1) {s=s.substring(0,TwoXG) s.substring(TwoXG 1);s_NoCase=s_NoCa
se.substring(0,TwoXG) s_NoCase.substring(TwoXG 1);}
}
int OneXG=s.indexOf("/");
if(OneXG==-1) {s=s "/";s_NoCase ="/";} //将xx.xx.xx.xxx转换为xx.xx.xx.xxx/的
标准形式
if (!s.startsWith("HTTP://")) {s="HTTP://" s;s_NoCase="HTTP://" s_NoCase;}
}
}
if(counts.containsKey(s_NoCase)) ((Counter)counts.get(s_NoCase)).increment();
else counts.put(s_NoCase,new Counter());
}
} catch(IOException e) {
System.out.println("st.nextToken() unsuccessful");
}
}
Collection values() { return counts.values(); }
Set keySet() { return counts.keySet(); }
Counter getCounter(String s) { return (Counter)counts.get(s); }
public static void main(String[] argv) throws FileNotFoundException {
try{
Class.forName("org.gjt.mm.mysql.Driver").newInstance();
}
catch (Exception E) {
System.out.println("加载Jdbc驱动程序失败");
E.printStackTrace();
}
try{
Connection conn = DriverManager.getConnection(
"jdbc:mysql://localhost/Spider?user=root&password=mypassword");
Statement stmt = conn.createStatement();
String myurl;
for(int i=1;i<=6;i ){
String query = "SELECT Url FROM link WHERE IsSearchLink=0 and Class=" (i-1) "
ORDER BY Url";
ResultSet rs = stmt.executeQuery(query);
while (rs.next()) {
myurl = rs.getString("Url");
String StartOnly = null;
if(argv.length>0) StartOnly=argv[0];
LinkToDB wc = new LinkToDB(myurl,StartOnly);
if(wc.reader!=null){
stmt.executeUpdate("UPDATE Link SET IsSearchLink=1 WHERE Class=" (i-1) " a
nd Url='" myurl "'");
wc.countWords();
Iterator keys = wc.keySet().iterator();
while(keys.hasNext()) {
String key = (String)keys.next();
System.out.println("分析找到链接:" key ": " wc.getCounter(key).read());
int ErrorDB=0;
if(StartWith==null||(StartWith!=null&&key.startsWith(StartWith))){
try{//-------------------------- 找到的链接插入数据库link -----------------
--
stmt.executeUpdate("INSERT INTO Link(Id,Url,Class) VALUES(0,'" key "',"
i ")");
}
catch(SQLException ex){
ErrorDB=1;
System.out.println("插入数据错 SQLException: " ex.getMessage())
;
}
if(ErrorDB!=1){ //链接不重复就下载网页到WebPageLocal
System.out.println("下载网页:" key);
int length; // 读的字符数
int filelength=200000;
InputStreamReader read=null;
URL rurl=null;
URLConnection urlc=null;
String Content="";
try{ rurl = new URL(key); }
catch(MalformedURLException mu) {
System.out.println("打开下载网页出错:" mu.getMessage());
}
if(rurl!=null){
int ucError=0;
try{ urlc = rurl.openConnection(); urlc.connect();}
catch(IOException io) { ucError=1; System.out.println("下载网页打不开:" ke
y); }
if(ucError==0){
try{
filelength=urlc.getContentLength();
if (filelength>=200000) System.out.println("网页太大,我不下载了。" key);
else read = new InputStreamReader(rurl.openStream());
}
catch(IOException io) {System.out.println("下载网页打不开:" key);}
}
// 读入 URL 并写入数据库
if(read!=null&&filelength<200000){
try{
while((length = read.read(buffer)) != -1) {
String s = new String(buffer, 0, length);
Content=Content s;
}
}
catch(IOException io) {
Content="";
System.out.println("不能读入URL文件");
}
try{
Statement stmt2 = conn.createStatement(ResultSet.TYPE_SCROLL_SENSITIVE, Res
ultSet.CONCUR_UPDATABLE);
ResultSet uprs = stmt2.executeQuery("SELECT Id,Url,Content FROM WebPageLoca
l WHERE 0");//WHERE 0很重要,否则会耗尽内存
uprs.moveToInsertRow();
uprs.updateInt("Id",0);
uprs.updateString("Url",key);
uprs.updateString("Content",Content);
uprs.insertRow();
uprs.beforeFirst();
uprs.close();
stmt2.close();
}
catch(SQLException ex){
System.out.println("插入数据错:" ex.getMessage());
}
}//if(read!=null&&filelength<200000)
}//
}
}
//------------------------------- 下载网页 ----------------------------------
}//while(keys.hasNext())
wc.cleanup();
}//if(wc.reader!=null)
}//while rs.next
rs.close(); //关闭记录结果
}//end for
stmt.close(); //关闭语句
conn.close(); //关闭连接
}//try
catch(SQLException ex){ System.out.println("SQL异常:" ex.getMessage()); }
}//main()函数结束
}//类 LinkToDB 结束
三、编译和运行此Java程序
d:/Spider/> set CLASSPATH=d:/j/mm.mysql.jdbc2;
d:/Spider/> d:/j/bin/javac LinkToDB.java
d:/Spider/> d:/j/bin/java LinkToDB
其中第一行命令是设置MySQL的JDBC驱动程序路径。 四、由于网页中含有大量的无用的格式信息,直接用它来搜索要浪费大量的时间,所以需要掉其中的HTML格式控制信息,并将太长的网页截短,然后将整理后的用于搜索的信息存到另一个数据表中。由于PHP4中有一个很方便的函数strip_tags可以去掉其中的HTML格式标记,所以我们用PHP来整理。 MakeFast.php的内容如下:
<?php
mysql_connect("localhost","root","mypassword");
$result = mysql_db_query("Spider","select Id,Url,Content from WebPageLocal whe
re Id>$n1 and Id<$n2");
while($mt = mysql_fetch_array($result)){
$Title = "";
$Body = "";
$mt2 = strtoupper($mt[2]);
$PosTitleL = strpos($mt2,"<TITLE>");
$PosTitleR = strpos($mt2,"</TITLE>");
$PosBody = strpos($mt2,"<BODY");
$PosHeadR = strpos($mt2,"</HEAD>");
if($PosTitleL&&$PosTitleR) $Title = substr($mt[2],$PosTitleL 7,$PosTitl
eR-$PosTitleL-7);
$Title = eregi_replace("'","’",$Title);
if($PosBody) $Body = substr($mt[2],$PosBody);
else if($PosHeadR) $Body = substr($mt[2],$PosHeadR 7);
else if($PosTitleR) $Body = substr($mt[2],$PosTitleR 8);
else if($PosTitleL) $Body = substr($mt[2],$PosTitleL);
else $Body = $mt[2];
$BodyText = strip_tags($Body);
$BodyNoSpace = eregi_replace(" ","",$BodyText);
$BodyNoQuote = eregi_replace("'","",$BodyNoSpace);
$Body512 = substr($BodyNoQuote,0,511)." ";
$Id = $mt[0];
$Url = $mt[1];
$sql="Insert Into WebPageFindFast(Id,Url,Title,Content)
VALUES($Id,'$Url','$Title','$Body512')";
mysql_db_query("Spider",$sql) or die($sql);
echo $Id." ";
}
?>
使用方式: 在浏览器中输入http://mywebsite/Spider/MakeFast.php?n1=1&n2=10000
五、以上是建立搜索引擎所用到的数据,下面编制用于用户搜索的网页和PHP脚本文件。首先是用于搜索的表单页面SearchForm.htm,其内容如下。
<html>
<head>
<title>红蜘蛛搜索引擎-V0.1</title>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312">
<link rel="stylesheet" href="../All.css" type="text/css">
</head>
<body bgcolor="#eeffee" text="#000000">
<table width="600" border="0" cellspacing="2" cellpadding="2" align="center" bgc
olor="#99CC00">
<tr>
<td>
<div align="center"><font color="#FF0000"><b><span class="pt16">红蜘蛛搜索
引擎</span>
<span class="pt12">V0.1</span></b></font></div>
</td>
</tr>
</table>
<form name="form1" method="post" action="Search.php">
<table width="600" border="1" cellspacing="1" cellpadding="1" align="center" b
ordercolor="#99CC00">
<tr>
<td>
<div align="left"><span class="pt15"><font color="#FF0000"><b>关 键 字</
b>:</font></span>
<input type="text" name="KeyWords" size="40" maxlength="40">
</div>
</td>
<td>
<div align="left"><span class="pt15"><font color="#FF0000"><b>查找范围</
b>:</font></span>
<select name="SearchIn">
<option value="Content" selected>网页正文</option>
<option value="Title">网页标题</option>
</select>
</div>
</td>
</tr>
<tr>
<td colspan="2"><span class="pt15"><font color="#FF0000"><b>查找方式</b>:
</font></span>
<select name="Speed">
<option value="Fast" selected>快速查找</option>
<option value="Slow">更深查找</option>
</select>
</td>
</tr>
<tr>
<td colspan="2">
<div align="left">
<input type="submit" name="Submit" value="搜索">
</div>
</td>
</tr>
</table>
</form>
<table width="600" border="0" cellspacing="2" cellpadding="2" align="center">
<tr>
<td height="18">
<p class="pt12"><font color="#FF0000"><b>使用方法</b></font>:仅需在关键字
一栏输入查询内容并按回车键(Enter)即可。
</p>
<blockquote>
<p align="left" class="pt12">如果希望输入多个条件,只需要用空格分隔即可:
</p>
<p class="pt12">例如:要查询同时包含“西昌”和“卫星”的网页,只需输入[西
昌 卫星]。</p>
<p class="pt12">又如:要查询只包含关键字“西昌”而不包含“卫星”的网页,
只需要输入[西昌 -卫星]。注意中间的空格不能少。</p>
</blockquote>
<p class="pt12"><font color="#FF0000"><b>查找范围</b></font>:你可以选择从
“网页标题”中查找或者从“网页正文”中查找。</p>
<p class="pt12"><font color="#FF0000"><b>查找方式</b></font>:“快速查找”
速度快但找到的网页数可能较少,因为:</p>
<blockquote>
<p class="pt12">“快速查找”只搜索网页正文的前512个字符。</p>
<p class="pt12">“更深查找”搜索网页正文的前2048个字符。</p>
<div align="right"><a href="mailto:zdyhlp@263.net"><font color="#FF0000" class="pt13"><b>欢迎
提出宝贵意见</b></font></a></div>
</blockquote>
</td>
</tr>
</table>
</body>
</html>
search.php根据用户输入的条件,完成搜索,显示找到的网页的链接地址、标题和提要信息 。内容如下:
<TITLE>红蜘蛛正在搜索关键词为[<?php echo $KeyWords?>]的网页</TITLE>
<link rel="stylesheet" href="../All.css" type="text/css">
<body bgcolor="#eeffee">
<table width="96%" border="0" cellspacing="2" cellpadding="2" align="center" bgc
olor="#99CC00">
<tr>
<td>
<div align="center"><font color="#FF0000"><b><span class="pt16">红蜘蛛搜索
引擎</span>
<span class="pt12">V0.1</span></b></font></div>
</td>
</tr>
</table>
<form name="form1" method="post" action="Search.php">
<table width="96%" border="1" cellspacing="1" cellpadding="1" align="center" b
ordercolor="#99CC00">
<tr>
<td valign="top"> <font color="#FF0000"><b><span class="pt13">关键字</span
></b><span class="pt13">:</span></font>
<input type="text" name="KeyWords" value="<?php echo $KeyWords?>" size="
30" maxlength="30">
<input type="submit" name="Submit" value="重新搜索">
</td>
<td valign="top"><font color="#FF0000"><b><span class="pt13">查找范围</spa
n></b><span class="pt13">:</span></font>
<select name="SearchIn">
<option value="Content" <?php if ($SearchIn=="Content") echo "selected
";?>>网页正文</option>
<option value="Title" <?php if ($SearchIn=="Title") echo "selected
";?>>网页标题</option>
</select>
</td>
<td valign="top">
<div align="left"><font color="#FF0000"><b><span class="pt13">查找方式</
span></b><span class="pt13">:</span></font>
<select name="Speed">
<option value="Fast" <?php if ($Speed=="Fast") echo "selected";?>>快
速查找</option>
<option value="Slow" <?php if ($Speed=="Slow") echo "selected";?>>更
深查找</option>
</select>
</div>
</td>
</tr>
</table>
</form>
<?php
if($SearchIn=="Title") $SQL="SELECT Id,Url,Title,Content FROM WebPageFindFast
WHERE ";
else $SQL="SELECT Id,Url,Title,Content FROM WebPageFind$Speed WHERE ";
$KeyWords=str_replace(" ", " ", $KeyWords);
if($KeyWords=="") {echo "关键字不能为空"; exit();}
$tok = strtok($KeyWords," ");
$i=0;
$j=0;
while($tok) {
$i ;
$tok = strtok(" ");
}
$key = strtok($KeyWords," ");
while($key) {
$j ;
if(substr($key,0,1)!="-") {
$SQL=$SQL.$SearchIn." LIKE '%".$key."%' ";
$Words[]=$key;
}
else {
$SQL=$SQL.$SearchIn." NOT LIKE '%".substr($key,1)."%' ";
}
if($j<$i) $SQL.=" AND ";
$key = strtok(" ");
}
if($CurPos!="") $SQL.=" AND Id>=$CurPos ";
$SQL.=" LIMIT 100";
//echo "/$SQL=".$SQL."<br>";
mysql_connect("localhost","root","mypassword");
$result=mysql_db_query("Spider",$SQL);
$RowCount=mysql_num_rows($result);
$FindCount=0;
?>
<table border=0 align=center width="96%">
<tr>
<th nowrap width="41%">
<div align="left" class="pt12">共找到关键字为 <font color=red>
<?php echo $KeyWords?>
</font> 的网页共 <font color=red>
<?php echo $RowCount;?>
</font> 个</div>
</th>
<td nowrap>
</td>
</tr>
<tr bgcolor="#FF0000">
<th nowrap colspan="2" height="3"></th>
</tr>
<?php while($row= mysql_fetch_array($result)){
$Pos=$row[0];
$FindCount ;
if($FindCount>20) break;?>
<tr>
<td nowrap colspan="2">
<?php echo $FindCount;?>
<a href="<?php echo $row[1]?>" target=_black>
<?php if($row[2]!="") echo $row[2];
else echo substr($row[3],0,64);
?>
</a></td>
</tr>
<tr>
<td colspan="2" ><span class="pt13">摘要:</span>
<?php
if($SearchIn=="Title") {
$ZhaiYao=substr($row[3],0,1024);
}
else{
if($Speed=="Fast") $ZhaiYao=$row[3];
else{
$RowLen=strlen($row[3]);
if ($RowLen<1024) {
$ZhaiYao=$row[3];
}
else {
$CutPos=0;
$PosWord1=strpos($row[3],$Words[0]);
if($PosWord1-512<0) $ZhaiYao=substr($row[3],0,1024);
else {
for($i=24;$i<500;$i ){ //避免将中文字符从半个字处截断,选择从英文处截断
if(ord(substr($row[3],$PosWord1-$i,1))<128) {$CutPos=$i;break;}
}
$ZhaiYao=substr($row[3],$PosWord1-$CutPos,1024);
}
}
}
for($i=0;$i<count($Words);$i ){
$ZhaiYao=str_replace($Words[$i],"<font color=red>".$Words[$i]."</font>", $ZhaiY
ao);
}
}
echo $ZhaiYao;
?>
</td>
</tr>
<tr>
<td colspan="2" align="right"><a href="One.php?num=<?php echo $row[0]?>" tar
get=_black>
<font color="#0033FF" class="pt12">本地镜像</font></a></td>
</tr>
<tr bgcolor="#999933">
<td nowrap colspan="2" height="1"></td>
</tr>
<?php } ?>
<?php if($RowCount>20){ ?>
<tr>
<td align="right" colspan="2" height="10">
<form name="form2" method="post" action="Search.php">
<input type="hidden" name="KeyWords" value="<?php echo $KeyWords;?>">
<input type="hidden" name="SearchIn" value="<?php echo $SearchIn;?>">
<input type="hidden" name="Speed" value="<?php echo $Speed;?>">
<input type="hidden" name="CurPos" value="<?php echo $Pos;?>">
<input type="submit" name="Submit" value="下20个网页">
</form>
</td>
</tr>
<?php } ?>
</table>
One.php用于从本地镜像中显示一个找到的网页。由于网页的原始信息已经在WebPageLocal中存储,所以 只需简单的读出,发给用户。
<?php
mysql_connect("localhost","root","mypassword");
$sql="select Url,Content from WebPageLocal where ";
if($num!="") $sql=$sql."Id=$num";
else exit();
$result=mysql_db_query("Spider",$sql);
$mt=mysql_fetch_row($result);
echo $mt[1];
?>