搜索引擎URL中的汉字解析

<script type="text/javascript"><!-- google_ad_client = "pub-0241434510974184"; /* auto-http.cn 右边 ,468x60 */ google_ad_slot = "0902256228"; google_ad_width = 468; google_ad_height = 60; // --></script><script src="http://pagead2.googlesyndication.com/pagead/show_ads.js" type="text/javascript"></script>

搜索引擎URL中的汉字解析

代码说明一切:

<? php
/*
*Createdon2008-2-4
*
*Tochangethetemplateforthisgeneratedfilegoto
*Window-Preferences-PHPeclipse-PHP-CodeTemplates
*/
// "http://www.baidu.com/baidu?wd=%D5%FD%D4%F2%B1%ED%B4%EF%CA%BD&q=3"

function requestCharacters( $strURL )
{
if ( preg_match_all ( " /(%[a-zA-Z0-9]{2})+/ " , $strURL , $matches ) != FALSE )
{
return $matches [ 0 ][ 0 ];
}
return "" ;
}

function ConvertUrlDecode( $textUrlChar )
{
$textUrl = htmlspecialchars ( urldecode ( $textUrlChar ));
return $textUrl ;
}

function ConvertEncoding( $textEncode )
{
$textEncode = mb_convert_encoding( $textEncode , " UTF-8 " , " GB2312 " );
return $textEncode ;
}


function Chinese( $word = "" )
{
if ( empty ( $word ))
{
return "" ;
}
if ( preg_match ( " /^([ " . chr ( 228 ) . " - " . chr ( 233 ) . " ]{1}[ " . chr ( 128 ) . " - " . chr ( 191 ) . " ]{1}[ " . chr ( 128 ) . " - " . chr ( 191 ) . " ]{1}){1}/ " , $word ) == true || preg_match ( " /([ " . chr ( 228 ) . " - " . chr ( 233 ) . " ]{1}[ " . chr ( 128 ) . " - " . chr ( 191 ) . " ]{1}[ " . chr ( 128 ) . " - " . chr ( 191 ) . " ]{1}){1}$/ " , $word ) == true || preg_match ( " /([ " . chr ( 228 ) . " - " . chr ( 233 ) . " ]{1}[ " . chr ( 128 ) . " - " . chr ( 191 ) . " ]{1}[ " . chr ( 128 ) . " - " . chr ( 191 ) . " ]{1}){2,}/ " , $word ) == true )
{
return " 结果:很好，这是一个UTF-8编码的汉字 " ;
}
else
{
return " 结果:抱歉，这不是一个UTF-8编码的汉字 " ;
}
}
$radioGB2312 = "" ;
$radioUTF8 = "" ;
$radioflg = $_REQUEST [ ' radioflg ' ];
if ( $radioflg == " GB2312 " )
{
$radioGB2312 = " checked " ;
}
else if ( $radioflg == " UTF-8 " )
{
$radioUTF8 = " checked " ;
}
else
{
$radioUTF8 = " checked " ;
}

?>

<! DOCTYPEhtml PUBLIC " -//W3C//DTDXHTML1.0Transitional//EN "
" http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd " >
< htmlxmlns = " http://www.w3.org/1999/xhtml " xml : lang = " ja " lang = " ja " >
< head >
< metahttp - equiv = " Content-Language " content = " ja " />
< metahttp - equiv = " Content-Script-Type " content = " text/javascript " />
< metahttp - equiv = " Content-Type " content = " text/html;charset=utf-8 " />
< title > URL解析 </ title >
< scriptlanguage = " Javascript " >
function btSubmit()
{
document . urlrequest . action = ' urlcharacters.php ' ;
document . urlrequest . submit();
}
function radioSubmit(flgType)
{
document . urlrequest . radioflg . value = flgType;
}
</ script >
</ head >
< body >
< formname = " urlrequest " method = " post " >
< textareaname = " urltext " rows = " 8 " cols = " 40 " ><?= $_REQUEST [ " urltext " ]; ?></ textarea >
< p >

< inputtype = " radio " name = " mainrd " id = " GB2312 " onclick = " javascript:radioSubmit('GB2312') " value = " 0 " <?= $radioGB2312 ?>>
< labelid = " label_GB2312 " for = " GB2312 " style = " CURSOR:hand " > GB2312 </ label >

< inputtype = " radio " name = " mainrd " id = " UTF-8 " onclick = " javascript:radioSubmit('UTF-8') " value = " 1 " <?= $radioUTF8 ?>>
< labelid = " label_UTF-8 " for = " UTF-8 " style = " CURSOR:hand " > UTF - 8 </ label >

</ p >
< p >< inputtype = " button " value = " URL汉字编码解析 " onclick = " javascript:btSubmit(); " /></ p >
< p >
<? php
$strURL = $_REQUEST [ " urltext " ]; // "http://www.baidu.com/baidu?wd=%D5%FD%D4%F2%B1%ED%B4%EF%CA%BD&q=3";

$textEncode = requestCharacters( $strURL );


echo " 正则表达式提取: " . $textEncode ;

$convertText = ConvertUrlDecode( $textEncode );


if ( $radioflg == " GB2312 " )
{
$convertText = ConvertEncoding( $convertText );
}


echo " <br><br>URL解析:$convertText<br><br> " ;

echo Chinese( $convertText );

?>
</ p >

< inputtype = " hidden " name = " radioflg " id = " radioflg " value = " <?=$radioflg?> " />
</ form >
</ body >
</ html >