分享一个PHP 网站SEO及过滤类,方便使用

PHP中文网
リリース: 2016-05-25 17:11:53
オリジナル
1018 人が閲覧しました

在给网站页面做SEO的时候,长用到得一些函数。 
比如:良好URL生成,用户名过滤,email检测,截取字符串,全角替换成半角,删除html等 

1. [PHP]代码

<?php
 
class SeoTools
{
    public function friendlyURL($string, $replacement = &#39;-&#39;) {
        $map = array(
            &#39;/à|á|å|â|ä/&#39; => &#39;a&#39;,
            &#39;/è|é|ê|ẽ|ë/&#39; => &#39;e&#39;,
            &#39;/ì|í|î/&#39; => &#39;i&#39;,
            &#39;/ò|ó|ô|ø/&#39; => &#39;o&#39;,
            &#39;/ù|ú|ů|û/&#39; => &#39;u&#39;,
            &#39;/ç|č/&#39; => &#39;c&#39;,
            &#39;/ñ|ň/&#39; => &#39;n&#39;,
            &#39;/ľ/&#39; => &#39;l&#39;,
            &#39;/ý/&#39; => &#39;y&#39;,
            &#39;/ť/&#39; => &#39;t&#39;,
            &#39;/ž/&#39; => &#39;z&#39;,
            &#39;/š/&#39; => &#39;s&#39;,
            &#39;/æ/&#39; => &#39;ae&#39;,
            &#39;/ö/&#39; => &#39;oe&#39;,
            &#39;/ü/&#39; => &#39;ue&#39;,
            &#39;/Ä/&#39; => &#39;Ae&#39;,
            &#39;/Ü/&#39; => &#39;Ue&#39;,
            &#39;/Ö/&#39; => &#39;Oe&#39;,
            &#39;/ß/&#39; => &#39;ss&#39;,
            &#39;/ /&#39;=>&#39; &#39;,
            &#39;/ /&#39;=>&#39;&#39;,
       &#39;/~|·|!|@|#|¥|%|…|&|×|(|)|-|\+|=|『|【|』|】|、|:|;|“|”|\&#39;|
       《|,|》|。|?|\/|—|_|:|√|<|°|丶|>|-|★|||│|‖|ˇ/&#39;=>&#39; &#39;,
            &#39;/[^\w\s\x80-\xff]/&#39; => &#39; &#39;,
            &#39;/\\s+/&#39; => $replacement
        );
        $string = trim($string);
        $string = preg_replace(array_keys($map), array_values($map), $string);
        $string = preg_replace(&#39;/\\s+/&#39;,$replacement, strtolower($string));
        $string = trim($string,$replacement);
        return $string;
    }
     
    //判断email
    public function isEmail($mailAddr)
    {
        return strlen($mailAddr) > 6 && preg_match("/^[\w\-\.]+@[\w\-]+(\.\w+)+$/", $mailAddr);
 
    }
    //过滤用户
    public function CheckUser($string,$replacement = &#39;_&#39;)
    {
        $map = array(
            &#39;/à|á|å|â|ä/&#39; => &#39;a&#39;,
            &#39;/è|é|ê|ẽ|ë/&#39; => &#39;e&#39;,
            &#39;/ì|í|î/&#39; => &#39;i&#39;,
            &#39;/ò|ó|ô|ø/&#39; => &#39;o&#39;,
            &#39;/ù|ú|ů|û/&#39; => &#39;u&#39;,
            &#39;/ç|č/&#39; => &#39;c&#39;,
            &#39;/ñ|ň/&#39; => &#39;n&#39;,
            &#39;/ľ/&#39; => &#39;l&#39;,
            &#39;/ý/&#39; => &#39;y&#39;,
            &#39;/ť/&#39; => &#39;t&#39;,
            &#39;/ž/&#39; => &#39;z&#39;,
            &#39;/š/&#39; => &#39;s&#39;,
            &#39;/æ/&#39; => &#39;ae&#39;,
            &#39;/ö/&#39; => &#39;oe&#39;,
            &#39;/ü/&#39; => &#39;ue&#39;,
            &#39;/Ä/&#39; => &#39;Ae&#39;,
            &#39;/Ü/&#39; => &#39;Ue&#39;,
            &#39;/Ö/&#39; => &#39;Oe&#39;,
            &#39;/ß/&#39; => &#39;ss&#39;,
            &#39;/ /&#39;=>&#39; &#39;,
            &#39;/ /&#39;=>&#39;&#39;,
            &#39;/~|·|!|@|#|¥|%|…|&|×|(|)|-|\+|=|『|【|』|】|、|:|;|“|”|\&#39;|《|,|》|。
            |?|\/|—|_|:|√|<|°|丶|>|-|★|||│|‖|ˇ/&#39;=>&#39; &#39;,
            &#39;/[^\w\s\x80-\xff]/&#39; => &#39; &#39;,
            &#39;/\\s+/&#39; => $replacement
        );
        $string = trim($string);
        $string = preg_replace(array_keys($map), array_values($map), $string);
        $string = preg_replace(&#39;/\\s+/&#39;,$replacement, strtolower($string));
        $string = trim($string,$replacement);
        return $string;
    }
     
    public function mktitle($string, $replacement = &#39;_&#39;)
    {
        $map = array(
            &#39;/à|á|å|â|ä/&#39; => &#39;a&#39;,
            &#39;/è|é|ê|ẽ|ë/&#39; => &#39;e&#39;,
            &#39;/ì|í|î/&#39; => &#39;i&#39;,
            &#39;/ò|ó|ô|ø/&#39; => &#39;o&#39;,
            &#39;/ù|ú|ů|û/&#39; => &#39;u&#39;,
            &#39;/ç|č/&#39; => &#39;c&#39;,
            &#39;/ñ|ň/&#39; => &#39;n&#39;,
            &#39;/ľ/&#39; => &#39;l&#39;,
            &#39;/ý/&#39; => &#39;y&#39;,
            &#39;/ť/&#39; => &#39;t&#39;,
            &#39;/ž/&#39; => &#39;z&#39;,
            &#39;/š/&#39; => &#39;s&#39;,
            &#39;/æ/&#39; => &#39;ae&#39;,
            &#39;/ö/&#39; => &#39;oe&#39;,
            &#39;/ü/&#39; => &#39;ue&#39;,
            &#39;/Ä/&#39; => &#39;Ae&#39;,
            &#39;/Ü/&#39; => &#39;Ue&#39;,
            &#39;/Ö/&#39; => &#39;Oe&#39;,
            &#39;/ß/&#39; => &#39;ss&#39;,
            &#39;/ /&#39;=>&#39; &#39;,
            &#39;/ /&#39;=>&#39;&#39;,
            &#39;/~|·|!|@|#|¥|%|…|&|×|(|)|-|\+|=|『|【|』|】|、|:|;|“|”|\&#39;|《|,|》|。
            |?|\/|—|_|:|√|<|°|丶|>|-|★|||│|‖|ˇ/&#39;=>&#39; &#39;,
            &#39;/[^\w\s^.\x80-\xff]/&#39; => &#39; &#39;,
            &#39;/\\s+/&#39; => $replacement
        );
        $string = trim($string);
        $string = preg_replace(array_keys($map), array_values($map), $string);
        $string = preg_replace(&#39;/\\s+/&#39;,$replacement, strtolower($string));
        $string = trim($string,$replacement);
        return $string;
    }
     
    // 全角替换成半角
    public function Qj2bj($string)
    {
        $qj2bj = array(
            &#39;1&#39; => &#39;1&#39;, &#39;2&#39; => &#39;2&#39;, &#39;3&#39; => &#39;3&#39;, &#39;4&#39; => &#39;4&#39;, &#39;5&#39; => &#39;5&#39;,
            &#39;6&#39; => &#39;6&#39;, &#39;7&#39; => &#39;7&#39;, &#39;8&#39; => &#39;8&#39;, &#39;9&#39; => &#39;9&#39;, &#39;0&#39; => &#39;0&#39;,
            &#39;a&#39; => &#39;a&#39;, &#39;b&#39; => &#39;b&#39;, &#39;c&#39; => &#39;c&#39;, &#39;d&#39; => &#39;d&#39;, &#39;e&#39; => &#39;e&#39;,
            &#39;f&#39; => &#39;f&#39;, &#39;g&#39; => &#39;g&#39;, &#39;h&#39; => &#39;h&#39;, &#39;i&#39; => &#39;i&#39;, &#39;j&#39; => &#39;j&#39;,
            &#39;k&#39; => &#39;k&#39;, &#39;l&#39; => &#39;l&#39;, &#39;m&#39; => &#39;m&#39;, &#39;n&#39; => &#39;n&#39;, &#39;o&#39; => &#39;o&#39;,
            &#39;p&#39; => &#39;p&#39;, &#39;q&#39; => &#39;q&#39;, &#39;r&#39; => &#39;r&#39;, &#39;s&#39; => &#39;s&#39;, &#39;t&#39; => &#39;t&#39;,
            &#39;u&#39; => &#39;u&#39;, &#39;v&#39; => &#39;v&#39;, &#39;w&#39; => &#39;w&#39;, &#39;x&#39; => &#39;x&#39;, &#39;y&#39; => &#39;y&#39;,
            &#39;z&#39; => &#39;z&#39;, &#39;A&#39; => &#39;A&#39;, &#39;B&#39; => &#39;B&#39;, &#39;C&#39; => &#39;C&#39;, &#39;D&#39; => &#39;D&#39;,
            &#39;E&#39; => &#39;E&#39;, &#39;F&#39; => &#39;F&#39;, &#39;G&#39; => &#39;G&#39;, &#39;H&#39; => &#39;H&#39;, &#39;I&#39; => &#39;I&#39;,
            &#39;J&#39; => &#39;J&#39;, &#39;K&#39; => &#39;K&#39;, &#39;L&#39; => &#39;L&#39;, &#39;M&#39; => &#39;M&#39;, &#39;N&#39; => &#39;N&#39;,
            &#39;O&#39; => &#39;O&#39;, &#39;P&#39; => &#39;P&#39;, &#39;Q&#39; => &#39;Q&#39;, &#39;R&#39; => &#39;R&#39;, &#39;S&#39; => &#39;S&#39;,
            &#39;T&#39; => &#39;T&#39;, &#39;U&#39; => &#39;U&#39;, &#39;V&#39; => &#39;V&#39;, &#39;W&#39; => &#39;W&#39;, &#39;X&#39; => &#39;X&#39;,
            &#39;Y&#39; => &#39;Y&#39;, &#39;Z&#39; => &#39;Z&#39;, &#39; &#39; => &#39; &#39;
        );
        return strtr($string, $qj2bj);
    }
     
    public function DelNbsp($string)
    {
        $map = array(
            &#39;/ /&#39;=>&#39; &#39;,
            &#39;/\?/&#39;=>&#39; &#39;,
            &#39;/ /&#39;=>&#39;&#39;,
        );
        $string = preg_replace(array_keys($map), array_values($map), $string);
        $string = preg_replace(&#39;/\\s+/&#39;,&#39;&#39;,$string);
        return $string;
    }
    public function getZipcode($str)
    {
        $pattern = "/[0-9]{1}(\d+){4,5}/";
        preg_match_all($pattern,$str,$zipcodeArr); 
        if(empty($zipcodeArr[0]))
        {
            return &#39;&#39;;
        }
        else {
            return $zipcodeArr[0][0];
        }
     
    }
 
    public function checkZipcode($str)
    {
        $strwidth=strlen($str);
        $zipcode=$str;
        switch($strwidth)
        {
            case 4:$zipcode="00".$str;break;
            case 5:$zipcode="0".$str;break;
            case 6:$zipcode=$str;break;
            default:$zipcode="";break;
        }
        return $zipcode;
    }
     
    public function getEmail($str) { 
        $pattern = "/\w+([-+.]\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*/i"; 
        preg_match_all($pattern,$str,$emailArr); 
        if(empty($emailArr[0]))
        {
            return &#39;&#39;;
        }
        else {
            $email_str=implode(",", $emailArr[0]);
            return $email_str;
        }
    } 
    public function getUrl($str)
    {
        $pattern = "/(http:\/\/|https:\/\/|ftp:\/\/)?([\w:\/\.\?=&-_]+)/is"; 
        preg_match_all($pattern,$str,$urlArr);
        if(empty($urlArr[0]))
        {
            return &#39;&#39;;
        }
        else {
            $url_str=implode(",", $urlArr[0]);
            $url_str=preg_replace(&#39;/(http:\/\/|https:\/\/|ftp:\/\/)/&#39;,&#39;&#39;,$url_str);
            return $url_str;
        }
 
         
    }
    public function match_links($document) {  
    $match=array();  
       preg_match_all("&#39;<\s*a\s.*?href\s*=\s*([\"\&#39;])?(?(1)(.*?)\\1|([^\s\>]+))[^>]*>?(.*?)
       </a>&#39;isx",$document,$links);                        
       while(list($key,$val) = each($links[2])) {
           if(!empty($val))
               $match[&#39;link&#39;][] = $val;
       }
       while(list($key,$val) = each($links[3])) {
           if(!empty($val))
               $match[&#39;link&#39;][] = $val;
       }        
       while(list($key,$val) = each($links[4])) {
           if(!empty($val))
               $match[&#39;content&#39;][] = $val;
       }
       while(list($key,$val) = each($links[0])) {
           if(!empty($val))
               $match[&#39;all&#39;][] = $val;
       }                
       return $match;
    }
    public function DelNoStr($string)
    {
        $map = array(
            &#39;/à|á|å|â|ä/&#39; => &#39;a&#39;,
            &#39;/è|é|ê|ẽ|ë/&#39; => &#39;e&#39;,
            &#39;/ì|í|î/&#39; => &#39;i&#39;,
            &#39;/ò|ó|ô|ø/&#39; => &#39;o&#39;,
            &#39;/ù|ú|ů|û/&#39; => &#39;u&#39;,
            &#39;/ç|č/&#39; => &#39;c&#39;,
            &#39;/ñ|ň/&#39; => &#39;n&#39;,
            &#39;/ľ/&#39; => &#39;l&#39;,
            &#39;/ý/&#39; => &#39;y&#39;,
            &#39;/ť/&#39; => &#39;t&#39;,
            &#39;/ž/&#39; => &#39;z&#39;,
            &#39;/š/&#39; => &#39;s&#39;,
            &#39;/æ/&#39; => &#39;ae&#39;,
            &#39;/ö/&#39; => &#39;oe&#39;,
            &#39;/ü/&#39; => &#39;ue&#39;,
            &#39;/Ä/&#39; => &#39;Ae&#39;,
            &#39;/Ü/&#39; => &#39;Ue&#39;,
            &#39;/Ö/&#39; => &#39;Oe&#39;,
            &#39;/ß/&#39; => &#39;ss&#39;,
            &#39;/ /&#39;=>&#39; &#39;,
            &#39;/ /&#39;=>&#39;&#39;,
            &#39;/~|·|!|@|#|¥|%|…|&|×|(|)|-|\+|=|『|【|』|】|、|:|;|“|”|’|《|,|》|。
            |?|\/|—|_|‘|:|√|<|°|丶|ˇ/&#39;=>&#39; &#39;,
            &#39;/[^\w\s\x80-\xff]/&#39; => &#39; &#39;,
           // &#39;/\\s+/&#39; => $replacement
        );
        $string = trim($string);
        $string = preg_replace(array_keys($map), array_values($map), $string);
        $string = preg_replace(&#39;/\\s+/&#39;,&#39;&#39;,$string);
        $string = trim($string,&#39;&#39;);
        return $string;
    }
    public function UrlToStr($string, $find = &#39;/-/&#39;)
    {   
        $string = preg_replace($find," ", strtolower($string));
        $string = trim($string);
        return $string;
    }
     
    public function GetPyLetter($str)
    {
        return substr(pinyin($str, $ucfirst=true), 0,1);
    }
    public function GetPinYin($str)
    {
        return strtolower(pinyin($str, $ucfirst=true));
    }
     
    public function DelCode($str)
    {
         
        $search = array("&#39;<script[^>]*?>.*?</script>&#39;si",    // strip out javascript
                        "&#39;<[\/\!]*?[^<>]*?>&#39;si",            // strip out html tags
                        "&#39;([\r\n])[\s]+&#39;",                  // strip out white space
                        "&#39;&(quot|#34|#034|#x22);&#39;i",        // replace html entities
                        "&#39;&(amp|#38|#038|#x26);&#39;i",         // added hexadecimal values
                        "&#39;&(lt|#60|#060|#x3c);&#39;i",
                        "&#39;&(gt|#62|#062|#x3e);&#39;i",
                        "&#39;&(nbsp|#160|#xa0);&#39;i",
                        "&#39;&(iexcl|#161);&#39;i",
                        "&#39;&(cent|#162);&#39;i",
                        "&#39;&(pound|#163);&#39;i",
                        "&#39;&(copy|#169);&#39;i",
                        "&#39;&(reg|#174);&#39;i",
                        "&#39;&(deg|#176);&#39;i",
                        "&#39;&(#39|#039|#x27);&#39;",
                        "&#39;&(euro|#8364);&#39;i",                // europe
                        "&#39;&a(uml|UML);&#39;",                   // german
                        "&#39;&o(uml|UML);&#39;",
                        "&#39;&u(uml|UML);&#39;",
                        "&#39;&A(uml|UML);&#39;",
                        "&#39;&O(uml|UML);&#39;",
                        "&#39;&U(uml|UML);&#39;",
                        "&#39;&szlig;&#39;i",
                        );
        $replace = array("",
                            "",
                            "\\1",
                            "\"",
                            "&",
                            "<",
                            ">",
                            " ",
                            chr(161),
                            chr(162),
                            chr(163),
                            chr(169),
                            chr(174),
                            chr(176),
                            chr(39),
                            chr(128),
                            "?",
                            "?",
                            "?",
                            "?",
                            "?",
                            "?",
                            "?",
                        );
        $str = preg_replace($search,$replace,$str);
        return trim($str);
    }
     
     
    public function CutStr($sourcestr,$cutlength)
    {
       $returnstr=&#39;&#39;;
       $i=0;
       $n=0;
       $sourcestr=rtrim(SeoTools::DelCode($sourcestr));
       $str_length=strlen($sourcestr);//字符串的字节数
        while (($n<$cutlength) and ($i<=$str_length))
        {
          $temp_str=substr($sourcestr,$i,1);
          $ascnum=Ord($temp_str);//得到字符串中第$i位字符的ascii码
          if ($ascnum>=224)    //如果ASCII位高与224,
          {
            $returnstr=$returnstr.substr($sourcestr,$i,3); //根据UTF-8编码规范,将3个连续的字符计为单个字符       
             $i=$i+3;            //实际Byte计为3
             $n++;            //字串长度计1
          }
          elseif ($ascnum>=192) //如果ASCII位高与192,
          {
             $returnstr=$returnstr.substr($sourcestr,$i,2); //根据UTF-8编码规范,将2个连续的字符计为单个字符
             $i=$i+2;            //实际Byte计为2
             $n++;            //字串长度计1
          }
          elseif ($ascnum>=65 && $ascnum<=90) //如果是大写字母,
          {
             $returnstr=$returnstr.substr($sourcestr,$i,1);
             $i=$i+1;            //实际的Byte数仍计1个
             $n++;            //但考虑整体美观,大写字母计成一个高位字符
          }
          else                //其他情况下,包括小写字母和半角标点符号,
          {
             $returnstr=$returnstr.substr($sourcestr,$i,1);
             $i=$i+1;            //实际的Byte数计1个
             $n=$n+0.5;        //小写字母和半角标点等与半个高位字符宽...
          }
        }
        if ($str_length>$i){
            $returnstr = $returnstr . ".";//超过长度时在尾处加上省略号
        }
        return htmlspecialchars($returnstr);
    }
     
    public function CreateTagLink($tags_str)
    {
        $tags_array=explode(",",$tags_str);
        $link_tpl="";
        foreach($tags_array as $v)
        {
            $tag=trim($v);
            $alias=SeoTools::friendlyURL($tag);
        //  $link_tpl.=&#39;<a href="/s/&#39;.urlencode($alias).&#39;" title="&#39;.$tag.&#39;">&#39;.$tag.&#39;</a>  &#39;;
            $link_tpl.=$tag.&#39;  &#39;;
        }
        return $link_tpl;
    }
     
}
 
 
 
 
/**
 * 中文转拼类
 *
 * @author  Lukin <my@lukin.cn>
 * @date    2011-01-25 10:44
 */
class PinYin {
    // 码表
    private $fp  = null;
    private $dat = &#39;pinyin.dat&#39;;
 
    public function __construct(){
        $this->dat = dirname(__FILE__).&#39;/&#39;.$this->dat;
        if (is_file($this->dat)) {
            $this->fp = fopen($this->dat, &#39;rb&#39;);
        }
    }
    /**
     * 转拼音
     *
     * @param string $str   汉字
     * @param bool $ucfirst 首字母大写
     * @param bool $polyphony 忽略多读音
     * @return string
     */
    public function encode($str, $ucfirst=true, $polyphony=true) {
        $ret = &#39;&#39;; $len = mb_strlen($str, &#39;UTF-8&#39;);
        for ($i = 0; $i < $len; $i++) {
            $py = $this->pinyin(mb_substr($str, $i, 1, &#39;UTF-8&#39;));
            if ($ucfirst && strpos($py,&#39;,&#39;) !== false) {
                $pys = explode(&#39;,&#39;, $py); 
                $ret.= implode(&#39;,&#39;, array_map(&#39;ucfirst&#39;, ($polyphony ? array_slice($pys, 0, 1) : $pys)));
            } else {
                $ret.= $ucfirst ? ucfirst($py) : $py;
               
            }
        }
         
        return $ret;
    }
    /**
     * 汉字转十进制
     *
     * @param string $word
     * @return number
     */
    private function char2dec($word) {
        $bins  = &#39;&#39;;
        $chars = str_split($word);
        foreach($chars as $char) $bins.= decbin(ord($char));
        $bins = preg_replace(&#39;/^.{4}(.{4}).{2}(.{6}).{2}(.{6})$/&#39;, &#39;$1$2$3&#39;, $bins);
        return bindec($bins);
    }
    /**
     * 单个字转拼音
     *
     * @param string $char  汉字
     * @return string
     */
    public function pinyin($char){
        if (strlen($char) == 3 && $this->fp) {
            $offset = $this->char2dec($char);
            // 判断 off 值
            if ($offset >= 0) {
                fseek($this->fp, ($offset - 19968) << 4, SEEK_SET);
                return trim(fread($this->fp, 16));
            }
        }
        return $char;
    }
 
    public function __destruct() {
        if ($this->fp) {
            fclose($this->fp);
        }
    }
}
/**
 * 取得实例
 *
 * @return $pinyin
 */
function &_pinyin_get_object() {
    static $pinyin;
    if ( is_null($pinyin) )
        $pinyin = new PinYin();
    return $pinyin;
}
 
if (!function_exists(&#39;pinyin&#39;)) :
/**
 * 取得拼音
 *
 * @param string $str
 * @param bool $ucfirst 首字母大写
 * @return string
 */
function pinyin($str, $ucfirst=true) {
    $py = _pinyin_get_object();
    return $py->encode($str, $ucfirst);
}
endif;
ログイン後にコピー

以上就是分享一个PHP 网站SEO及过滤类,方便使用的内容,更多相关内容请关注PHP中文网(www.php.cn)!


関連ラベル:
ソース:php.cn
このウェブサイトの声明
この記事の内容はネチズンが自主的に寄稿したものであり、著作権は原著者に帰属します。このサイトは、それに相当する法的責任を負いません。盗作または侵害の疑いのあるコンテンツを見つけた場合は、admin@php.cn までご連絡ください。
最新の問題
人気のおすすめ
人気のチュートリアル
詳細>
最新のダウンロード
詳細>
ウェブエフェクト
公式サイト
サイト素材
フロントエンドテンプレート
私たちについて 免責事項 Sitemap
PHP中国語ウェブサイト:福祉オンライン PHP トレーニング,PHP 学習者の迅速な成長を支援します!