PHP正则过滤替换

2019独角兽企业重金招聘Python工程师标准>>>

对字符串进行去重的核心方法如下Common.cls.php：

class Common {

    /**
     * 获取新行程中的文字
     * 将$title中的img标签去除
     * @param  $title
     * @return Ambigous <boolean, multitype:>
     */
    public static function getSubTitle($title){
        //应该不会出现一天换5次交通的情况吧
        $pattern = '/<img (.*?)[<(.*?)>]{0,5}>/';
        preg_match_all($pattern, $title, $matches );
        if(isset($matches[0]) && !empty($matches[0])){
            $match_info =  $matches[0];
            foreach ($match_info as $str){
                $title = str_replace($str, '::', $title) ;
            }
            $title = self::removeSpecial($title);
            $title_arr = explode('::',$title);
        }
        if(isset($title_arr) && !empty($title_arr)){
            $result = $title_arr;
        }else{
            $title = self::removeSpecial($title);
            $result = array($title);
        }
        return $result;
    }
 
    /**
     * 过滤特殊字符，去除Html标签
     * @param  $title
     * @return string
     */
    private static function removeSpecial($title){
        $title_tmp = $title;
        //过滤title中的特殊字符
        $html_info = array("<br>","\r\n","\n","&nbsp;");
        foreach ($html_info as $hi ){
            $title_tmp = str_replace($hi, '', $title_tmp);
        }
        //去除标题中的（...）
        $title_tmp = preg_replace('/（.*?）/', '', $title_tmp);
        //过滤html标签
        $title_tmp = strip_tags($title_tmp);
        return trim($title_tmp);
    }
    
    /**
     * 获取当前时间
     * @return number
     */
    public static function getMicroTime(){
        list($usec, $sec) = explode(" ",microtime());
        return ((float)$usec + (float)$sec);
    }    
}

下面是对其的测试应用test.php

require_once 'Common.cls.php';

$data = '[{"day":"1","title":"南京<img src=\"http://img3.tuniucdn.com/site/images/index/logo_v4.gif\">北京","summary":["难道是匹配行程里的。九寨沟 天坛<br>"]},{"day":"2","title":"北京<img src=\"http://img3.tuniucdn.com/site/images/index/logo_v4.gif\">东京","summary":["一线天 三亚<br>"]},{"day":"3","title":"东京<img src=\"http://img3.tuniucdn.com/site/images/index/logo_v4.gif\">西京","summary":["黄石公园 博物馆<br>"]}]' ;

$info = json_decode($data,true);

$title_arr = array();
foreach ($info as $route_info){
    $title_tmp = Common::getSubTitle($route_info['title']);

    $title_tmp_end = end($title_tmp) ;
    foreach ($title_tmp as $t){
        if(count($title_arr) == 0){
            $title_arr[] = $t;
            continue;

        }
        if($t != $title_tmp_end){
            $title_arr[] = $t;
        }
    }
}

$result = implode('>>', $title_arr);

header('Content-type: text/html; charset=utf-8');
echo $result;

转载于:https://my.oschina.net/andyfeng/blog/326879