PHP 去除字符串中所有html代码(格式化代码html)

/**
 * 去除字符串中所有html代码(格式化代码html)
 */
if ( ! function_exists('clearHtml')) {
    function clearHtml($content)
    {
        $content = preg_replace("/<a[^>]*>/i", "", $content);
        $content = preg_replace("/<\/a>/i", "", $content);
        $content = preg_replace("/<p(.*?)>/i", "<p>", $content);//去除p标签里的样式
        $content = preg_replace("/<p><\/p>/i", "", $content);
        $content = preg_replace("/<p> <\/p>/i", "", $content);
        $content = preg_replace("/<p><br><\/p>/i", "", $content);
        $content = preg_replace("/<p><br\/><\/p>/i", "", $content);
        $content = preg_replace("/<p><br \/><\/p>/i", "", $content);
        $content = preg_replace("/<div[^>]*>/i", "", $content);
        $content = preg_replace("/<\/div>/i", "", $content);
        //$content = preg_replace("/<!--[^>]*-->/i", "", $content);//注释内容
        $content = preg_replace("/<!--(.*?)-->/i", "", $content);//注释内容
        $content = preg_replace("/<style>(.*)<\/style>/i", '', $content);//去除样式
        $content = preg_replace("/style=.+?\"/i", '', $content);//去除样式
        $content = preg_replace("/style=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/class=.+?['|\"]/i", '', $content);//去除样式
        //$content = preg_replace("/id=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/lang=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/width=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/height=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/border=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/face=.+?['|\"]/i", '', $content);//去除样式
        $content = preg_replace("/face=.+?['|\"]/", '', $content);//去除样式只允许小写正则匹配没有带 i 参数
        $content = preg_replace("<fieldset(.*?)>", "div", $content);
        $content = preg_replace("</fieldset(.*?)>", "div", $content);
        $content = preg_replace("<voice(.*?)>", "span", $content);
        $content = preg_replace("</voice(.*?)>", "span", $content);
        $content = preg_replace("<section(.*?)>", "div", $content);     //去除section标签
        $content = preg_replace("</section(.*?)>", "div", $content);    //去除section标签
        $content = preg_replace("/<strong(.*?)>/i", "", $content);//去除加粗
        $content = preg_replace("/<\/strong>/i", "", $content);//去除加粗
        $content = preg_replace("/<script(.*?)>/i", "", $content);
        $content = preg_replace("/<\/script>/i", "", $content);//去除script
        $content = preg_replace("/<button(.*?)>(.*?)<\/button>/i", "", $content);//去除button
        //$content = preg_replace("/<\/button>/i", "", $content);//去除button
        $content = preg_replace('/<svg viewbox=(.*?)\/>/i', "", $content);
        $content = preg_replace('/<!\[CDATA(.*?)\]\]>/i', "", $content);
        $content = preg_replace("/<h1(.*?)>/i", "<p>", $content);
        $content = preg_replace("/<\/h1(.*?)>/i", "<\/p>", $content);
        $content = preg_replace("/<h2(.*?)>/i", "<p>", $content);
        $content = preg_replace("/<\/h2(.*?)>/i", "<\/p>", $content);
        $content = preg_replace("/<h3(.*?)>/i", "<p>", $content);
        $content = preg_replace("/<\/h3(.*?)>/i", "<\/p>", $content);
        $content = preg_replace("/<h4(.*?)>/i", "<p>", $content);
        $content = preg_replace("/<\/h4(.*?)>/i", "<\/p>", $content);
        $content = preg_replace("/(\xc2\xa0)/", '', $content);  //去除全角空格

        $content = str_replace("<b>", "", $content);//去除加粗
        $content = str_replace("<\/b>", "", $content);//去除加粗
        $content = str_replace("<u>", "", $content);
        $content = str_replace("<u >", "", $content);
        $content = str_replace("</u>", "", $content);
        $content = str_replace("<b >", "", $content);
        $content = str_replace("<b>", "", $content);
        $content = str_replace("</b>", "", $content);
        $content = str_replace(" ", "", $content);

        //$content = str_replace("\t", '', $content);//去除\t
        //$content = str_replace("\n", '', $content);//去除\n

        return $content;
    }
}
PHP 去除字符串中所有html代码(格式化代码html)
© 版权声明
THE END
喜欢就支持一下吧
点赞11 分享
评论 抢沙发

请登录后发表评论

    blank

    暂无评论内容