PHP清除网页格式，文章自动格式化

在转载网上的文章时，经常会碰到代码冗长杂乱，布满链接的情况，另外，直接从WORD里面的文章拷贝到网页上的话，代码也会极其的冗长，非常影响浏览速度。下面是赵云建站使用PHP开发制作的文章自动格式化的编辑工具，源码贴出来给大家分享：

前台页面：

    <div class="form1" id="arc_edit">
  <form method="post" id="arc_form">
    <table cellpadding="0" cellspacing="0">
      <tbody>
        <tr>
          <td>标题：</td>
          <td><input type="text" name="title" class="text_m" value="" /></td>
        </tr>
        <tr>
          <td>关键词：</td>
          <td><input type="text" name="keywords" class="text_m" value="" /></td>
        </tr>
        <tr>
          <td valign="top">描述：</td>
          <td><textarea class="area_m" name="description"></textarea></td>
        </tr>
        <tr>
          <td valign="top">正文：</td>
          <td><input type="hidden" id="acontent" name="acontent" value="" style="display:none" /><input type="hidden" id="acontent___Config" value="" style="display:none" /><iframe id="acontent___Frame" src="lib/editor/editor/fckeditor.html?InstanceName=acontent&amp;Toolbar=Basic" width="600" height="500" frameborder="0" scrolling="no"></iframe></td>
        </tr>
        <tr class="msg">
          <td valign="top">提示：</td>
          <td>第一步：格式化。  第二步：手工编辑。  第三步：自动加链接。  第四步：保存或编辑下一篇。</td>
        </tr>
        <tr class="operate2">
          <td valign="top">操作：</td>
          <td><a href="javascript:submitform('fat');" class="btn1">格式化文本</a></td>
        </tr>
        <tr class="operate2">
          <td valign="top"></td>
          <td valign="middle"><a href="javascript:submitform('autolink');" class="btn1">自动加链接</a> <select name="lid" style=" float:left"><option>关键词词库</option><option value="2">www.hnzymr.cn</option><option value="3">www.hnzymr.com</option><option value="4">www.hydyyy.com</option></select></td>
        </tr>
        <tr class="operate2">
          <td valign="top"></td>
          <td><a href="javascript:submitform('save');" class="btn1">保存到草稿箱</a> <input type="hidden" name="aid" value="" /></td>
        </tr>
      </tbody>
    </table>
  </form>
</div>
<script type="text/javascript">
  function submitform(type){
   var oEditor = FCKeditorAPI.GetInstance('acontent');
      var acontent = oEditor.GetXHTML(true);
            document.getElementById('acontent').value = acontent;
             var form = document.getElementById('arc_form');
    form.action='?m=arc&o=edit&submit=1&type='+type;
    form.submit();
  }
</script>

处理代码：

if(!empty($arc['content'])){
  $replaces = array("/<style.*?>.*<\/style>/i" => '',
        "/<img.*?>/i" => '',
           "/<font.*?>/i" => '',
        "/<\/font>/i" => '',
           "/<strong>/i" => '',
        "/<\/strong>/i" => '',
        "/<span.*?>/i" => '',
        "/<\/span>/i" => '',
        "/<div.*?>/i" => "<p>",
        "/<\/div>/i" => "</p>",
     "/<table.*?>/i" => '',
     "/<\/table>/i" => '',
     "/<tbody.*?>/i" => '',
     "/<\/tbody>/i" => '',
     "/<tr.*?>/i" => '<p>',
     "/<\/tr>/i" => '</p>',
     "/<td.*?>/i" => '',
     "/<\/td>/i" => '',
        "/<ul.*?>/i" => "<p>",
        "/<\/ul>/i" => "</p>",
        "/<li.*?>/i" => "<p>",
        "/<\/li>/i" => "</p>",
        "/<h[1-6]+.*?>/i" => "<p>",
        "/<\/h[1-6]+?>/i" => "</p>",
        "/<a.*?>/i" => '',
        "/<\/a>/i" => '',
        "/<br(.*)?>/i" => "</p></p>",
        "/<b>/i" => '',
        "/<\/b>/i" => '',
        "/<script.*?>.*<\/script>/i" => '',
        "/<iframe.*?>.*<\/iframe>/i" => '',
        "/style=\".*?\"/i" => '',
        "/style=\'.*?\'/i" => '',
     "/&nbsp;/i" => '',
        "/<p.*?>/i" => '<p>',
     "/[( )|(　)]/u" => '',
     "/[\r|\n]+/" => '',
     "/<p>(<p>)+/i" => '<p>',
     "/<\/p>(<\/p>)+/i" => '</p>',
     "/(<p><\/p>)+/i" => '',
     "/<p>/i" => '<p>　　',
     );
 
  foreach($replaces as $k  => $v)
    $arc['content'] = preg_replace($k,$v,$arc['content']);
}