Community Learn Tools Library Leisure
search
English
Home > Backend Development > PHP Tutorial > body text

php正则替换处理HTML页面的方法_php技巧

WBOY
Release： 2016-05-16 20:13:39
Original
793 people have browsed it

本文实例讲述了php正则替换处理HTML页面的方法。分享给大家供大家参考。具体如下：

<&#63;php
if(!defined('BASEPATH')) exit('No direct script access allowed');
 /**
  * HTML替换处理类，考虑如下几种替换
  * 1. img src : '/<img (.+&#63;)src=([\'\" ])&#63;(.+&#63;)([  alt="php正则替换处理HTML页面的方法_php技巧" >]+&#63;)/i'
  * 2. a href : '/<a(.+&#63;)href=([\'\" ])&#63;(.+&#63;)([ >]+&#63;)/i'
  * 3. ifram.src : '/<iframe(.+&#63;)src=([\'\" ])&#63;(.+&#63;)([ >]+&#63;)/i'
  * 4. frame src : '/<frame(.+&#63;)src=([\'\" ])&#63;(.+&#63;)([ >]+&#63;)/i'
  * 5. js  : '/window.open([( ]+&#63;)([\'" ]+&#63;)(.+&#63;)([ )+&#63;])/i'
  * 6. css  : '/background(.+&#63;)url([( ])([\'" ]+&#63;)(.+&#63;)([ )+&#63;])/i'
  */
 class Myreplace {
  private $moudle_array = array('udata','tdata','tresult','dresult');
  private $content;
  private $relative_dirname;
  private $projectid;
  private $moudle;
  function __construct() {
   $this->CI = &get_instance ();
  }
  /**
   * 替换
   * @param string $content HTML内容
   * @param string $relative 相对路径
   * @param int  $projectid 项目id
   * @moudle string $moudle  模板标识: udata,tdata,tresult,dresult
   */
  public function my_replace($content,$relative,$projectid,$moudle) {
   $this->content = $content;
   $this->relative_dirname = $relative;
   $this->projectid = $projectid;
   if(in_array(strtolower($moudle),$this->moudle_array))
    $this->moudle = $moudle;
   else exit;
   switch($this->moudle) {
    case 'udata':
     $this->CI->load->model('mupload_data','model');
     break;
    case 'tdata':
     $this->CI->load->model('taskdata','model');
     break;
    case 'tresult':
     $this->CI->load->model('taskresult','model');
     break;
    case 'dresult':
     $this->CI->load->model('dmsresult','model');
     break;
    default:
     break;
   }
   $pattern = '/<img (.+&#63;)src=([\'\" ])&#63;(.+&#63;)([  alt="php正则替换处理HTML页面的方法_php技巧" >]+&#63;)/i';
   $content = preg_replace_callback( $pattern, array($this, 'image_replace') , $content );
   $pattern = '/<a(.+&#63;)href=([\'\" ])&#63;(.+&#63;)([ >]+&#63;)/i';
   $content = preg_replace_callback( $pattern, array($this, 'html_replace') , $content );
   $pattern = '/<iframe(.+&#63;)src=([\'\" ])&#63;(.+&#63;)([ >]+&#63;)/i';
   $content = preg_replace_callback( $pattern, array($this, 'iframe_replace') , $content );
   $pattern = '/<frame(.+&#63;)src=([\'\" ])&#63;(.+&#63;)([ >]+&#63;)/i'; 
   $content = preg_replace_callback( $pattern, array($this, 'frame_replace'), $content );
   $pattern = '/window.open([( ]+&#63;)([\'" ]+&#63;)(.+&#63;)([ )]+&#63;)/i';
   $content = preg_replace_callback( $pattern, array($this, 'js_replace'), $content );
   $pattern = '/background(.+&#63;)url([( ])([\'" ]+&#63;)(.+&#63;)([ )+&#63;])/i';
   $content = preg_replace_callback( $pattern, array($this, 'css_replace'), $content);
   return $content;
  }
  private function image_replace($matches) {
   if(count($matches) < 4) return '';
   if( empty($matches[3]) ) return '';
   $matches[3] = rtrim($matches[3],'\'"/');
   //获取图片的id
   $parent_dir_num = substr_count( $matches[3], '../');
   $relative_dirname = $this->relative_dirname;
   for($i=0; $i<$parent_dir_num; $i++) {
    $relative_dirname = substr( $relative_dirname, 0, strrpos($relative_dirname,"/") );
   }
   $relativepath = rtrim($relative_dirname,'/') . '/'.ltrim($matches[3],'./');
   $image_id = $this->CI->model->get_id_by_path_and_project($relativepath,$this->projectid);
   //输出
   if( !empty($image_id) ) {
    if($this->moudle == 'dresult') {
     return "<img ".$matches[1]."src=".$matches[2].$this- alt="php正则替换处理HTML页面的方法_php技巧" >CI->config->item("base_url")."cdms/".$this->moudle."/readpic/$image_id&#63;pid=".$this->projectid .$matches[2]. $matches[4];
    } else {
     return "<img ".$matches[1]."src=".$matches[2].$this- alt="php正则替换处理HTML页面的方法_php技巧" >CI->config->item("base_url")."cdms/".$this->moudle."/picfile/$image_id&#63;pid=".$this->projectid .$matches[2]. $matches[4];
    }
   } else {
    return "<img".$matches[1]."src=".$matches[2].$matches[3].$matches[2].$matches[4];
   }
  }
  private function html_replace( $matches ) {
   if(count($matches) < 4) return '';
   if( empty($matches[3]) ) return '';
   //如果href的链接($matches[3])以http或www或mailto开始，则不进行处理
   //if(preg_match('/^[http|www|mailto](.+&#63;)/i',$matches[3])) 
   // return "<a".$matches[1]."href=".$matches[2].$matches[3].$matches[4];
   $matches[3] = rtrim($matches[3],'\'"/');
   //处理锚点
   if(substr_count($matches[3],'#')>0) 
    $matches[3] = substr($matches[3],0,strrpos($matches[3],'#'));
   //获取html的id
   $parent_dir_num = substr_count( $matches[3], '../');
   $relative_dirname = $this->relative_dirname;
   for($i=0; $i<$parent_dir_num; $i++) {
    $relative_dirname = substr( $relative_dirname, 0, strrpos($relative_dirname,"/") );
   }
   $relativepath = rtrim($relative_dirname,'/') . '/'.ltrim($matches[3],'./');
   $txtfile_id = $this->CI->model->get_id_by_path_and_project($relativepath,$this->projectid);
   //输出
   if( !empty($txtfile_id ) ) {
    if($this->moudle == 'dresult') {
     return "<a".$matches[1]."href=".$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/readfile/$txtfile_id&#63;pid=".$this->projectid .$matches[2].$matches[4];
    } else {
     return "<a".$matches[1]."href=".$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/txtfile/$txtfile_id&#63;pid=".$this->projectid .$matches[2].$matches[4];
    }
   } else {
    return "<a".$matches[1]."href=".$matches[2].$matches[3].$matches[2].$matches[4];
   }
  }
  private function iframe_replace( $matches ) {
   if(count($matches) < 4) return '';
   if( empty($matches[3]) ) return '';
   $matches[3] = rtrim($matches[3],'\'"/');
   //处理锚点
   if(substr_count($matches[3],'#')>0) 
    $matches[3] = substr($matches[3],0,strrpos($matches[3],'#'));
   //获取html的id
   $parent_dir_num = substr_count( $matches[3], '../');
   $relative_dirname = $this->relative_dirname;
   for($i=0; $i<$parent_dir_num; $i++) {
    $relative_dirname = substr( $relative_dirname, 0, strrpos($relative_dirname,"/") );
   }
   $relativepath = rtrim($relative_dirname,'/') . '/'.ltrim($matches[3],'./');
   $txtfile_id = $this->CI->model->get_id_by_path_and_project($relativepath,$this->projectid);
   //输出
   if( !empty($txtfile_id ) ) {
    if($this->moudle == 'dresult') {  
     return "<iframe".$matches[1]."src=".$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/readfile/$txtfile_id&#63;pid=".$this->projectid .$matches[2].$matches[4];
    } else {
     return "<iframe".$matches[1]."src=".$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/txtfile/$txtfile_id&#63;pid=".$this->projectid .$matches[2].$matches[4];
    }
   } else {
    return "<iframe".$matches[1]."src=".$matches[2].$matches[3].$matches[2].$matches[4];
   }
  }
  private function frame_replace( $matches ) {   
   if(count($matches) < 4) return '';
   if( empty($matches[3]) ) return '';
   $matches[3] = rtrim($matches[3],'\'"/');
   //处理锚点
   if(substr_count($matches[3],'#')>0) 
    $matches[3] = substr($matches[3],0,strrpos($matches[3],'#'));
   //获取html的id
   $parent_dir_num = substr_count( $matches[3], '../');
   $relative_dirname = $this->relative_dirname;
   for($i=0; $i<$parent_dir_num; $i++) {
    $relative_dirname = substr( $relative_dirname, 0, strrpos($relative_dirname,"/") );
   }
   $relativepath = rtrim($relative_dirname,'/') . '/'.ltrim($matches[3],'./');
   $txtfile_id = $this->CI->model->get_id_by_path_and_project($relativepath,$this->projectid);
   //输出
   if( !empty($txtfile_id ) ) {
    if($this->moudle == 'dresult') { 
     return "<frame".$matches[1]."src=".$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/readfile/$txtfile_id&#63;pid=".$this->projectid.$matches[2].$matches[4];
    } else {
     return "<frame".$matches[1]."src=".$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/txtfile/$txtfile_id&#63;pid=".$this->projectid.$matches[2].$matches[4];
    }
   } else {
    return "<frame".$matches[1]."src=".$matches[2].$matches[3].$matches[2].$matches[4];
   }
  }
  private function js_replace( $matches ){
   if(count($matches) < 4) return '';
   if( empty($matches[3]) ) return '';
   //处理链接
   $arr_html = split(',',$matches[3]);
   $href = $arr_html[0];
   $other = '';
   for($i=0; $i<count($arr_html); $i++)
    $other = $arr_html[$i].", ";
   $other = rtrim($other,"\, ");
   $href =rtrim($href,'\'\"');
   //处理锚点
   if(substr_count($href,'#')>0) 
    return "window.open".$matches[1].$matches[2].$matches[3].$matches[4];;
   //获取html的id
   $parent_dir_num = substr_count( $href, '../');
   $relative_dirname = $this->relative_dirname;
   for($i=0; $i<$parent_dir_num; $i++) {
    $relative_dirname = substr( $relative_dirname, 0, strrpos($relative_dirname,"/") );
   }
   $relativepath = rtrim($relative_dirname,'/') . '/'.ltrim($href,'./');
   $txtfile_id = $this->CI->model->get_id_by_path_and_project($relativepath,$this->projectid);
   //输出
   if( !empty($txtfile_id ) ) {
    if($this->moudle == 'dresult') { 
     return "window.open".$matches[1].$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/readfile/$txtfile_id&#63;pid=".$this->projectid.$matches[2].','.$other.$matches[4];
    } else {
     return "window.open".$matches[1].$matches[2].$this->CI->config->item("base_url")."cdms/".$this->moudle."/txtfile/$txtfile_id&#63;pid=".$this->projectid.$matches[2].','.$other.$matches[4];
    }
   } else {
    return "window.open".$matches[1].$matches[2].$matches[3].$matches[4];
   }
  }
  private function css_replace( $matches ) {
   if(count($matches) < 5) return '';
   if( empty($matches[4]) ) return '';
    
   $matches[4] = rtrim($matches[4],'\'"/');
   //获取图片的id
   $parent_dir_num = substr_count( $matches[4], '../');
   $relative_dirname = $this->relative_dirname;
   for($i=0; $i<$parent_dir_num; $i++) {
    $relative_dirname = substr( $relative_dirname, 0, strrpos($relative_dirname,"/") );
   }
   $relativepath = rtrim($relative_dirname,'/') . '/'.ltrim($matches[4],'./');
   $image_id = $this->CI->model->get_id_by_path_and_project($relativepath,$this->projectid);
   //输出
   if( !empty($image_id) ) {
    if($this->moudle == 'dresult') {
     return "background".$matches[1]."url".$matches[2].$matches[3].$this->CI->config->item("base_url")."cdms/".$this->moudle."/readpic/$image_id&#63;pid=".$this->projectid .$matches[3]. $matches[5];
    } else {
     return "background".$matches[1]."url".$matches[2].$matches[3].$this->CI->config->item("base_url")."cdms/".$this->moudle."/picfile/$image_id&#63;pid=".$this->projectid .$matches[3]. $matches[5];
    }
   } else {
    return "background".$matches[1]."url".$matches[2].$matches[3].$matches[4].$matches[3].$matches[5];
   }
  }
 }
/* End of Myreplace.php */
/* Location: /application/libraries/Myreplace.php */
Copy after login

希望本文所述对大家的php程序设计有所帮助。

Related labels：
html page php
source：php.cn
Previous article：试用php中oci8扩展_php技巧 Next article：php常用表单验证类用法实例_php技巧
Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Latest Articles by Author
Latest Issues
PHP arrays obtained from URL parameters do not behave as expected I have a URL parameter that contains the category ID and I want to treat it as an array li...
From 2024-04-06 22:09:02
0
1
1428
Where should I place CustomLog directive in apache I'm using php:7.2-apachedocker. I need to disable health check url login access log. Based...
From 2024-04-06 22:03:59
0
1
990
What is the format of the variables in the return value? I am a new learner of php. I found a piece of code: if($x<time()){return[false,'error']...
From 2024-04-06 21:55:20
0
1
778
Problems encountered when using opentbs to generate odt files: values ​​of the same key are displayed in the same row instead of separate columns. I'm using a library called OpenTbs to create odt using PHP, I'm using it because columns a...
From 2024-04-06 20:18:18
0
1
483
Group MySQL results by ID for looping over I have a table with flight data in mysql. I'm writing a php code that will group and displ...
From 2024-04-06 17:27:56
0
1
406
Related Topics
More>
Popular Recommendations
Popular Tutorials
More>
Related Tutorials
Popular Recommendations
Latest courses
Latest Downloads
More>
Web Effects
Website Source Code
Website Materials
Front End Template