php获取页面中指定内容的实现类_PHP教程

/** grep class 
* Date: 2013-06-15 
* Author: fdipzone 
* Ver: 1.0 
* 
* Func: 
* 
* set: 设置内容 
* get: 返回指定的内容 
* replace: 返回替换后的内容 
* get_pattern 根据type返回pattern 
*/ 

class Grep{ // class start 

private $_pattern = array( 
'url' => '/'email' => '/([\w\-\.]+@[\w\-\.]+(\.\w+))/', 
'https://www.gxlcms.com/image' => '//i' 
); 

private $_content = ''; // 源内容 


/* 設置搜尋的內容 
* @param String $content 
*/ 
public function set($content=''){ 
$this->_content = $content; 
} 


/* 获取指定内容 
* @param String $type 
* @param int $unique 0:all 1:unique 
* @return Array 
*/ 
public function get($type='', $unique=0){ 

$type = strtolower($type); 

if($this->_content=='' || !in_array($type, array_keys($this->_pattern))){ 
return array(); 
} 

$pattern = $this->get_pattern($type); // 获取pattern 

preg_match_all($pattern, $this->_content, $matches); 

return isset($matches[1])? ( $unique==0? $matches[1] : array_unique($matches[1]) ) : array(); 

} 


/* 获取替换后的内容 
* @param String $type 
* @param String $callback 
* @return String 
*/ 
public function replace($type='', $callback=''){ 

$type = strtolower($type); 

if($this->_content=='' || !in_array($type, array_keys($this->_pattern)) || $callback==''){ 
return $this->_content; 
} 

$pattern = $this->get_pattern($type); 

return preg_replace_callback($pattern, $callback, $this->_content); 

} 


/* 根据type获取pattern 
* @param String $type 
* @return String 
*/ 
private function get_pattern($type){ 
return $this->_pattern[$type]; 
} 
} // class end 

?> 
 
Demo 
 代码如下:

header('content-type:text/htm;charset=utf8'); 

require('Grep.class.php'); 

$content = file_get_contents('http://www.test.com/'); 

$obj = new Grep(); 
$obj->set($content); 

$url = $obj->get('url', 0); 
$email = $obj->get('email', 1); 
$https://www.gxlcms.com/image = $obj->get('https://www.gxlcms.com/image', 1); 

print_r($url); 
print_r($email); 
print_r($https://www.gxlcms.com/image); 

$url_new = $obj->replace('url', 'replace_url'); 
echo $url_new; 

function replace_url($matches){ 
return isset($matches[1])? '[url]'.$matches[1].'[/url]' : ''; 
} 
?> 


http://www.bkjia.com/PHPjc/726021.htmlwww.bkjia.comtruehttp://www.bkjia.com/PHPjc/726021.htmlTechArticle功能： 1.获取内容中的url，email，https://www.gxlcms.com/image。 2.替换内容中的url，email，https://www.gxlcms.com/image。 url：a href="url"xxx/a email：admin@admin.com https://www.gxlcms.com/image：img src="https://www.gxlcms.com/image" Grep.class.ph...