สอบถามวิธีการดึงข้อมูลเฉพาะส่วนจาก Website แบบตั้งเวลาดึง

?php
     include('C:\AppServ\www\simple_html_dom.php');
     
 $html = file_get_html('http://www.su.ac.th/html_news/all_news.asp'); //ดึงมาทุกหมวด
 foreach($html->find('td[class=ms11search]') as $e)  //ช่วงนี้ใช้ค้นหาหมวดหมู่ในCode
 echo $e->innertext.'<br>';
   
    $html = file_get_html('http://su.ac.th/html_news/news_01.asp'); //ต้องการให้ดึงหัวข้อมาแต่โค้ดยังไม่แสดงการดึงหัวข้อข่าว
    
	echo $html;
    foreach($html -> find('td class=ms09search') as $s) //ช่วงในการค้นหาหัวข้อข่าว
    echo $s ->innertext.'<br>';

  
    $urlWithoutProtocol = "http://su.ac.th/html_news/news_template.asp?id=5775"; //linkของข่าวที่ต้องการนำมาสกัด
    $request         = "";
    $isRequestHeader = false;
 
    $exHeaderInfoArr   = array();
    $exHeaderInfoArr[] = "Content-type: text/xml";
    $exHeaderInfoArr[] = "Authorization: "."Basic ".base64_encode("authen_user:authen_pwd");
 
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $urlWithoutProtocol);
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, $request);
    curl_setopt($ch, CURLOPT_HEADER, (($isRequestHeader) ? 1 : 0));
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    if( is_array($exHeaderInfo) && !empty($exHeaderInfo) )
    {
        curl_setopt($ch, CURLOPT_HTTPHEADER, $exHeaderInfo);
    }
    $response = curl_exec($ch);
    curl_close($ch);
	$html = str_get_html($response);
    $elem = $html->find('table td.ms09', 0)->plaintext;

    echo $elem; 
 
   //echo $response;
?>

<ul>
<?php
include('simple_html_dom.php');
$html = file_get_html('http://www.su.ac.th/html_news/all_news.asp');
foreach($html->find('td[class=ms11search] > a') as $a) {
	$text = strip_tags($a->innertext);
	echo "<li>$text ($a->href)<ul>";
	if (($page = @file_get_html("http://www.su.ac.th/html_news/$a->href"))) {
		foreach($page->find('td[class=ms09] > a') as $a) {
			$text = strip_tags(iconv('TIS-620', 'UTF-8', $a->innertext));
			echo "<li>$text ($a->href)</li>";
		}
	}
	echo '</ul>';
}
?>
</ul>

<ul>
<?php
include('simple_html_dom.php');
$html = file_get_html('http://www.su.ac.th/html_news/all_news.asp');
foreach($html->find('td[class=ms11search] > a') as $a) {
	$text = strip_tags(iconv('TIS-620', 'UTF-8', $a->innertext));
	echo "$text $a->href <br>";
	if (($page = @file_get_html("http://www.su.ac.th/html_news/$a->href"))) {
		foreach($page->find('td[class=ms09] > a') as $a) {
			$text = (iconv('TIS-620', 'UTF-8', $a->innertext));
		echo "<li>$text ($a->href)</li>";
			$link = $a->href;
	//	 preg_match_all
	//	( '/\<a href\="(\.\.\/html_news\/news_template\.asp\?id\=\d+)"\>([^\<]+)\</', $link, $link_2, PREG_SET_ORDER ) ;
			
		
			$result = str_replace(".." ,"", $link);

			$link_2 = "http://www.su.ac.th/$result";
			echo $link_2;
			$link_3 = str_get_html($link_2);
			
			 $request         = "";
			 $isRequestHeader = false;
			 $exHeaderInfoArr   = array();
			 $exHeaderInfoArr[] = "Content-type: text/xml";
			 $exHeaderInfoArr[] = "Authorization: "."Basic ".base64_encode("authen_user:authen_pwd");
			 $ch = curl_init();
			curl_setopt($ch, CURLOPT_URL, $urlWithoutProtocol);
			curl_setopt($ch, CURLOPT_POST, 1);
			curl_setopt($ch, CURLOPT_POSTFIELDS, $request);
			curl_setopt($ch, CURLOPT_HEADER, (($isRequestHeader) ? 1 : 0));
			curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
			if( is_array($exHeaderInfo) && !empty($exHeaderInfo) )
				{
					curl_setopt($ch, CURLOPT_HTTPHEADER, $exHeaderInfo);
				}
			$response = curl_exec($ch);
			curl_close($ch);
			$link_3 = file_get_html($link_2);
			$link_4 = strip_tags($link_3->find('table td.ma09linespace', 0)->innertext);
			echo $link_4 .'<br>';
			echo $response;
			ini_set('memory_limit', '512M'); //ปรับขนาดที่ต้องการจนกว่ามันจะไม่ error
			ini_set('max_execution_time', '60'); //อันนี้แถมเผื่อเวลาโปรเซสไม่พอ
			
	
	}
	}
	

	echo '</ul>';
}
?>
</ul>

<ul>
<?php
	ini_set('memory_limit', '512M'); //ปรับขนาดที่ต้องการจนกว่ามันจะไม่ error
	ini_set('max_execution_time', '400'); //อันนี้แถมเผื่อเวลาโปรเซสไม่พ

include('simple_html_dom.php');
include('connect-1.php');
include('connect.php');
$html = file_get_html(WEB_URL."/html_news/all_news.asp");
$type_id = 0;
foreach($html->find('td[class=ms11search] > a') as $a) 
{
	$type_id++;
	$head =  strip_tags($a->innertext);
	echo "<li> $head($a->href)<ul>"; 
	echo $type_id;
if (($page = @file_get_html(WEB_URL."/html_news/{$a->href}"))) 
		{
				foreach($page->find('td[class=ms09] > font > a') as $page_a) 
					{
						$text_1 = strip_tags(iconv('TIS-620', 'UTF-8', $page_a->innertext));
						echo "<li> $text_1 ($page_a->href)</li>";
						$page_a->href = str_replace(".." ,"", $page_a->href);
						//echo $page_a->href; 

						if(($news = @file_get_html(WEB_URL."/{$page_a->href}")))
							{
								$url = WEB_URL."/{$page_a->href}";
							        $u = parse_url($url);
							        parse_str($u['query'], $p); 
								$newsid = $p['id'];
								echo $newsid;
								foreach($news->find('td[class=ma09linespace] > font') as $news_a)
									
								{
									$news_name = strip_tags(iconv('TIS-620', 'UTF-8', $news_a->innertext));
									echo $news_name ."<br>";
									


								}
							
							
							
							}
					}
		}
		
	echo '</ul>';

}	

// mysql_close();
?>
</ul>