如何使用PHP获取元素内的脚本链接？

Question

  

嗨！我制作了以下代码来解析网站并获取其中的所有链接。但我刚刚发现我的代码只获得了第三层内的链接。我想深入解析并获得第四层内的所有链接。我怎样才能做到这一点？我需要添加什么东西才能深入解析网站？ TIA！

     

*注意：第1层=红色;第二=黄色; 3 =绿色;第四=蓝色;请看下面的图片。

<?php

 $c = array();

 $url = "http://www.nytimes.com";

 function get_links($url)
 {  
    global $c;
    $doc = new DOMDocument();
    libxml_use_internal_errors(true);
    $doc->loadHTMLFile($url);
    libxml_clear_errors();
    $base_url = parse_url($url, PHP_URL_HOST);

    // fetching all stylesheet
    foreach( $doc->getElementsByTagName('link') as $style){

        $href =  $style->getAttribute('href');
        if (substr($href,0,2) == "//") {
        $href = substr($href, 2);
        }
        if (strpos($href, "#")) {
        $href = substr($href, 0, strpos($href, "#"));

        }

        if (strpos($href, "?")) {
            $href = substr($href, 0, strpos($href, "?"));

        }

        if (!in_array($href, $c)) {
        array_push($c, $href);

        }                   
    }

// fetching all href
    foreach( $doc->getElementsByTagName('a') as $a){

        $href =  $a->getAttribute('href');

        if (strpos($href, "#")) {
            $href = substr($href, 0, strpos($href, "#"));
        }
        if (strpos($href, "?")) {
            $href = substr($href, 0, strpos($href, "?"));
        }
        if (substr($href,0,1) == ".") {
            $href = substr($href, 1);
        }
        if (substr($href,0,7) == "http://") {
            $href = $href;
        }
        else if (substr($href,0,8) == "https://") {
            $href = $href;
        }
        else if (substr($href,0,2) == "//") {
            $href = substr($href, 2);
        }
        else if (substr($href,0,1) == "#") {
            $href = $url;
        }
        else if (substr($href,0,7) == "mailto:") {
            $href = "[".$href."]";
        }
        else {
            if (substr($href, 0, 1) != "/") {
                $href = $base_url."/".$href;
            }
            else {
                $href = $base_url.$href;
                }
        }   

        if (substr($href, 0, 7) != "http://" && substr($href, 0, 8) != "https://" && substr($href, 0, 1) != "[") {
            if (substr($href, 0, 8) == "https://") {
                $href = "https://".$href;
            }
            else {
                $href = "http://".$href;
            }
        }
        if (!in_array($href, $c)) {
            array_push($c, $href);

         }             
    }

// fetching all image
    foreach( $doc->getElementsByTagName('img') as $image){

        $href =  $image->getAttribute('src');
        if (substr($href,0,2) == "//") {
        $href = substr($href, 2);
        }
        if (strpos($href, "#")) {
        $href = substr($href, 0, strpos($href, "#"));

        }
        if (strpos($href, "?")) {
            $href = substr($href, 0, strpos($href, "?"));

        }

        if (!in_array($href, $c)) {
            array_push($c, $href);
         }                      
    }

// fetching all script
    foreach( $doc->getElementsByTagName('script') as $scripts){

        $href =  $scripts->getAttribute('src');

        if (substr($href,0,2) == "//") {
        $href = substr($href, 2);
        }
        if (strpos($href, "#")) {
        $href = substr($href, 0, strpos($href, "#"));

        }
        if (strpos($href, "?")) {
            $href = substr($href, 0, strpos($href, "?"));

        }


         if (!in_array($href, $c)) {
            array_push($c, $href);
         }                                  
    }

}

get_links($url);
var_dump($c);
?>