웹사이트에서 링크와 콘텐츠를 추출하는 간단한 PHP 크롤러를 어떻게 구축합니까?

<?php
function crawl_page($url, $depth = 5)
{
    // Prevent endless recursion and circular references
    static $seen = array();
    if (isset($seen[$url]) || $depth === 0) {
        return;
    }

    // Mark the URL as seen
    $seen[$url] = true;

    // Load the web page using DOM
    $dom = new DOMDocument('1.0');
    @$dom->loadHTMLFile($url);

    // Iterate over all anchor tags (<a>)
    $anchors = $dom->getElementsByTagName('a');
    foreach ($anchors as $element) {
        $href = $element->getAttribute('href');

        // Convert relative URLs to absolute URLs
        if (0 !== strpos($href, 'http')) {
            $path = '/' . ltrim($href, '/');
            if (extension_loaded('http')) {
                $href = http_build_url($url, array('path' => $path));
            } else {
                $parts = parse_url($url);
                $href = $parts['scheme'] . '://';
                if (isset($parts['user']) &amp;&amp; isset($parts['pass'])) {
                    $href .= $parts['user'] . ':' . $parts['pass'] . '@';
                }
                $href .= $parts['host'];
                if (isset($parts['port'])) {
                    $href .= ':' . $parts['port'];
                }
                $href .= dirname($parts['path'], 1) . $path;
            }
        }

        // Recursively crawl the linked page
        crawl_page($href, $depth - 1);
    }

    // Output the crawled page's URL and content
    echo "URL: " . $url . PHP_EOL . "CONTENT: " . PHP_EOL . $dom->saveHTML() . PHP_EOL . PHP_EOL;
}
crawl_page("http://example.com", 2);
?>