Wie erstellt man einen PHP-Webcrawler, um Daten aus mehreren Links zu sammeln?

function crawl_page($url, $depth = 5)
{
    static $seen = array();
    if (isset($seen[$url]) || $depth === 0) {
        return;
    }

    $seen[$url] = true;

    $dom = new DOMDocument('1.0');
    @$dom->loadHTMLFile($url);

    $anchors = $dom->getElementsByTagName('a');
    foreach ($anchors as $element) {
        $href = $element->getAttribute('href');
        // Handle relative URLs
        if (0 !== strpos($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'] . '://';
                $href .= $parts['host'];
                if (isset($parts['port'])) {
                    $href .= ':' . $parts['port'];
                }
                $href .= dirname($parts['path'], 1).$path;
            }
        }
        crawl_page($href, $depth - 1);
    }

    // Output data
    echo "URL:", $url, PHP_EOL, "CONTENT:", PHP_EOL, $dom->saveHTML(), PHP_EOL, PHP_EOL;
}

// Usage
crawl_page("http://hobodave.com", 2);