<?php
	// http://web.archive.org/web/20110227035341id_/http://www.cheops.org/index2.htm
	define('BASE', 'http://web.archive.org/web/20110227035341id_/http://www.cheops.org/');
	
	libxml_use_internal_errors(false);
	
	function dl_img($src) {
		if ($dir = dirname($src) and !is_dir($dir))
			@mkdir($dir, 0777, true);
		if (!file_exists($src)) {
			echo "dl img " . $src . "\n";
			copy(BASE . $src, $src);
		}
	}
	
	$paths = array();
	
	function download($path) {
		global $paths;
		echo "start " . $path . "\n";
		if ($dir = dirname($path) and !is_dir($dir))
			@mkdir($dir, 0777, true);
		if (!file_exists($path))
			copy(BASE . $path, $path);
		if (in_array($path, $paths))
			return;
		$paths[] = $path;
		$dom = new DOMDocument();
		@$dom->loadHTMLFile($path);
		foreach ($dom->getElementsByTagName('a') as $a) {
			$href = $a->getAttribute('href');
			//echo "href " . $href . "\n";
			if (!$href ||
				substr($href, 0, 4) === 'http' ||
				substr($href, 0, 2) === '..' ||
				strpos($href, '#') !== false)
				continue;
			if (substr($href, -4) === '.htm' || substr($href, -5) === '.html')
				download(preg_replace('@[^/]*$@', $href, $path, 1));
		}
		if (preg_match_all('@SRC = "([^"]+\.htm)"@', file_get_contents($path), $m)) {
			foreach ($m[1] as $href) {
				$href = preg_replace('@[^/]*$@', $href, $path, 1);
				//echo "frame " . $href . "\n";
				download($href);
			}
			//print_r($m);
		}
		foreach ($dom->getElementsByTagName('img') as $img) {
			$src = $img->getAttribute('src');
			//echo "src " . $src . "\n";
			if (!$src ||
				substr($src, 0, 4) === 'http' ||
				substr($src, 0, 2) === '..')
				continue;
			dl_img(preg_replace('@[^/]*$@', $src, $path, 1));
		}
		/*if (preg_match_all('@\.src = "([^"]+\.JPG)"@', file_get_contents($path), $m)) {
			foreach ($m[1] as $src) {
				dl_img(preg_replace('@[^/]*$@', $src, $path, 1));
			}
			//print_r($m);
		}*/
	}
	download('index2.htm');
?>