Gets the full urls form directory index page generated by http server.

get_full_urls.php

#!/usr/bin/php
<?php

/*
** Gets the full urls form directory index page
** generated by http server.
** Usage: ./get_full_urls.php url_to_directory_listing
*/

if(count($argv) < 2 || !$argv[1]) {
	die("usage: {$argv[0]} url\n");
}

$html = file_get_contents($argv[1]);

if ($html === false) {
	die("Failed to fetch given url\n");
}

$argv[1] = rtrim($argv[1], '/');
$argv[1] .= '/';

$doc = new DOMDocument();
$doc->loadHTML($html);
$xpath = new DOMXPath($doc);
$nodeList = $xpath->query('//a/@href');
for ($i = 0; $i < $nodeList->length; $i++) {
    $url = $nodeList->item($i)->value;

    if (in_array($url, array('..', '.', '../', './', '/../', '/./'))) {
	    continue;
    }

    echo $argv[1].$url."\n";
}