@Blog

<?php
echo json_encode($obj);
exit;
function get_linkarray($link)
{
	$context = stream_context_create(array("http" => array("method" => "GET", "header" => "User-Agent: simplecrawler.library.php 0.0.1")));
	$resultR = array();
	$resultS = simplecrawler($context, $link, $link, parse_url($link));
	foreach ($resultS as $k => $v) {
		$resultR[] = $v;
	}
	return $resultR;
}
function simplecrawler($context, $link, $burl, $base, $linkArrayDat = array())
{
	$linkArrayPre = crawler_link(crawler_page($link, $burl, $base, $context), $link, parse_url($link));
	foreach ($linkArrayPre as $k => $v) {
		if (!isset($linkArrayDat[$v])) {
			$linkArrayDat[$v] = $v;
			//$linkArrayDat = array_merge($linkArrayDat, simplecrawler($context, $v, $burl, $base, $linkArrayDat));
		}
	}
	return $linkArrayDat;
}
function crawler_page($link, $burl, $base, $context)
{
	if (strpos($link, $burl) === 0) {
		$page = @file_get_contents($link, false, $context);
		return $page === FALSE ? null : $page;
	} else {
		return null;
	}
}
function crawler_link($page, $burl, $base)
{
	$linkArray = array();
	if ($page === null) {
		return $linkArray;
	}
	preg_match_all("/[\s\n\t]+href\s?=\s?”(.*?)”/i", $page, $href);
	for ($i = 0; $i < count($href[1]); $i++) {
		$link = $href[1][$i];
		if (preg_match("/^http(s)*\:\/\//", $link)) {
			$result = $link;
		} elseif (preg_match("/^\/.+$/", $link)) {
			$result = $base["scheme"] . "://" . $base["host"] . $link;
		} else {
			// echo $base["path"] . “\n”;
			$b = preg_split("/\//", dirname($base["path"]));
			$t = preg_split("/\//", $link);
			foreach ($t as $v) {
				$l = $v === "." ? true : ($v === ".." ? array_pop($b) : array_push($b, $v));
			}
			$result = $base["scheme"] . "://" . $base["host"] . join("/", $b);
		}
		$linkArray[$result] = $result;
	}
	return $linkArray;
}