$scheme = $bp['scheme'];
}
$b = $scheme . "://" . $bp['host'] . "/";
}
if (substr($u, 0, 2) == "//") {
$u = "http:" . $u;
}
if (substr($u, 0, 4) != "http") {
$u = rel2abs($u, $b);
}
return $u;
}
function crawl_site($u)
{
global $crawled_urls;
$uen = urlencode($u);
if (array_key_exists($uen, $crawled_urls) == 0 || $crawled_urls[$uen] < date("YmdHis", strtotime('-25 seconds', time()))) {
$html = file_get_html($u);
$crawled_urls[$uen] = date("YmdHis");
foreach ($html->find("a") as $li) {
$url = perfect_url($li->href, $u);
$enurl = urlencode($url);
if ($url != '' && substr($url, 0, 4) != "mail" && substr($url, 0, 4) != "java" && array_key_exists($enurl, $found_urls) == 0) {
$found_urls[$enurl] = 1;
echo "<li><a target='_blank' href='" . $url . "'>" . $url . "</a></li>";
}
}
}
}
crawl_site("https://crawlbot.isc");
}
$b = $scheme . "://" . $bp['host'] . "/";
}
if (substr($u, 0, 2) == "//") {
$u = "http:" . $u;
}
if (substr($u, 0, 4) != "http") {
$u = rel2abs($u, $b);
}
return $u;
}
function crawl_site($u)
{
global $crawled_urls, $found_urls;
$uen = urlencode($u);
if (array_key_exists($uen, $crawled_urls) == 0 || $crawled_urls[$uen] < date("YmdHis", strtotime('-25 seconds', time()))) {
$html = file_get_html($u);
$crawled_urls[$uen] = date("YmdHis");
foreach ($html->find("a") as $li) {
$url = perfect_url($li->href, $u);
$enurl = urlencode($url);
if ($url != '' && substr($url, 0, 4) != "mail" && substr($url, 0, 4) != "java" && array_key_exists($enurl, $found_urls) == 0) {
$found_urls[$enurl] = 1;
echo $url . "<br/>";
}
}
}
}
crawl_site("http://facebook.com");
crawl_site($url);
$content = $html->find('div[id=content]');
$rss_head = "<rss version=\"2.0\"><channel>";
$rss_title = "<title>HD-Area Suche</title>";
$rss_desc = "<description>HD-Area-RSS-Feed-Generator</description>";
$rss_link = "<link>http://www.hd-area.org/?s=search&q=" . $u . "/</link>";
$rss_item = "";
$rss_tail = "</channel></rss>";
foreach ($html->find('div[id=content]') as $element) {
$urls = $element->find('a');
foreach ($urls as $url) {
$title = $url->title;
$link = $url->href;
if (!empty($title)) {
$rss_item = $rss_item . "<item>";
$rss_item = $rss_item . "<title>" . $title . "</title>";
$rss_item = $rss_item . "<link>" . $link . "</link>";
$rss_item = $rss_item . "</item>";
}
}
}
echo $rss_head;
echo $rss_title;
echo $rss_desc;
echo $rss_link;
echo $rss_item;
echo $rss_tail;
echo "\n";
}
//crawl_site($argv[1]);
crawl_site($_GET['var']);
if(($bp['path']!="/" && $bp['path']!="") || $bp['path']==''){
if($bp['scheme']==""){$scheme="http";}else{$scheme=$bp['scheme'];}
$b=$scheme."://".$bp['host']."/";
}
if(substr($u,0,2)=="//"){
$u="http:".$u;
}
if(substr($u,0,4)!="http"){
$u=rel2abs($u,$b);
}
return $u;
}
function crawl_site($u){
global $crawled_urls;
$uen=urlencode($u);
if((array_key_exists($uen,$crawled_urls)==0 || $crawled_urls[$uen] < date("YmdHis",strtotime('-25 seconds', time())))){
$html = file_get_html($u);
$crawled_urls[$uen]=date("YmdHis");
foreach($html->find("a") as $li){
$url=perfect_url($li->href,$u);
$enurl=urlencode($url);
if($url!='' && substr($url,0,4)!="mail" && substr($url,0,4)!="java" && array_key_exists($enurl,$found_urls)==0){
$found_urls[$enurl]=1;
echo "<li><a target='_blank' href='".$url."'>".$url."</a></li>";
}
}
}
}
crawl_site("http://www.subinsb.com");
?>
