2010-07-23 01:41:45 -04:00
|
|
|
<?php
|
|
|
|
|
|
|
|
require_once('library/HTML5/Parser.php');
|
|
|
|
|
|
|
|
function parse_url_content(&$a) {
|
2010-07-23 02:17:41 -04:00
|
|
|
|
2010-07-23 01:41:45 -04:00
|
|
|
$url = trim($_GET['url']);
|
|
|
|
|
2010-07-23 02:17:41 -04:00
|
|
|
$template = "<a href=\"%s\" >%s</a>%s";
|
2010-07-23 01:41:45 -04:00
|
|
|
|
|
|
|
if($url)
|
|
|
|
$s = fetch_url($url);
|
2010-07-23 02:17:41 -04:00
|
|
|
else {
|
|
|
|
echo '';
|
|
|
|
killme();
|
|
|
|
}
|
2010-07-23 01:41:45 -04:00
|
|
|
|
|
|
|
if(! $s) {
|
2010-07-23 02:17:41 -04:00
|
|
|
echo sprintf($template,$url,$url,'');
|
2010-07-23 01:41:45 -04:00
|
|
|
killme();
|
|
|
|
}
|
|
|
|
|
|
|
|
$dom = HTML5_Parser::parse($s);
|
|
|
|
|
|
|
|
if(! $dom)
|
|
|
|
return $ret;
|
|
|
|
|
|
|
|
$items = $dom->getElementsByTagName('title');
|
2010-07-23 02:17:41 -04:00
|
|
|
|
|
|
|
if($items) {
|
|
|
|
foreach($items as $item) {
|
2010-12-06 19:26:32 -05:00
|
|
|
$title = trim($item->textContent);
|
2010-07-23 02:17:41 -04:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
$items = $dom->getElementsByTagName('p');
|
|
|
|
if($items) {
|
|
|
|
foreach($items as $item) {
|
|
|
|
$text = $item->textContent;
|
|
|
|
$text = strip_tags($text);
|
|
|
|
if(strlen($text) < 100)
|
|
|
|
continue;
|
|
|
|
$text = substr($text,0,250) . '...' ;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if(strlen($text)) {
|
|
|
|
$text = '<br />' . $text;
|
2010-07-23 01:41:45 -04:00
|
|
|
}
|
|
|
|
|
2010-07-23 02:17:41 -04:00
|
|
|
echo sprintf($template,$url,$title,$text);
|
2010-07-23 01:41:45 -04:00
|
|
|
killme();
|
|
|
|
}
|