X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=mod%2Fparse_url.php;h=7a520ba92f6e5dde83dc8dcf2978abbad803e714;hb=bcb672e7ff859168b639ffffc38553bbcf7e918c;hp=aa71893ab47ebade0e5043976157f57d174daf59;hpb=0afc71a95a54f6b648a551584c2f7fc7a6c16880;p=friendica.git
diff --git a/mod/parse_url.php b/mod/parse_url.php
index aa71893ab4..7a520ba92f 100644
--- a/mod/parse_url.php
+++ b/mod/parse_url.php
@@ -1,29 +1,103 @@
' . implode(' ',$arr_tags) . '
';
+ }
+ }
+
+ logger('parse_url: ' . $url);
+
+
+ $template = "
%s%s
";
+
+
+ $arr = array('url' => $url, 'text' => '');
+
+ call_hooks('parse_link', $arr);
+
+ if(strlen($arr['text'])) {
+ echo $arr['text'];
+ killme();
+ }
+
+ if($url && $title && $text) {
+
+ $text = '
' . $text . '
';
+ $title = str_replace(array("\r","\n"),array('',''),$title);
+
+ $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags;
+
+ logger('parse_url (unparsed): returns: ' . $result);
+
+ echo $result;
+ killme();
+ }
- $template = "%s%s";
- if($url)
+ if($url) {
$s = fetch_url($url);
- else {
+ } else {
echo '';
killme();
}
-
+
+ logger('parse_url: data: ' . $s, LOGGER_DATA);
+
if(! $s) {
- echo sprintf($template,$url,$url,'');
+ echo sprintf($template,$url,$url,'') . $str_tags;
killme();
}
- $dom = HTML5_Parser::parse($s);
+ if(! $title) {
+ if(strpos($s,'')) {
+ $title = substr($s,strpos($s,'')+7,64);
+ if(strpos($title,'<') !== false)
+ $title = strip_tags(substr($title,0,strpos($title,'<')));
+ }
+ }
- if(! $dom)
- return $ret;
+ $config = HTMLPurifier_Config::createDefault();
+ $config->set('Cache.DefinitionImpl', null);
+
+ $purifier = new HTMLPurifier($config);
+ $s = $purifier->purify($s);
+
+ try {
+ $dom = HTML5_Parser::parse($s);
+ } catch (DOMException $e) {
+ logger('scrape_dfrn: parse error: ' . $e);
+ }
+
+ if(! $dom) {
+ echo sprintf($template,$url,$url,'') . $str_tags;
+ killme();
+ }
$items = $dom->getElementsByTagName('title');
@@ -34,22 +108,65 @@ function parse_url_content(&$a) {
}
}
- $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(! $text) {
+ $divs = $dom->getElementsByTagName('div');
+ if($divs) {
+ foreach($divs as $div) {
+ $class = $div->getAttribute('class');
+ if($class && (stristr($class,'article') || stristr($class,'content'))) {
+ $items = $div->getElementsByTagName('p');
+ if($items) {
+ foreach($items as $item) {
+ $text = $item->textContent;
+ if(stristr($text,'