X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;ds=inline;f=mod%2Fparse_url.php;h=a238ecb2f915cabb071787f3e0156867611c7a27;hb=906addf865ccab2c98d5035fc6c1b10d43004dfe;hp=b3b42b6cb6f2ced24b4da9be57d3d16222116c9e;hpb=f6556e0a720bb3de29107520464aa4de242e1631;p=friendica.git
diff --git a/mod/parse_url.php b/mod/parse_url.php
index b3b42b6cb6..a238ecb2f9 100644
--- a/mod/parse_url.php
+++ b/mod/parse_url.php
@@ -1,15 +1,40 @@
' . implode(' ',$arr_tags) . '
';
+ }
+ }
+
+ logger('parse_url: ' . $url);
+
- $template = "%s%s";
+ $template = "
%s%s
";
$arr = array('url' => $url, 'text' => '');
@@ -21,23 +46,56 @@ function parse_url_content(&$a) {
killme();
}
- if($url)
+ if($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 $result;
+ killme();
+ }
+
+
+ if($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();
}
+ if(! $title) {
+ if(strpos($s,'')) {
+ $title = substr($s,strpos($s,'')+7,64);
+ if(strpos($title,'<') !== false)
+ $title = strip_tags(substr($title,0,strpos($title,'<')));
+ }
+ }
+
+ $config = HTMLPurifier_Config::createDefault();
+ $config->set('Cache.DefinitionImpl', null);
+
+ $purifier = new HTMLPurifier($config);
+ $s = $purifier->purify($s);
+
+// logger('parse_url: purified: ' . $s, LOGGER_DATA);
+
$dom = @HTML5_Parser::parse($s);
- if(! $dom)
- return $ret;
+ if(! $dom) {
+ echo sprintf($template,$url,$url,'') . $str_tags;
+ killme();
+ }
$items = $dom->getElementsByTagName('title');
@@ -49,44 +107,64 @@ function parse_url_content(&$a) {
}
- $divs = $dom->getElementsByTagName('div');
- if($divs) {
- foreach($divs as $div) {
- $class = $div->getAttribute('class');
- if($class && stristr($class,'article')) {
- $items = $div->getElementsByTagName('p');
- if($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,'