X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;ds=inline;f=mod%2Fparse_url.php;h=2df9de4763c77afe1bc55932b87284c8343f995a;hb=a1a07e7287e9e764912bbd08383cf43503deb9e8;hp=ec28d74111817db7fcc540afcb3a769a5c8ee729;hpb=24d41e2c6e759baf17a10aa2e48d4b1907d5c7a0;p=friendica.git
diff --git a/mod/parse_url.php b/mod/parse_url.php
index ec28d74111..2df9de4763 100644
--- a/mod/parse_url.php
+++ b/mod/parse_url.php
@@ -3,17 +3,38 @@
require_once('library/HTML5/Parser.php');
require_once('library/HTMLPurifier.auto.php');
+function arr_add_hashes(&$item,$k) {
+ $item = '#' . $item;
+}
+
function parse_url_content(&$a) {
- logger('parse_url: ' . $_GET['url']);
+ $text = null;
+ $str_tags = '';
+
+ if(x($_GET,'binurl'))
+ $url = trim(hex2bin($_GET['binurl']));
+ else
+ $url = trim($_GET['url']);
+
+ if($_GET['title'])
+ $title = strip_tags(trim($_GET['title']));
+
+ if($_GET['description'])
+ $text = strip_tags(trim($_GET['description']));
- $url = trim(hex2bin($_GET['url']));
+ if($_GET['tags']) {
+ $arr_tags = str_getcsv($_GET['tags']);
+ if(count($arr_tags)) {
+ array_walk($arr_tags,'arr_add_hashes');
+ $str_tags = '
' . implode(' ',$arr_tags) . '
';
+ }
+ }
logger('parse_url: ' . $url);
- $text = null;
- $template = "%s\n%s";
+ $template = "
%s%s
";
$arr = array('url' => $url, 'text' => '');
@@ -25,6 +46,21 @@ function parse_url_content(&$a) {
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 $result;
+ killme();
+ }
+
+
if($url) {
$s = fetch_url($url);
} else {
@@ -32,23 +68,49 @@ function parse_url_content(&$a) {
killme();
}
- logger('parse_url: data: ' . $s, LOGGER_DATA);
+// logger('parse_url: data: ' . $s, LOGGER_DATA);
if(! $s) {
- echo sprintf($template,$url,$url,'');
+ echo sprintf($template,$url,$url,'') . $str_tags;
killme();
}
+ $matches = '';
+ $c = preg_match('/\(.*?)\<\/head\>/ism',$s,$matches);
+ if($c) {
+// logger('parse_url: header: ' . $matches[2], LOGGER_DATA);
+ try {
+ $domhead = HTML5_Parser::parse($matches[2]);
+ } catch (DOMException $e) {
+ logger('scrape_dfrn: parse error: ' . $e);
+ }
+ if($domhead)
+ logger('parsed header');
+ }
+
+ 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);
- $dom = @HTML5_Parser::parse($s);
+// logger('purify_output: ' . $s);
+
+ try {
+ $dom = HTML5_Parser::parse($s);
+ } catch (DOMException $e) {
+ logger('scrape_dfrn: parse error: ' . $e);
+ }
if(! $dom) {
- echo sprintf($template,$url,$url,'');
+ echo sprintf($template,$url,$url,'') . $str_tags;
killme();
}
@@ -61,48 +123,118 @@ function parse_url_content(&$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 $item) {
- if($item->getElementsByTagName('script'))
- continue;
- $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,'