X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;ds=inline;f=mod%2Fparse_url.php;h=2df9de4763c77afe1bc55932b87284c8343f995a;hb=a1a07e7287e9e764912bbd08383cf43503deb9e8;hp=89ef24f8760fa5b99576351169d944429a04145c;hpb=8a11cec61a87600273f1349e3d112e7fc1e65486;p=friendica.git diff --git a/mod/parse_url.php b/mod/parse_url.php index 89ef24f876..2df9de4763 100644 --- a/mod/parse_url.php +++ b/mod/parse_url.php @@ -3,9 +3,14 @@ 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) { $text = null; + $str_tags = ''; if(x($_GET,'binurl')) $url = trim(hex2bin($_GET['binurl'])); @@ -15,8 +20,16 @@ function parse_url_content(&$a) { if($_GET['title']) $title = strip_tags(trim($_GET['title'])); - if($_GET['desc']) - $text = strip_tags(trim($_GET['desc'])); + if($_GET['description']) + $text = strip_tags(trim($_GET['description'])); + + 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: ' . $url); @@ -33,12 +46,13 @@ function parse_url_content(&$a) { killme(); } + if($url && $title && $text) { $text = '

' . $text . '

'; $title = str_replace(array("\r","\n"),array('',''),$title); - $result = sprintf($template,$url,($title) ? $title : $url,$text); + $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags; logger('parse_url (unparsed): returns: ' . $result); @@ -54,13 +68,26 @@ function parse_url_content(&$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($s,'<title>')+7,64); @@ -71,16 +98,19 @@ function parse_url_content(&$a) { $config = HTMLPurifier_Config::createDefault(); $config->set('Cache.DefinitionImpl', null); - $purifier = new HTMLPurifier($config); $s = $purifier->purify($s); -// logger('parse_url: purified: ' . $s, LOGGER_DATA); +// logger('purify_output: ' . $s); - $dom = @HTML5_Parser::parse($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,'') . $str_tags; killme(); } @@ -142,13 +172,66 @@ function parse_url_content(&$a) { } } + if(! $text) { + logger('parsing meta'); + $items = $domhead->getElementsByTagName('meta'); + if($items) { + foreach($items as $item) { + $property = $item->getAttribute('property'); + if($property && (stristr($property,':description'))) { + + $text = $item->getAttribute('content'); + if(stristr($text,'<script')) { + $text = ''; + continue; + } + $text = strip_tags($text); + + + $text = substr($text,0,250) . '...' ; + } + if($property && (stristr($property,':image'))) { + + $image = $item->getAttribute('content'); + if(stristr($text,'<script')) { + $image = ''; + continue; + } + $image = strip_tags($image); + + $i = fetch_url($image); + if($i) { + require_once('include/Photo.php'); + $ph = new Photo($i); + if($ph->is_valid()) { + if($ph->getWidth() > 300 || $ph->getHeight() > 300) { + $ph->scaleImage(300); + $new_width = $ph->getWidth(); + $new_height = $ph->getHeight(); + $image = '<br /><br /><img height="' . $new_height . '" width="' . $new_width . '" src="' .$image . '" alt="photo" />'; + } + else + $image = '<br /><br /><img src="' . $image . '" alt="photo" />'; + } + else + $image = ''; + + } + } + } + } + } + if(strlen($text)) { $text = '<br /><br /><blockquote>' . $text . '</blockquote><br />'; } + if($image) { + $text = $image . '<br />' . $text; + } $title = str_replace(array("\r","\n"),array('',''),$title); - $result = sprintf($template,$url,($title) ? $title : $url,$text); + $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags; logger('parse_url: returns: ' . $result);