3 https://developers.google.com/+/plugins/snippet/
5 <meta itemprop="name" content="Toller Titel">
6 <meta itemprop="description" content="Eine tolle Beschreibung">
7 <meta itemprop="image" content="http://maple.libertreeproject.org/images/tree-icon.png">
9 <body itemscope itemtype="http://schema.org/Product">
10 <h1 itemprop="name">Shiny Trinket</h1>
11 <img itemprop="image" src="{image-url}" />
12 <p itemprop="description">Shiny trinkets are shiny.</p>
16 if(!function_exists('deletenode')) {
17 function deletenode(&$doc, $node)
19 $xpath = new DomXPath($doc);
20 $list = $xpath->query("//".$node);
21 foreach ($list as $child)
22 $child->parentNode->removeChild($child);
26 function completeurl($url, $scheme) {
27 $urlarr = parse_url($url);
29 if (isset($urlarr["scheme"]))
32 $schemearr = parse_url($scheme);
34 $complete = $schemearr["scheme"]."://".$schemearr["host"];
36 if ($schemearr["port"] != "")
37 $complete .= ":".$schemearr["port"];
39 if(strpos($urlarr['path'],'/') !== 0)
42 $complete .= $urlarr["path"];
44 if ($urlarr["query"] != "")
45 $complete .= "?".$urlarr["query"];
47 if ($urlarr["fragment"] != "")
48 $complete .= "#".$urlarr["fragment"];
53 function parseurl_getsiteinfo($url) {
57 curl_setopt($ch, CURLOPT_URL, $url);
58 curl_setopt($ch, CURLOPT_HEADER, 1);
59 curl_setopt($ch, CURLOPT_NOBODY, 0);
60 curl_setopt($ch, CURLOPT_TIMEOUT, 3);
61 curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
62 curl_setopt($ch,CURLOPT_USERAGENT,'Opera/9.64(Windows NT 5.1; U; de) Presto/2.1.1');
64 $header = curl_exec($ch);
67 // Fetch the first mentioned charset. Can be in body or header
68 if (preg_match('/charset=(.*?)['."'".'"\s\n]/', $header, $matches))
69 $charset = trim(array_pop($matches));
73 $pos = strpos($header, "\r\n\r\n");
76 $body = trim(substr($header, $pos));
80 $body = mb_convert_encoding($body, "UTF-8", $charset);
81 $body = mb_convert_encoding($body, 'HTML-ENTITIES', "UTF-8");
83 $doc = new DOMDocument();
84 @$doc->loadHTML($body);
86 deletenode($doc, 'style');
87 deletenode($doc, 'script');
88 deletenode($doc, 'option');
89 deletenode($doc, 'h1');
90 deletenode($doc, 'h2');
91 deletenode($doc, 'h3');
92 deletenode($doc, 'h4');
93 deletenode($doc, 'h5');
94 deletenode($doc, 'h6');
95 deletenode($doc, 'ol');
96 deletenode($doc, 'ul');
98 $xpath = new DomXPath($doc);
100 //$list = $xpath->query("head/title");
101 $list = $xpath->query("//title");
102 foreach ($list as $node)
103 $siteinfo["title"] = html_entity_decode($node->nodeValue, ENT_QUOTES, "UTF-8");
105 //$list = $xpath->query("head/meta[@name]");
106 $list = $xpath->query("//meta[@name]");
107 foreach ($list as $node) {
109 if ($node->attributes->length)
110 foreach ($node->attributes as $attribute)
111 $attr[$attribute->name] = $attribute->value;
113 $attr["content"] = html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8");
115 switch (strtolower($attr["name"])) {
117 $siteinfo["title"] = $attr["content"];
120 $siteinfo["text"] = $attr["content"];
123 $siteinfo["title"] = $attr["content"];
125 case "dc.description":
126 $siteinfo["text"] = $attr["content"];
131 //$list = $xpath->query("head/meta[@property]");
132 $list = $xpath->query("//meta[@property]");
133 foreach ($list as $node) {
135 if ($node->attributes->length)
136 foreach ($node->attributes as $attribute)
137 $attr[$attribute->name] = $attribute->value;
139 $attr["content"] = html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8");
141 switch (strtolower($attr["property"])) {
143 $siteinfo["image"] = $attr["content"];
146 $siteinfo["title"] = $attr["content"];
148 case "og:description":
149 $siteinfo["text"] = $attr["content"];
154 if ($siteinfo["image"] == "") {
155 $list = $xpath->query("//img[@src]");
156 foreach ($list as $node) {
158 if ($node->attributes->length)
159 foreach ($node->attributes as $attribute)
160 $attr[$attribute->name] = $attribute->value;
162 $src = completeurl($attr["src"], $url);
163 $photodata = @getimagesize($src);
165 if (($photodata) && ($photodata[0] > 150) and ($photodata[1] > 150)) {
166 if ($photodata[0] > 300) {
167 $photodata[1] = round($photodata[1] * (300 / $photodata[0]));
170 if ($photodata[1] > 300) {
171 $photodata[0] = round($photodata[0] * (300 / $photodata[1]));
174 $siteinfo["images"][] = array("src"=>$src,
175 "width"=>$photodata[0],
176 "height"=>$photodata[1]);
181 $src = completeurl($siteinfo["image"], $url);
183 unset($siteinfo["image"]);
185 $photodata = @getimagesize($src);
187 if (($photodata) && ($photodata[0] > 10) and ($photodata[1] > 10))
188 $siteinfo["images"][] = array("src"=>$src,
189 "width"=>$photodata[0],
190 "height"=>$photodata[1]);
193 if ($siteinfo["text"] == "") {
196 $list = $xpath->query("//div[@class='article']");
197 foreach ($list as $node)
198 if (strlen($node->nodeValue) > 40)
199 $text .= " ".trim($node->nodeValue);
202 $list = $xpath->query("//div[@class='content']");
203 foreach ($list as $node)
204 if (strlen($node->nodeValue) > 40)
205 $text .= " ".trim($node->nodeValue);
208 // If none text was found then take the paragraph content
210 $list = $xpath->query("//p");
211 foreach ($list as $node)
212 if (strlen($node->nodeValue) > 40)
213 $text .= " ".trim($node->nodeValue);
217 $text = trim(str_replace(array("\n", "\r"), array(" ", " "), $text));
219 while (strpos($text, " "))
220 $text = trim(str_replace(" ", " ", $text));
222 $siteinfo["text"] = html_entity_decode(substr($text,0,350), ENT_QUOTES, "UTF-8").'...';
229 function arr_add_hashes(&$item,$k) {
233 function parse_url_content(&$a) {
240 if(local_user() && (! feature_enabled(local_user(),'richtext')))
244 $br = (($textmode) ? "\n" : '<br />');
246 if(x($_GET,'binurl'))
247 $url = trim(hex2bin($_GET['binurl']));
249 $url = trim($_GET['url']);
252 $title = strip_tags(trim($_GET['title']));
254 if($_GET['description'])
255 $text = strip_tags(trim($_GET['description']));
258 $arr_tags = str_getcsv($_GET['tags']);
259 if(count($arr_tags)) {
260 array_walk($arr_tags,'arr_add_hashes');
261 $str_tags = $br . implode(' ',$arr_tags) . $br;
265 logger('parse_url: ' . $url);
268 $template = $br . '[bookmark=%s]%s[/bookmark]%s' . $br;
270 $template = "<br /><a class=\"bookmark\" href=\"%s\" >%s</a>%s<br />";
272 $arr = array('url' => $url, 'text' => '');
274 call_hooks('parse_link', $arr);
276 if(strlen($arr['text'])) {
282 if($url && $title && $text) {
285 $text = $br . '[quote]' . trim($text) . '[/quote]' . $br;
287 $text = '<br /><blockquote>' . trim($text) . '</blockquote><br />';
289 $title = str_replace(array("\r","\n"),array('',''),$title);
291 $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags;
293 logger('parse_url (unparsed): returns: ' . $result);
299 $siteinfo = parseurl_getsiteinfo($url);
301 if($siteinfo["title"] == "") {
302 echo sprintf($template,$url,$url,'') . $str_tags;
305 $text = $siteinfo["text"];
306 $title = $siteinfo["title"];
311 if(sizeof($siteinfo["images"]) > 0){
312 /* Execute below code only if image is present in siteinfo */
315 $max_images = get_config('system','max_bookmark_images');
316 if($max_images === false)
319 $max_images = intval($max_images);
321 foreach ($siteinfo["images"] as $imagedata) {
323 $image .= '[img='.$imagedata["width"].'x'.$imagedata["height"].']'.$imagedata["src"].'[/img]' . "\n";
325 $image .= '<img height="'.$imagedata["height"].'" width="'.$imagedata["width"].'" src="'.$imagedata["src"].'" alt="photo" /><br />';
327 if($max_images && $max_images >= $total_images)
334 $text = $br.'[quote]'.trim($text).'[/quote]'.$br ;
336 $text = '<br /><blockquote>'.trim($text).'</blockquote><br />';
340 $text = $br.$br.$image.$text;
342 $title = str_replace(array("\r","\n"),array('',''),$title);
344 $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags;
346 logger('parse_url: returns: ' . $result);