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, $no_guessing = false, $do_oembed = true, $count = 1) {
58 logger("parseurl_getsiteinfo: Endless loop detected for ".$url, LOGGER_DEBUG);
62 $url = trim($url, "'");
63 $url = trim($url, '"');
64 $siteinfo["url"] = $url;
65 $siteinfo["type"] = "link";
68 curl_setopt($ch, CURLOPT_URL, $url);
69 curl_setopt($ch, CURLOPT_HEADER, 1);
70 curl_setopt($ch, CURLOPT_NOBODY, 0);
71 curl_setopt($ch, CURLOPT_TIMEOUT, 3);
72 curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
73 //curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
74 //curl_setopt($ch,CURLOPT_USERAGENT,' Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:24.0) Gecko/20100101 Firefox/24.0');
75 curl_setopt($ch,CURLOPT_USERAGENT, "Mozilla/5.0 (compatible; Friendica)");
77 $header = curl_exec($ch);
78 $curl_info = @curl_getinfo($ch);
79 $http_code = $curl_info['http_code'];
82 if ((($curl_info['http_code'] == "301") OR ($curl_info['http_code'] == "302") OR ($curl_info['http_code'] == "303") OR ($curl_info['http_code'] == "307"))
83 AND (($curl_info['redirect_url'] != "") OR ($curl_info['location'] != ""))) {
84 if ($curl_info['redirect_url'] != "")
85 $siteinfo = parseurl_getsiteinfo($curl_info['redirect_url'], $no_guessing, $do_oembed, ++$count);
87 $siteinfo = parseurl_getsiteinfo($curl_info['location'], $no_guessing, $do_oembed, ++$count);
92 require_once("include/oembed.php");
94 $oembed_data = oembed_fetch_url($url);
96 if ($oembed_data->type != "error")
97 $siteinfo["type"] = $oembed_data->type;
100 // Fetch the first mentioned charset. Can be in body or header
102 if (preg_match('/charset=(.*?)['."'".'"\s\n]/', $header, $matches))
103 $charset = trim(trim(trim(array_pop($matches)), ';,'));
108 $pos = strpos($header, "\r\n\r\n");
111 $body = trim(substr($header, $pos));
115 if (($charset != '') AND (strtoupper($charset) != "UTF-8")) {
116 logger("parseurl_getsiteinfo: detected charset ".$charset, LOGGER_DEBUG);
117 //$body = mb_convert_encoding($body, "UTF-8", $charset);
118 $body = iconv($charset, "UTF-8//TRANSLIT", $body);
121 $body = mb_convert_encoding($body, 'HTML-ENTITIES', "UTF-8");
123 $doc = new DOMDocument();
124 @$doc->loadHTML($body);
126 deletenode($doc, 'style');
127 deletenode($doc, 'script');
128 deletenode($doc, 'option');
129 deletenode($doc, 'h1');
130 deletenode($doc, 'h2');
131 deletenode($doc, 'h3');
132 deletenode($doc, 'h4');
133 deletenode($doc, 'h5');
134 deletenode($doc, 'h6');
135 deletenode($doc, 'ol');
136 deletenode($doc, 'ul');
138 $xpath = new DomXPath($doc);
140 $list = $xpath->query("//meta[@content]");
141 foreach ($list as $node) {
143 if ($node->attributes->length)
144 foreach ($node->attributes as $attribute)
145 $attr[$attribute->name] = $attribute->value;
147 if (@$attr["http-equiv"] == 'refresh') {
148 $path = $attr["content"];
149 $pathinfo = explode(";", $path);
151 foreach ($pathinfo AS $value) {
152 if (substr(strtolower($value), 0, 4) == "url=")
153 $content = substr($value, 4);
155 if ($content != "") {
156 $siteinfo = parseurl_getsiteinfo($content, $no_guessing, $do_oembed, ++$count);
162 //$list = $xpath->query("head/title");
163 $list = $xpath->query("//title");
164 foreach ($list as $node)
165 $siteinfo["title"] = html_entity_decode($node->nodeValue, ENT_QUOTES, "UTF-8");
167 //$list = $xpath->query("head/meta[@name]");
168 $list = $xpath->query("//meta[@name]");
169 foreach ($list as $node) {
171 if ($node->attributes->length)
172 foreach ($node->attributes as $attribute)
173 $attr[$attribute->name] = $attribute->value;
175 $attr["content"] = trim(html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8"));
177 if ($attr["content"] != "")
178 switch (strtolower($attr["name"])) {
180 $siteinfo["title"] = $attr["content"];
183 $siteinfo["text"] = $attr["content"];
185 case "twitter:image":
186 $siteinfo["image"] = $attr["content"];
189 if (($siteinfo["type"] == "") OR ($attr["content"] == "photo"))
190 $siteinfo["type"] = $attr["content"];
192 case "twitter:description":
193 $siteinfo["text"] = $attr["content"];
195 case "twitter:title":
196 $siteinfo["title"] = $attr["content"];
199 $siteinfo["title"] = $attr["content"];
201 case "dc.description":
202 $siteinfo["text"] = $attr["content"];
205 if ($siteinfo["type"] == "summary")
206 $siteinfo["type"] = "link";
209 //$list = $xpath->query("head/meta[@property]");
210 $list = $xpath->query("//meta[@property]");
211 foreach ($list as $node) {
213 if ($node->attributes->length)
214 foreach ($node->attributes as $attribute)
215 $attr[$attribute->name] = $attribute->value;
217 $attr["content"] = trim(html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8"));
219 if ($attr["content"] != "")
220 switch (strtolower($attr["property"])) {
222 $siteinfo["image"] = $attr["content"];
225 $siteinfo["title"] = $attr["content"];
227 case "og:description":
228 $siteinfo["text"] = $attr["content"];
233 if (isset($oembed_data) AND ($oembed_data->type == "link") AND ($siteinfo["type"] != "photo")) {
234 if (isset($oembed_data->title) AND (trim($oembed_data->title) != ""))
235 $siteinfo["title"] = $oembed_data->title;
236 if (isset($oembed_data->description) AND (trim($oembed_data->description) != ""))
237 $siteinfo["text"] = trim($oembed_data->description);
238 if (isset($oembed_data->thumbnail_url) AND (trim($oembed_data->thumbnail_url) != ""))
239 $siteinfo["image"] = $oembed_data->thumbnail_url;
242 if ((@$siteinfo["image"] == "") AND !$no_guessing) {
243 $list = $xpath->query("//img[@src]");
244 foreach ($list as $node) {
246 if ($node->attributes->length)
247 foreach ($node->attributes as $attribute)
248 $attr[$attribute->name] = $attribute->value;
250 $src = completeurl($attr["src"], $url);
251 $photodata = @getimagesize($src);
253 if (($photodata) && ($photodata[0] > 150) and ($photodata[1] > 150)) {
254 if ($photodata[0] > 300) {
255 $photodata[1] = round($photodata[1] * (300 / $photodata[0]));
258 if ($photodata[1] > 300) {
259 $photodata[0] = round($photodata[0] * (300 / $photodata[1]));
262 $siteinfo["images"][] = array("src"=>$src,
263 "width"=>$photodata[0],
264 "height"=>$photodata[1]);
269 $src = completeurl($siteinfo["image"], $url);
271 unset($siteinfo["image"]);
273 $photodata = @getimagesize($src);
275 if (($photodata) && ($photodata[0] > 10) and ($photodata[1] > 10))
276 $siteinfo["images"][] = array("src"=>$src,
277 "width"=>$photodata[0],
278 "height"=>$photodata[1]);
281 if ((@$siteinfo["text"] == "") AND (@$siteinfo["title"] != "") AND !$no_guessing) {
284 $list = $xpath->query("//div[@class='article']");
285 foreach ($list as $node)
286 if (strlen($node->nodeValue) > 40)
287 $text .= " ".trim($node->nodeValue);
290 $list = $xpath->query("//div[@class='content']");
291 foreach ($list as $node)
292 if (strlen($node->nodeValue) > 40)
293 $text .= " ".trim($node->nodeValue);
296 // If none text was found then take the paragraph content
298 $list = $xpath->query("//p");
299 foreach ($list as $node)
300 if (strlen($node->nodeValue) > 40)
301 $text .= " ".trim($node->nodeValue);
305 $text = trim(str_replace(array("\n", "\r"), array(" ", " "), $text));
307 while (strpos($text, " "))
308 $text = trim(str_replace(" ", " ", $text));
310 $siteinfo["text"] = trim(html_entity_decode(substr($text,0,350), ENT_QUOTES, "UTF-8").'...');
314 logger("parseurl_getsiteinfo: Siteinfo for ".$url." ".print_r($siteinfo, true), LOGGER_DEBUG);
319 function arr_add_hashes(&$item,$k) {
323 function parse_url_content(&$a) {
330 if(local_user() && (! feature_enabled(local_user(),'richtext')))
334 $br = (($textmode) ? "\n" : '<br />');
336 if(x($_GET,'binurl'))
337 $url = trim(hex2bin($_GET['binurl']));
339 $url = trim($_GET['url']);
342 $title = strip_tags(trim($_GET['title']));
344 if($_GET['description'])
345 $text = strip_tags(trim($_GET['description']));
348 $arr_tags = str_getcsv($_GET['tags']);
349 if(count($arr_tags)) {
350 array_walk($arr_tags,'arr_add_hashes');
351 $str_tags = $br . implode(' ',$arr_tags) . $br;
355 logger('parse_url: ' . $url);
358 $template = '[bookmark=%s]%s[/bookmark]%s';
360 $template = "<a class=\"bookmark\" href=\"%s\" >%s</a>%s";
362 $arr = array('url' => $url, 'text' => '');
364 call_hooks('parse_link', $arr);
366 if(strlen($arr['text'])) {
372 if($url && $title && $text) {
374 $title = str_replace(array("\r","\n"),array('',''),$title);
377 $text = '[quote]' . trim($text) . '[/quote]' . $br;
379 $text = '<blockquote>' . htmlspecialchars(trim($text)) . '</blockquote><br />';
380 $title = htmlspecialchars($title);
383 $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags;
385 logger('parse_url (unparsed): returns: ' . $result);
391 $siteinfo = parseurl_getsiteinfo($url);
393 $url= $siteinfo["url"];
397 if($siteinfo["title"] == "") {
398 $sitedata .= sprintf($template,$url,$url,'') . $str_tags;
401 $text = $siteinfo["text"];
402 $title = $siteinfo["title"];
407 if (($siteinfo["type"] != "video") AND (sizeof($siteinfo["images"]) > 0)){
408 /* Execute below code only if image is present in siteinfo */
411 $max_images = get_config('system','max_bookmark_images');
412 if($max_images === false)
415 $max_images = intval($max_images);
417 foreach ($siteinfo["images"] as $imagedata) {
419 $image .= '[img='.$imagedata["width"].'x'.$imagedata["height"].']'.$imagedata["src"].'[/img]' . "\n";
421 $image .= '<img height="'.$imagedata["height"].'" width="'.$imagedata["width"].'" src="'.$imagedata["src"].'" alt="photo" /><br />';
423 if($max_images && $max_images >= $total_images)
430 $text = '[quote]'.trim($text).'[/quote]';
432 $text = '<blockquote>'.htmlspecialchars(trim($text)).'</blockquote>';
436 $text = $br.$br.$image.$text;
440 $title = str_replace(array("\r","\n"),array('',''),$title);
442 $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags;
444 logger('parse_url: returns: ' . $result);
446 $sitedata .= trim($result);
448 if (($siteinfo["type"] == "video") AND ($url != ""))
449 echo "[class=type-video]".$sitedata."[/class]";
450 elseif (($siteinfo["type"] != "photo"))
451 echo "[class=type-link]".$sitedata."[/class]";
453 echo "[class=type-photo]".$title.$br.$image."[/class]";