<?php
-require_once('include/Photo.php');
+/* To-Do
+https://developers.google.com/+/plugins/snippet/
+
+<meta itemprop="name" content="Toller Titel">
+<meta itemprop="description" content="Eine tolle Beschreibung">
+<meta itemprop="image" content="http://maple.libertreeproject.org/images/tree-icon.png">
+
+<body itemscope itemtype="http://schema.org/Product">
+ <h1 itemprop="name">Shiny Trinket</h1>
+ <img itemprop="image" src="{image-url}" />
+ <p itemprop="description">Shiny trinkets are shiny.</p>
+</body>
+*/
if(!function_exists('deletenode')) {
function deletenode(&$doc, $node)
}
}
+function completeurl($url, $scheme) {
+ $urlarr = parse_url($url);
+
+ if (isset($urlarr["scheme"]))
+ return($url);
+
+ $schemearr = parse_url($scheme);
+
+ $complete = $schemearr["scheme"]."://".$schemearr["host"];
+
+ if ($schemearr["port"] != "")
+ $complete .= ":".$schemearr["port"];
+
+ $complete .= $urlarr["path"];
+
+ if ($urlarr["query"] != "")
+ $complete .= "?".$urlarr["query"];
+
+ if ($urlarr["fragment"] != "")
+ $complete .= "#".$urlarr["fragment"];
+
+ return($complete);
+}
+
function parseurl_getsiteinfo($url) {
$siteinfo = array();
$header = curl_exec($ch);
curl_close($ch);
- if (preg_match('/charset=(.*?)\n/', $header, $matches))
+ // Fetch the first mentioned charset. Can be in body or header
+ if (preg_match('/charset=(.*?)['."'".'"\s\n]/', $header, $matches))
$charset = trim(array_pop($matches));
else
$charset = "utf-8";
$xpath = new DomXPath($doc);
- $list = $xpath->query("head/title");
+ //$list = $xpath->query("head/title");
+ $list = $xpath->query("//title");
foreach ($list as $node)
$siteinfo["title"] = html_entity_decode($node->nodeValue, ENT_QUOTES, "UTF-8");
- $list = $xpath->query("head/meta[@name]");
+ //$list = $xpath->query("head/meta[@name]");
+ $list = $xpath->query("//meta[@name]");
foreach ($list as $node) {
$attr = array();
if ($node->attributes->length)
}
}
- $list = $xpath->query("head/meta[@property]");
+ //$list = $xpath->query("head/meta[@property]");
+ $list = $xpath->query("//meta[@property]");
foreach ($list as $node) {
$attr = array();
if ($node->attributes->length)
foreach ($node->attributes as $attribute)
$attr[$attribute->name] = $attribute->value;
- // guess mimetype from headers or filename
- $type = guess_image_type($attr["src"],true);
-
- $i = fetch_url($attr["src"]);
- $ph = new Photo($i, $type);
-
- if($ph->is_valid() and ($ph->getWidth() > 200) and ($ph->getHeight() > 200)) {
- if ($siteinfo["image"] == "")
- $siteinfo["image"] = $attr["src"];
-
- if($ph->getWidth() > 300 || $ph->getHeight() > 300) {
- $ph->scaleImage(300);
- $siteinfo["images"][] = array("src"=>$attr["src"],
- "width"=>$ph->getWidth(),
- "height"=>$ph->getHeight());
- } else
- $siteinfo["images"][] = array("src"=>$attr["src"],
- "width"=>$ph->getWidth(),
- "height"=>$ph->getHeight());
+ $src = completeurl($attr["src"], $url);
+ $photodata = getimagesize($src);
+
+ if (($photodata[0] > 150) and ($photodata[1] > 150)) {
+ if ($photodata[0] > 300) {
+ $photodata[1] = round($photodata[1] * (300 / $photodata[0]));
+ $photodata[0] = 300;
+ }
+ if ($photodata[1] > 300) {
+ $photodata[0] = round($photodata[0] * (300 / $photodata[1]));
+ $photodata[1] = 300;
+ }
+ $siteinfo["images"][] = array("src"=>$src,
+ "width"=>$photodata[0],
+ "height"=>$photodata[1]);
}
+
}
} else {
- // guess mimetype from headers or filename
- $type = guess_image_type($siteinfo["image"],true);
+ $src = completeurl($siteinfo["image"], $url);
+
+ unset($siteinfo["image"]);
- $i = fetch_url($siteinfo["image"]);
- $ph = new Photo($i, $type);
+ $photodata = getimagesize($src);
- if($ph->is_valid())
- $siteinfo["images"][] = array("src"=>$siteinfo["image"],
- "width"=>$ph->getWidth(),
- "height"=>$ph->getHeight());
+ if (($photodata[0] > 10) and ($photodata[1] > 10))
+ $siteinfo["images"][] = array("src"=>$src,
+ "width"=>$photodata[0],
+ "height"=>$photodata[1]);
}
if ($siteinfo["text"] == "") {
$list = $xpath->query("//div[@class='article']");
foreach ($list as $node)
- $text .= " ".trim($node->nodeValue);
+ if (strlen($node->nodeValue) > 40)
+ $text .= " ".trim($node->nodeValue);
if ($text == "") {
$list = $xpath->query("//div[@class='content']");
foreach ($list as $node)
- $text .= " ".trim($node->nodeValue);
+ if (strlen($node->nodeValue) > 40)
+ $text .= " ".trim($node->nodeValue);
}
// If none text was found then take the paragraph content
if ($text == "") {
$list = $xpath->query("//p");
foreach ($list as $node)
- $text .= " ".trim($node->nodeValue);
+ if (strlen($node->nodeValue) > 40)
+ $text .= " ".trim($node->nodeValue);
}
if ($text != "") {
if($url && $title && $text) {
if($textmode)
- $text = $br . $br . '[quote]' . trim($text) . '[/quote]' . $br;
+ $text = $br . '[quote]' . trim($text) . '[/quote]' . $br;
else
- $text = '<br /><br /><blockquote>' . trim($text) . '</blockquote><br />';
+ $text = '<br /><blockquote>' . trim($text) . '</blockquote><br />';
$title = str_replace(array("\r","\n"),array('',''),$title);
$image = "";
- foreach ($siteinfo["images"] as $imagedata)
+ if(sizeof($siteinfo["images"]) > 0){
+ /*
+ Execute below code only if image is present in siteinfo
+ */
+ foreach ($siteinfo["images"] as $imagedata)
if($textmode)
- $image .= '[img='.$imagedata["width"].'x'.$imagedata["height"].']'.$imagedata["src"].'[/img]';
+ $image .= '[img='.$imagedata["width"].'x'.$imagedata["height"].']'.$imagedata["src"].'[/img]';
else
- $image .= '<img height="'.$imagedata["height"].'" width="'.$imagedata["width"].'" src="'.$imagedata["src"].'" alt="photo" />';
-
-/* if ($image != "") {
- $i = fetch_url($image);
- if($i) {
- require_once('include/Photo.php');
- // guess mimetype from headers or filename
- $type = guess_image_type($image,true);
-
- $ph = new Photo($i, $type);
- if($ph->is_valid()) {
- if($ph->getWidth() > 300 || $ph->getHeight() > 300) {
- $ph->scaleImage(300);
- $new_width = $ph->getWidth();
- $new_height = $ph->getHeight();
- if($textmode)
- $image = $br . $br . '[img=' . $new_width . 'x' . $new_height . ']' . $image . '[/img]';
- else
- $image = '<br /><br /><img height="' . $new_height . '" width="' . $new_width . '" src="' .$image . '" alt="photo" />';
- } else {
- if($textmode)
- $image = $br.$br.'[img]'.$image.'[/img]';
- else
- $image = '<br /><br /><img src="'.$image.'" alt="photo" />';
- }
- }
- }
- }*/
+ $image .= '<img height="'.$imagedata["height"].'" width="'.$imagedata["width"].'" src="'.$imagedata["src"].'" alt="photo" />';
+ }
if(strlen($text)) {
if($textmode)
}
if($image) {
- $text = $br.$br.$image.$br.$text;
+ $text = $br.$br.$image.$text;
}
$title = str_replace(array("\r","\n"),array('',''),$title);
logger('parse_url: returns: ' . $result);
- echo $result;
+ echo trim($result);
killme();
}