function parseurl_getsiteinfo_cached($url, $no_guessing = false, $do_oembed = true) {
- $data = Cache::get("parse_url:".$no_guessing.":".$do_oembed.":".$url);
+ if ($url == "")
+ return false;
+
+ $r = q("SELECT * FROM `parsed_url` WHERE `url` = '%s' AND `guessing` = %d AND `oembed` = %d",
+ dbesc(normalise_link($url)), intval(!$no_guessing), intval($do_oembed));
+
+ if ($r)
+ $data = $r[0]["content"];
+
if (!is_null($data)) {
$data = unserialize($data);
return $data;
$data = parseurl_getsiteinfo($url, $no_guessing, $do_oembed);
- Cache::set("parse_url:".$no_guessing.":".$do_oembed.":".$url,serialize($data), CACHE_DAY);
+ q("INSERT INTO `parsed_url` (`url`, `guessing`, `oembed`, `content`, `created`) VALUES ('%s', %d, %d, '%s', '%s')
+ ON DUPLICATE KEY UPDATE `content` = '%s', `created` = '%s'",
+ dbesc(normalise_link($url)), intval(!$no_guessing), intval($do_oembed),
+ dbesc(serialize($data)), dbesc(datetime_convert()),
+ dbesc(serialize($data)), dbesc(datetime_convert()));
return $data;
}
function parseurl_getsiteinfo($url, $no_guessing = false, $do_oembed = true, $count = 1) {
require_once("include/network.php");
+ require_once("include/Photo.php");
$a = get_app();
$siteinfo = array();
+ // Check if the URL does contain a scheme
+ $scheme = parse_url($url, PHP_URL_SCHEME);
+
+ if ($scheme == "") {
+ $url = "http://".trim($url, "/");
+ }
+
if ($count > 10) {
logger("parseurl_getsiteinfo: Endless loop detected for ".$url, LOGGER_DEBUG);
return($siteinfo);
$siteinfo["url"] = $url;
$siteinfo["type"] = "link";
+ $check_cert = get_config('system','verifyssl');
+
$stamp1 = microtime(true);
$ch = curl_init();
curl_setopt($ch, CURLOPT_NOBODY, 1);
curl_setopt($ch, CURLOPT_TIMEOUT, 3);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
- //curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
+ curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, (($check_cert) ? true : false));
+ curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, (($check_cert) ? 2 : false));
$header = curl_exec($ch);
$curl_info = @curl_getinfo($ch);
$oembed_data = oembed_fetch_url($url);
- if ($oembed_data->type != "error")
+ if (!in_array($oembed_data->type, array("error", "rich"))) {
$siteinfo["type"] = $oembed_data->type;
+ }
if (($oembed_data->type == "link") AND ($siteinfo["type"] != "photo")) {
if (isset($oembed_data->title))
curl_setopt($ch, CURLOPT_TIMEOUT, 10);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
+ curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, (($check_cert) ? true : false));
+ curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, (($check_cert) ? 2 : false));
$header = curl_exec($ch);
$curl_info = @curl_getinfo($ch);
}
}
- //$list = $xpath->query("head/title");
$list = $xpath->query("//title");
- foreach ($list as $node)
- $siteinfo["title"] = html_entity_decode($node->nodeValue, ENT_QUOTES, "UTF-8");
+ if ($list->length > 0)
+ $siteinfo["title"] = $list->item(0)->nodeValue;
//$list = $xpath->query("head/meta[@name]");
$list = $xpath->query("//meta[@name]");
$attr[$attribute->name] = $attribute->value;
$src = completeurl($attr["src"], $url);
- $photodata = @getimagesize($src);
+ $photodata = get_photo_info($src);
if (($photodata) && ($photodata[0] > 150) and ($photodata[1] > 150)) {
if ($photodata[0] > 300) {
}
}
- } else {
+ } elseif ($siteinfo["image"] != "") {
$src = completeurl($siteinfo["image"], $url);
unset($siteinfo["image"]);
- $photodata = @getimagesize($src);
+ $photodata = get_photo_info($src);
if (($photodata) && ($photodata[0] > 10) and ($photodata[1] > 10))
$siteinfo["images"][] = array("src"=>$src,
function parse_url_content(&$a) {
+ require_once("include/items.php");
+
$text = null;
$str_tags = '';
$siteinfo = parseurl_getsiteinfo($url);
-// if ($textmode) {
-// require_once("include/items.php");
-//
-// echo add_page_info_data($siteinfo);
-// killme();
-// }
-
- $url= $siteinfo["url"];
-
- // If the link contains BBCode stuff, make a short link out of this to avoid parsing problems
- if (strpos($url, '[') OR strpos($url, ']')) {
- require_once("include/network.php");
- $url = short_link($url);
- }
-
- $sitedata = "";
-
- if($siteinfo["title"] != "") {
- $text = $siteinfo["text"];
- $title = $siteinfo["title"];
- }
-
- $image = "";
-
- if (($siteinfo["type"] != "video") AND (sizeof($siteinfo["images"]) > 0)){
- /* Execute below code only if image is present in siteinfo */
+ unset($siteinfo["keywords"]);
- $total_images = 0;
- $max_images = get_config('system','max_bookmark_images');
- if($max_images === false)
- $max_images = 2;
- else
- $max_images = intval($max_images);
-
- foreach ($siteinfo["images"] as $imagedata) {
- if($textmode)
- $image .= '[img='.$imagedata["width"].'x'.$imagedata["height"].']'.$imagedata["src"].'[/img]' . "\n";
- else
- $image .= '<img height="'.$imagedata["height"].'" width="'.$imagedata["width"].'" src="'.$imagedata["src"].'" alt="photo" /><br />';
- $total_images ++;
- if($max_images && $max_images >= $total_images)
- break;
- }
- }
+ $info = add_page_info_data($siteinfo);
- if(strlen($text)) {
- if($textmode)
- $text = '[quote]'.trim($text).'[/quote]';
- else
- $text = '<blockquote>'.htmlspecialchars(trim($text)).'</blockquote>';
- }
+ if (!$textmode)
+ // Replace ' with ’ - not perfect - but the richtext editor has problems otherwise
+ $info = str_replace(array("'"), array("’"), $info);
- if($image)
- $text = $br.$br.$image.$text;
- else
- $text = $br.$text;
-
- $title = str_replace(array("\r","\n"),array('',''),$title);
-
- $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags;
-
- logger('parse_url: returns: ' . $result);
-
- $sitedata .= trim($result);
-
- if (($siteinfo["type"] == "video") AND ($url != ""))
- echo "[class=type-video]".$sitedata."[/class]";
- elseif (($siteinfo["type"] != "photo"))
- echo "[class=type-link]".$sitedata."[/class]";
- else
- echo "[class=type-photo]".$title.$br.$image."[/class]";
+ echo $info;
killme();
}