return($complete);
}
-function parseurl_getsiteinfo($url, $no_guessing = false) {
+function parseurl_getsiteinfo($url, $no_guessing = false, $do_oembed = true, $count = 1) {
+ require_once("include/network.php");
+
+ $a = get_app();
+
$siteinfo = array();
+ if ($count > 10) {
+ logger("parseurl_getsiteinfo: Endless loop detected for ".$url, LOGGER_DEBUG);
+ return($siteinfo);
+ }
+
$url = trim($url, "'");
$url = trim($url, '"');
+
+ $url = original_url($url);
+
$siteinfo["url"] = $url;
$siteinfo["type"] = "link";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 1);
- curl_setopt($ch, CURLOPT_NOBODY, 0);
+ curl_setopt($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,' Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:24.0) Gecko/20100101 Firefox/24.0');
+ curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
$header = curl_exec($ch);
$curl_info = @curl_getinfo($ch);
if ((($curl_info['http_code'] == "301") OR ($curl_info['http_code'] == "302") OR ($curl_info['http_code'] == "303") OR ($curl_info['http_code'] == "307"))
AND (($curl_info['redirect_url'] != "") OR ($curl_info['location'] != ""))) {
if ($curl_info['redirect_url'] != "")
- $siteinfo = parseurl_getsiteinfo($curl_info['redirect_url']);
+ $siteinfo = parseurl_getsiteinfo($curl_info['redirect_url'], $no_guessing, $do_oembed, ++$count);
else
- $siteinfo = parseurl_getsiteinfo($curl_info['location']);
+ $siteinfo = parseurl_getsiteinfo($curl_info['location'], $no_guessing, $do_oembed, ++$count);
return($siteinfo);
}
- require_once("include/oembed.php");
+ if ($do_oembed) {
+ require_once("include/oembed.php");
- $oembed_data = oembed_fetch_url($url);
+ $oembed_data = oembed_fetch_url($url);
+
+ if ($oembed_data->type != "error")
+ $siteinfo["type"] = $oembed_data->type;
+ }
+
+ // if the file is too large then exit
+ if ($curl_info["download_content_length"] > 1000000)
+ return($siteinfo);
+
+ // if it isn't a HTML file then exit
+ if (($curl_info["content_type"] != "") AND !strstr(strtolower($curl_info["content_type"]),"html"))
+ return($siteinfo);
+
+ // Now fetch the body as well
+ $ch = curl_init();
+ curl_setopt($ch, CURLOPT_URL, $url);
+ curl_setopt($ch, CURLOPT_HEADER, 1);
+ curl_setopt($ch, CURLOPT_NOBODY, 0);
+ curl_setopt($ch, CURLOPT_TIMEOUT, 10);
+ curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
+ curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
- if ($oembed_data->type != "error")
- $siteinfo["type"] = $oembed_data->type;
+ $header = curl_exec($ch);
+ $curl_info = @curl_getinfo($ch);
+ $http_code = $curl_info['http_code'];
+ curl_close($ch);
// Fetch the first mentioned charset. Can be in body or header
$charset = "";
if (preg_match('/charset=(.*?)['."'".'"\s\n]/', $header, $matches))
- $charset = trim(array_pop($matches));
+ $charset = trim(trim(trim(array_pop($matches)), ';,'));
if ($charset == "")
$charset = "utf-8";
else
$body = $header;
- $body = mb_convert_encoding($body, "UTF-8", $charset);
+ if (($charset != '') AND (strtoupper($charset) != "UTF-8")) {
+ logger("parseurl_getsiteinfo: detected charset ".$charset, LOGGER_DEBUG);
+ //$body = mb_convert_encoding($body, "UTF-8", $charset);
+ $body = iconv($charset, "UTF-8//TRANSLIT", $body);
+ }
+
$body = mb_convert_encoding($body, 'HTML-ENTITIES', "UTF-8");
$doc = new DOMDocument();
$content = substr($value, 4);
}
if ($content != "") {
- $siteinfo = parseurl_getsiteinfo($content);
+ $siteinfo = parseurl_getsiteinfo($content, $no_guessing, $do_oembed, ++$count);
return($siteinfo);
}
}
case "description":
$siteinfo["text"] = $attr["content"];
break;
+ case "thumbnail":
+ $siteinfo["image"] = $attr["content"];
+ break;
case "twitter:image":
$siteinfo["image"] = $attr["content"];
break;
+ case "twitter:image:src":
+ $siteinfo["image"] = $attr["content"];
+ break;
case "twitter:card":
- if ($siteinfo["type"] == "")
+ if (($siteinfo["type"] == "") OR ($attr["content"] == "photo"))
$siteinfo["type"] = $attr["content"];
break;
case "twitter:description":
case "dc.description":
$siteinfo["text"] = $attr["content"];
break;
+ case "keywords":
+ $keywords = explode(",", $attr["content"]);
+ break;
+ case "news_keywords":
+ $keywords = explode(",", $attr["content"]);
+ break;
}
if ($siteinfo["type"] == "summary")
$siteinfo["type"] = "link";
}
+ if (isset($keywords)) {
+ $siteinfo["keywords"] = array();
+ foreach ($keywords as $keyword)
+ $siteinfo["keywords"][] = trim($keyword);
+ }
+
//$list = $xpath->query("head/meta[@property]");
$list = $xpath->query("//meta[@property]");
foreach ($list as $node) {
}
}
- if ($oembed_data->type == "link") {
+ if (isset($oembed_data) AND ($oembed_data->type == "link") AND ($siteinfo["type"] != "photo")) {
if (isset($oembed_data->title) AND (trim($oembed_data->title) != ""))
$siteinfo["title"] = $oembed_data->title;
if (isset($oembed_data->description) AND (trim($oembed_data->description) != ""))
logger("parseurl_getsiteinfo: Siteinfo for ".$url." ".print_r($siteinfo, true), LOGGER_DEBUG);
+ call_hooks('getsiteinfo', $siteinfo);
+
return($siteinfo);
}
$siteinfo = parseurl_getsiteinfo($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"] == "") {
killme();
}
+?>
projects / friendica.git / blobdiff