X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FUtil%2FParseUrl.php;h=24be55cab931ced253b360a51070f93852dcb0d0;hb=093dd70e790def206d6f7d48cfac095c29eb10a5;hp=03cfd7d7611cf338f71f375763be4dcc28b3fb20;hpb=d62f21cfa146d6ecb704e54ae765780830edcf0d;p=friendica.git

diff --git a/src/Util/ParseUrl.php b/src/Util/ParseUrl.php
index 03cfd7d761..24be55cab9 100644
--- a/src/Util/ParseUrl.php
+++ b/src/Util/ParseUrl.php
@@ -1,6 +1,6 @@
 <?php
 /**
- * @copyright Copyright (C) 2010-2021, the Friendica project
+ * @copyright Copyright (C) 2010-2022, the Friendica project
  *
  * @license GNU AGPL version 3 or any later version
  *
@@ -60,13 +60,19 @@ class ParseUrl
 	public static function getContentType(string $url)
 	{
 		$curlResult = DI::httpClient()->head($url);
+
+		// Workaround for systems that can't handle a HEAD request
+		if (!$curlResult->isSuccess() && ($curlResult->getReturnCode() == 405)) {
+			$curlResult = DI::httpClient()->get($url, [HttpClientOptions::CONTENT_LENGTH => 1000000]);
+		}
+
 		if (!$curlResult->isSuccess()) {
 			return [];
 		}
 
 		$contenttype =  $curlResult->getHeader('Content-Type')[0] ?? '';
 		if (empty($contenttype)) {
-			return [];
+			return ['application', 'octet-stream'];
 		}
 
 		return explode('/', current(explode(';', $contenttype)));
@@ -216,6 +222,7 @@ class ParseUrl
 
 		$curlResult = DI::httpClient()->get($url, [HttpClientOptions::CONTENT_LENGTH => 1000000]);
 		if (!$curlResult->isSuccess() || empty($curlResult->getBody())) {
+			Logger::info('Empty body or error when fetching', ['url' => $url, 'success' => $curlResult->isSuccess(), 'code' => $curlResult->getReturnCode()]);
 			return $siteinfo;
 		}
 
@@ -451,6 +458,12 @@ class ParseUrl
 					case 'og:site_name':
 						$siteinfo['publisher_name'] = trim($meta_tag['content']);
 						break;
+					case 'og:locale':
+						$siteinfo['language'] = trim($meta_tag['content']);
+						break;
+					case 'og:type':
+						$siteinfo['pagetype'] = trim($meta_tag['content']);
+						break;
 					case 'twitter:description':
 						$siteinfo['text'] = trim($meta_tag['content']);
 						break;
@@ -521,7 +534,7 @@ class ParseUrl
 	 *
 	 * @param string $page_url
 	 * @param array $siteinfo
-	 * @return void
+	 * @return array
 	 */
 	private static function checkMedia(string $page_url, array $siteinfo) : array
 	{
@@ -967,6 +980,16 @@ class ParseUrl
 			}
 		}
 
+		$content = JsonLD::fetchElement($jsonld, 'datePublished');
+		if (!empty($content) && is_string($content)) {
+			$jsonldinfo['published'] = DateTimeFormat::utc($content);
+		}
+
+		$content = JsonLD::fetchElement($jsonld, 'dateModified');
+		if (!empty($content) && is_string($content)) {
+			$jsonldinfo['modified'] = DateTimeFormat::utc($content);
+		}
+
 		$jsonldinfo = self::parseJsonLdAuthor($jsonldinfo, $jsonld);
 
 		Logger::info('Fetched article information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);