X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FUtil%2FParseUrl.php;h=79f427a654df4b5f672bc52f3470ebe01deb2b5b;hb=e1863951986ba5be173758324a00652bc5af870c;hp=a0ff0f1773a9d74f1799a688e53e09d33d3e611d;hpb=2957a3def6052fcd1120f3196e3695d4c278d7fe;p=friendica.git
diff --git a/src/Util/ParseUrl.php b/src/Util/ParseUrl.php
index a0ff0f1773..79f427a654 100644
--- a/src/Util/ParseUrl.php
+++ b/src/Util/ParseUrl.php
@@ -1,6 +1,6 @@
head($url, array_merge([HttpClientOptions::ACCEPT_CONTENT => $accept], $options));
+ try {
+ $curlResult = DI::httpClient()->head($url, array_merge([HttpClientOptions::ACCEPT_CONTENT => $accept], $options));
+ } catch (\Exception $e) {
+ DI::logger()->debug('Got exception', ['url' => $url, 'message' => $e->getMessage()]);
+ return [];
+ }
// Workaround for systems that can't handle a HEAD request. Don't retry on timeouts.
if (!$curlResult->isSuccess() && ($curlResult->getReturnCode() >= 400) && !in_array($curlResult->getReturnCode(), [408, 504])) {
@@ -89,7 +96,7 @@ class ParseUrl
}
/**
- * Search for chached embeddable data of an url otherwise fetch it
+ * Search for cached embeddable data of an url otherwise fetch it
*
* @param string $url The url of the page which should be scraped
* @param bool $do_oembed The false option is used by the function fetch_oembed()
@@ -214,7 +221,7 @@ class ParseUrl
];
if ($count > 10) {
- Logger::notice('Endless loop detected', ['url' => $url]);
+ Logger::warning('Endless loop detected', ['url' => $url]);
return $siteinfo;
}
@@ -283,25 +290,13 @@ class ParseUrl
}
$charset = '';
- // Look for a charset, first in headers
- // Expected form: Content-Type: text/html; charset=ISO-8859-4
- if (preg_match('/charset=([a-z0-9-_.\/]+)/i', $curlResult->getContentType(), $matches)) {
- $charset = trim(trim(trim(array_pop($matches)), ';,'));
- }
-
- // Then in body that gets precedence
- // Expected forms:
- // -
- // -
- // -
- // -
- // We escape