set character encoding to utf-8 for parsing rendered-html

This commit is contained in:
Marek Bachmann 2022-12-07 18:50:16 +01:00
parent c8b43e688f
commit d590df9a72
1 changed files with 2 additions and 2 deletions

View File

@ -3143,9 +3143,9 @@ class Item
*/ */
private function cutAttachedImages($rendered_html) private function cutAttachedImages($rendered_html)
{ {
$doc = new DOMDocument(); $doc = new DOMDocument('1.0', 'UTF-8');
libxml_use_internal_errors(true); libxml_use_internal_errors(true);
$doc->loadHTML($rendered_html); $doc->loadHTML(mb_convert_encoding($rendered_html, 'html-entities', 'utf-8'));
libxml_clear_errors(); libxml_clear_errors();
$root = $doc->getElementsByTagName("p")[0]; $root = $doc->getElementsByTagName("p")[0];