Keep h1 and other headings

Even though using h1 tags for sections inside an article is semantically wrong, a lot of websites are doing it anyway. So the idea here is to stop stripping headings, including h1 on Readability's side. Fixes wallabag/wallabag#5805 Signed-off-by: Kevin Decherf <[email protected]>
j0k3r · Jun 11, 2022 · ada8ff0 · ada8ff0
1 parent c506b7e
commit ada8ff0
Showing 1 changed file with 0 additions and 12 deletions.
diff --git a/src/Readability.php b/src/Readability.php
@@ -427,18 +427,6 @@ public function prepArticle(\DOMNode $articleContent)
         $this->clean($articleContent, 'object');
         $this->clean($articleContent, 'iframe');
         $this->clean($articleContent, 'canvas');
-        $this->clean($articleContent, 'h1');
-
-        /*
-         * If there is only one h2, they are probably using it as a main header, so remove it since we
-         *  already have a header.
-         */
-        $h2s = $articleContent->getElementsByTagName('h2');
-        if (1 === $h2s->length && mb_strlen($this->getInnerText($h2s->item(0), true, true)) < 100) {
-            $this->clean($articleContent, 'h2');
-        }
-
-        $this->cleanHeaders($articleContent);
 
         // Do these last as the previous stuff may have removed junk that will affect these.
         $this->cleanConditionally($articleContent, 'form');