Strip mw:PageProp meta tags

These have no purpose in epubs and cause validation failures. Bug: T287548
wikimedia · Nov 8, 2021 · 95892c0 · 95892c0
1 parent 0a56e74
commit 95892c0
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/src/PageParser.php b/src/PageParser.php
@@ -273,6 +273,8 @@ public function getContent( $isMainPage ) {
 		$this->removeNodesWithXpath( '//a[@class="mw-headline-anchor"]' );
 		$this->removeNodesWithXpath( '//div[@class="mediaContainer"]' );
 		$this->removeNodesWithXpath( '//link[@rel="mw:PageProp/Category"]' );
+		// Remove meta tags such as <meta property="mw:PageProp/disambiguation" about="#mwt1" />
+		$this->removeNodesWithXpath( '//meta[starts-with(@property, "mw:PageProp/")]' );
 		$this->removeNodesWithXpath( '//link[contains(@typeof, "mw:Extension")]' );
 		$this->deprecatedNodes( 'big', 'span', 'font-size:large;' );
 		$this->deprecatedNodes( 'center', 'div', 'text-align:center;' );