From 5dea3734ddd13dc3cea55e58c3196353b1b2b9f7 Mon Sep 17 00:00:00 2001 From: quenousimporte Date: Thu, 30 May 2024 09:12:23 +0200 Subject: [PATCH] mediapart: simplify content --- mediapart.php | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/mediapart.php b/mediapart.php index 964f8b0..afc4520 100644 --- a/mediapart.php +++ b/mediapart.php @@ -51,10 +51,21 @@ foreach ($items as $item) $doc->loadHTML($article); $finder = new DomXPath($doc); - $svgs = $finder->query('//svg'); - foreach ($svgs as $svg) + // strip images + $toremove = $finder->query('//svg'); + foreach ($toremove as $elt) { - $svg->parentNode->removeChild($svg); + $elt->parentNode->removeChild($elt); + } + $toremove = $finder->query('//figure'); + foreach ($toremove as $elt) + { + $elt->parentNode->removeChild($elt); + } + $toremove = $finder->query('//span[@class="screen-reader-only"]'); + foreach ($toremove as $elt) + { + $elt->parentNode->removeChild($elt); } $result = '

' . $title . '

'; @@ -84,7 +95,7 @@ foreach ($items as $item) $outerHTML = $node->ownerDocument->saveHTML($node); $textcontent = $node->textContent; - $result .= '
' . $innerHTML . '
'; + $result .= '
' . strip_tags($innerHTML, '

') . '

'; $epub->AddPage($result, false, $title); }