}
/**
- * Escape script tags within HTML content.
+ * Create and load a DOMDocument from the given html content.
*/
- protected function escapeScripts(string $html) : string
+ protected function loadDocumentFromHtml(string $html): DOMDocument
{
- if (empty($html)) {
- return $html;
- }
-
libxml_use_internal_errors(true);
$doc = new DOMDocument();
+ $html = '<body>' . $html . '</body>';
$doc->loadHTML(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'));
- $xPath = new DOMXPath($doc);
-
- // Remove standard script tags
- $scriptElems = $xPath->query('//script');
- foreach ($scriptElems as $scriptElem) {
- $scriptElem->parentNode->removeChild($scriptElem);
- }
-
- // Remove clickable links to JavaScript URI
- $badLinks = $xPath->query('//*[contains(@href, \'javascript:\')]');
- foreach ($badLinks as $badLink) {
- $badLink->parentNode->removeChild($badLink);
- }
-
- // Remove forms with calls to JavaScript URI
- $badForms = $xPath->query('//*[contains(@action, \'javascript:\')] | //*[contains(@formaction, \'javascript:\')]');
- foreach ($badForms as $badForm) {
- $badForm->parentNode->removeChild($badForm);
- }
-
- // Remove meta tag to prevent external redirects
- $metaTags = $xPath->query('//meta[contains(@content, \'url\')]');
- foreach ($metaTags as $metaTag) {
- $metaTag->parentNode->removeChild($metaTag);
- }
-
- // Remove data or JavaScript iFrames
- $badIframes = $xPath->query('//*[contains(@src, \'data:\')] | //*[contains(@src, \'javascript:\')] | //*[@srcdoc]');
- foreach ($badIframes as $badIframe) {
- $badIframe->parentNode->removeChild($badIframe);
- }
-
- // Remove 'on*' attributes
- $onAttributes = $xPath->query('//@*[starts-with(name(), \'on\')]');
- foreach ($onAttributes as $attr) {
- /** @var \DOMAttr $attr*/
- $attrName = $attr->nodeName;
- $attr->parentNode->removeAttribute($attrName);
- }
-
- $html = '';
- $topElems = $doc->documentElement->childNodes->item(0)->childNodes;
- foreach ($topElems as $child) {
- $html .= $doc->saveHTML($child);
- }
-
- return $html;
+ return $doc;
}
+
+ /**
+ * Retrieve first image in page content and return the source URL.
+ */
+ public function fetchFirstImage()
+ {
+ $htmlContent = $this->page->html;
+
+ $dom = new \DomDocument();
+ $dom->loadHTML($htmlContent);
+ $images = $dom->getElementsByTagName('img');
+
+ return $images->length > 0 ? $images[0]->getAttribute('src') : null;
+ }
}
projects / bookstack / commitdiff