feat: add guzzle-powered recursive website crawling and masterminds/html5 integration

This commit is contained in:
Enes Yakıştır
2026-06-06 13:22:35 +03:00
parent b805741ef2
commit c42ab714ff
5 changed files with 368 additions and 180 deletions
+4 -3
View File
@@ -28,9 +28,10 @@ class Scanner
return [];
}
$doc = new \DOMDocument();
// Suppress warnings for malformed HTML
@$doc->loadHTML('<?xml encoding="utf-8" ?>' . $html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
$html5 = new \Masterminds\HTML5([
'disable_html_ns' => true,
]);
$doc = $html5->loadHTML($html);
return $this->engine->run($doc);
}