Do not remove html tag attributes

They might contains useful information (at least language)
This commit is contained in:
Jeremy Benoist
2015-09-23 21:09:38 +02:00
parent 255a2fc7bc
commit f71c3a4196
-1
View File
@@ -186,7 +186,6 @@ class Readability
$this->original_html = $html;
$this->tidied = true;
$html = $tidy->value;
$html = preg_replace('/<html[^>]+>/i', '<html>', $html);
$html = preg_replace('/[\r\n]+/is', "\n", $html);
}
unset($tidy);