mirror of
https://github.com/j0k3r/php-readability.git
synced 2026-09-27 06:26:17 +00:00
Do not remove html tag attributes
They might contains useful information (at least language)
This commit is contained in:
@@ -186,7 +186,6 @@ class Readability
|
|||||||
$this->original_html = $html;
|
$this->original_html = $html;
|
||||||
$this->tidied = true;
|
$this->tidied = true;
|
||||||
$html = $tidy->value;
|
$html = $tidy->value;
|
||||||
$html = preg_replace('/<html[^>]+>/i', '<html>', $html);
|
|
||||||
$html = preg_replace('/[\r\n]+/is', "\n", $html);
|
$html = preg_replace('/[\r\n]+/is', "\n", $html);
|
||||||
}
|
}
|
||||||
unset($tidy);
|
unset($tidy);
|
||||||
|
|||||||
Reference in New Issue
Block a user