Do not remove html tag attributes

They might contains useful information (at least language)
pull/10/head v1.0.8
Jeremy Benoist 11 years ago
parent 255a2fc7bc
commit f71c3a4196
  1. 1
      src/Readability.php

@ -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);

Loading…
Cancel
Save