Convert HTML to Plain Text without tags in PHP

Use for text editor like TinyMce content. Remove html tags from string, best use for META tags.

function stripAlpha($item)

{

  $search = array(
    '@&lt;script[^&gt;]*?&gt;.*?&lt;/script&gt;@si' // Strip out javascript 
    , '@&lt;style[^&gt;]*?&gt;.*?&lt;/style&gt;@siU' // Strip style tags properly 
    , '@&lt;[\/\!]*?[^&lt;&gt;]*?&gt;@si' // Strip out HTML tags
    , '@&lt;![\s\S]*?–[ \t\n\r]*&gt;@' // Strip multi-line comments including CDATA
    , '/\s{2,}/', '/(\s){2,}/'

  );

  $pattern = array(

    '#[^a-zA-Z ]#' // Non alpha characters
    , '/\s+/' // More than one whitespace

  );

  $replace = array(
    '', ' '

  );

  $item = preg_replace($search, '', html_entity_decode($item));
  $item = trim(preg_replace($pattern, $replace, strip_tags($item)));
  return $item;

}

function stripAlpha($item)

{

$search = array(

'@<script[^>]*?>.*?</script>@si' // Strip out javascript

, '@<style[^>]*?>.*?</style>@siU' // Strip style tags properly

, '@<[\/\!]*?[^<>]*?>@si' // Strip out HTML tags

, '@<![\s\S]*?–[ \t\n\r]*>@' // Strip multi-line comments including CDATA

, '/\s{2,}/', '/(\s){2,}/'

);

$pattern = array(

'#[^a-zA-Z ]#' // Non alpha characters

, '/\s+/' // More than one whitespace

);

$replace = array(

'', ' '

);

$item = preg_replace($search, '', html_entity_decode($item));

$item = trim(preg_replace($pattern, $replace, strip_tags($item)));

return $item;

}

Useful for Meta Tag description etd

Leave a Reply Cancel reply