Remove all HTML to plain text
This function removes all HTML and keeps the plain text and is an enhancement of PHP strip_tags() function by strip out styles, scripts, embedded objects, and other unwanted page code.
<?php
/**
* Remove HTML tags, including invisible text such as style and
* script code, and embedded objects. Add line breaks around
* block-level tags to prevent word joining after tag removal.
*/
function strip_html_tags( $text )
{
// Remove invisible content
$text = preg_replace(
array(
//ADD a (') before @<head ON NEXT LINE. Why? see below
'@<head[^>]*?>.*?</head>@siu',
'@<style[^>]*?>.*?</style>@siu',
'@<script[^>]*?.*?</script>@siu',
'@<object[^>]*?.*?</object>@siu',
'@<embed[^>]*?.*?</embed>@siu',
'@<applet[^>]*?.*?</applet>@siu',
'@<noframes[^>]*?.*?</noframes>@siu',
'@<noscript[^>]*?.*?</noscript>@siu',
'@<noembed[^>]*?.*?</noembed>@siu',
// Add line breaks before and after blocks
'@</?((address)|(blockquote)|(center)|(del))@iu',
'@</?((div)|(h[1-9])|(ins)|(isindex)|(p)|(pre))@iu',
'@</?((dir)|(dl)|(dt)|(dd)|(li)|(menu)|(ol)|(ul))@iu',
'@</?((table)|(th)|(td)|(caption))@iu',
'@</?((form)|(button)|(fieldset)|(legend)|(input))@iu',
'@</?((label)|(select)|(optgroup)|(option)|(textarea))@iu',
'@</?((frameset)|(frame)|(iframe))@iu',
),
array(
' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
"\n\$0", "\n\$0", "\n\$0", "\n\$0", "\n\$0", "\n\$0",
"\n\$0", "\n\$0",
),
$text );
return strip_tags( $text );
}
?>
Example
<?php
/* Read an HTML file */
$raw_text = file_get_contents( $filename );
/* Get the file's character encoding from a <meta> tag */
preg_match( '@<meta\s+http-equiv="Content-Type"\s+content="([\w/]+)(;\s+charset=([^\s"]+))?@i',
$raw_Text, $matches );
$encoding = $matches[3];
/* Convert to UTF-8 before doing anything else */
$utf8_text = iconv( $encoding, "utf-8", $raw_text );
/* Strip HTML tags and invisible text */
$utf8_text = strip_html_tags( $utf8_text );
/* Decode HTML entities */
$utf8_text = html_entity_decode( $utf8_text, ENT_QUOTES, "UTF-8" );
?>
Reference: http://nadeausoftware.com/articles/2007/09/php_tip_how_strip_html_tags_w...