<?php
// Using DOM to fix sloppy HTML.
// An example by Tyson Clugg <tyson@clugg.net>
//
// vim: syntax=php expandtab tabstop=2
function tidyHTML($buffer)
{
// load our document into a DOM object
$dom = @DOMDocument::loadHTML($buffer);
// we want nice output
$dom->formatOutput = true;
return($dom->saveHTML());
}
// start output buffering, using our nice
// callback funtion to format the output.
ob_start("tidyHTML");
?>
<html>
<p>It's like comparing apples to oranges.
</html>
<?php
// this will be called implicitly, but we'll
// call it manually to illustrate the point.
ob_end_flush();
?>
The above code takes out sloppy HTML:
<html>
<p>It's like comparing apples to oranges.
</html>
And cleans it up to the following:
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
<html><body><p>It's like comparing apples to oranges.
</p></body></html>