[SOLVED] Delete lines from htm file until body tag is found

rossh · June 28, 2008

Hi,

I've been working on a sanitize script to clean html files. I'm trying to figure out how to delete lines from the top of the file until the <body> tag is found. Any help would be appreciated.

R

<?php

$base_dir = 'c:\\xampp\\htdocs\\sanitize\\';

//CLEAN DATA HERE
$sanitize = array(
	' & ' => ' & ',
	'£' => '£',
	'Â£' => '£',
	'<b>' => '<strong>',
	'</b>' => '</strong>',
	'<i>' => '<em>',
	'</i>' => '</em>'
);

//Output the current directories content
function outputDir(){
	global $base_dir;
	$my_dir = $base_dir.$my_dir;
	$dir = opendir($my_dir) or die('Couldn\'t open directory, please contact the web administrator');

	while(($file = readdir($dir)) !== false){
		if($file != '.' && $file != '..'){
			$fname[] = $file;
		}
	}
	closedir($dir);

	foreach($fname as $file){
		if(!is_dir($file) && $file != 'sanitize.php'){
			$filenames .= $file.',';
		}
	}
	return $filenames = substr_replace($filenames ,'',-1);
}
//Read file, add title to anchor tags and output to new file
function sanitizeFile($file){
	global $base_dir, $sanitize;
	$lines = file($base_dir.$file);
	if(empty($lines)){
		echo 'File: '.$file.' empty!';
	}
	$new_lines = array();

	foreach ($lines as $line){		
		foreach($sanitize as $search => $replace){
			$line = str_replace($search, $replace, $line);
		}
		array_push ($new_lines, $line);
	}
	$content = implode('', $new_lines);
	$fp = fopen ($base_dir.'sanitized\\'.$file, w);
	fwrite ($fp, $content);
	fclose ($fp);
}
//Get filenames and sanitize
if(isset($_POST['submit'])){
	$filenames = outputDir();
	$filenames = explode(',', $filenames);

	$response .= '<ul>'."\n";
	foreach($filenames as $file){
		sanitizeFile($file);
		$response .= '<li>Sanitized: '.$file.'</li>'."\n";
	}
	$response .= '</ul>'."\n";
}
?>

<p>Base Directory: <?php echo $base_dir; ?></p>

<form name="sanitize_data" action="<?php echo $_SERVER['PHP_SELF']; ?>" method="post">
<input type="submit" name="submit" value="Sanitize!" id="submit" />
</form>

<?php echo $response; ?>

Sulman · June 28, 2008

Here is one way you could do it:

<?php
$unsanitesedHTMLstring;//use fopen & freads to get the html page in to a string

$bits=explode("<body>", $unsanitesedHTMLstring); //explode on body to leave 2 bits
$sanitisedHTMLstring="<body>".$bits[1]; //get the final string and add the body tag

?>

The script would need tidying and error checking etc (for instance if the page has a body onload event you would need to alter it slightly)

rossh · June 28, 2008

I figured it out.

<?php
$base_dir = 'c:\\xampp\\htdocs\\work\\sanitize\\';

//CLEAN DATA HERE
$sanitize = array(
	' & ' => ' & ',
	'£' => '£',
	'Â£' => '£',
	'<b>' => '<strong>',
	'</b>' => '</strong>',
	'<i>' => '<em>',
	'</i>' => '</em>'
);

//Output the current directories content
function outputDir(){
	global $base_dir;
	$my_dir = $base_dir.$my_dir;
	$dir = opendir($my_dir) or die('Couldn\'t open directory, please contact the web administrator');

	while(($file = readdir($dir)) !== false){
		if($file != '.' && $file != '..'){
			$fname[] = $file;
		}
	}
	closedir($dir);

	foreach($fname as $file){
		if(!is_dir($file) && $file != 'sanitize.php'){
			$filenames .= $file.',';
		}
	}
	return $filenames = substr_replace($filenames ,'',-1);
}
//Read file, add title to anchor tags and output to new file
function sanitizeFile($file){
	global $base_dir, $sanitize;		
	$lines = file($base_dir.$file);
	if(empty($lines)){
		echo 'File: '.$file.' empty!';
	}
	$new_lines = array();

	foreach($lines as $line_num => $line){
		if($found = strpos($line, 'body') == TRUE){
			echo $body_tag_line = $line_num;
		}
		/*CLEAN DATA HERE*/
		$line = preg_replace('/<a[^>]*?href=[\'"](.*?)[\'"][^>]*?>(.*?)<\/a>/si','<a href="$1" title="$2">$2</a>',$line); //Add titles to anchor tags
		foreach($sanitize as $search => $replace){
			$line = str_replace($search, $replace, $line);
		}
		array_push ($new_lines, $line);
	}
	for($i=1;$i<$body_tag_line;$i++){ //
		unset($new_lines[$i]);
	}
	$content = implode('', $new_lines);
	$fp = fopen ($base_dir.'sanitized\\'.$file, w);
	fwrite ($fp, $content);
	fclose ($fp);
}
//Get filenames and sanitize
if(isset($_POST['submit'])){
	$filenames = outputDir();
	$filenames = explode(',', $filenames);

	$response .= '<ul>'."\n";
	foreach($filenames as $file){
		sanitizeFile($file);
		$response .= '<li>Sanitized: '.$file.'</li>'."\n";
	}
	$response .= '</ul>'."\n";
}
?>

<p>Base Directory: <?php echo $base_dir; ?></p>

<form name="sanitize_data" action="<?php echo $_SERVER['PHP_SELF']; ?>" method="post">
<input type="submit" name="submit" value="Sanitize!" id="submit" />
</form>

<?php echo $response; ?>

Sign In

[SOLVED] Delete lines from htm file until body tag is found

Recommended Posts

rossh

Link to comment

Share on other sites

Sulman

Link to comment

Share on other sites

rossh

Link to comment

Share on other sites

Join the conversation

Browse

Activity

Important Information