Recently A List Apart had an article by Dean Frickey titled A More Useful 404. It was a good article about making a more useful 404 page that attempts to figure out what went wrong and it will email you some information. I modified the code from Perl to PHP for WordPress and figured I’d save people time from building it themselves by posting it here. Feel free to edit what you need to. The code goes inside your 404.php template.
<?php
//based on http://www.alistapart.com/articles/amoreuseful404
//just to break any email addresses or spam that might get spoofed in falsed headers, might just use a regex later
$disallowed_strings = array('@', '\t', '\r', '\n', '\v', '\f', '<', '>');
$clean_server_name = preg_replace('/[^a-zA-Z0-9\-\.]/', '', $_SERVER['SERVER_NAME']);
$clean_http_referer = str_ireplace($disallowed_strings, '', $_SERVER['HTTP_REFERER']);
$clean_request_uri = str_ireplace($disallowed_strings, '', $_SERVER['REQUEST_URI']);
$search_engine_domains = array('google.com', 'images.google.com', 'translate.google.com', 'yahoo.com', 'ask.com', 'live.com', 'aol.com', 'search.msn.com');//add more if you want
$search_message = '<p>You may want to try searching this site or using our <a href="' . get_bloginfo('url') . '/sitemap/">sitemap</a> to find what you were looking for.</p>';//if you have a sitemap
?>
<p>Sorry, but the page you were trying to get to <!–http:// ,–> does not exist.</p>
<?php
if ($_SERVER['HTTP_REFERER'] == '')
{
?>
<p>It looks like this was the result of either</p>
<ul>
<li>a mistyped address</li>
<li>or an out-of-date bookmark in your web browser.</li>
</ul>
<?php
echo $search_message;
}
else
{
//make it easier to search referer
$disallowed_url_strings = array('http://', 'https://', 'www.');//filter out https:// anyway
$referer = str_ireplace($disallowed_url_strings, '', $_SERVER['HTTP_REFERER']);
$referer_array = explode('/', $referer);
$referer = $referer_array[0];
$myblog_url = get_bloginfo('url');
$myblog_url = str_ireplace($disallowed_url_strings, '', $myblog_url);
$myblog_url_array = explode('/', $myblog_url);
$myblog_url = $myblog_url_array[0];
if ($referer == $myblog_url)
{
?>
<p>Apparently, we have a broken link on our page. An e-mail has just been sent to the person who can fix this and it should be corrected shortly. No further action is required on your part.</p>
<?php
$email_subject = 'Broken link on my site, ' . $clean_server_name;
$email_message = 'BROKEN LINK ON MY SITE' . "\r\n\r\n" . 'There appears to be a broken link on my page, ' . $clean_http_referer . " \r\n\r\n" . ' Someone was trying to get to ' . $clean_request_uri . ' from that page.';
$email_message .= "\r\n\r\n" . 'Why don\'t you take a look at it and see what\'s wrong?';
mail(get_bloginfo('admin_email'), $email_subject, $email_message, 'FROM: 404@example.com');
}
else
{
//see if it was a search engine
$domains_matched = 0;
$total_domains = count($search_engine_domains);
for ($x = 0; $x < $total_domains; $x++)
{
if ($referer == $search_engine_domains[$x])
$domains_matched++;
}
if ($domains_matched != 0)
{
?>
<p>It looks like the search engine has returned a link to an old page. These old links should eventually be removed from their indexes but since these are automatically generated there is no one to contact to try to correct the problem.</p>
<?php
echo $search_message;
}
else
{
?>
<p>Apparently, there is a broken link on the page you just came from. We have been notified and will attempt to contact the owner of that page and let them know about it.</p>
<?php
echo $search_message;
$email_subject = 'Broken link on somebody else\'s site.';
$email_message = 'BROKEN LINK ON SOMEBODY ELSE\'S SITE' . "\r\n\r\n" . 'There appears to be a broken link on the page, ' . $clean_http_referer . " \r\n\r\n" . ' Someone was trying to get to ' . $clean_request_uri . ' from that page.';
$email_message .= "\r\n\r\n" . 'Why don\'t you take a look at it and see if you can contact the page owner and let them know about it?';
mail(get_bloginfo('admin_email'), $email_subject, $email_message, 'FROM: 404@example.com');
}
}
}
?>
