<?php
// Web Page Expiry Checker
// A script to automatically email web page content owners (at most
// once per day) to remind them when their web pages have reached/
// exceeded their expiry dates, and to email webmasters when pages
// have expired over a month ago (the latter limited to one email
// per month max).
// Author = Martin Bush, South Bank University [bushm@sbu.ac.uk]
// Date = 3 March 2003
// Filename = expirychecker.php3
// Version = 1.6
// Changes with respect to version 1.5 =
// This version checks the url of the expired page to
// ensure that it is within the SBU domain to prevent
// activation by copies of the expired page that have
// been archived by search engines, or by some other
// (possibly rogue) page on the Internet. Also, the
// reminder email message now warns of the possibility
// that the message may by due to a cached old version
// of the page being viewed after the live version has
// been updated.
// INSTALLATION INSTRUCTIONS:
// To install, put this script into the cgi-bin directory and edit
// the contents of the two email messages ($mail_message1 and
// $mail_message2) and the email address of the webmaster as
// appropriate. (See bottom of this script.) If you have created
// a new cgi-bin directory in which to put this script, remember to
// type the "wwwset" command to enable the script to be executed.
//
// Once installed, this script can be called from any web page by
// including the following (with "???" replaced by the appropriate
// userid) anywhere within the body of the web page:
//
// <!-- Insert values below for "owner", "expirydate" -->
// <!-- and "message" to activate the Expiry Checker. -->
// <img width="1" height="1" border="0" alt=""
// src="http://www.sbu.ac.uk/php-cgiwrap/???/expirychecker.php3?
// owner=email@ddress
// &
// expirydate=dd/mm/yy
// &
// message=a line of free text - no quotation marks please!
// ">
//
// Note that this will insert a one pixel image into the web page.
// This seems to be imperceptible with modern browsers, but a small
// dot is displayed when using both Netscape 4 and IE 4 on a Mac
// (at least). Not only that, but depending on where it is placed it
// can also cause a blank line to appear, in which case it really
// does have quite a noticeable effect. For example it'll cause a
// blank line if it's placed inbetween two tables. Ideally, it
// should be inserted immediately before or after some text so that
// it will just cause a small dot to be displayed in those browsers.
//
// If the value for the expiry date is left as the literal character
// string "dd/mm/yy" this shouldn't cause a problem, and no expiry
// reminder emails will be sent. The script will accept dd/mm/yy
// dates containing single digits - e.g. either 15/6/03 or 15/06/03
// would be processed correctly.
//
// The Expiry Checker creates/maintains the following two "expiry
// reminders sent" files within the cgi-bin directory:
// expiryrems_sent_today.txt
// expiryrems_sent_yesterday.txt
// The second file is for information only.
// parse query_string to get $owner, $expirydate and $message
parse_str($QUERY_STRING);
// discover url of referrer
$url = $GLOBALS["HTTP_REFERER"];
// if (url is within the SBU domain) then
if (eregi("www.sbu.ac.uk", $url)) {
// one level of indentation deliberately skipped here!
//get today's date in dd/mm/yy format
$today = date("d/m/y");
// convert to yymmdd format - e.g. 24/08/02 becomes 020824
// *** end-of-century bug - will fail in the year 2100! ***
$today_day = substr($today,-8,2);
$today_month = substr($today,-5,2);
$today_year = substr($today,-2,2);
$today_yymmdd = $today_year.$today_month.$today_day;
// convert expiry date to yymmdd format
// handles dd/mm/yy dates including single digits for dd, mm, yy
// - e.g. 06/06/03, 6/6/03, 06/6/03, 6/06/03, 06/06/3 etc.
$position_of_first_slash = strpos($expirydate, "/");
$expiry_day = substr($expirydate, 0, $position_of_first_slash);
$expiry_mm_yy = substr($expirydate, $position_of_first_slash + 1,
strlen($expirydate));
$position_of_second_slash = strpos($expiry_mm_yy, "/");
$expiry_month = substr($expiry_mm_yy, 0, $position_of_second_slash);
$expiry_year = substr($expiry_mm_yy, $position_of_second_slash + 1,
strlen($expirydate));
// if any of dd, mm or yy are single digits then add a leading zero
if ( strlen($expiry_day) == 1) { $expiry_day = "0".$expiry_day; }
if ( strlen($expiry_month) == 1) { $expiry_month = "0".$expiry_month; }
if ( strlen($expiry_year) == 1) { $expiry_year = "0".$expiry_year; }
$expiry_yymmdd = $expiry_year.$expiry_month.$expiry_day;
// if (web page content has expired) then
if ( $expiry_yymmdd <= $today_yymmdd ) {
// if (expiryrems_sent_today.txt doesn't exist) then
$reminders_file = "expiryrems_sent_today.txt";
if (!(file_exists($reminders_file))) {
// create new reminders file containing date plus first
// reminder entry, and make a note to send an email.
//
// create and open reminders file - "r+" for read/write
touch ($reminders_file);
$reminders_fp = fopen($reminders_file, "r+");
// lock reminders file - "2" for exclusive writing lock
$lock = flock($reminders_fp, 2);
// continue when lock is obtained
if ($lock) {
// write today's date
fwrite($reminders_fp, "$today\n");
// prepare new reminder entry
$new_reminder = "_url=".$url."&_exp=".$expirydate.
"&_own=".$owner."&_mes=".$message;
// insert new reminder entry
fwrite($reminders_fp, ("$new_reminder\n"));
$email_needed = 1;
// unlock and close reminders file - "3" is for unlock
}
$lock = flock($reminders_fp, 3);
fclose($reminders_fp);
} else { // expiryrems_sent_today.txt already exists
// assume that an email won't be necessary
$email_needed = 0;
// open and lock reminders file
$reminders_fp = fopen($reminders_file, "r+");
$lock = flock($reminders_fp, 2);
// continue when lock is obtained
if ($lock) {
// read $date_of_file\n and convert to yymmdd format
$date_of_file = fgets($reminders_fp, 256);
$filedate_day = substr($date_of_file,-9,2);
$filedate_month = substr($date_of_file,-6,2);
$filedate_year = substr($date_of_file,-3,2);
$filedate_yymmdd = $filedate_year.$filedate_month.
$filedate_day;
// if (filedate is older than today's date) then
if ( $filedate_yymmdd < $today_yymmdd ) {
// rename reminders file to yesterday's reminders file
rename($reminders_file, "expiryrems_sent_yesterday.txt");
// create, open and lock a fresh reminders file
// ***Note - another process could potentially...
// ...intervene here, but as this isn't a...
// ...safety-critical system I'm ignoring it!***
touch ($reminders_file);
$reminders_fp = fopen($reminders_file, "r+");
$lock = flock($reminders_fp, 2);
if ($lock) {
// write today's date plus new reminder entry
fwrite($reminders_fp, "$today\n");
$new_reminder = "_url=".$url."&_exp=".$expirydate
."&_own=".$owner."&_mes=".$message;
fwrite($reminders_fp, "$new_reminder\n");
// make a note to send an email
$email_needed = 1;
// (unlocking & closing reminders file happens later)
}
} else { // ($date_of_file = today's date)
// start accumulating file contents
$file_contents_so_far = $today."\n";
// parse first entry to get $_url, $_exp, $_own, $_mes
$next_entry = fgets($reminders_fp, 256);
parse_str($next_entry);
// if (first $_url is >= $url) then don't search
if ($_url >= $url) {
$need_next_entry = 0;
} else { // else search is needed
$need_next_entry = 1;
// accumulate file contents
$file_contents_so_far = $file_contents_so_far.
$next_entry;
} // endif
// while ($need_next_entry) search for url in file
while ($need_next_entry == 1) {
// get and parse next entry
$next_entry = fgets($reminders_fp, 256);
// if (next entry was blank) then stop searchng
if (strlen($next_entry) < 2) {
$need_next_entry = 0;
} else {
parse_str($next_entry); // parse to get $_url
if ($_url >= $url) { // found or searched too far
$need_next_entry = 0;
} else { // accumulate and keep searching
$file_contents_so_far = $file_contents_so_far
.$next_entry;
} // endif
} // endif
} // endwhile
// if ($url not found in file) then insert into file
if ($_url != $url) {
// store contents of file after point of insertion
$file_contents_after = $next_entry.
fread($reminders_fp,filesize($reminders_file));
// rewind the file
rewind($reminders_fp);
// write accumulate entries up to point of insertion
fwrite($reminders_fp, "$file_contents_so_far");
// prepare new reminder entry
$new_reminder = "_url=".$url."&_exp=".$expirydate.
"&_own=".$owner."&_mes=".$message;
// insert new reminder entry
fwrite($reminders_fp, "$new_reminder\n");
// write remaining contents
fwrite($reminders_fp, "$file_contents_after");
// make a note to send an email
$email_needed = 1;
} // endif ($url not found in file)
} // endif (filedate is older than today's date)
} // unlock and close reminders file
$lock = flock($reminders_fp, 3);
fclose($reminders_fp);
} // endif (reminders file doesn't exist)
// email url and message to owner if necessary
if ($email_needed == 1) {
$mail_message1 = "This is to remind you that this web page...
\n $url
\n...expired on $expirydate. Here is the reminder message (if any):
\n*** $message ***
\nYou will receive a reminder each day that this page is hit.
Please update the page as necessary, and remember to specify a new
expiry date.
Please note that it is possible for email reminder messages to be
sent for several days after the page has been updated - this will
happen if cached old versions of the page are viewed.";
mail($owner, "Expiry Checker: $url", $mail_message1);
}
// email webmaster if page has expired over a month ago, but limit
// these emails to one a month max. If the expiry date is the nth
// day of a certain month, then an email will be sent on the nth
// day of every subsequent month (assuming page hits on those days).
if ($email_needed == 1) {
if ((($today_month - $expiry_month) > 0) ||
(($today_year - $expiry_year) > 0)) {
if ($expiry_day == $today_day) {
$mail_message2 = "According to the Expiry Checker,
this web page...
\n$url
\n...has exceeded its expiry date by at least a month. The
expiry date is: $expirydate. The email address of the owner
is: $owner.";
mail("webmaster@wherever", "Expiry Checker - outdated page
alert - $url",
$mail_message2);
}
}
}
} // endif (web page had not expired)
} // endif (web page url was not within SBU domain)
?>
|