If you want to see the last cache of a webpage indexed by Google, you can make a search on Google with this string:
cache:domeniu.tld/the_page_address
Or, directly in the address bar of your browser, access this url:
http://webcache.googleusercontent.com/search?q=cache:the_page_address
- "the_page_address" - is the URL of the page, without http:// .
The example bellow contains a function ( googleCache() ) that returns an array with 2 elements:
- "pg_cache" - contains the HTML code of the page in cache (without the additional code added by Google).
- "dt_cache" - the date and time of last cache.
Also, you can separate the <head> and <body> of the page added in cache. For more details, see the comments in code.
<?php
/* $pg is the URL address of your page (without http://)
returns an array with 2 elements:
- 'dt_cache' = date and time of last cache
- 'pg_cache' = HTML code of the page in cache
*/
function googleCache($pg) {
// get datetime of last google cache ( https://coursesweb.net/ )
$re = array('dt_cache'=>'', 'pg_cache'=>'');
// gets the page from Google
$page = file_get_contents('http://webcache.googleusercontent.com/search?q=cache:'.$pg);
// extract the date/time of the cache
if(preg_match('/snapshot of the page as it appeared on ([a-z0-9 :]+) GMT/i', $page, $mdc)) {
$re['dt_cache'] = 'Date-time of the last cache: '. $mdc[1];
}
// extract the HTML code of the page in cache
if(preg_match('#\<div style="position:relative"\>([\s\S]+)#i', $page, $mpc)) {
$re['pg_cache'] = $mpc[1];
}
return $re;
}
// Test
$pg = 'coursesweb.net/html/'; // URL address of page (without http://)
$g_cache = googleCache($pg); // get the array with 'dt_cache' and 'pg_cache'
echo $g_cache['dt_cache'];
// if you want to output the page
// echo $g_cache['pg_cache'];
/* the following instructions store in:
$head_cache - the HTML <head> of the page in cache
$body_cache - the HTML code added in the <body> of the page in cache
*/
if(preg_match('#\<head\>([\s\S]+)\</head\>#i', $g_cache['pg_cache'], $mh)) $head_cache = $mh[1];
if(preg_match('#\<body([^\>]*)\>([\s\S]+)\</body\>#i', $g_cache['pg_cache'], $mb)) $body_cache = $mb[2];
?>