Created
April 22, 2014 17:42
-
-
Save moertel/11188079 to your computer and use it in GitHub Desktop.
decode google click id
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
function gclid_decode($gclid, $splitTimestamp = true) | |
{ | |
// Copyright 2013 Deed Poll Office Ltd, UK <https://deedpolloffice.com> | |
// Licensed under Apache Licence v2.0 <http://apache.org/licenses/LICENSE-2.0> | |
// http://blog.deedpolloffice.com/articles/decoding-gclid-parameter | |
preg_match_all('/ | |
(?=[\x5\xd\x15\x1d%\-5=EMU\]emu}\x85\x8d\x95\x9d\xa5\xad\xb5\xbd\xc5\xcd\xd5 | |
\xdd\xe5\xed\xf5\xfd]) # 32-bit wire type | |
([\x80-\xff]*[\0-\x7f])(.{4}) | | |
([\x80-\xff]*[\0-\x7f])([\x80-\xff]*[\0-\x7f]) # default to varint wire type | |
/sx', | |
base64_decode(str_replace(array('_','-'), array('+','/'), $gclid)), | |
$matches, | |
PREG_SET_ORDER); | |
$ret = array(); | |
foreach ($matches as $m) { | |
$key = $val = 0; | |
foreach (str_split($m[1] ? $m[1] : $m[3]) as $i => $c) | |
$key += (ord($c) & 0x7f) << $i * 7; | |
if ($m[1]) { // 32-bit (probably) unsigned int (not supported by PHP) | |
foreach (str_split($m[2]) as $i => $c) { | |
$val = PHP_INT_SIZE < 5 && function_exists('bcadd') ? | |
bcadd($val, bcmul(ord($c), bcpow(2, $i * 8))) : | |
$val + (ord($c) * pow(2, $i * 8)); | |
} | |
} else { | |
foreach (str_split($m[4]) as $i => $c) { | |
$val = PHP_INT_SIZE < 8 && function_exists('bcadd') ? | |
bcadd($val, bcmul(ord($c) & 0x7f, bcpow(2, $i * 7))) : | |
$val + ((ord($c) & 0x7f) * pow(2, $i * 7)); | |
} | |
} | |
$ret[$key >> 3] = $val; | |
} | |
if ($splitTimestamp) $ret[1] = array( // Split into seconds / microseconds | |
(int) floor($ret[1] / 1000000), | |
is_int($ret[1]) ? $ret[1] % 1000000 : | |
(is_string($ret[1]) ? bcmod($ret[1], 1000000) : null), | |
); | |
return $ret; | |
} | |
print_r(gclid_decode('CMSIupnOu7cCFYeS3godDCsArAn')); | |
?> |
there are currently 3 different kinds of gclid. after decoded from base64/web the resulting byte arrays define the type of the GCLID at offset 0:
- 0x08 (index 1, type varint): the old gclid type, with the microsecond-timestamp at offset 1
- 0x10 (index 2, type varint): a version that has the message of the old GCLID in a sub-sub-message - the old message starts at offset 8 (also starting with 0x08), the timestamp is at offset 9
- 0x0A (index 1, type string) a version with seconds-since-epoch (only containing the date at PST midnight) - the timestamp starts at offset 5
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
No problem at all!
I never did figure it out, but maybe someone will at some point!
Thanks for the reply!