/**
* Do we think the current user is a spider?
*
* @package SearchEngines
* @return int
*/
function spiderCheck()
{
global $modSettings;
$db = database();
if (isset($_SESSION['id_robot'])) {
unset($_SESSION['id_robot']);
}
$_SESSION['robot_check'] = time();
// We cache the spider data for five minutes if we can.
if (($spider_data = cache_get_data('spider_search', 300)) === null) {
$request = $db->query('', '
SELECT id_spider, user_agent, ip_info
FROM {db_prefix}spiders
ORDER BY LENGTH(user_agent) DESC', array());
$spider_data = array();
while ($row = $db->fetch_assoc($request)) {
$spider_data[] = $row;
}
$db->free_result($request);
// Save it in the cache
cache_put_data('spider_search', $spider_data, 300);
}
if (empty($spider_data)) {
return false;
}
// We need the user agent
$req = request();
// Always attempt IPv6 first.
if (strpos($_SERVER['REMOTE_ADDR'], ':') !== false) {
$ip_parts = convertIPv6toInts($_SERVER['REMOTE_ADDR']);
} else {
preg_match('/^(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})$/', $_SERVER['REMOTE_ADDR'], $ip_parts);
}
foreach ($spider_data as $spider) {
// User agent is easy.
if (!empty($spider['user_agent']) && strpos(strtolower($req->user_agent()), strtolower($spider['user_agent'])) !== false) {
$_SESSION['id_robot'] = $spider['id_spider'];
} elseif (!empty($ip_parts)) {
$ips = explode(',', $spider['ip_info']);
foreach ($ips as $ip) {
$ip = ip2range($ip);
if (!empty($ip)) {
foreach ($ip as $key => $value) {
if ($value['low'] > $ip_parts[$key + 1] || $value['high'] < $ip_parts[$key + 1]) {
break;
} elseif ($key == 7 && strpos($_SERVER['REMOTE_ADDR'], ':') !== false || $key == 3 && strpos($_SERVER['REMOTE_ADDR'], ':') === false) {
$_SESSION['id_robot'] = $spider['id_spider'];
}
}
}
}
}
if (isset($_SESSION['id_robot'])) {
break;
}
}
// If this is low server tracking then log the spider here as oppossed to the main logging function.
if (!empty($modSettings['spider_mode']) && $modSettings['spider_mode'] == 1 && !empty($_SESSION['id_robot'])) {
logSpider();
}
return !empty($_SESSION['id_robot']) ? $_SESSION['id_robot'] : 0;
}
/**
* Do we think the current user is a spider?
*
* @todo Should this not be... you know... in a different file?
* @return int
*/
function SpiderCheck()
{
global $modSettings;
if (isset($_SESSION['id_robot'])) {
unset($_SESSION['id_robot']);
}
$_SESSION['robot_check'] = time();
// We cache the spider data for five minutes if we can.
if (($spider_data = CacheAPI::getCache('spider_search', 300)) === null) {
$request = smf_db_query('
SELECT id_spider, user_agent, ip_info
FROM {db_prefix}spiders', array());
$spider_data = array();
while ($row = mysql_fetch_assoc($request)) {
$spider_data[] = $row;
}
mysql_free_result($request);
CacheAPI::putCache('spider_search', $spider_data, 300);
}
if (empty($spider_data)) {
return false;
}
// Only do these bits once.
$ci_user_agent = strtolower($_SERVER['HTTP_USER_AGENT']);
// Always attempt IPv6 first.
if (strpos($_SERVER['REMOTE_ADDR'], ':') !== false) {
$ip_parts = convertIPv6toInts($_SERVER['REMOTE_ADDR']);
} else {
preg_match('/^(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})$/', $_SERVER['REMOTE_ADDR'], $ip_parts);
}
foreach ($spider_data as $spider) {
// User agent is easy.
if (!empty($spider['user_agent']) && strpos($ci_user_agent, strtolower($spider['user_agent'])) !== false) {
$_SESSION['id_robot'] = $spider['id_spider'];
} elseif (!empty($ip_parts)) {
$ips = explode(',', $spider['ip_info']);
foreach ($ips as $ip) {
$ip = ip2range($ip);
if (!empty($ip)) {
foreach ($ip as $key => $value) {
if ($value['low'] > $ip_parts[$key + 1] || $value['high'] < $ip_parts[$key + 1]) {
break;
} elseif ($key == 7 && strpos($_SERVER['REMOTE_ADDR'], ':') !== false || $key == 3 && strpos($_SERVER['REMOTE_ADDR'], ':') === false) {
$_SESSION['id_robot'] = $spider['id_spider'];
}
}
}
}
}
if (isset($_SESSION['id_robot'])) {
break;
}
}
// If this is low server tracking then log the spider here as oppossed to the main logging function.
if (!empty($modSettings['spider_mode']) && $modSettings['spider_mode'] == 1 && !empty($_SESSION['id_robot'])) {
logSpider();
}
return !empty($_SESSION['id_robot']) ? $_SESSION['id_robot'] : 0;
}
/**
* Another helper function that put together the
* @param string $fullip An IP address either IPv6 or not
* @return string A SQL condition
*/
function constructBanQueryIP($fullip)
{
// First attempt a IPv6 address.
if (isValidIPv6($fullip)) {
$ip_parts = convertIPv6toInts($fullip);
$ban_query = '((' . $ip_parts[0] . ' BETWEEN bi.ip_low1 AND bi.ip_high1)
AND (' . $ip_parts[1] . ' BETWEEN bi.ip_low2 AND bi.ip_high2)
AND (' . $ip_parts[2] . ' BETWEEN bi.ip_low3 AND bi.ip_high3)
AND (' . $ip_parts[3] . ' BETWEEN bi.ip_low4 AND bi.ip_high4)
AND (' . $ip_parts[4] . ' BETWEEN bi.ip_low5 AND bi.ip_high5)
AND (' . $ip_parts[5] . ' BETWEEN bi.ip_low6 AND bi.ip_high6)
AND (' . $ip_parts[6] . ' BETWEEN bi.ip_low7 AND bi.ip_high7)
AND (' . $ip_parts[7] . ' BETWEEN bi.ip_low8 AND bi.ip_high8))';
} elseif (preg_match('/^(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})$/', $fullip, $ip_parts) == 1) {
$ban_query = '((' . $ip_parts[1] . ' BETWEEN bi.ip_low1 AND bi.ip_high1)
AND (' . $ip_parts[2] . ' BETWEEN bi.ip_low2 AND bi.ip_high2)
AND (' . $ip_parts[3] . ' BETWEEN bi.ip_low3 AND bi.ip_high3)
AND (' . $ip_parts[4] . ' BETWEEN bi.ip_low4 AND bi.ip_high4))';
} else {
$ban_query = '(bi.ip_low1 = 255 AND bi.ip_high1 = 255
AND bi.ip_low2 = 255 AND bi.ip_high2 = 255
AND bi.ip_low3 = 255 AND bi.ip_high3 = 255
AND bi.ip_low4 = 255 AND bi.ip_high4 = 255)';
}
return $ban_query;
}