Blockbot: Avoid false positives #849
1 changed files with 41 additions and 13 deletions
|
@ -27,23 +27,51 @@ function blockbot_uninstall() {
|
||||||
function blockbot_init_1(App $a) {
|
function blockbot_init_1(App $a) {
|
||||||
$crawlerDetect = new CrawlerDetect();
|
$crawlerDetect = new CrawlerDetect();
|
||||||
|
|
||||||
// List of strings of known "good" agents
|
$logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']];
|
||||||
$agents = ['diaspora-connection-tester', 'DiasporaFederation', 'Friendica', '(compatible; zot)',
|
|
||||||
'Micro.blog', 'Mastodon', 'hackney', 'GangGo', 'python/federation', 'GNU social', 'winHttp',
|
|
||||||
'Go-http-client', 'Mr.4x3 Powered', 'Test Certificate Info', 'WordPress.com', 'zgrab',
|
|
||||||
'curl/', 'StatusNet', 'OpenGraphReader/', 'Uptimebot/', 'python-opengraph-jaywink'];
|
|
||||||
|
|
||||||
if ($crawlerDetect->isCrawler()) {
|
if (!$crawlerDetect->isCrawler()) {
|
||||||
|
logger::debug('Good user agent detected', $logdata);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
// List of strings of reported false positives
|
||||||
|
$agents = ['Mastodon', 'hackney', 'Faraday', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests',
|
||||||
|
'WordPress'];
|
||||||
foreach ($agents as $agent) {
|
foreach ($agents as $agent) {
|
||||||
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
||||||
// @ToDo: Report every false positive here: https://github.com/JayBizzle/Crawler-Detect/issues/326
|
// The agents had been reported to https://github.com/JayBizzle/Crawler-Detect/issues/
|
||||||
logger::notice('False positive', ['agent' => $_SERVER['HTTP_USER_AGENT']]);
|
logger::notice('Already reported wrong detection', $logdata);
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
logger::info('Blocked bot', ['agent' => $_SERVER['HTTP_USER_AGENT']]);
|
|
||||||
|
// List of strings of known "good" agents
|
||||||
|
$agents = ['diaspora-connection-tester', 'DiasporaFederation', 'Friendica', '(compatible; zot)',
|
||||||
|
'Micro.blog', 'GangGo', 'python/federation', 'GNU social', 'winHttp',
|
||||||
|
'Go-http-client', 'Mr.4x3 Powered', 'Test Certificate Info', 'WordPress.com', 'zgrab',
|
||||||
|
'curl/', 'StatusNet', 'OpenGraphReader/', 'Uptimebot/', 'python-opengraph-jaywink',
|
||||||
|
'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'Social-Relay'];
|
||||||
|
|
||||||
|
foreach ($agents as $agent) {
|
||||||
|
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
||||||
|
// Report every false positive here: https://github.com/JayBizzle/Crawler-Detect/issues/
|
||||||
|
// After report move it into the array above
|
||||||
|
logger::notice('False positive', $logdata);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// List of known crawlers. They are added here to avoid having them logged at the end of the function.
|
||||||
|
// This helps to detect false positives
|
||||||
|
$agents = ['Mozilla/5.0 (compatible; SemrushBot/3~bl; +http://www.semrush.com/bot.html)', 'SEMrushBot',
|
||||||
|
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36 AppEngine-Google; (+http://code.google.com/appengine; appid: s~feedly-nikon3)'];
|
||||||
|
|
||||||
|
foreach ($agents as $agent) {
|
||||||
|
if ($_SERVER['HTTP_USER_AGENT'] == $agent) {
|
||||||
System::httpExit(403, 'Bots are not allowed');
|
System::httpExit(403, 'Bots are not allowed');
|
||||||
} else {
|
|
||||||
logger::debug('Good user agent detected', ['agent' => $_SERVER['HTTP_USER_AGENT']]);
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
logger::info('Blocked bot', $logdata);
|
||||||
|
System::httpExit(403, 'Bots are not allowed');
|
||||||
|
}
|
||||||
|
|
Loading…
Reference in a new issue