4 * Description: Blocking bots based on detecting bots/crawlers/spiders via the user agent and http_from header.
6 * Author: Philipp Holzer <admin@philipp.info>
11 use Friendica\Core\Hook;
12 use Friendica\Core\System;
13 use Jaybizzle\CrawlerDetect\CrawlerDetect;
14 use Friendica\Core\Logger;
16 require_once __DIR__ . DIRECTORY_SEPARATOR . 'vendor' . DIRECTORY_SEPARATOR . 'autoload.php';
18 function blockbot_install() {
19 Hook::register('init_1', __FILE__, 'blockbot_init_1');
23 function blockbot_uninstall() {
24 Hook::unregister('init_1', __FILE__, 'blockbot_init_1');
27 function blockbot_init_1(App $a) {
28 $crawlerDetect = new CrawlerDetect();
30 $logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']];
32 if (!$crawlerDetect->isCrawler()) {
33 logger::debug('Good user agent detected', $logdata);
37 // List of strings of reported false positives
38 $agents = ['Mastodon', 'hackney', 'Faraday', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests',
39 'WordPress', 'http.rb'];
40 foreach ($agents as $agent) {
41 if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
42 // The agents had been reported to https://github.com/JayBizzle/Crawler-Detect/issues/
43 logger::notice('Already reported wrong detection', $logdata);
48 // List of strings of known "good" agents
49 $agents = ['diaspora-connection-tester', 'DiasporaFederation', 'Friendica', '(compatible; zot)',
50 'Micro.blog', 'GangGo', 'python/federation', 'GNU social', 'winHttp',
51 'Go-http-client', 'Mr.4x3 Powered', 'Test Certificate Info', 'WordPress.com', 'zgrab',
52 'curl/', 'StatusNet', 'OpenGraphReader/', 'Uptimebot/', 'python-opengraph-jaywink',
53 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'Social-Relay'];
55 foreach ($agents as $agent) {
56 if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
57 // Report every false positive here: https://github.com/JayBizzle/Crawler-Detect/issues/
58 // After report move it into the array above
59 logger::notice('False positive', $logdata);
64 // List of known crawlers. They are added here to avoid having them logged at the end of the function.
65 // This helps to detect false positives
66 $agents = ['Mozilla/5.0 (compatible; SemrushBot/3~bl; +http://www.semrush.com/bot.html)', 'SEMrushBot',
67 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36 AppEngine-Google; (+http://code.google.com/appengine; appid: s~feedly-nikon3)'];
69 foreach ($agents as $agent) {
70 if ($_SERVER['HTTP_USER_AGENT'] == $agent) {
71 System::httpExit(403, 'Bots are not allowed');
75 logger::info('Blocked bot', $logdata);
76 System::httpExit(403, 'Bots are not allowed');