X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=blockbot%2Fblockbot.php;h=10327edf3b437c3eab6ab2edd81103ae5907e2d1;hb=187ba8383d96aa510dfa112dc2366c7a79d98e28;hp=e22dc47193d4f331892ae1ca45bf89ba7c108f29;hpb=3c5d0dc0cdd002862ce90deafb2a3f0cd914cd3e;p=friendica-addons.git diff --git a/blockbot/blockbot.php b/blockbot/blockbot.php index e22dc471..10327edf 100644 --- a/blockbot/blockbot.php +++ b/blockbot/blockbot.php @@ -8,9 +8,7 @@ * */ -use Friendica\App; use Friendica\Core\Hook; -use Friendica\Core\System; use Friendica\DI; use Jaybizzle\CrawlerDetect\CrawlerDetect; use Friendica\Core\Logger; @@ -24,7 +22,7 @@ function blockbot_install() Hook::register('init_1', __FILE__, 'blockbot_init_1'); } -function blockbot_addon_admin(App $a, &$o) +function blockbot_addon_admin(string &$o) { $t = Renderer::getMarkupTemplate('admin.tpl', 'addon/blockbot/'); @@ -36,14 +34,14 @@ function blockbot_addon_admin(App $a, &$o) ]); } -function blockbot_addon_admin_post(App $a) +function blockbot_addon_admin_post() { DI::config()->set('blockbot', 'good_crawlers', $_POST['good_crawlers'] ?? false); DI::config()->set('blockbot', 'block_gab', $_POST['block_gab'] ?? false); DI::config()->set('blockbot', 'training', $_POST['training'] ?? false); } -function blockbot_init_1(App $a) +function blockbot_init_1() { if (empty($_SERVER['HTTP_USER_AGENT'])) { return; @@ -52,12 +50,15 @@ function blockbot_init_1(App $a) $logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']]; // List of "good" crawlers - $good_agents = ['fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', + $good_agents = [ + 'fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/', - 'PTST/', 'Zabbix', 'Poduptime/']; + 'PTST/', 'Zabbix', 'Poduptime/' + ]; // List of known crawlers. - $agents = ['SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/', + $agents = [ + 'SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/', 'Diffbot/', 'Twitterbot/', 'YisouSpider', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/', 'PaperLiBot/', 'Nuzzel', 'um-LN/', 'Google Favicon', 'Datanyze', 'BLEXBot/', '360Spider', 'adscanner/', 'HeadlessChrome', 'wpif', 'startmebot/', 'Googlebot/', 'Applebot/', @@ -79,7 +80,8 @@ function blockbot_init_1(App $a) 'Google-Apps-Script; beanserver;', 'woorankreview/', 'Seekport Crawler;', 'AHC/', 'SkypeUriPreview Preview/', 'Semanticbot/', 'Embed PHP library', 'XoviOnpageCrawler;', 'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher', 'Google-Adwords-Instant', 'newspaper/', - 'YurichevBot/', 'Crawling at Home Project', 'InfoTigerBot/']; + 'YurichevBot/', 'Crawling at Home Project', 'InfoTigerBot/' + ]; if (!DI::config()->get('blockbot', 'good_crawlers')) { $agents = array_merge($agents, $good_agents); @@ -114,7 +116,8 @@ function blockbot_init_1(App $a) } // List of false positives' strings of known "good" agents. - $agents = ['curl', 'zgrab', 'Go-http-client', 'curb', 'github.com', 'reqwest', 'Feedly/', + $agents = [ + 'curl', 'zgrab', 'Go-http-client', 'curb', 'github.com', 'reqwest', 'Feedly/', 'Python-urllib/', 'Liferea/', 'aiohttp/', 'WordPress.com Reader', 'hackney/', 'Faraday v', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests', 'WordPress/', 'http.rb/', 'Apache-HttpClient/', 'WordPress.com;', 'Pleroma', @@ -122,7 +125,8 @@ function blockbot_init_1(App $a) 'lua-resty-http/', 'Tiny Tiny RSS/', 'Wget/', 'PostmanRuntime/', 'W3C_Validator/', 'NetNewsWire', 'FeedValidator/', 'theoldreader.com', 'axios/', 'Paw/', 'PeerTube/', 'fedi.inex.dev', 'FediDB/', 'index.community crawler', - 'Slackbot-LinkExpanding']; + 'Slackbot-LinkExpanding' + ]; if (DI::config()->get('blockbot', 'good_crawlers')) { $agents = array_merge($agents, $good_agents); @@ -130,11 +134,11 @@ function blockbot_init_1(App $a) foreach ($agents as $agent) { if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) { - logger::notice('False positive', $logdata); + logger::info('False positive', $logdata); return; } } - logger::info('Blocked bot', $logdata); + logger::notice('Blocked bot', $logdata); throw new ForbiddenException('Bots are not allowed'); }