X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=blockbot%2Fblockbot.php;h=b602bf63bbc7ac86030b8fd27232f4a017b1b90d;hb=bdbfd9e9194a054e3b3380bd17f241d76a347af7;hp=587bc9d13f82656a7650181a4079b01fbd79fbe0;hpb=939d17e1eded0636dd36dd65910a88d1bf289466;p=friendica-addons.git diff --git a/blockbot/blockbot.php b/blockbot/blockbot.php index 587bc9d1..b602bf63 100644 --- a/blockbot/blockbot.php +++ b/blockbot/blockbot.php @@ -2,16 +2,19 @@ /** * Name: blockbot * Description: Blocking bots based on detecting bots/crawlers/spiders via the user agent and http_from header. - * Version: 0.1 + * Version: 0.2 * Author: Philipp Holzer + * Author: Michael Vogel * */ use Friendica\App; use Friendica\Core\Hook; use Friendica\Core\System; +use Friendica\DI; use Jaybizzle\CrawlerDetect\CrawlerDetect; use Friendica\Core\Logger; +use Friendica\Core\Renderer; require_once __DIR__ . DIRECTORY_SEPARATOR . 'vendor' . DIRECTORY_SEPARATOR . 'autoload.php'; @@ -19,56 +22,108 @@ function blockbot_install() { Hook::register('init_1', __FILE__, 'blockbot_init_1'); } +function blockbot_addon_admin(&$a, &$o) { + $t = Renderer::getMarkupTemplate("admin.tpl", "addon/blockbot/"); -function blockbot_uninstall() { - Hook::unregister('init_1', __FILE__, 'blockbot_init_1'); + $o = Renderer::replaceMacros($t, [ + '$submit' => DI::l10n()->t('Save Settings'), + '$good_crawlers' => ['good_crawlers', DI::l10n()->t('Allow "good" crawlers'), DI::config()->get('blockbot', 'good_crawlers'), "Don't block fediverse crawlers, relay servers and other bots with good purposes."], + '$block_gab' => ['block_gab', DI::l10n()->t('Block GabSocial'), DI::config()->get('blockbot', 'block_gab'), 'Block the software GabSocial. This will block every access for that software. You can block dedicated gab instances in the blocklist settings in the admin section.'], + '$training' => ['training', DI::l10n()->t('Training mode'), DI::config()->get('blockbot', 'training'), "Activates the training mode. This is only meant for developing purposes. Don't activate this on a production machine. This can cut communication with some systems."], + ]); +} + +function blockbot_addon_admin_post(&$a) { + 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) { - $crawlerDetect = new CrawlerDetect(); + if (empty($_SERVER['HTTP_USER_AGENT'])) { + return; + } $logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']]; - if (!$crawlerDetect->isCrawler()) { - logger::debug('Good user agent detected', $logdata); - return; - } + // List of "good" crawlers + $good_agents = ['fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', + 'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/', + 'PTST/']; - // List of strings of reported false positives - $agents = ['Mastodon', 'hackney', 'Faraday', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests', - 'WordPress']; - foreach ($agents as $agent) { - if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) { - // The agents had been reported to https://github.com/JayBizzle/Crawler-Detect/issues/ - logger::notice('Already reported wrong detection', $logdata); - return; + // List of known crawlers. + $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/', + 'facebookexternalhit/', 'GoogleImageProxy', 'bingbot/', 'heritrix/', 'ldspider', + 'AwarioRssBot/', 'Zabbix', 'TweetmemeBot/', 'dcrawl/', 'PhantomJS/', 'Googlebot-Image/', + 'CrowdTanglebot/', 'Mediapartners-Google', 'Baiduspider/', 'datagnionbot', + 'MegaIndex.ru/', 'SMUrlExpander', 'Hatena-Favicon/', 'Wappalyzer', 'FlipboardProxy/', + 'NetcraftSurveyAgent/', 'Dataprovider.com', 'SMTBot/', 'Nimbostratus-Bot/', + 'DuckDuckGo-Favicons-Bot/', 'IndieWebCards/', 'proximic', 'netEstate NE Crawler', + 'AhrefsBot/', 'YandexBot/', 'Exabot/', 'Mediumbot-MetaTagFetcher/', 'WhatsApp/', + 'TelegramBot', 'SurdotlyBot/', 'BingPreview/', 'SabsimBot/', 'CCBot/', 'WbSrch/', + 'DuckDuckBot-Https/', 'HTTP Banner Detection', 'YandexImages/', 'archive.org_bot', + 'ArchiveTeam ArchiveBot/', 'yacybot', 'https://developers.google.com/+/web/snippet/', + 'Scrapy/', 'github-camo', 'MJ12bot/', 'DotBot/', 'Pinterestbot/', 'Jooblebot/', + 'Cliqzbot/', 'YaK/', 'Mediatoolkitbot', 'Snacktory', 'FunWebProducts', 'oBot/', + '7Siters/', 'KOCMOHABT', 'Google-SearchByImage', 'FemtosearchBot/', + 'HubSpot Crawler', 'DomainStatsBot/', 'Re-re Studio', 'AwarioSmartBot/', + 'SummalyBot/', 'DNSResearchBot/', 'PetalBot;', 'Nmap Scripting Engine;', + 'Google-Apps-Script; beanserver;', 'woorankreview/', 'Seekport Crawler;', 'AHC/', + 'SkypeUriPreview Preview/', 'Semanticbot/', 'Embed PHP library', 'XoviOnpageCrawler;', + 'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher']; + + if (!DI::config()->get('blockbot', 'good_crawlers')) { + $agents = array_merge($agents, $good_agents); + } else { + foreach ($good_agents as $good_agent) { + if (stristr($_SERVER['HTTP_USER_AGENT'], $good_agent)) { + return; + } } } - // 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']; + if (DI::config()->get('blockbot', 'block_gab')) { + $agents[] = 'GabSocial/'; + } foreach ($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; + System::httpExit(403, 'Bots are not allowed'); } } - // 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)']; + // This switch here is only meant for developers who want to add more bots to the list above, it is not safe for production. + if (!DI::config()->get('blockbot', 'training')) { + return; + } + + $crawlerDetect = new CrawlerDetect(); + + if (!$crawlerDetect->isCrawler()) { + logger::debug('Good user agent detected', $logdata); + return; + } + + // List of false positives' strings of known "good" agents. + $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', + 'Dispatch/', 'Ruby', 'Java/', 'libwww-perl/', 'Mastodon/', 'FeedlyApp/', + 'lua-resty-http/', 'Tiny Tiny RSS/', 'Wget/', 'PostmanRuntime/', + 'W3C_Validator/', 'NetNewsWire', 'FeedValidator/', 'theoldreader.com']; + + if (DI::config()->get('blockbot', 'good_crawlers')) { + $agents = array_merge($agents, $good_agents); + } foreach ($agents as $agent) { - if ($_SERVER['HTTP_USER_AGENT'] == $agent) { - System::httpExit(403, 'Bots are not allowed'); + if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) { + logger::notice('False positive', $logdata); + return; } }