From af09a922cfd596a9b91c64f4c9f752c1906896f4 Mon Sep 17 00:00:00 2001 From: Michael Date: Thu, 20 Jun 2019 16:03:13 +0000 Subject: [PATCH] And some more bots that I just detected --- blockbot/blockbot.php | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/blockbot/blockbot.php b/blockbot/blockbot.php index c47e7705..c8cf7902 100644 --- a/blockbot/blockbot.php +++ b/blockbot/blockbot.php @@ -33,8 +33,8 @@ function blockbot_init_1(App $a) { $logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']]; // List of known crawlers. - $agents = ['SEMrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/', - 'Diffbot/', 'Twitterbot/', 'YisouSpider/', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/', + $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', @@ -47,7 +47,8 @@ function blockbot_init_1(App $a) { 'TelegramBot', 'SurdotlyBot/', 'BingPreview/', 'SabsimBot/', 'CCBot/', 'WbSrch/', 'DuckDuckBot-Https/', 'HTTP Banner Detection', 'YandexImages/', 'archive.org_bot', 'ArchiveTeam ArchiveBot/', 'yacybot', 'https://developers.google.com/+/web/snippet/', - 'Scrapy/', 'github-camo', 'MJ12bot/']; + 'Scrapy/', 'github-camo', 'MJ12bot/', 'DotBot/', 'Pinterestbot/', 'Jooblebot/', + 'Cliqzbot/', 'YaK/', 'Mediatoolkitbot']; foreach ($agents as $agent) { if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {