From 18f77b94e18f0def8a1ec8292f78097b20e8f273 Mon Sep 17 00:00:00 2001 From: Michael Vogel Date: Sat, 27 Apr 2019 20:55:58 +0200 Subject: [PATCH] And some more false positives and known bots --- blockbot/blockbot.php | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/blockbot/blockbot.php b/blockbot/blockbot.php index dd84df37..c4a6fda3 100644 --- a/blockbot/blockbot.php +++ b/blockbot/blockbot.php @@ -47,7 +47,7 @@ function blockbot_init_1(App $a) { // List of false positives' strings of known "good" agents we haven't reported (yet) $agents = ['fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'Social-Relay/', - 'curl', 'zgrab', 'Go-http-client', 'curb']; + 'curl', 'zgrab', 'Go-http-client', 'curb', 'github.com', 'reqwest']; foreach ($agents as $agent) { if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) { @@ -59,7 +59,8 @@ function blockbot_init_1(App $a) { // 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. $agents = ['SEMrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/', - 'Diffbot/']; + 'Diffbot/', 'Twitterbot/', 'YisouSpider/', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/', + 'PaperLiBot/', 'Nuzzel', 'um-LN/', 'Google Favicon']; foreach ($agents as $agent) { if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {