lib/mysql.php: actually forbid access for bots

1 files changed, 18 insertions, 1 deletions

diff --git a/lib/mysql.php b/lib/mysql.php
index 7564a3d..d3b210f 100644
--- a/lib/mysql.php
+++ b/lib/mysql.php
@@ -100,13 +100,30 @@ function arch_filter_query($table) {
 }
 
 function abort_iff_webspider() {
+  $is_a_bot = in_array(
+    $_SERVER['HTTP_USER_AGENT'],
+    array(
+      'Mozilla/5.0 (compatible; AhrefsBot/6.1; +http://ahrefs.com/robot/)',
+      'Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)',
+      "'Mozilla/5.0 (compatible; DuckDuckBot-Https/1.1; https://duckduckgo.com/duckduckbot)'",
+      'Mozilla/5.0 (compatible; SeznamBot/3.2; +http://napoveda.seznam.cz/en/seznambot-intro/)',
+      'Mozilla/5.0 (Compatible; Supybot 2019.02.23)',
+      'Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)',
+      'Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.96 Mobile Safari/537.36 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)',
+      'ZoominfoBot (zoominfobot at zoominfo dot com)'
+    )
+  );
   if (($fp = fopen(BASE . '/user-agent-log', 'a')) !== false) {
     flock($fp, LOCK_EX);
     fwrite($fp,
-      date('Y-m-d H:i:s') . " " .
+      date('Y-m-d H:i:s') . " " . ($is_a_bot ? 'bot' : 'human') . " " .
       $_SERVER['HTTP_USER_AGENT'] . "\n"
     );
     flock($fp, LOCK_UN);
     fclose($fp);
   }
+  if ($is_a_bot) {
+    include_once BASE . "/lib/http.php";
+    throw_http_error(403, 'Forbidden', 'Access forbidden for bots');
+  }
 }