infra/services/block-crawlers/default.nix
raito 6f56566032 feat: block automatically crawlers if the blocker is enabled
This help us getting rid of useless traffic by crawlers.

It is enabled for gerrit01 which is suffering the most from this.

Signed-off-by: Raito Bezarius <masterancpp@gmail.com>
2024-10-19 19:07:30 +02:00

33 lines
874 B
Nix

{ pkgs, config, lib, ... }:
let
inherit (lib) mkEnableOption mkIf mkOption types concatStringsSep mkDefault;
cfg = config.bagel.services.nginx.crawler-blocker;
mkRobotsFile = blockedUAs: pkgs.writeText "robots.txt" ''
${concatStringsSep "\n" (map (ua: "User-Agent: ${ua}") blockedUAs)}
Disallow: /
'';
in
{
options = {
bagel.services.nginx.crawler-blocker = {
enable = mkEnableOption "the crawler blocker";
userAgents = mkOption {
type = types.listOf types.str;
default = builtins.split "\n" (builtins.readFile ./blocked-ua.txt);
};
};
services.nginx.virtualHosts = mkOption {
type = types.attrsOf (types.submodule {
config = {
locations."= /robots.txt" = mkIf cfg.enable (mkDefault {
alias = mkRobotsFile cfg.userAgents;
});
};
});
};
};
}