Files
sanasto-wiki/test/controllers/bot_blocking_test.rb
Runar Ingebrigtsen 7118f1ea45
CI / scan_ruby (push) Successful in 18s
CI / scan_js (push) Successful in 14s
CI / lint (push) Failing after 21s
CI / test (push) Successful in 36s
block bots
2026-01-30 08:52:17 +01:00

55 lines
2.0 KiB
Ruby

require "test_helper"
class BotBlockingTest < ActionDispatch::IntegrationTest
test "should block GPTBot" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GPTBot/1.3; +https://openai.com/gptbot)" }
assert_response :forbidden
assert_match(/bot access is not allowed/i, response.body)
end
test "should block ChatGPT bot" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 (compatible; ChatGPT-User/1.0; +https://openai.com/bot)" }
assert_response :forbidden
end
test "should block Googlebot" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)" }
assert_response :forbidden
end
test "should block Bingbot" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)" }
assert_response :forbidden
end
test "should block generic bot user agent" do
get root_path, headers: { "User-Agent" => "SomeBot/1.0" }
assert_response :forbidden
end
test "should allow normal browsers" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36" }
assert_response :success
end
test "should allow Firefox" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 (X11; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0" }
assert_response :success
end
test "should allow Safari" do
get root_path, headers: { "User-Agent" => "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/605.1.15" }
assert_response :success
end
test "should block crawler" do
get root_path, headers: { "User-Agent" => "SomeCrawler/1.0" }
assert_response :forbidden
end
test "should block scraper" do
get root_path, headers: { "User-Agent" => "WebScraper/2.0" }
assert_response :forbidden
end
end