From ec4c8f6cab8cf07270a0df4ff88dda29aacc5840 Mon Sep 17 00:00:00 2001
From: "Gustavo L de Mello (Guz)" <contact@guz.one>
Date: Tue, 17 Dec 2024 11:24:51 -0300
Subject: [PATCH] feat: add ai.txt and robots.txt to prevent AI crawlers

---
 app/app.go        | 21 +++++++++++++++++++++
 assets/ai.txt     |  6 ++++++
 assets/assets.go  |  2 +-
 assets/robots.txt | 42 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 70 insertions(+), 1 deletion(-)
 create mode 100644 assets/ai.txt
 create mode 100644 assets/robots.txt

diff --git a/app/app.go b/app/app.go
index 2cfb1ec..0720ba1 100644
--- a/app/app.go
+++ b/app/app.go
@@ -11,6 +11,7 @@ import (
 	"forge.capytal.company/capytalcode/project-comicverse/lib/router"
 	"forge.capytal.company/capytalcode/project-comicverse/lib/router/rerrors"
 	"github.com/minio/minio-go/v7"
+	"keikos.work/assets"
 	"keikos.work/configs"
 	"keikos.work/handlers/pages"
 )
@@ -70,6 +71,26 @@ func NewWeb(opts Options) App {
 	r.Handle("/", &pages.Home{})
 	r.Handle("/assets/", opts.Assets)
 
+	robots, err := assets.ASSETS.ReadFile("robots.txt")
+	if err != nil {
+		panic(err)
+	}
+	r.HandleFunc("/robots.txt", func(w http.ResponseWriter, r *http.Request) {
+		if _, err := w.Write(robots); err != nil {
+			rerrors.InternalError(err).ServeHTTP(w, r)
+		}
+	})
+
+	ai, err := assets.ASSETS.ReadFile("ai.txt")
+	if err != nil {
+		panic(err)
+	}
+	r.HandleFunc("/ai.txt", func(w http.ResponseWriter, r *http.Request) {
+		if _, err := w.Write(ai); err != nil {
+			rerrors.InternalError(err).ServeHTTP(w, r)
+		}
+	})
+
 	// imgs := &pages.Images{S3: opts.S3}
 	// r.HandleFunc("GET /images", imgs.List)
 	// r.HandleFunc("GET /images/{name}", imgs.Get)
diff --git a/assets/ai.txt b/assets/ai.txt
new file mode 100644
index 0000000..9df92b0
--- /dev/null
+++ b/assets/ai.txt
@@ -0,0 +1,6 @@
+# Spawning AI
+# Prevent datasets from using the following file types
+
+User-Agent: *
+Disallow: /
+Disallow: *
diff --git a/assets/assets.go b/assets/assets.go
index 8f7a143..66c08c8 100644
--- a/assets/assets.go
+++ b/assets/assets.go
@@ -4,5 +4,5 @@ import (
 	"embed"
 )
 
-//go:embed css fonts img
+//go:embed css fonts img robots.txt ai.txt
 var ASSETS embed.FS
diff --git a/assets/robots.txt b/assets/robots.txt
new file mode 100644
index 0000000..c41ed6d
--- /dev/null
+++ b/assets/robots.txt
@@ -0,0 +1,42 @@
+User-agent: AI2Bot
+User-agent: Ai2Bot-Dolma
+User-agent: Amazonbot
+User-agent: anthropic-ai
+User-agent: Applebot
+User-agent: Applebot-Extended
+User-agent: Bytespider
+User-agent: CCBot
+User-agent: ChatGPT-User
+User-agent: Claude-Web
+User-agent: ClaudeBot
+User-agent: cohere-ai
+User-agent: Diffbot
+User-agent: DuckAssistBot
+User-agent: FacebookBot
+User-agent: FriendlyCrawler
+User-agent: Google-Extended
+User-agent: GoogleOther
+User-agent: GoogleOther-Image
+User-agent: GoogleOther-Video
+User-agent: GPTBot
+User-agent: iaskspider/2.0
+User-agent: ICC-Crawler
+User-agent: ImagesiftBot
+User-agent: img2dataset
+User-agent: ISSCyberRiskCrawler
+User-agent: Kangaroo Bot
+User-agent: Meta-ExternalAgent
+User-agent: Meta-ExternalFetcher
+User-agent: OAI-SearchBot
+User-agent: omgili
+User-agent: omgilibot
+User-agent: PanguBot
+User-agent: PerplexityBot
+User-agent: PetalBot
+User-agent: Scrapy
+User-agent: Sidetrade indexer bot
+User-agent: Timpibot
+User-agent: VelenPublicWebCrawler
+User-agent: Webzio-Extended
+User-agent: YouBot
+Disallow: /