From a8c54c1a32764d38727fb7c9f02ed9bc298e3174 Mon Sep 17 00:00:00 2001
From: mbays <mbays@sdf.org>
Date: Wed, 25 Aug 2021 12:08:56 +0200
Subject: [PATCH] Serve robots.txt disallowing all robots

This overrides any robots.txt file in the proxied gemini capsule, on the
basis that this is intended for gemini robots (which can be expected to
follow the robots.txt companion spec) rather than web robots.

The main purpose though for disallowing web robots is to prevent them
from crawling the proxied cross-site geminispace under /x/, since web
robots won't know even to read the robots.txt files for other capsules
proxied this way.
---
 main.go | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/main.go b/main.go
index c600985..2b227a0 100644
--- a/main.go
+++ b/main.go
@@ -583,6 +583,12 @@ func main() {
 			return
 		}
 
+		if r.URL.Path == "/robots.txt" {
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("User-agent: *\nDisallow: /\n"))
+			return
+		}
+
 		req := gemini.Request{}
 		req.URL = &url.URL{}
 		req.URL.Scheme = root.Scheme