From dd83ad053c0cde5b948cbfe34ec4864cf0a123e3 Mon Sep 17 00:00:00 2001
From: tobi <31960611+tsmethurst@users.noreply.github.com>
Date: Thu, 29 Sep 2022 12:03:17 +0200
Subject: [feature] Add `meta robots` tag; allow robots to index profile card
 if user is Discoverable (#842)

* rework robots.txt response

* don't let robots snippet from statuses/threads

* allow robots to index if user is Discoverable

* add license text
---
 internal/api/security/robots.go | 46 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 43 insertions(+), 3 deletions(-)

(limited to 'internal/api/security/robots.go')

diff --git a/internal/api/security/robots.go b/internal/api/security/robots.go
index 65056072a..5b8ba3c05 100644
--- a/internal/api/security/robots.go
+++ b/internal/api/security/robots.go
@@ -1,3 +1,21 @@
+/*
+   GoToSocial
+   Copyright (C) 2021-2022 GoToSocial Authors admin@gotosocial.org
+
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU Affero General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU Affero General Public License for more details.
+
+   You should have received a copy of the GNU Affero General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
 package security
 
 import (
@@ -7,11 +25,33 @@ import (
 )
 
 const robotsString = `User-agent: *
-Disallow: /
+Crawl-delay: 500
+# api stuff
+Disallow: /api/
+# auth/login stuff
+Disallow: /auth/
+Disallow: /oauth/
+Disallow: /check_your_email
+Disallow: /wait_for_approval
+Disallow: /account_disabled
+# well known stuff
+Disallow: /.well-known/
+# files
+Disallow: /fileserver/
+# s2s AP stuff
+Disallow: /users/
+Disallow: /emoji/
+# panels
+Disallow: /admin
+Disallow: /user
+Disallow: /settings/
 `
 
-// RobotsGETHandler returns the most restrictive possible robots.txt file in response to a call to /robots.txt.
-// The response instructs bots with *any* user agent not to index the instance at all.
+// RobotsGETHandler returns a decent robots.txt that prevents crawling
+// the api, auth pages, settings pages, etc.
+//
+// More granular robots meta tags are then applied for web pages
+// depending on user preferences (see internal/web).
 func (m *Module) RobotsGETHandler(c *gin.Context) {
 	c.String(http.StatusOK, robotsString)
 }
-- 
cgit v1.2.3