2023-03-12 15:00:57 +00:00
|
|
|
// GoToSocial
|
|
|
|
// Copyright (C) GoToSocial Authors admin@gotosocial.org
|
|
|
|
// SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
//
|
|
|
|
// 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/>.
|
2022-09-29 10:03:17 +00:00
|
|
|
|
|
|
|
package web
|
|
|
|
|
2023-01-02 12:10:50 +00:00
|
|
|
import (
|
|
|
|
"net/http"
|
|
|
|
|
|
|
|
"github.com/gin-gonic/gin"
|
|
|
|
)
|
|
|
|
|
2022-09-29 10:03:17 +00:00
|
|
|
const (
|
2023-01-02 12:10:50 +00:00
|
|
|
robotsPath = "/robots.txt"
|
|
|
|
robotsMetaAllowSome = "nofollow, noarchive, nositelinkssearchbox, max-image-preview:standard" // https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag#robotsmeta
|
|
|
|
robotsTxt = `# GoToSocial robots.txt -- to edit, see internal/web/robots.go
|
2023-08-08 11:16:34 +00:00
|
|
|
# More info @ https://developers.google.com/search/docs/crawling-indexing/robots/intro
|
|
|
|
|
|
|
|
# Before we commence, a giant fuck you to ChatGPT in particular.
|
|
|
|
# https://platform.openai.com/docs/gptbot
|
|
|
|
User-agent: GPTBot
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
# Rules for everything else.
|
2023-01-02 12:10:50 +00:00
|
|
|
User-agent: *
|
|
|
|
Crawl-delay: 500
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# API endpoints.
|
2023-01-02 12:10:50 +00:00
|
|
|
Disallow: /api/
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# Auth/login endpoints.
|
2023-01-02 12:10:50 +00:00
|
|
|
Disallow: /auth/
|
|
|
|
Disallow: /oauth/
|
|
|
|
Disallow: /check_your_email
|
|
|
|
Disallow: /wait_for_approval
|
|
|
|
Disallow: /account_disabled
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# Well-known endpoints.
|
2023-01-02 12:10:50 +00:00
|
|
|
Disallow: /.well-known/
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# Fileserver/media.
|
2023-01-02 12:10:50 +00:00
|
|
|
Disallow: /fileserver/
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# Fedi S2S API endpoints.
|
2023-01-02 12:10:50 +00:00
|
|
|
Disallow: /users/
|
|
|
|
Disallow: /emoji/
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# Settings panels.
|
2023-01-02 12:10:50 +00:00
|
|
|
Disallow: /admin
|
|
|
|
Disallow: /user
|
2023-01-25 17:06:41 +00:00
|
|
|
Disallow: /settings/
|
2023-08-08 11:16:34 +00:00
|
|
|
|
|
|
|
# Domain blocklist.
|
2023-01-25 17:06:41 +00:00
|
|
|
Disallow: /about/suspended`
|
2022-09-29 10:03:17 +00:00
|
|
|
)
|
2023-01-02 12:10:50 +00:00
|
|
|
|
|
|
|
// 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, robotsTxt)
|
|
|
|
}
|