gotosocial/internal/web/robots.go
Daenney 5e2bf0bdca
[chore] Improve copyright header handling (#1608)
* [chore] Remove years from all license headers

Years or year ranges aren't required in license headers. Many projects
have removed them in recent years and it avoids a bit of yearly toil.

In many cases our copyright claim was also a bit dodgy since we added
the 2021-2023 header to files created after 2021 but you can't claim
copyright into the past that way.

* [chore] Add license header check

This ensures a license header is always added to any new file. This
avoids maintainers/reviewers needing to remember to check for and ask
for it in case a contribution doesn't include it.

* [chore] Add missing license headers

* [chore] Further updates to license header

* Use the more common // indentend comment format
* Remove the hack we had for the linter now that we use the // format
* Add SPDX license identifier
2023-03-12 16:00:57 +01:00

63 lines
2 KiB
Go

// 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/>.
package web
import (
"net/http"
"github.com/gin-gonic/gin"
)
const (
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
# more info @ https://developers.google.com/search/docs/crawling-indexing/robots/intro
User-agent: *
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/
# domain blocklist
Disallow: /about/suspended`
)
// 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)
}