gotosocial/internal/web/robots.go
tobi 941893a774
[chore] The Big Middleware and API Refactor (tm) (#1250)
* interim commit: start refactoring middlewares into package under router

* another interim commit, this is becoming a big job

* another fucking massive interim commit

* refactor bookmarks to new style

* ambassador, wiz zeze commits you are spoiling uz

* she compiles, we're getting there

* we're just normal men; we're just innocent men

* apiutil

* whoopsie

* i'm glad noone reads commit msgs haha :blob_sweat:

* use that weirdo go-bytesize library for maxMultipartMemory

* fix media module paths
2023-01-02 12:10:50 +00:00

62 lines
1.9 KiB
Go

/*
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 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/`
)
// 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)
}