gtsocial-umbx

Unnamed repository; edit this file 'description' to name the repository.
Log | Files | Refs | README | LICENSE

robots.go (2021B)


      1 // GoToSocial
      2 // Copyright (C) GoToSocial Authors admin@gotosocial.org
      3 // SPDX-License-Identifier: AGPL-3.0-or-later
      4 //
      5 // This program is free software: you can redistribute it and/or modify
      6 // it under the terms of the GNU Affero General Public License as published by
      7 // the Free Software Foundation, either version 3 of the License, or
      8 // (at your option) any later version.
      9 //
     10 // This program is distributed in the hope that it will be useful,
     11 // but WITHOUT ANY WARRANTY; without even the implied warranty of
     12 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
     13 // GNU Affero General Public License for more details.
     14 //
     15 // You should have received a copy of the GNU Affero General Public License
     16 // along with this program.  If not, see <http://www.gnu.org/licenses/>.
     17 
     18 package web
     19 
     20 import (
     21 	"net/http"
     22 
     23 	"github.com/gin-gonic/gin"
     24 )
     25 
     26 const (
     27 	robotsPath          = "/robots.txt"
     28 	robotsMetaAllowSome = "nofollow, noarchive, nositelinkssearchbox, max-image-preview:standard" // https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag#robotsmeta
     29 	robotsTxt           = `# GoToSocial robots.txt -- to edit, see internal/web/robots.go
     30 # more info @ https://developers.google.com/search/docs/crawling-indexing/robots/intro
     31 User-agent: *
     32 Crawl-delay: 500
     33 # api stuff
     34 Disallow: /api/
     35 # auth/login stuff
     36 Disallow: /auth/
     37 Disallow: /oauth/
     38 Disallow: /check_your_email
     39 Disallow: /wait_for_approval
     40 Disallow: /account_disabled
     41 # well known stuff
     42 Disallow: /.well-known/
     43 # files
     44 Disallow: /fileserver/
     45 # s2s AP stuff
     46 Disallow: /users/
     47 Disallow: /emoji/
     48 # panels
     49 Disallow: /admin
     50 Disallow: /user
     51 Disallow: /settings/
     52 # domain blocklist
     53 Disallow: /about/suspended`
     54 )
     55 
     56 // robotsGETHandler returns a decent robots.txt that prevents crawling
     57 // the api, auth pages, settings pages, etc.
     58 //
     59 // More granular robots meta tags are then applied for web pages
     60 // depending on user preferences (see internal/web).
     61 func (m *Module) robotsGETHandler(c *gin.Context) {
     62 	c.String(http.StatusOK, robotsTxt)
     63 }