mirror of
https://github.com/superseriousbusiness/gotosocial.git
synced 2024-12-13 02:20:47 +01:00
9b50151f17
* [chore] Synchronise our robots.txt with upstream * [feature] Add headers to escape AI crawlers This adds 2 headers that a number of AI crawlers respect to signal that content should not be included in their datasets.
127 lines
3.3 KiB
Go
127 lines
3.3 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
|
|
|
|
# AI scrapers and the like.
|
|
# https://github.com/ai-robots-txt/ai.robots.txt/
|
|
User-agent: AdsBot-Google
|
|
User-agent: Amazonbot
|
|
User-agent: anthropic-ai
|
|
User-agent: Applebot-Extended
|
|
User-agent: Bytespider
|
|
User-agent: CCBot
|
|
User-agent: ChatGPT-User
|
|
User-agent: ClaudeBot
|
|
User-agent: Claude-Web
|
|
User-agent: cohere-ai
|
|
User-agent: Diffbot
|
|
User-agent: FacebookBot
|
|
User-agent: facebookexternalhit
|
|
User-agent: FriendlyCrawler
|
|
User-agent: Google-Extended
|
|
User-agent: GoogleOther
|
|
User-agent: GoogleOther-Image
|
|
User-agent: GoogleOther-Video
|
|
User-agent: GPTBot
|
|
User-agent: ImagesiftBot
|
|
User-agent: img2dataset
|
|
User-agent: Meta-ExternalAgent
|
|
User-agent: OAI-SearchBot
|
|
User-agent: omgili
|
|
User-agent: omgilibot
|
|
User-agent: PerplexityBot
|
|
User-agent: PetalBot
|
|
User-agent: Scrapy
|
|
User-agent: Timpibot
|
|
User-agent: VelenPublicWebCrawler
|
|
User-agent: YouBot
|
|
Disallow: /
|
|
|
|
# Marketing/SEO "intelligence" data scrapers
|
|
User-agent: AwarioRssBot
|
|
User-agent: AwarioSmartBot
|
|
User-agent: DataForSeoBot
|
|
User-agent: magpie-crawler
|
|
User-agent: Meltwater
|
|
User-agent: peer39_crawler
|
|
User-agent: peer39_crawler/1.0
|
|
User-agent: PiplBot
|
|
User-agent: scoop.it
|
|
User-agent: Seekr
|
|
Disallow: /
|
|
|
|
# Well-known.dev crawler. Indexes stuff under /.well-known.
|
|
# https://well-known.dev/about/
|
|
User-agent: WellKnownBot
|
|
Disallow: /
|
|
|
|
# Rules for everything else.
|
|
User-agent: *
|
|
Crawl-delay: 500
|
|
|
|
# API endpoints.
|
|
Disallow: /api/
|
|
|
|
# Auth/Sign in endpoints.
|
|
Disallow: /auth/
|
|
Disallow: /oauth/
|
|
Disallow: /check_your_email
|
|
Disallow: /wait_for_approval
|
|
Disallow: /account_disabled
|
|
Disallow: /signup
|
|
|
|
# Well-known endpoints.
|
|
Disallow: /.well-known/
|
|
|
|
# Fileserver/media.
|
|
Disallow: /fileserver/
|
|
|
|
# Fedi S2S API endpoints.
|
|
Disallow: /users/
|
|
Disallow: /emoji/
|
|
|
|
# Settings 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)
|
|
}
|