mirror of
https://github.com/superseriousbusiness/gotosocial.git
synced 2025-10-29 11:02:25 -05:00
[feature] Use X-Robots-Tag headers to instruct scrapers/crawlers (#3737)
* [feature] Use `X-Robots-Tag` headers to instruct scrapers/crawlers * use switch for RobotsHeaders
This commit is contained in:
parent
bfb81f5bac
commit
baed591a1d
15 changed files with 311 additions and 142 deletions
|
|
@ -20,6 +20,7 @@ package api
|
|||
import (
|
||||
"github.com/gin-gonic/gin"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/api/nodeinfo"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/config"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/middleware"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/processing"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/router"
|
||||
|
|
@ -43,6 +44,16 @@ func (w *NodeInfo) Route(r *router.Router, m ...gin.HandlerFunc) {
|
|||
}),
|
||||
)
|
||||
|
||||
// If instance is configured to serve instance stats
|
||||
// faithfully at nodeinfo, we should allow robots to
|
||||
// crawl nodeinfo endpoints in a limited capacity.
|
||||
// In all other cases, disallow everything.
|
||||
if config.GetInstanceStatsMode() == config.InstanceStatsModeServe {
|
||||
nodeInfoGroup.Use(middleware.RobotsHeaders("allowSome"))
|
||||
} else {
|
||||
nodeInfoGroup.Use(middleware.RobotsHeaders(""))
|
||||
}
|
||||
|
||||
w.nodeInfo.Route(nodeInfoGroup.Handle)
|
||||
}
|
||||
|
||||
|
|
|
|||
52
internal/api/robots.go
Normal file
52
internal/api/robots.go
Normal file
|
|
@ -0,0 +1,52 @@
|
|||
// 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 api
|
||||
|
||||
import (
|
||||
"github.com/gin-gonic/gin"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/api/robots"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/middleware"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/router"
|
||||
)
|
||||
|
||||
type Robots struct {
|
||||
robots *robots.Module
|
||||
}
|
||||
|
||||
func (rb *Robots) Route(r *router.Router, m ...gin.HandlerFunc) {
|
||||
// Create a group so we can attach middlewares.
|
||||
robotsGroup := r.AttachGroup("robots.txt")
|
||||
|
||||
// Use passed-in middlewares.
|
||||
robotsGroup.Use(m...)
|
||||
|
||||
// Allow caching for 24 hrs.
|
||||
// https://www.rfc-editor.org/rfc/rfc9309.html#section-2.4
|
||||
robotsGroup.Use(
|
||||
middleware.CacheControl(middleware.CacheControlConfig{
|
||||
Directives: []string{"public", "max-age=86400"},
|
||||
Vary: []string{"Accept-Encoding"},
|
||||
}),
|
||||
)
|
||||
|
||||
rb.robots.Route(robotsGroup.Handle)
|
||||
}
|
||||
|
||||
func NewRobots() *Robots {
|
||||
return &Robots{}
|
||||
}
|
||||
57
internal/api/robots/robots.go
Normal file
57
internal/api/robots/robots.go
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
// 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 robots
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
apiutil "github.com/superseriousbusiness/gotosocial/internal/api/util"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/config"
|
||||
)
|
||||
|
||||
type Module struct{}
|
||||
|
||||
func New() *Module {
|
||||
return &Module{}
|
||||
}
|
||||
|
||||
func (m *Module) Route(attachHandler func(method string, path string, f ...gin.HandlerFunc) gin.IRoutes) {
|
||||
// Serve different robots.txt file depending on instance
|
||||
// stats mode: Don't disallow scraping nodeinfo if admin
|
||||
// has opted in to serving accurate stats there. In all
|
||||
// other cases, disallow scraping nodeinfo.
|
||||
var handler gin.HandlerFunc
|
||||
if config.GetInstanceStatsMode() == config.InstanceStatsModeServe {
|
||||
handler = m.robotsGETHandler
|
||||
} else {
|
||||
handler = m.robotsGETHandlerDisallowNodeInfo
|
||||
}
|
||||
|
||||
// Attach handler at empty path as this
|
||||
// is already grouped under /robots.txt.
|
||||
attachHandler(http.MethodGet, "", handler)
|
||||
}
|
||||
|
||||
func (m *Module) robotsGETHandler(c *gin.Context) {
|
||||
c.String(http.StatusOK, apiutil.RobotsTxt)
|
||||
}
|
||||
|
||||
func (m *Module) robotsGETHandlerDisallowNodeInfo(c *gin.Context) {
|
||||
c.String(http.StatusOK, apiutil.RobotsTxtDisallowNodeInfo)
|
||||
}
|
||||
133
internal/api/util/robots.go
Normal file
133
internal/api/util/robots.go
Normal file
|
|
@ -0,0 +1,133 @@
|
|||
// 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 util
|
||||
|
||||
// See:
|
||||
//
|
||||
// - https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag#robotsmeta
|
||||
// - https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Robots-Tag
|
||||
// - https://www.rfc-editor.org/rfc/rfc9309.html
|
||||
const (
|
||||
RobotsDirectivesDisallow = "noindex, nofollow"
|
||||
RobotsDirectivesAllowSome = "nofollow, noarchive, nositelinkssearchbox, max-image-preview:standard"
|
||||
RobotsTxt = `# GoToSocial robots.txt -- to edit, see internal/api/util/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: AI2Bot
|
||||
User-agent: Ai2Bot-Dolma
|
||||
User-agent: Amazonbot
|
||||
User-agent: anthropic-ai
|
||||
User-agent: Applebot
|
||||
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: cohere-training-data-crawler
|
||||
User-agent: Diffbot
|
||||
User-agent: DuckAssistBot
|
||||
User-agent: FacebookBot
|
||||
User-agent: FriendlyCrawler
|
||||
User-agent: Google-Extended
|
||||
User-agent: GoogleOther
|
||||
User-agent: GoogleOther-Image
|
||||
User-agent: GoogleOther-Video
|
||||
User-agent: GPTBot
|
||||
User-agent: iaskspider/2.0
|
||||
User-agent: ICC-Crawler
|
||||
User-agent: ImagesiftBot
|
||||
User-agent: img2dataset
|
||||
User-agent: ISSCyberRiskCrawler
|
||||
User-agent: Kangaroo Bot
|
||||
User-agent: Meta-ExternalAgent
|
||||
User-agent: Meta-ExternalFetcher
|
||||
User-agent: OAI-SearchBot
|
||||
User-agent: omgili
|
||||
User-agent: omgilibot
|
||||
User-agent: PanguBot
|
||||
User-agent: PerplexityBot
|
||||
User-agent: PetalBot
|
||||
User-agent: Scrapy
|
||||
User-agent: Sidetrade indexer bot
|
||||
User-agent: Timpibot
|
||||
User-agent: VelenPublicWebCrawler
|
||||
User-agent: Webzio-Extended
|
||||
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
|
||||
|
||||
# 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
|
||||
|
||||
# Webfinger endpoint.
|
||||
Disallow: /.well-known/webfinger
|
||||
`
|
||||
RobotsTxtDisallowNodeInfo = RobotsTxt + `
|
||||
# Disallow nodeinfo
|
||||
Disallow: /.well-known/nodeinfo
|
||||
Disallow: /nodeinfo/
|
||||
`
|
||||
)
|
||||
|
|
@ -21,6 +21,7 @@ import (
|
|||
"net/http"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/middleware"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/processing"
|
||||
)
|
||||
|
||||
|
|
@ -40,5 +41,6 @@ func New(processor *processing.Processor) *Module {
|
|||
}
|
||||
|
||||
func (m *Module) Route(attachHandler func(method string, path string, f ...gin.HandlerFunc) gin.IRoutes) {
|
||||
attachHandler(http.MethodGet, HostMetaPath, m.HostMetaGETHandler)
|
||||
// Attach handler, injecting robots http header middleware to disallow all.
|
||||
attachHandler(http.MethodGet, HostMetaPath, middleware.RobotsHeaders(""), m.HostMetaGETHandler)
|
||||
}
|
||||
|
|
|
|||
|
|
@ -21,6 +21,10 @@ import (
|
|||
"net/http"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
apiutil "github.com/superseriousbusiness/gotosocial/internal/api/util"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/config"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/middleware"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/processing"
|
||||
)
|
||||
|
||||
|
|
@ -42,5 +46,57 @@ func New(processor *processing.Processor) *Module {
|
|||
}
|
||||
|
||||
func (m *Module) Route(attachHandler func(method string, path string, f ...gin.HandlerFunc) gin.IRoutes) {
|
||||
attachHandler(http.MethodGet, NodeInfoWellKnownPath, m.NodeInfoWellKnownGETHandler)
|
||||
// If instance is configured to serve instance stats
|
||||
// faithfully at nodeinfo, we should allow robots to
|
||||
// crawl nodeinfo endpoints in a limited capacity.
|
||||
// In all other cases, disallow everything.
|
||||
var robots gin.HandlerFunc
|
||||
if config.GetInstanceStatsMode() == config.InstanceStatsModeServe {
|
||||
robots = middleware.RobotsHeaders("allowSome")
|
||||
} else {
|
||||
robots = middleware.RobotsHeaders("")
|
||||
}
|
||||
|
||||
// Attach handler, injecting robots http header middleware.
|
||||
attachHandler(http.MethodGet, NodeInfoWellKnownPath, robots, m.NodeInfoWellKnownGETHandler)
|
||||
}
|
||||
|
||||
// NodeInfoWellKnownGETHandler swagger:operation GET /.well-known/nodeinfo nodeInfoWellKnownGet
|
||||
//
|
||||
// Returns a well-known response which redirects callers to `/nodeinfo/2.0`.
|
||||
//
|
||||
// eg. `{"links":[{"rel":"http://nodeinfo.diaspora.software/ns/schema/2.0","href":"http://example.org/nodeinfo/2.0"}]}`
|
||||
// See: https://nodeinfo.diaspora.software/protocol.html
|
||||
//
|
||||
// ---
|
||||
// tags:
|
||||
// - .well-known
|
||||
//
|
||||
// produces:
|
||||
// - application/json
|
||||
//
|
||||
// responses:
|
||||
// '200':
|
||||
// schema:
|
||||
// "$ref": "#/definitions/wellKnownResponse"
|
||||
func (m *Module) NodeInfoWellKnownGETHandler(c *gin.Context) {
|
||||
if _, err := apiutil.NegotiateAccept(c, apiutil.JSONAcceptHeaders...); err != nil {
|
||||
apiutil.ErrorHandler(c, gtserror.NewErrorNotAcceptable(err, err.Error()), m.processor.InstanceGetV1)
|
||||
return
|
||||
}
|
||||
|
||||
resp, errWithCode := m.processor.Fedi().NodeInfoRelGet(c.Request.Context())
|
||||
if errWithCode != nil {
|
||||
apiutil.ErrorHandler(c, errWithCode, m.processor.InstanceGetV1)
|
||||
return
|
||||
}
|
||||
|
||||
// Encode JSON HTTP response.
|
||||
apiutil.EncodeJSONResponse(
|
||||
c.Writer,
|
||||
c.Request,
|
||||
http.StatusOK,
|
||||
apiutil.AppJSON,
|
||||
resp,
|
||||
)
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,66 +0,0 @@
|
|||
// 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 nodeinfo
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
apiutil "github.com/superseriousbusiness/gotosocial/internal/api/util"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
|
||||
)
|
||||
|
||||
// NodeInfoWellKnownGETHandler swagger:operation GET /.well-known/nodeinfo nodeInfoWellKnownGet
|
||||
//
|
||||
// Returns a well-known response which redirects callers to `/nodeinfo/2.0`.
|
||||
//
|
||||
// eg. `{"links":[{"rel":"http://nodeinfo.diaspora.software/ns/schema/2.0","href":"http://example.org/nodeinfo/2.0"}]}`
|
||||
// See: https://nodeinfo.diaspora.software/protocol.html
|
||||
//
|
||||
// ---
|
||||
// tags:
|
||||
// - .well-known
|
||||
//
|
||||
// produces:
|
||||
// - application/json
|
||||
//
|
||||
// responses:
|
||||
// '200':
|
||||
// schema:
|
||||
// "$ref": "#/definitions/wellKnownResponse"
|
||||
func (m *Module) NodeInfoWellKnownGETHandler(c *gin.Context) {
|
||||
if _, err := apiutil.NegotiateAccept(c, apiutil.JSONAcceptHeaders...); err != nil {
|
||||
apiutil.ErrorHandler(c, gtserror.NewErrorNotAcceptable(err, err.Error()), m.processor.InstanceGetV1)
|
||||
return
|
||||
}
|
||||
|
||||
resp, errWithCode := m.processor.Fedi().NodeInfoRelGet(c.Request.Context())
|
||||
if errWithCode != nil {
|
||||
apiutil.ErrorHandler(c, errWithCode, m.processor.InstanceGetV1)
|
||||
return
|
||||
}
|
||||
|
||||
// Encode JSON HTTP response.
|
||||
apiutil.EncodeJSONResponse(
|
||||
c.Writer,
|
||||
c.Request,
|
||||
http.StatusOK,
|
||||
apiutil.AppJSON,
|
||||
resp,
|
||||
)
|
||||
}
|
||||
|
|
@ -21,6 +21,7 @@ import (
|
|||
"net/http"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/middleware"
|
||||
"github.com/superseriousbusiness/gotosocial/internal/processing"
|
||||
)
|
||||
|
||||
|
|
@ -41,5 +42,6 @@ func New(processor *processing.Processor) *Module {
|
|||
}
|
||||
|
||||
func (m *Module) Route(attachHandler func(method string, path string, f ...gin.HandlerFunc) gin.IRoutes) {
|
||||
attachHandler(http.MethodGet, WebfingerBasePath, m.WebfingerGETRequest)
|
||||
// Attach handler, injecting robots http header middleware to disallow all.
|
||||
attachHandler(http.MethodGet, WebfingerBasePath, middleware.RobotsHeaders(""), m.WebfingerGETRequest)
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue