-
-
Notifications
You must be signed in to change notification settings - Fork 365
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[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
- Loading branch information
1 parent
bfb81f5
commit baed591
Showing
15 changed files
with
311 additions
and
142 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,52 @@ | ||
| // GoToSocial | ||
| // Copyright (C) GoToSocial Authors [email protected] | ||
| // 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{} | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,57 @@ | ||
| // GoToSocial | ||
| // Copyright (C) GoToSocial Authors [email protected] | ||
| // 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) | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.