mirror of
https://github.com/superseriousbusiness/gotosocial.git
synced 2024-11-24 17:30:59 +00:00
[feature] Beef up our AI opt-outs (#3165)
* [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.
This commit is contained in:
parent
e5e996b28a
commit
9b50151f17
2 changed files with 16 additions and 0 deletions
|
@ -44,5 +44,12 @@ func ExtraHeaders() gin.HandlerFunc {
|
|||
//
|
||||
// See: https://github.com/patcg-individual-drafts/topics
|
||||
c.Header("Permissions-Policy", "browsing-topics=()")
|
||||
|
||||
// Some AI scrapers respect the following tags to opt-out
|
||||
// of their crawling and datasets.
|
||||
c.Header("X-Robots-Tag", "noimageai")
|
||||
// c.Header calls .Set(), but we want to emit the header
|
||||
// twice, not override it.
|
||||
c.Writer.Header().Add("X-Robots-Tag", "noai")
|
||||
}
|
||||
}
|
||||
|
|
|
@ -43,15 +43,24 @@ 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: /
|
||||
|
||||
|
|
Loading…
Reference in a new issue