103 lines
1.5 KiB
Text
103 lines
1.5 KiB
Text
# Block AI crawlers and scrapers
|
|
User-agent: GPTBot
|
|
Disallow: /
|
|
|
|
User-agent: ChatGPT-User
|
|
Disallow: /
|
|
|
|
User-agent: CCBot
|
|
Disallow: /
|
|
|
|
User-agent: anthropic-ai
|
|
Disallow: /
|
|
|
|
User-agent: Claude-Web
|
|
Disallow: /
|
|
|
|
User-agent: Google-Extended
|
|
Disallow: /
|
|
|
|
User-agent: GoogleOther
|
|
Disallow: /
|
|
|
|
User-agent: PerplexityBot
|
|
Disallow: /
|
|
|
|
User-agent: Omgilibot
|
|
Disallow: /
|
|
|
|
User-agent: FacebookBot
|
|
Disallow: /
|
|
|
|
User-agent: Diffbot
|
|
Disallow: /
|
|
|
|
User-agent: Bytespider
|
|
Disallow: /
|
|
|
|
User-agent: ImagesiftBot
|
|
Disallow: /
|
|
|
|
User-agent: cohere-ai
|
|
Disallow: /
|
|
|
|
User-agent: Applebot-Extended
|
|
Disallow: /
|
|
|
|
User-agent: YouBot
|
|
Disallow: /
|
|
|
|
User-agent: Meta-ExternalAgent
|
|
Disallow: /
|
|
|
|
User-agent: Meta-ExternalFetcher
|
|
Disallow: /
|
|
|
|
User-agent: OAI-SearchBot
|
|
Disallow: /
|
|
|
|
User-agent: PetalBot
|
|
Disallow: /
|
|
|
|
User-agent: Amazonbot
|
|
Disallow: /
|
|
|
|
User-agent: ClaudeBot
|
|
Disallow: /
|
|
|
|
User-agent: Timpibot
|
|
Disallow: /
|
|
|
|
User-agent: Kangaroo Bot
|
|
Disallow: /
|
|
|
|
User-agent: img2dataset
|
|
Disallow: /
|
|
|
|
User-agent: ISSCyberRiskCrawler
|
|
Disallow: /
|
|
|
|
User-agent: iaskspider/2.0
|
|
Disallow: /
|
|
|
|
User-agent: Scrapy
|
|
Disallow: /
|
|
|
|
User-agent: Zealbot
|
|
Disallow: /
|
|
|
|
User-agent: newspaper
|
|
Disallow: /
|
|
|
|
# Allow other bots
|
|
User-agent: *
|
|
{{ if eq (getenv "HUGO_ENV") "production" | or (eq .Site.Params.env "production") }}
|
|
Disallow:
|
|
{{ else }}
|
|
Disallow: /
|
|
{{ end }}
|
|
|
|
# Sitemap location (update with your actual sitemap URL)
|
|
{{ if eq (getenv "HUGO_ENV") "production" | or (eq .Site.Params.env "production") }}
|
|
Sitemap: {{ .Site.BaseURL }}sitemap.xml
|
|
{{ end }}
|