# Spoti Terms: https://spoti.co.ke/terms
#
# Human browsing allowed.
# Automated extraction, AI training, dataset generation,
# and unauthorized commercial reuse prohibited.

Sitemap: https://spoti.co.ke/sitemap.xml
Sitemap: https://spoti.co.ke/sitemap-news.xml

User-agent: *

# Query params
Disallow: /*?

# Allow controlled params
Allow: /*?page=
Allow: /*.xml
Allow: /*.xml?
Allow: /*rss
Allow: /*rss?

# Allow rendering/static assets
Allow: /*.js
Allow: /*.css
Allow: /*.ico
Allow: /*.svg
Allow: /*.png
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.webp
Allow: /static/
Allow: /assets/

# Internal/private/system routes
Disallow: /search
Disallow: /preview/
Disallow: /auth/
Disallow: /account/
Disallow: /profile
Disallow: /admin/
Disallow: /api/
Disallow: /internal/
Disallow: /pr/

###
# Social/media/rendering bots
###

User-agent: FacebookExternalHit
User-agent: Twitterbot
User-agent: Pinterestbot
User-agent: LinkedInBot
User-agent: TikTokSpider
User-agent: Storebot-Google
User-agent: Google-InspectionTool
User-agent: AmazonAdBot
Allow: /

###
# AI training / retrieval / archive bots
###

User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: meta-webindexer
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: cohere-training-data-crawler
User-agent: cohere-ai
User-agent: CCBot
User-agent: PanguBot
User-agent: PetalBot
User-agent: Bytespider
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: Timpibot
User-agent: Webzio
User-agent: Webzio-Extended
User-agent: archive.org_bot
User-agent: ia_archiver
User-agent: ia_archiver-web.archive.org
User-agent: heritrix
Disallow: /