# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt for hotfruit.co.za
# Last updated: 2026-06-29

# Default: allow all reputable search engines
User-agent: *
Allow: /
Disallow: /play/
Disallow: /go/
Disallow: /out/
Disallow: /*?ref=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /404.html

# Googlebot, Bingbot, DuckDuckBot: explicit allow
User-agent: Googlebot
Allow: /
Disallow: /play/
Disallow: /go/
Disallow: /out/

User-agent: Bingbot
Allow: /
Disallow: /play/
Disallow: /go/
Disallow: /out/

User-agent: DuckDuckBot
Allow: /
Disallow: /play/
Disallow: /go/

# Image bots: allow
User-agent: Googlebot-Image
Allow: /

# Block aggressive scrapers and AI training crawlers
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: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

# Crawl-delay for politeness (where supported)
User-agent: *
Crawl-delay: 1

# Sitemaps. Primary feed is /sitemap-feed (served with application/xml content-type).
# /sitemap.xml is a Cloudflare _redirects rewrite to /sitemap-feed because a zone-level
# rule intercepts requests ending in .xml on this domain. Text fallback also provided.
Sitemap: https://hotfruit.co.za/sitemap-feed
Sitemap: https://hotfruit.co.za/sitemap.xml
Sitemap: https://hotfruit.co.za/sitemap.txt