# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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 — www.hellamax.com
# Policy: allow classic search engines AND AI search / retrieval crawlers so that
# Hellamax content can be found and cited in AI answers. Pure model-training
# crawlers stay blocked (blocking them does NOT affect AI search visibility).
#
# NOTE: Cloudflare's AI Crawl Control injects its own rules ABOVE these (managed
# block). In the dashboard keep the "AI Crawler" entries blocked and the
# "AI Search" / "AI Assistant" entries unblocked, so the two rule sets never
# contradict each other.

# ---- Content usage signals (IETF draft) ----
# search=yes      may be indexed and shown in search results
# ai-input=yes    may be retrieved/cited as input for generative AI answers
# ai-train=no     not authorised for model training or fine-tuning
# use=reference   may be consumed by reference (with attribution/link)
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no,use=reference
Allow: /

# ---- Classic search engines ----
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Applebot
Allow: /
User-agent: YandexBot
Allow: /
User-agent: Baiduspider
Allow: /

# ---- AI search / retrieval crawlers (ALLOW = get found and cited by AI) ----
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /

# ---- Model-training opt-out tokens (blocked on purpose) ----
# Google-Extended and Applebot-Extended are TRAINING controls, not search
# crawlers. Disallowing them does not affect Google or Apple search indexing
# (that is Googlebot / Applebot, both allowed above) — it only withholds our
# content from Gemini and Apple Intelligence model training.
User-agent: Google-Extended
Disallow: /
User-agent: Applebot-Extended
Disallow: /

# ---- Pure AI training crawlers (blocked: no effect on AI search citations) ----
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Amazonbot
Disallow: /
# Additional training / data-scraping crawlers. Cloudflare's AI Crawl Control
# also blocks these at the edge; listing them here keeps the policy intact even
# if that dashboard setting is ever reset. Only user-agent strings we can verify
# are listed — a misspelled UA is a dead rule that only looks protective.
User-agent: PetalBot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Google-CloudVertexBot
Disallow: /

# ---- Paths we do not want crawled ----
User-agent: *
Disallow: /index.php
Disallow: /admin/

Sitemap: https://www.hellamax.com/sitemap.xml