# robots.txt — Lamon Hekwerk (https://lamonhekwerken.be)
# Afsluitingen en omheiningen — Sint-Truiden, Limburg (BE)
#
# Policy: the whole site is public and crawlable. Search engines and
# AI assistants are both welcome — being cited in AI answers is a
# distribution channel, not a leak. Only infrastructure paths and
# tracking-parameter duplicates are excluded.

# ---------------------------------------------------------------------------
# Default — every crawler not named below
# ---------------------------------------------------------------------------
User-agent: *
Allow: /

# /_astro/ is deliberately NOT blocked. Google and Bing must fetch the hashed
# CSS/JS/font bundles to render the page; hashed asset files are not indexable
# content anyway, and on a site this size crawl budget is a non-issue. Blocking
# it and re-allowing per extension is fragile — longest-match rule precedence
# can let the Disallow win and break rendering.

# Non-content endpoints: server routes, not pages.
Disallow: /_server-islands/
Disallow: /_actions/
Disallow: /_image
Disallow: /api/

# Campaign / session parameters create duplicate URLs with no unique content.
Disallow: /*?*utm_
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /*?*sessionid=

# ---------------------------------------------------------------------------
# Search engines — explicit, so a future tightening of `*` can't lock them out
# ---------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Qwantify
Allow: /

User-agent: Applebot
Allow: /

# ---------------------------------------------------------------------------
# AI assistants and answer engines (GEO)
# Allowed on purpose: these agents surface the business in AI answers.
# ---------------------------------------------------------------------------

# Google — Gemini / AI Overviews grounding
User-agent: Google-Extended
Allow: /

# OpenAI — ChatGPT live browsing, search index, model training
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

# Anthropic — Claude live fetches and search index
User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Microsoft Copilot
User-agent: Applebot-Extended
Allow: /

# Common Crawl — feeds many downstream models
User-agent: CCBot
Allow: /

# Others
User-agent: Meta-ExternalAgent
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Bytespider
Allow: /

# ---------------------------------------------------------------------------
# SEO / scraping tools — blocked to save bandwidth, not for secrecy.
# Remove a block if you start using that tool for your own site audits.
# ---------------------------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SeekportBot
Disallow: /

# ---------------------------------------------------------------------------
# Sitemap — absolute URL, as required by the protocol
# ---------------------------------------------------------------------------
Sitemap: https://lamonhekwerken.be/sitemap-index.xml