# robots.txt — what-els.eu
# WhatEls! — officiële online flagship store voor K-design & You're My Lobster
# Last updated: 2026-08-26

# ============================================================
# Default rules — alle crawlers
# ============================================================
User-agent: *
Allow: /

# Expliciete allow-lijst: indexeerbare kernsecties (alle talen)
Allow: /$
Allow: /shop
Allow: /brands/
Allow: /lookbook
Allow: /outlet
Allow: /help
Allow: /levering
Allow: /stayfresh
Allow: /en/
Allow: /fr/
Allow: /de/

# Machine-readable bronnen (LLM's & shopping-crawlers)
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /product-feed.json
Allow: /merchant-feed.xml
Allow: /merchant-feed-be-fr.xml
Allow: /merchant-feed-fr.xml
Allow: /merchant-feed-de.xml
Allow: /sitemap-index.xml
Allow: /sitemap-pages.xml
Allow: /sitemap-products.xml
Allow: /sitemap-colours.xml


# Categorie-filters blijven crawlbaar zodat Google de canonical naar de
# merk-hub (/brands/:merk/:categorie) kan lezen; de hub is de versie die
# geïndexeerd hoort te worden.
Allow: /shop?categorie=*
Allow: /shop?merk=*

# Kleurvarianten zijn eigen indexeerbare pagina's (sitemap-colours.xml).
# Maatvarianten niet: die vallen samen met de kleur-URL.
Allow: /product/*?colour=*
Disallow: /*?size=*
Disallow: /*&size=*


# Privacy / persoonlijke gebruikersdata (ook in /en/, /fr/, /de/)
Disallow: /wishlist
Disallow: /account
Disallow: /profile
Disallow: /*/wishlist
Disallow: /*/account
Disallow: /*/profile

# Transactie-flows (geen waarde voor zoekresultaten)
Disallow: /cart
Disallow: /checkout
Disallow: /thank-you
Disallow: /order-confirmation
Disallow: /*/cart
Disallow: /*/checkout
Disallow: /*/thank-you
Disallow: /*/order-confirmation

# Interne / utility routes
Disallow: /api/
Disallow: /.lovable/
Disallow: /admin
Disallow: /admin/
Disallow: /samen/
Disallow: /preview
Disallow: /*?preview=*

# Crawl-budget besparen op zoek- en filter-noise
Disallow: /*?zoek=*
Disallow: /*?q=*
Disallow: /*?search=*
Disallow: /*?sort=*
Disallow: /*?page=*
Disallow: /*?sorteer=*
Disallow: /*&sorteer=*
Disallow: /*?filter=*
Disallow: /*&filter=*
Disallow: /*?pagina=*
Disallow: /*&pagina=*
Disallow: /*&zoek=*
Disallow: /*?utm_*
Disallow: /*&utm_*
Disallow: /*?fbclid=*
Disallow: /*?gclid=*
Disallow: /*?kleur=*
Disallow: /*&kleur=*
Disallow: /*?maat=*
Disallow: /*&maat=*
Disallow: /*?prijs=*
Disallow: /*&prijs=*

# ============================================================
# Zoekmachines — geen extra beperkingen, maar expliciet zodat
# per-agent regels de *-groep niet per ongeluk overschrijven.
# ============================================================
User-agent: Googlebot
Allow: /
Disallow: /account
Disallow: /wishlist
Disallow: /cart
Disallow: /checkout
Disallow: /admin
Disallow: /api/
Disallow: /*?zoek=*
Disallow: /*?sort=*
Disallow: /*?page=*
Disallow: /*?sorteer=*
Disallow: /*?filter=*
Disallow: /*?pagina=*

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /account
Disallow: /wishlist
Disallow: /cart
Disallow: /checkout
Disallow: /admin
Disallow: /api/

# ============================================================
# AI / LLM crawlers — expliciet toegestaan voor brand-visibility
# (per agent dezelfde privacy- en transactie-uitsluitingen)
# ============================================================
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Meta-ExternalAgent
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /product-feed.json
Disallow: /account
Disallow: /profile
Disallow: /wishlist
Disallow: /cart
Disallow: /checkout
Disallow: /thank-you
Disallow: /order-confirmation
Disallow: /admin
Disallow: /admin/
Disallow: /api/
Disallow: /samen/

# ============================================================
# Aggressieve scrapers beperken (bandwidth-bescherming)
# ============================================================
User-agent: AhrefsBot
Crawl-delay: 10
Disallow: /account
Disallow: /cart
Disallow: /checkout
Disallow: /admin
Disallow: /api/

User-agent: SemrushBot
Crawl-delay: 10
Disallow: /account
Disallow: /cart
Disallow: /checkout
Disallow: /admin
Disallow: /api/

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# ============================================================
# Sitemaps — één bron van waarheid (de index verwijst door naar
# sitemap-pages.xml en sitemap-products.xml)
# ============================================================
Sitemap: https://what-els.eu/sitemap-index.xml

# Host preference (helpt sommige crawlers met canonical)
Host: what-els.eu