# 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

# ============================================================
# Introgreen.nl
# AI-zoekmachines en beperkte AI-training toegestaan
# Meta volledig geblokkeerd
# ============================================================

# ------------------------------------------------------------
# META — VOLLEDIG BLOKKEREN
# ------------------------------------------------------------

User-agent: MetaAI
User-agent: meta-externalagent
User-agent: meta-webindexer
User-agent: facebookexternalhit
User-agent: Facebot
Content-Signal: search=no,ai-input=no,ai-train=no,use=immediate
Disallow: /

# ------------------------------------------------------------
# CLAUDE EN OPENAI — BEPERKTE TRAINING TOEGESTAAN
# ------------------------------------------------------------

User-agent: ClaudeBot
User-agent: GPTBot
Content-Signal: ai-train=yes,use=reference

# Magento-parameters blokkeren
Disallow: /*?

# Persoonlijke en technische routes blokkeren
Disallow: /customer/
Disallow: /checkout/
Disallow: /catalogsearch/
Disallow: /wishlist/
Disallow: /catalog/product_compare/
Disallow: /admin/
Disallow: /bin/
Disallow: /setup/
Disallow: /update/
Disallow: /dev/

# Openbare assets toestaan
Allow: /media/
Allow: /static/

# ------------------------------------------------------------
# ONGEWENSTE BULK- EN SEO-CRAWLERS
# ------------------------------------------------------------

User-agent: CCBot
User-agent: Bytespider
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: DataForSeoBot
Disallow: /

# ------------------------------------------------------------
# ZOEKMACHINES EN AI-ZOEKBOTS
# ------------------------------------------------------------

User-agent: *
Content-Signal: search=yes,ai-input=yes,use=reference

# Alle Magento-filterparameters blokkeren
Disallow: /*?

# Persoonlijke en technische routes blokkeren
Disallow: /customer/
Disallow: /checkout/
Disallow: /catalogsearch/
Disallow: /wishlist/
Disallow: /catalog/product_compare/
Disallow: /admin/
Disallow: /bin/
Disallow: /setup/
Disallow: /update/
Disallow: /dev/

# Openbare assets toestaan
Allow: /media/
Allow: /static/

# ------------------------------------------------------------
# SITEMAP
# ------------------------------------------------------------

Sitemap: https://introgreen.nl/pub/media/sitemap/sitemap.xml