# 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.

# ============================================================
# Default policy: search OK, AI retrieval OK, AI training NO
# ============================================================
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
# Paramètres qui contournent le cache : variantes de devise et ajouts aux favoris.
# Mêmes pages que l'URL sans paramètre ; chaque visite coûte 2 à 5 s de calcul serveur.
Disallow: /*wmc-currency=
Disallow: /*add_to_wishlist=

# ============================================================
# AI TRAINING crawlers — disallowed
# ============================================================

# OpenAI — training
User-agent: GPTBot
Disallow: /

# Anthropic — training
User-agent: ClaudeBot
Disallow: /

# Anthropic — legacy training UAs (deprecated but still observed)
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Common Crawl — dataset feeding many LLMs
User-agent: CCBot
Disallow: /

# Google — Gemini training (Googlebot for Search reste autorisé)
User-agent: Google-Extended
Disallow: /

# Apple — Apple Intelligence training (Applebot reste autorisé pour Siri/Spotlight)
User-agent: Applebot-Extended
Disallow: /

# Meta — Llama training
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

# ByteDance — Doubao training
User-agent: Bytespider
Disallow: /

# Amazon — training/Alexa
User-agent: Amazonbot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# Autres scrapers connus utilisés pour training
User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FriendlyCrawler
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: PetalBot
Disallow: /

# ============================================================
# AI SEARCH / RETRIEVAL / USER-INITIATED — explicitly allowed
# (listed for clarity even if allowed by default)
# ============================================================

# Anthropic (Claude-SearchBot, Claude-User), OpenAI (OAI-SearchBot, ChatGPT-User),
# Perplexity (PerplexityBot, Perplexity-User) — recherche et consultation à la demande.
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /
Disallow: /*wmc-currency=
Disallow: /*add_to_wishlist=

# ============================================================
# Website's specific
# ============================================================

User-agent: Googlebot-Image
Disallow: /wp-content/uploads/2020/09/signature.svg
Disallow: /wp-content/uploads/2021/04/signature-small-1.png

Sitemap: https://www.thomascrauwels.ch/sitemap_index.xml