# 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 — legarecords.fr
# https://www.robotstxt.org/

User-agent: *
Allow: /

# Pages publiques : tout est indexable par défaut.
# On bloque uniquement les endpoints internes et les surfaces sensibles.

# Endpoints admin / debug — pas censés être atteignables sans auth de toute
# façon (cf. SEC-1 à SEC-5) mais on les exclut explicitement par prudence.
Disallow: /admin
Disallow: /admin/
Disallow: /debug-artists
Disallow: /*?debug-artists

# Callbacks OAuth — pas d'intérêt pour le SEO
Disallow: /*?code=
Disallow: /*?state=

# Pages de tunnel de vente (LemonSqueezy) — pas notre canonical
Disallow: /checkout
Disallow: /payment-success
Disallow: /payment-cancelled

# Sitemap principal
Sitemap: https://legarecords.fr/sitemap.xml

# Crawl-delay raisonnable pour ne pas surcharger l'edge function
# (la plupart des bots sérieux l'ignorent mais ça reste un signal)
Crawl-delay: 2

# Bots à bannir totalement (IA scrapers — protège la propriété intellectuelle
# du contenu musical contre l'entraînement non consenti)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /