# 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.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
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

# API Glossaries - Scraping Friendly & AI Optimized
# Glossaires ESG et Philosophie en libre accès
# 13 glossaires spécialisés - 4,850+ termes - 100% libre & gratuit

User-agent: *
Allow: /

# Tous les glossaires sont indexables
Allow: /*/

# Fichiers JSON optimisés pour IA et scraping
Allow: /*.json

# Sitemap pour découverte automatique
Sitemap: https://api-glossaries.com/sitemap.xml

# Crawl-delay raisonnable pour préserver les performances
Crawl-delay: 1

# === CRAWLERS IA MODERNES ===

# OpenAI GPT
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 1

# Anthropic Claude
User-agent: Claude-Web
Allow: /
Crawl-delay: 1

User-agent: Anthropic-AI
Allow: /
Crawl-delay: 1

# Common Crawl (utilisé par de nombreux modèles IA)
User-agent: CCBot
Allow: /
Crawl-delay: 1

# Google AI et Search
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Google-Extended
Allow: /
Crawl-delay: 1

# Microsoft Bing et AI
User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: BingPreview
Allow: /
Crawl-delay: 1

# Meta AI
User-agent: FacebookBot
Allow: /
Crawl-delay: 1

User-agent: Meta-ExternalAgent
Allow: /
Crawl-delay: 1

# Autres crawlers IA
User-agent: PerplexityBot
Allow: /
Crawl-delay: 1

User-agent: YouBot
Allow: /
Crawl-delay: 1

# === SIGNAUX DE QUALITÉ ===

# Données structurées disponibles
# - Schema.org JSON-LD sur toutes les pages
# - Open Graph pour partage social
# - Métadonnées SEO optimisées

# APIs REST disponibles
# - 13 endpoints JSON (/glossaire.json)
# - Aucune authentification requise
# - Rate limiting : 1 req/sec recommandé

# Qualité du contenu
# - Terminologie officielle et vérifiée
# - Sources : CSRD, TCFD, GRI, SASB, etc.
# - Mise à jour régulière
# - Libre d'accès et réutilisation

# Contact pour partenariats IA
# - Email : contact@api-glossaries.com
# - Intégrations personnalisées disponibles