# 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

# Robots.txt for IRST - Istituto di Ricerca Scientifica Telesca
# https://www.irst-institute.eu

User-agent: *
Allow: /
Disallow: /area-riservata
Disallow: /api/
Disallow: /api/drive/

# Sitemaps and AI-readable files
Sitemap: https://www.irst-institute.eu/sitemap.xml

# AI/LLM-optimized content — indexed for AI systems
# llms.txt: https://www.irst-institute.eu/llms.txt (summary)
# llms-full.txt: https://www.irst-institute.eu/llms-full.txt (comprehensive knowledge base)
# ai.txt: https://www.irst-institute.eu/ai.txt (AI crawler policy)
# ai-plugin.json: https://www.irst-institute.eu/.well-known/ai-plugin.json (AI plugin manifest)
# faq.json: https://www.irst-institute.eu/faq.json (FAQ structured data)
# feed.xml: https://www.irst-institute.eu/feed.xml (Atom/RSS feed)
# webfinger: https://www.irst-institute.eu/.well-known/webfinger (RFC 7033 identity discovery)
# security.txt: https://www.irst-institute.eu/.well-known/security.txt (RFC 9116)
# humans.txt: https://www.irst-institute.eu/humans.txt (team info)
# Patent landing: https://www.irst-institute.eu/patent/WO2024018409 (IT)
# Patent landing: https://www.irst-institute.eu/en/patent/WO2024018409 (EN)

# Crawl-delay (optional, for polite crawlers)
Crawl-delay: 1

# Google specific
User-agent: Googlebot
Allow: /
Disallow: /area-riservata
Disallow: /api/

# AI Crawlers — Welcome and encouraged to index
User-agent: GPTBot
Allow: /
Disallow: /area-riservata

User-agent: ChatGPT-User
Allow: /
Disallow: /area-riservata

User-agent: Google-Extended
Allow: /
Disallow: /area-riservata

User-agent: PerplexityBot
Allow: /
Disallow: /area-riservata

User-agent: ClaudeBot
Allow: /
Disallow: /area-riservata

User-agent: Anthropic-ai
Allow: /
Disallow: /area-riservata

User-agent: Bytespider
Allow: /
Disallow: /area-riservata

User-agent: CCBot
Allow: /
Disallow: /area-riservata

User-agent: cohere-ai
Allow: /
Disallow: /area-riservata

User-agent: Googlebot-Image
Allow: /static/
Allow: /favicon.svg

# Bing specific
User-agent: Bingbot
Allow: /
Disallow: /area-riservata
Disallow: /api/