# 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 marcotoniut.github.io
# Purpose: Allow legitimate search engines while blocking AI training crawlers
# Content-signal directives are provided via HTTP headers (see next.config.js) because robots.txt rejects that format.

# ============================================================
# ALLOWED: Legitimate search engine crawlers
# ============================================================

# Google Search
User-agent: Googlebot
Allow: /

# Bing Search
User-agent: Bingbot
Allow: /

# DuckDuckGo Search
User-agent: DuckDuckBot
Allow: /

# Yandex Search
User-agent: Yandex
Allow: /

# Yahoo Search
User-agent: Slurp
Allow: /

# ============================================================
# DISALLOWED: AI training and data mining crawlers
# ============================================================

# OpenAI Crawlers (GPT, ChatGPT)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Google Extended (AI training)
User-agent: Google-Extended
Disallow: /

# Anthropic Claude
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Common Crawl (dataset for AI training)
User-agent: CCBot
Disallow: /

# Perplexity AI
User-agent: PerplexityBot
Disallow: /

# Meta/Facebook AI
User-agent: FacebookBot
Disallow: /

User-agent: facebookexternalhit
Disallow: /

# Bytespider (TikTok/ByteDance)
User-agent: Bytespider
Disallow: /

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

# Diffbot
User-agent: Diffbot
Disallow: /

# Omgili (content aggregation)
User-agent: omgili
Disallow: /

# ============================================================
# GLOBAL RULES: Apply to all other crawlers not listed above
# ============================================================

User-agent: *
Allow: /

# ============================================================
# SITEMAP
# ============================================================

Sitemap: https://marcotoniut.github.io/sitemap.xml