# 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

# Allow all legitimate crawlers by default
User-agent: *
Allow: /
Crawl-delay: 1

# Block sensitive and build areas
Disallow: /admin/
Disallow: /.git/
Disallow: /.github/
Disallow: /_site/
Disallow: /node_modules/
Disallow: /assets/dist/
Disallow: /.devcontainer/
Disallow: /scripts/

# Sitemaps for better indexing
Sitemap: https://deanmilojevic.com/sitemap.xml
Sitemap: https://deanmilojevic.com/feed.xml

# Major search engines (explicit allow with optimized crawl rates)
User-agent: Googlebot
Allow: /
Crawl-delay: 0

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

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

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

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

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

# Social media and sharing bots
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: SkypeUriPreview
Allow: /

User-agent: SlackBot
Allow: /

User-agent: DiscordBot
Allow: /

# Accessibility and validation bots
User-agent: W3C_Validator
Allow: /

User-agent: W3C_CSS_Validator
Allow: /

User-agent: HTML_Validator
Allow: /

# Block AI/LLM scrapers
User-agent: OpenAI
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Anthropic-AI
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: ia_archiver
Disallow: /

# Block aggressive crawlers and SEO tools
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

# Block generic scrapers and tools
User-agent: Scrapy
Disallow: /

User-agent: python-requests
Disallow: /

User-agent: Wget
Disallow: /

User-agent: curl
Disallow: /