# 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

User-agent: *
Disallow: /

# ── Google ──
User-agent: Googlebot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: AdsBot-Google
Disallow: /

# ── OpenAI / ChatGPT ──
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: OAI-SearchBot
Disallow: /

# ── Anthropic / Claude ──
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Claude-Web
Disallow: /

# ── Common Crawl (nguồn train nhiều model) ──
User-agent: CCBot
Disallow: /

# ── Meta / Facebook ──
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /

# ── Apple ──
User-agent: Applebot
Disallow: /
User-agent: Applebot-Extended
Disallow: /

# ── Perplexity ──
User-agent: PerplexityBot
Disallow: /

# ── ByteDance / TikTok ──
User-agent: Bytespider
Disallow: /

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

# ── Diffbot ──
User-agent: Diffbot
Disallow: /

# ── You.com ──
User-agent: YouBot
Disallow: /

# ── Allen Institute AI ──
User-agent: AI2Bot
Disallow: /

# ── Webz.io / Omgili ──
User-agent: Omgilibot
Disallow: /
User-agent: Omgili
Disallow: /

# ── iask.ai ──
User-agent: iaskspider
Disallow: /

# ── Huawei PetalSearch ──
User-agent: PetalBot
Disallow: /

# ── Magpie / Magnite ──
User-agent: magpie-crawler
Disallow: /

# ── DataForSeo ──
User-agent: DataForSeoBot
Disallow: /

# ── img2dataset (AI training tool) ──
User-agent: img2dataset
Disallow: /

# ── Timpi ──
User-agent: Timpibot
Disallow: /

# ── Amazon Alexa ──
User-agent: Amazonbot
Disallow: /

# ── Bing / Microsoft ──
User-agent: bingbot
Disallow: /
User-agent: BingPreview
Disallow: /
User-agent: msnbot
Disallow: /

# ── Baidu ──
User-agent: Baiduspider
Disallow: /

# ── Yandex ──
User-agent: YandexBot
Disallow: /

# ── SEO/data scrapers (thường dùng để train hoặc aggregate) ──
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: rogerbot
Disallow: /
User-agent: PaperLiBot
Disallow: /

# ── Turnitin (academic plagiarism / AI training) ──
User-agent: TurnitinBot
Disallow: /

Sitemap: https://calendar.nickyraghavan.com/robots.txt