# 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

# db.dov.vn — robots.txt
# Tối ưu cho AI crawlers

# ── Standard crawlers ─────────────────────────────────
User-agent: *
Allow: /
Disallow: /cache/
Disallow: /includes/
Disallow: /api/
Disallow: /pages/
Disallow: /search?

# ── Google ────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

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

User-agent: BingPreview
Allow: /

# ── OpenAI ────────────────────────────────────────────
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ── Anthropic ─────────────────────────────────────────
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

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

User-agent: Perplexity-User
Allow: /

# ── Google Bard / Gemini ──────────────────────────────
User-agent: Bard
Allow: /

# ── Apple ─────────────────────────────────────────────
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ── Common Crawl ──────────────────────────────────────
User-agent: CCBot
Allow: /

# ── Meta ──────────────────────────────────────────────
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

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

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

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

# ── Mistral ───────────────────────────────────────────
User-agent: MistralAI-User
Allow: /

# ── DuckDuckGo ────────────────────────────────────────
User-agent: DuckDuckBot
Allow: /

# ── Sitemaps & AI discovery ──────────────────────────
Sitemap: https://db.dov.vn/sitemap.xml

# Hint cho LLM crawler — file llms.txt + ai.json
# (không phải chuẩn robots.txt nhưng nhiều AI parse được)
# AI-Discovery: https://db.dov.vn/ai.json
# LLM-Index:    https://db.dov.vn/llms.txt
# LLM-Full:     https://db.dov.vn/llms-full.txt