# 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

# tarabya.net — robots.txt
# Last updated: 2026-04-28
# Strategy: ALL bots welcome during initial index test phase.

# ─── Major search engines ────────────────────────────────
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Slurp
Allow: /
User-agent: YandexBot
Allow: /
User-agent: YandexImages
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Baiduspider
Allow: /
User-agent: Sogou
Allow: /
User-agent: Applebot
Allow: /

# ─── AI / LLM crawlers (GEO — Generative Engine Optimization) ───
# We WANT to be cited by AI search. Allow all known AI bots.
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Bytespider
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: Meta-ExternalAgent
Allow: /
User-agent: FacebookBot
Allow: /
User-agent: meta-externalagent
Allow: /
User-agent: ImagesiftBot
Allow: /
User-agent: YouBot
Allow: /
User-agent: PiplBot
Allow: /
User-agent: Mojeek
Allow: /
User-agent: Diffbot
Allow: /

# ─── SEO audit & monitoring tools ─────────────────────────
User-agent: AhrefsBot
Allow: /
User-agent: SemrushBot
Allow: /
User-agent: MJ12bot
Allow: /
User-agent: DotBot
Allow: /
User-agent: BLEXBot
Allow: /

# ─── Default catch-all ────────────────────────────────────
User-agent: *
Allow: /
Disallow: /_design-import/
Disallow: /brand/_autogen-tokens.json
Disallow: /.claude/
Disallow: /*.jsx$
Disallow: /demo.html

# Crawl politeness for unknown bots
Crawl-delay: 1

# Sitemap index
Sitemap: https://tarabya.net/sitemap.xml

# Host (canonical preference for Yandex)
Host: tarabya.net