# 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 – Mini1221
# https://mini1221.online/robots.txt
# Generated: 2025-06-15

# ─── Allow All Major Search Engines ───────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 2

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 3

User-agent: Slurp
Allow: /
Crawl-delay: 5

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /
Crawl-delay: 5

User-agent: YandexBot
Allow: /
Crawl-delay: 5

User-agent: facebot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

# ─── Allow AI Crawlers (LLM Indexing) ─────────────────────────────
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

# ─── Default Rule ──────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /wp-admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /private/
Disallow: /api/internal/
Disallow: /user/account/
Disallow: /login
Disallow: /register
Disallow: /*?ref=*
Disallow: /*?utm_source=*
Disallow: /*?session=*
Disallow: /search?*
Crawl-delay: 5

# ─── Sitemaps ──────────────────────────────────────────────────────
Sitemap: https://mini1221.online/sitemap.xml
Sitemap: https://mini1221.online/sitemap-images.xml
Sitemap: https://mini1221.online/sitemap-news.xml

# ─── Host Directive ────────────────────────────────────────────────
Host: https://mini1221.online