# 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

# ARWANATOTOPRO robots.txt
# This file controls how search engines and bots crawl the site

# ====================================================================
# CONTENT SIGNALS per EU Directive 2019/790
# ====================================================================
# search=yes:        Allow search engines to index and display results
# ai-input=yes:      Allow AI models to use content for real-time generation
# ai-train=no:       DO NOT allow training data collection for AI models
# ====================================================================

# General rule for all bots (SINGLE DEFINITION)
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
Allow: /login
Allow: /register
Disallow: /api/
Disallow: /admin/
Disallow: /private/
Disallow: /*.json$
Disallow: /*?*sort=
Disallow: /*?*filter=
Disallow: /*?*utm_
Disallow: /search
Disallow: /checkout
Crawl-delay: 1

# Priority untuk search engines utama (override general rule)
User-agent: Googlebot
Allow: /
Crawl-delay: 0

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

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

# ====================================================================
# BLOK: Bot Agresif (Competitive Intelligence & Data Scraping)
# ====================================================================
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# ====================================================================
# BLOK: AI Training Bots (Anti-scraping untuk model training)
# ====================================================================
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# ====================================================================
# SITEMAP REFERENCES
# ====================================================================
Sitemap: https://ARWANATOTOPRO.net/sitemap.xml
Sitemap: https://ARWANATOTOPRO.net/sitemap-0.xml