# 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

# CitizenHub - AI & Traditional Search Bot Configuration
# Updated: March 17, 2026

# Allow all traditional search engine crawlers
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# AI Bot Configuration - Allow all AI crawlers for maximum visibility

# OpenAI GPTBot (ChatGPT)
User-agent: GPTBot
Allow: /

# Anthropic Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Google AI Training (Gemini, Bard)
User-agent: Google-Extended
Allow: /

# Common Crawl (used by many AI models for training)
User-agent: CCBot
Allow: /

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

# Meta/Facebook AI
User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Bytespider (TikTok/ByteDance)
User-agent: Bytespider
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# Allow all other bots by default
User-agent: *
Allow: /

# Disallow admin/private areas (if any)
Disallow: /admin/
Disallow: /private/
Disallow: /*.json$
Disallow: /api/

# Sitemaps
Sitemap: https://citizenhub.in/sitemap.xml
Sitemap: https://citizenhub.in/llms.txt
Sitemap: https://citizenhub.in/llms-full.txt

# Crawl-delay (optional, adjust if needed)
# Crawl-delay: 1