# Bataoo robots.txt
# Policy: https://bataoo.com/bot
# Grievance: https://bataoo.com/grievance · contact@bataoo.com
#
# Bataoo does NOT actively crawl the open web. We index only:
#   - RSS feeds (publisher-consented syndication)
#   - Open-license corpora (Wikipedia CC-BY-SA, Wikidata CC0, data.gov.in OGDL,
#     AI4Bharat Sangraha CC-BY, etc.)
#   - Government public-domain sources
#   - User-generated content on /pucho/ (Bataoo is intermediary; IT Rules 2021)
#
# This file controls crawlers that visit bataoo.com itself.

# ---- Allow real search engines (we want SEO traffic) ----
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: BraveBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Mojeekbot
Allow: /

# ---- Allow citation-driving AI engines (they cite sources; drive direct clicks) ----
User-agent: PerplexityBot
Allow: /
Disallow: /pucho/

User-agent: ClaudeBot
Allow: /
Disallow: /pucho/

# ---- Block training-only AI bots (no citation; just data extraction) ----
User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# ---- Default for everything else ----
User-agent: *
Disallow: /api/
Disallow: /talk
Disallow: /admin/
Disallow: /frontadmin/
Allow: /

Sitemap: https://bataoo.com/sitemap.xml