# 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

# 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