# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Bhavishya News robots.txt
# https://bhavishyanews.com/
#
# /search, /auth and /local/saved are not blocked: those pages send "noindex",
# which Google can only see if it may crawl them.
#
# One shared group: every crawler below (search, AI, social previews and all
# others) may read the public site. Private areas are closed to all of them.
# (A crawler follows only its most specific group, so the rules must live in
# the same group as its User-agent line.)

# Search engines
User-agent: Googlebot
User-agent: Googlebot-News
User-agent: Googlebot-Image
User-agent: Google-Extended
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: YandexBot
User-agent: Baiduspider
# AI / LLM crawlers
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
# Social / link previews
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: Facebot
User-agent: LinkedInBot
User-agent: WhatsApp
User-agent: TelegramBot
# Everyone else
User-agent: *
Allow: /
Allow: /api/public/media/
Disallow: /admin
Disallow: /api/

Sitemap: https://bhavishyanews.com/sitemap.xml
Sitemap: https://bhavishyanews.com/news-sitemap.xml