# 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

# NewsDarpan robots.txt
# AEO/GEO discovery files for AI assistants and search systems:
# LLM context: https://newsdarpan.in/llms.txt
# Full LLM context: https://newsdarpan.in/llms-full.txt
# RSS feed: https://newsdarpan.in/feed.xml
# News sitemap: https://newsdarpan.in/news-sitemap.xml
# Sitemap index: https://newsdarpan.in/sitemap-index.xml
# Section sitemap: https://newsdarpan.in/sitemap-sections.xml
# IMPORTANT: Crawl-delay is optional — set to 1 second to be considerate

User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /login
Disallow: /saved
Disallow: /account
Disallow: /search
Disallow: /search/
Disallow: /api/

# Answer assistants and search engines — allow content crawling for AI summaries and citations
User-agent: GPTBot
Allow: /article/
Allow: /category/
Allow: /tag/
Allow: /author/
Allow: /
Crawl-delay: 1

User-agent: Google-Extended
Allow: /article/
Allow: /category/
Allow: /tag/
Allow: /author/
Allow: /
Crawl-delay: 1

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

User-agent: ClaudeBot
Allow: /article/
Allow: /category/
Allow: /tag/
Allow: /
Crawl-delay: 1

User-agent: Applebot-Extended
Allow: /
Crawl-delay: 1

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 1

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

# Training/data harvesters — block these entirely
User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Bytespider
Disallow: /

Host: newsdarpan.in
Sitemap: https://newsdarpan.in/sitemap-index.xml
Sitemap: https://newsdarpan.in/sitemap.xml
Sitemap: https://newsdarpan.in/news-sitemap.xml
Sitemap: https://newsdarpan.in/sitemap-sections.xml