# 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

# robots.txt for madhavbaug.org
# Updated: 2025-09-12
# Purpose: Block hacked/spammy URLs, demo/staging, and non-public resources
# while ensuring SEO-critical resources remain crawlable.

User-agent: *
# Block hacked/spammy paths
Disallow: /goods/
Disallow: /project-cat/
Disallow: /author/

# Block admin, sensitive, or duplicate environments
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /cgi-bin/
Disallow: /includes/
Disallow: /private/
Disallow: /scripts/
Disallow: /demo/
Disallow: /staging/
Disallow: /test/

# Allow essential static resources (needed for rendering)
Allow: /*.css$
Allow: /*.js$
Allow: /wp-content/uploads/

# Security: Prevent indexing of backup/original files
Disallow: /backup-oroginal/

# Ensure all other public pages are crawlable
Allow: /

# Sitemap(s) - must exist and only contain clean URLs
Sitemap: https://madhavbaug.org/sitemap.xml