#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

# robots.txt — cleaned and AI-friendly

# --- AI Crawlers: explicitly allowed ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /


# --- Block administrative paths ---
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/

# --- Block core system directories ---
Disallow: /core/
Disallow: /profiles/
Disallow: /sites/default/files/private/

# --- Sensitive files ---
Disallow: /README.txt
Disallow: /web.config

# --- Default crawler rules ---
User-agent: *

Sitemap: https://www.nexgardforpets.com/sitemap.xml