# robots.txt — www.regeneron.com
# updated 09/11/2026
#
# CHANGES IN THIS VERSION (vs. 05/14/2026):
#   1. Added Content-Signal directives to BOTH crawler groups (see note below).
#   2. No other rules added, removed, or reordered.
#
# NOTE ON CONTENT-SIGNAL PLACEMENT:
#   robots.txt group matching is most-specific-wins. A crawler named in the
#   "AI / LLM Crawlers" group below does NOT read the "User-agent: *" group at
#   all. Content-Signal must therefore appear in BOTH groups to reach every
#   crawler. Declaring it only once under "User-agent: *" would leave all 13
#   named AI agents without a signal.
#
#   Declared preference: search=yes, ai-input=yes, ai-train=no
#     search=yes    -> permit traditional search indexing
#     ai-input=yes  -> permit use as grounding input for AI answers (citation)
#     ai-train=no   -> decline use as generative model training data
#
#   Reference: https://contentsignals.org

# AI / LLM Crawlers
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: Google-Extended
User-agent: ClaudeBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Diffbot

Content-Signal: search=yes, ai-input=yes, ai-train=no

Disallow: /about/leadership$
Disallow: /about/leadership/$
Disallow: /node/*
Disallow: /search-results*
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
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
# Paths (no clean URLs)
Disallow: /?q=admin
Disallow: /?q=comment/reply
Disallow: /?q=filter/tips
Disallow: /?q=node/add
Disallow: /?q=search
Disallow: /?q=user/password
Disallow: /?q=user/register
Disallow: /?q=user/login
Disallow: /?q=user/logout

User-agent: *

Content-Signal: search=yes, ai-input=yes, ai-train=no

Disallow: /node/*
Disallow: /search-results*
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
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
# Paths (no clean URLs)
Disallow: /?q=admin
Disallow: /?q=comment/reply
Disallow: /?q=filter/tips
Disallow: /?q=node/add
Disallow: /?q=search
Disallow: /?q=user/password
Disallow: /?q=user/register
Disallow: /?q=user/login
Disallow: /?q=user/logout

Sitemap: https://www.regeneron.com/sitemap.xml
Sitemap: https://www.regeneron.com/images-sitemap.xml
Sitemap: https://www.regeneron.com/video-sitemap.xml

# End robots.txt