www.adl.org

            Domain Name: ADL.ORG
Registrar: Network Solutions, LLC
Domain Status: client transfer prohibited
Registry Expiry Date: 2034-07-20T04:00:00Z
Creation Date: 1995-07-21T04:00:00.41Z
Updated Date: 2025-12-19T00:04:35.658Z
Name Server: DARL.NS.CLOUDFLARE.COM
Name Server: IRIS.NS.CLOUDFLARE.COM
REGISTRAR Contact: Network Solutions, LLC
>>> Last update of RDAP database: 2026-02-16T21:39:25Z         

			#
# 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

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# 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
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# ============================================================
# robots.txt — Indexing allowed; AI browsing/retrieval allowed;
# AI training/embedding crawlers restricted (where respected).
# Drupal 11 + Cloudflare compatible
# ============================================================

# --- Sitemaps ---
Sitemap: https://www.adl.org/sitemap.xml

# ------------------------------------------------------------
# DEFAULT: allow public content to be crawled/indexed
# ------------------------------------------------------------
User-agent: *
Allow: /

# Explicitly allow public files (reports, PDFs, media)
Allow: /sites/default/files/

# ------------------------------------------------------------
# DRUPAL CORE/PROFILES: allow assets, disallow directories
# ------------------------------------------------------------
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg

Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg

Disallow: /core/
Disallow: /profiles/

# ------------------------------------------------------------
# NON-PUBLIC / LOW-VALUE DRUPAL ROUTES (crawl hygiene)
# ------------------------------------------------------------
Disallow: /admin/
Disallow: /user/login
Disallow: /user/logout
Disallow: /user/password
Disallow: /user/register
Disallow: /node/add/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /media/oembed
Disallow: /*/media/oembed

# No-clean-URL equivalents (if any still exist)
Disallow: /index.php/admin/
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/node/add/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# ------------------------------------------------------------
# INTERNAL SITE SEARCH (avoid indexing; reduce crawl traps)
# NOTE: Best practice is also meta robots "noindex,follow" in Drupal.
# ------------------------------------------------------------
Disallow: /search/
Disallow: /global-search
Disallow: /global-search?*
Disallow: /es/global-search
Disallow: /resources/search/research-analysis

# Optional parameter crawl traps (enable only if these exist at scale)
# Disallow: /*?page=
# Disallow: /*&page=
# Disallow: /*?sort=
# Disallow: /*&sort=
# Disallow: /*?filter=
# Disallow: /*&filter=

# ------------------------------------------------------------
# MAJOR SEARCH ENGINES (explicitly allowed)
# ------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

# ------------------------------------------------------------
# AI BROWSING / RETRIEVAL (ALLOWED per your request)
# ------------------------------------------------------------
# ChatGPT browsing / retrieval
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Perplexity browsing
User-agent: PerplexityBot
Allow: /

User-agent: PerplexityBot/1.0
Allow: /

# Claude web browsing
User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

# Gemini / Google AI retrieval is not consistently separable by UA.
# We allow normal Googlebot above (search). Any additional Google UAs
# used for retrieval are not standardized across products.

# ------------------------------------------------------------
# AI TRAINING / EMBEDDING CRAWLERS (DISALLOWED)
# ------------------------------------------------------------
# OpenAI training crawler
User-agent: GPTBot
Disallow: /

# Google training/“extended” (used for some AI features)
User-agent: Google-Extended
Disallow: /

# Apple’s extended crawling for training
User-agent: Applebot-Extended
Disallow: /

# Meta external agents (often used for AI ingestion)
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

# Common AI/data aggregators
User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

# ------------------------------------------------------------
# OPTIONAL: aggressive scanners (block if they cause load/noise)
# ------------------------------------------------------------
User-agent: AliyunSecBot
Disallow: /

# ------------------------------------------------------------
# SOCIAL PREVIEW BOTS (safe / desirable)
# ------------------------------------------------------------
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /