#
# robots.txt for NeworMedia.com
# Updated: 27 February 2026
#
# Purpose:
# Controls access for web crawlers, search engines, and AI agents.
# Complements llm.txt to guide LLMs on content access and usage.
#
# Learn more: https://www.robotstxt.org/robotstxt.html
#

User-agent: *
Crawl-delay: 10

# --- Allow: Essential assets for rendering ---
Allow: /misc/*.css$
Allow: /misc/*.css?
Allow: /misc/*.js$
Allow: /misc/*.js?
Allow: /misc/*.gif
Allow: /misc/*.jpg
Allow: /misc/*.jpeg
Allow: /misc/*.png

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

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

# --- Disallow: Internal and system directories ---
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/

# --- Disallow: Sensitive or system 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

# --- Disallow: Backend and user 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: Backend and user 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/

# --- AI / LLM Directives ---
# Public blog and educational resources may be crawled.
Allow: /blog/
Allow: /resources/

# Restricted business-sensitive areas
Disallow: /dashboard/
Disallow: /api/
Disallow: /partners/
Disallow: /publisher-data/
Disallow: /case-studies/

# --- Explicit LLM & AI Crawler Permissions ---
# These AI crawlers are permitted to access public content
# in accordance with https://www.newormedia.com/llms.txt

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: OmgiliBot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: BingPreview
Allow: /

# --- Sitemap & AI Policy Reference ---
Sitemap: https://www.newormedia.com/sitemap.xml
AI-Policy: https://www.newormedia.com/llms.txt