#
# 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/*.avif
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /core/*.webp
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.avif
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
Allow: /profiles/*.webp
# 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: /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/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


# ---------------------------------------------------------------------------
# Tradeline additions — appended to core's robots.txt at build time via the
# drupal-scaffold file-mapping in composer.json (assets/robots-additions.txt).
# Edit that file, not web/robots.txt (which is gitignored and regenerated).
# ---------------------------------------------------------------------------

# Continue the default group: never crawl the cron endpoint.
User-agent: *
Disallow: /cron
Disallow: /index.php/cron

# AI-training and answer-engine crawlers that send us no visitors.
# (Search crawlers that do — Googlebot, bingbot, Applebot, DuckDuckBot,
# OAI-SearchBot — remain allowed, as do live user-triggered fetchers
# like ChatGPT-User.)
#
# Google-Extended is deliberately NOT blocked: it is Google's single token
# for both Gemini training and Gemini live answers, with no way to allow
# one without the other, and blocking it made the site invisible to Gemini
# (it does not affect Google Search, AI Overviews, or AI Mode).
User-agent: Amazonbot
User-agent: GPTBot
User-agent: CCBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: PetalBot
User-agent: Timpibot
User-agent: ImageBot
User-agent: img2dataset
User-agent: omgili
User-agent: Diffbot
Disallow: /

# Search engines with no audience overlap for a US B2B facilities-planning
# site.
User-agent: Baiduspider
User-agent: Sogou web spider
User-agent: YandexBot
Disallow: /

# SEO-intelligence crawlers (they index us for their paying customers, not
# for searchers).
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: DataForSeoBot
User-agent: BLEXBot
Disallow: /

# Where to find the XML sitemap (group-independent directive).
Sitemap: https://www.tradelineinc.com/sitemap.xml