# robots.txt for troimarket.com (the real site).
# Do NOT put this file on cappermarket.co, and do NOT put cappermarket's file here.
#
# Open to search engines and AI crawlers: the homepage, /sell, /about, /faq, /llms.txt, every listing (/product/…, /recipe/…, /bundle/…),
# every storefront (/@name), the policy pages, and the files a page needs in order to load
# (app.js, the icons, and /og-image/, which link previews on X and elsewhere fetch).
#
# Two things about the layout below, both deliberate:
#  - No "Allow: /" line. Everything is allowed unless listed, and some crawlers obey the first
#    rule that matches, so an "Allow: /" at the top would cancel every line under it.
#  - No empty lines inside the block. Older crawlers read an empty line as "the rules end here".

User-agent: *
# Signed-in areas. A visitor with no account is sent back to the homepage, so there is nothing to index.
Disallow: /library
Disallow: /dashboard
Disallow: /seller
Disallow: /settings
Disallow: /create
# The "$" means "exactly /pro". Without it this line would also block every /product/… listing.
Disallow: /pro$
# The page that "verify your email" and "reset password" links open.
Disallow: /auth-action
# Second copies of the homepage (/index, /index.html, /index.php).
Disallow: /index

# AI assistants' crawlers, named so there is no doubt they are welcome. A crawler that finds its own
# name uses THIS group instead of the "*" one above, so the same signed-in areas are repeated here.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Bingbot
Disallow: /library
Disallow: /dashboard
Disallow: /seller
Disallow: /settings
Disallow: /create
Disallow: /pro$
Disallow: /auth-action
Disallow: /index

Sitemap: https://troimarket.com/sitemap.xml

Sitemap: https://troimarket.com/sitemap-listings.xml