# https://cuisine.eco/robots.txt
User-agent: *
Disallow: /admin
Disallow: /api
Disallow: /jumpstart
Disallow: /letter_opener
Disallow: /dashboard
Disallow: /recipes
Disallow: /meals
Disallow: /foods
Disallow: /grocery
Disallow: /conversations
Disallow: /bio/fiche
# The claim flow is nested per producer: /bio/<slug>/revendiquer. A literal
# "Disallow: /bio/revendiquer" would match no real URL (Disallow is a prefix
# match), and a bare "/bio/rev" prefix would block producer slugs starting with
# those letters -- hence the wildcard. These pages already redirect anonymous
# crawlers to sign-in, so this is about crawl budget, not indexation: without
# it, a crawler walks one dead-end claim URL per producer across ~62k fiches.
# "*" is not in the 1994 norm but is honoured by Google, Bing, and Yandex, and
# RFC 9309 (2022) standardised it; non-supporting crawlers ignore the line.
Disallow: /bio/*/revendiquer
Disallow: /users
Disallow: /accounts
Disallow: /subscriptions
Disallow: /charges
Disallow: /payment_methods
Disallow: /notifications

# Deliberately NO rule on /bio: filtered variants (?q=, ?bbox=, ?postal_code=)
# are deindexed via the meta robots tag, not here. A robots.txt block would
# prevent Google from reading the noindex, leaving the bare URL indexable.

# Generative engines: documented as allowed. Redundant with the absence of a
# block, but stating the intent is the GEO half of this project.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

Sitemap: https://cuisine.eco/sitemap.xml