# tosa.org — crawl policy
# AI search/answer bots (OAI-SearchBot, ChatGPT-User, Claude-User,
# Claude-SearchBot, PerplexityBot) and AI training bots (GPTBot, ClaudeBot,
# CCBot, Applebot-Extended, Google-Extended) are deliberately allowed: they
# follow the default group below. A machine-readable site summary for them
# lives at /llms.txt.

User-agent: *
Disallow: /ajaxscript/
Disallow: /*/search-index.json
# Login pages (also noindex): English slugs and their FR/DE/NL/ES/IT equivalents.
Disallow: /*/candidatelogin
Disallow: /*/adminlogin
Disallow: /*/connexion-candidat
Disallow: /*/connexion-admin
Disallow: /*/kandidaten-login
Disallow: /*/kandidaat-login
Disallow: /*/acceso-candidato
Disallow: /*/accesso-candidato
Disallow: /*/admin-login
Disallow: /*/acceso-administrador
Disallow: /*/accesso-amministratore
Disallow: /*/online-store/checkout
Disallow: /*/online-store/signin
Disallow: /*/blog?page=

Sitemap: https://www.tosa.org/sitemap.xml