# RecruitersFromIndia.com robots.txt
#
# Policy (2026-10-07), described for people at /ai-crawler-policy:
#   1. Search engines and AI search / answer-engine crawlers may read the public
#      pages. These fetch a page to list it in results or cite it in an answer.
#   2. Crawlers that collect content to train AI models are not permitted.
#   3. Signed-in areas, private documents and the internal API are closed to
#      every crawler.
#
# Per RFC 9309, a crawler applies only its own most-specific User-agent group and
# does NOT also inherit the wildcard group's rules -- so the search / answer
# group below repeats the wildcard group's Disallow set exactly. Keep the two in
# sync (tests/Feature/Phase6SeoAeoGeoTest.php enforces it).

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /staff/
Disallow: /employer/
Disallow: /agency/
Disallow: /notifications
Disallow: /requirement-documents/
Disallow: /employer-documents/
Disallow: /api/
# Crawl budget (2026-10-08): per-agency form pages, and filter views of pages that
# are already crawlable without the parameter. All are noindex or canonical to
# the plain URL, so fetching them only costs a database connection each.
Disallow: /report/
Disallow: /register/recruiting-agent?
Disallow: /*?*status=
Disallow: /*?*view=

# Search engines and AI search / answer-engine crawlers: public content only.
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckAssistBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-SearchBot
User-agent: Claude-User
Allow: /
Disallow: /admin/
Disallow: /staff/
Disallow: /employer/
Disallow: /agency/
Disallow: /notifications
Disallow: /requirement-documents/
Disallow: /employer-documents/
Disallow: /api/
# Crawl budget (2026-10-08): per-agency form pages, and filter views of pages that
# are already crawlable without the parameter. All are noindex or canonical to
# the plain URL, so fetching them only costs a database connection each.
Disallow: /report/
Disallow: /register/recruiting-agent?
Disallow: /*?*status=
Disallow: /*?*view=

# AI model-training crawlers: not permitted anywhere on the site.
# Google-Extended and Applebot-Extended are training controls only; Googlebot
# and Applebot above still index the site for search.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: meta-externalagent
Disallow: /

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