# =============================================================
# GHARPAYY — ROBOTS.TXT
# File: 09-robots.txt
# Deploy to: gharpayy.com/robots.txt  AND  gharpayy.in/robots.txt
#            (Must be at root of domain, exact filename: robots.txt)
# Verify at: https://www.gharpayy.com/robots.txt
# =============================================================

# All crawlers — full access to public pages
User-agent: *
Allow: /

# Block admin, login, and backend routes from indexing
Disallow: /admin/
Disallow: /admin-panel/
Disallow: /login/
Disallow: /register/
Disallow: /dashboard/
Disallow: /api/
Disallow: /api-internal/
Disallow: /checkout/
Disallow: /payment/
Disallow: /cart/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /.env
Disallow: /config/
Disallow: /uploads/temp/
Disallow: /staging/
Disallow: /test/
Disallow: /dev/

# Block duplicate content / filtered pages (if applicable)
Disallow: /*?sort=
Disallow: /*?filter=
Disallow: /*?page=
Disallow: /*?ref=
Disallow: /*?utm_
Disallow: /*&utm_

# Allow Googlebot — full access explicitly
User-agent: Googlebot
Allow: /
Disallow: /admin/
Disallow: /login/
Disallow: /api/

# Allow Googlebot-Image — for image indexing
User-agent: Googlebot-Image
Allow: /assets/
Allow: /images/
Allow: /uploads/

# Allow Bingbot
User-agent: Bingbot
Allow: /
Disallow: /admin/
Disallow: /login/
Crawl-delay: 5

# Allow DuckDuckBot
User-agent: DuckDuckBot
Allow: /
Crawl-delay: 5

# Sitemap location — CRITICAL: Update if using a different sitemap path
Sitemap: https://www.gharpayy.com/sitemap.xml

# NOTE FOR TECH TEAM:
# 1. Deploy this file to the ROOT of both domains:
#    gharpayy.com/robots.txt
#    gharpayy.in/robots.txt
#
# 2. After deployment, verify in Google Search Console:
#    GSC → Settings → Crawl Stats → robots.txt
#
# 3. If using a secondary domain (e.g. gharpayy.in redirects to gharpayy.com),
#    only the PRIMARY domain's robots.txt matters for Google.
#
# 4. Test your robots.txt at:
#    https://search.google.com/search-console/robots-testing-tool