# If the Joomla site is installed within a folder
# eg www.example.com/joomla/ then the robots.txt file
# MUST be moved to the site root
# eg www.example.com/robots.txt
# AND the joomla folder name MUST be prefixed to all of the
# paths.
# eg the Disallow rule for the /administrator/ folder MUST
# be changed to read
# Disallow: /joomla/administrator/
#
# For more information about the robots.txt standard, see:
# https://www.robotstxt.org/orig.html

User-agent: *
Disallow: /administrator/
Disallow: /api/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /cookie-consent/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /mobile-checkout/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
Disallow: /*checkout*
# Allow specific sitemap URLs
Allow: /en/component/osmap/?view=xml&id=1&format=xml
Allow: /da/component/osmap/?view=xml&id=1&format=xml
Allow: /de/component/osmap/?view=xml&id=1&format=xml
Allow: /no/component/osmap/?view=xml&id=1&format=xml
Allow: /sv/component/osmap/?view=xml&id=1&format=xml
Allow: /nl/component/osmap/?view=xml&id=1&format=xml
Allow: /en/component/osmap/?view=xml&id=1&images=1&format=xml
Allow: /da/component/osmap/?view=xml&id=1&images=1&format=xml
Allow: /de/component/osmap/?view=xml&id=1&images=1&format=xml
Allow: /no/component/osmap/?view=xml&id=1&images=1&format=xml
Allow: /sv/component/osmap/?view=xml&id=1&images=1&format=xml
Allow: /nl/component/osmap/?view=xml&id=1&images=1&format=xml
Disallow: /*?*  # Block all URLs with query strings

# ===== BLOCK WEB ARCHIVERS & SCRAPERS =====
User-agent: ia_archiver          # Wayback Machine (Internet Archive)
User-agent: archive.org_bot
User-agent: Wayback Machine
User-agent: web.archive.org
Disallow: /

User-agent: CCBot                # Common Crawl (public web archive)
User-agent: Barkrowler           # Alternative archiving bot
User-agent: BLEXBot              # Common Crawl affiliate
User-agent: Gigabot              # Sometimes archives
Disallow: /

# ===== BLOCK SEO/SCRAPER BOTS (optional) =====
User-agent: MJ12bot              # Majestic SEO
User-agent: AhrefsBot            # Ahrefs crawler
User-agent: SemrushBot           # SEMrush crawler
User-agent: DotBot               # SEO data collector
User-agent: ZoominfoBot          # Data scraper
Disallow: /

# ===== SITEMAPS (remain allowed despite ? blocking) =====
Sitemap: https://www.123carrental.com/en/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://www.123carrental.com/da/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://www.123carrental.com/de/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://www.123carrental.com/no/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://www.123carrental.com/sv/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://www.123carrental.com/nl/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://www.123carrental.com/en/component/osmap/?view=xml&id=1&images=1&format=xml
Sitemap: https://www.123carrental.com/da/component/osmap/?view=xml&id=1&images=1&format=xml
Sitemap: https://www.123carrental.com/de/component/osmap/?view=xml&id=1&images=1&format=xml
Sitemap: https://www.123carrental.com/no/component/osmap/?view=xml&id=1&images=1&format=xml
Sitemap: https://www.123carrental.com/sv/component/osmap/?view=xml&id=1&images=1&format=xml
Sitemap: https://www.123carrental.com/nl/component/osmap/?view=xml&id=1&images=1&format=xml