# Robots.txt file from http://www.searchengineworld.com



#



# Allows all Robots - but Bans from cgi-bin and images and _private



#



# Disallow /cgi-bin/







#User-agent: Mediapartners-Google*



User-agent: *

User-agent: Yandex
Crawl-delay: 10


Disallow: /cgi-bin/

Disallow: /config/

Disallow: /scripts/

Disallow: /articles/wp-admin/

Disallow: /articles/wp-includes/

Disallow: /articles/wp-content/

# ---------------------------------------------------------------------------
# AI crawlers, named one by one (6 October 2026). Every other crawler follows
# the rules above, as before. The same file is served on sellmyhouse.ie and on
# every town and county subdomain.
# ai-usage-policy: https://sellmyhouse.ie/ai-usage-policy.html
# ---------------------------------------------------------------------------

# AI search, and AI assistants fetching a page for a user: allowed, with the
# same rules as everyone else. Google-Extended is Google's one setting both
# for training Gemini and for using pages in Gemini's answers; it is allowed
# so the site can appear in those answers. It does not affect Google Search.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: Google-Extended
Crawl-delay: 10
Disallow: /cgi-bin/
Disallow: /config/
Disallow: /scripts/
Disallow: /articles/wp-admin/
Disallow: /articles/wp-includes/
Disallow: /articles/wp-content/

# Collecting pages to train AI models: not allowed.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: meta-externalagent
Disallow: /

# Other crawlers refused every path (7 October 2026).
User-agent: SelfSellItBot
Disallow: /

# The XML sitemap index, kept here by cronjobs/generate-sitemaps.php
Sitemap: https://sellmyhouse.ie/sitemap.xml