# worklodge.com — see docs/tracking-architecture.md
# robots.txt is a crawl-budget tool, not a security control.

User-agent: *
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /admin
Disallow: /api/
# Retired WordPress / WooCommerce route families (nothing here is served any more)
Disallow: /wp-admin
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /product/
Disallow: /products/
Disallow: /product-category/
Disallow: /service/
Disallow: /tag/
Disallow: /category/
Disallow: /author/
Disallow: /feed
Disallow: /comments
Disallow: /cart
Disallow: /my-account
Disallow: /shop
Disallow: /*?add-to-cart=
Disallow: /*?replytocom=
Disallow: /*?wc-ajax=

# Legitimate search crawling stays fully open on current pages.
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

# Invalid-traffic sources with no business value here.
User-agent: Sogou web spider
Disallow: /

User-agent: Sogou inst spider
Disallow: /

User-agent: Sogou Pic Spider
Disallow: /

User-agent: Sogou
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

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