# Prevent Crawling Unnecessary Endpoints - Dynamically added by BigScoots
User-agent: *
Disallow: /cdn-cgi/
Disallow: /wp-admin/
Disallow: /wp-json/
Disallow: /*?s=
Disallow: /*?attachment_id=
Disallow: /*?add-to-cart=
Disallow: /*&add-to-cart=
Disallow: /*?add_to_wishlist=
Disallow: /*&add_to_wishlist=

# The Hive Law - robots.txt
# https://www.thehivelaw.com/
# Updated: 2026-08-26
#
# Machine-readable site index: /llms.txt

# --------------------------------------------------------
# All crawlers - standard WordPress protections
# --------------------------------------------------------
User-agent: *
Allow: /wp-admin/admin-ajax.php

Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-login.php
Disallow: /wp-json/
Disallow: /wp-cron.php
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /cdn-cgi/

# Thin / duplicate content
Disallow: /?s=
Disallow: /*?s=
Disallow: /*?replytocom=
Disallow: /*?p=
Disallow: /?gf_page=
Disallow: /*?add-to-cart=
Disallow: /category/

# --------------------------------------------------------
# AI search agents - explicitly welcome
# These power answer engines and respect llms.txt signals.
# --------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Amazonbot
Allow: /

# --------------------------------------------------------
# Block pure training scrapers (no user-facing search)
# --------------------------------------------------------
User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Diffbot
Disallow: /

# --------------------------------------------------------
# Sitemaps
# --------------------------------------------------------
Sitemap: https://www.thehivelaw.com/sitemap_index.xml
Sitemap: https://www.thehivelaw.com/post-sitemap.xml
Sitemap: https://www.thehivelaw.com/page-sitemap.xml
Sitemap: https://www.thehivelaw.com/local-sitemap.xml