# Robots.txt for www.boston.com
# Passionate about publishing and technology? Visit https://www.bostonglobemedia.com/opportunities/

# Sitemaps
Sitemap: https://www.boston.com/sitemap_index.xml

# Disallow
# --WORD-4089-- New rules to limit crawl of real estate listings search result pages.
# -----------------------
User-agent: *
Disallow: *?s=
Disallow: /listings/*aggregate*
Disallow: /listings/*freetext*
Disallow: /listings/*refresh*
Disallow: /listings/*sortBy*
Disallow: /wp-admin/
# -----------------------

# Allow
User-agent: *
Allow: /wp-admin/admin-ajax.php

User-agent: AmazonAdBot
Allow: /

# AI Bots
User-agent: AI2Bot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot 
Disallow: /

User-agent: Meta-ExternalAgent

User-agent: omgili
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /