# ------------------------------------------------------------------
# DELIBERATELY ALL-ALLOW. DO NOT ADD Disallow RULES.
# This SPA replaced a legacy WordPress site. ~900 legacy URLs
# (/events/, /event/, /tag/, /category/, /author/, /wp-content/,
#  and ?tribe-bar-date / ?eventDisplay=past / ?et_blog / ?s= URLs)
# are still in Google's index. They are being de-indexed via HTTP
# 404 + a noindex meta tag on the SPA 404 route — NOT via robots.txt.
# Blocking them here would re-create GSC's "Indexed, though blocked
# by robots.txt" state: a Disallow stops crawling but NOT indexing
# from external links, so Googlebot could never crawl the page to
# see the noindex. Also NEVER Disallow JS/CSS/assets — Googlebot
# must fetch them to render this client-rendered SPA.
# ------------------------------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

# AI / LLM crawlers — explicitly allowed for Generative Engine Optimization (GEO)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: *
Allow: /

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