# Highlander Building Services — robots.txt
# Canonical host: https://highlandernc.com
# Policy: allow crawling of every public, indexable page and every rendering
# resource (CSS, JS, images, fonts). Only form-only funnels and internal
# utilities are disallowed. noindex (via meta) — not robots.txt — is used to
# keep individual pages out of the index.

# ── Default: all crawlers ───────────────────────────────────────────────
User-agent: *
Allow: /

# Explicitly allow rendering resources (belt-and-suspenders — Allow: / already covers these)
Allow: /assets/
Allow: /*.css$
Allow: /*.js$
Allow: /*.svg$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.webp$
Allow: /*.woff$
Allow: /*.woff2$
Allow: /*.ttf$

# NOTE: form-only funnels (/consultation, /quote-flow, /*-intake, /*-builder)
# are intentionally NOT blocked here. They use <meta name="robots"
# content="noindex,follow"> so Google can crawl the page and honor the
# noindex directive. Blocking them in robots.txt would prevent Google from
# ever seeing that directive and could leave stale URL-only entries in the
# index. Same reasoning for internal /admin/ and SEO QA pages — they carry
# noindex,nofollow via <meta>.

# Paid landing pages: ad-only entry points, no organic value.
Disallow: /admin/
Disallow: /lp/

# Internal receptionist call sheet — unlisted internal tool.
Disallow: /front-desk
Disallow: /front-desk/
Disallow: /intake
Disallow: /intake/

# ── Google Search ────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /

# ── Google Images (product & project photos should surface in image search)
User-agent: Googlebot-Image
Allow: /

# ── Microsoft Bing ───────────────────────────────────────────────────────
User-agent: Bingbot
Allow: /

# ── Social preview crawlers ──────────────────────────────────────────────
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# ── AI search discovery ─────────────────────────────────────────────────
# OpenAI ChatGPT Search (search-time citations, separate from training).
# Allowed so the site can appear in ChatGPT search results.
User-agent: OAI-SearchBot
Allow: /

# Perplexity (search-time citations).
User-agent: PerplexityBot
Allow: /

# ── AI answer engines & assistants ──────────────────────────────────────
# Business decision: allow AI crawlers so Highlander can be cited in
# AI Overviews, ChatGPT, Claude, and Perplexity answers.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

# ── Canonical sitemap ───────────────────────────────────────────────────
Sitemap: https://highlandernc.com/sitemap.xml
# Temporary migration sitemap (15 Sep 2026 SEO spec, T3): the old-site URLs
# still in Google's index, listed so they are recrawled and their 301s recorded.
# DELETE this line and public/sitemap-legacy.xml after 6 weeks (from 27 Oct 2026).
Sitemap: https://highlandernc.com/sitemap-legacy.xml