User-agent: *
Allow: /
Allow: /about-us
Allow: /companion-care
Allow: /personal-care
Allow: /home-health-care
Allow: /specialized-care
Allow: /pediatric-care
Allow: /private-pay
Allow: /service-by-age
Allow: /locations
Allow: /contact-us
Allow: /blog/
Allow: /news-and-press-releases
Allow: /videos/
Allow: /events/
Allow: /careers/
Allow: /story
Allow: /mission-and-vision
Allow: /team/
Allow: /privacy-and-policy
Allow: /terms-and-conditions
Allow: /disclaimer
Allow: /frequently-asked-questions
Allow: /resources/
Allow: /sitemap/
Allow: /sitemap.xml
Allow: /robots.txt
Allow: /feed.xml
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ads.txt
Allow: /favicon.ico

# Next.js static export emits a React Server Component prefetch payload
# (`index.txt`, `__next.*.txt`) next to every route's HTML, used only for
# client-side navigation cache — not real content. Left uncontrolled this is
# several thousand junk URLs (one set per route) for crawlers to fetch. The
# explicit Allow entries above for the site's real top-level .txt files take
# precedence over this wildcard.
Disallow: /*.txt$

# No data/JSON files are served from the site anymore (see src/lib/data/,
# src/lib/states/<state>/, src/lib/data/geo/ — all build-time imports, not
# public/ files). These rules are a guard against that ever changing back,
# not a fix for something currently live.
Disallow: /data/
Disallow: /*.json$

# Never block /_next/: it serves every page's JS, CSS, fonts and imported
# images. Googlebot needs them to render; blocking them was flagged as
# ~15k "blocked internal resources".

# /blog-index.json is the one deliberate exception: a build-generated catalog
# (src/app/blog-index.json/route.js, not a public/ file) that the blog
# search/filter UI fetches client-side. Needs to stay crawlable so Googlebot
# can render that UI; this explicit Allow takes precedence over the wildcard
# Disallow above.
Allow: /blog-index.json

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