User-agent: *
Allow: /
Disallow: /auth/
Disallow: /coming-soon

# The old WordPress site's by-products (BOBO-4680). Search Console lists about
# 1,300 of these, and every one answers 200 with this app's shell -- Amplify
# cannot send a 404 status (see iac, 2-services/marketing-sites/cmha-marketing.tf)
# -- so Google has to render the page to find the noindex on the not-found page,
# and keeps coming back. That spends the crawl budget the real pages need: 58 of
# them, most of /news, were "Discovered - currently not indexed" with no crawl.
# None of these prefixes is a route on this site.
Disallow: /events
Disallow: /locations/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /tag/
Disallow: /category/
Disallow: /author/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /wpbc-bfb-preview/
# /wp-content/uploads/ stays crawlable on purpose: old PDFs there may be given
# 301s to their re-hosted copies, and Google cannot follow a redirect on a URL
# it is not allowed to fetch.

Sitemap: https://www.cmhaacrossmb.ca/sitemap.xml