# prevent all bots from crawling internal pages
User-agent: *
Disallow: /l/
Disallow: /m/
Disallow: /s/
Disallow: /t2/
Disallow: /z/
Disallow: /cms/
Disallow: */fulfill/*
Disallow: /*.shtml$
Disallow: /*.asp$
Disallow: /*.axd$
Disallow: /*sbid=
Disallow: /*spid=
Disallow: /*spids=
Disallow: /*CJPID=

# prevents archive.org from indexing
User-agent: ia_archiver
Disallow: /

# twitterbot
User-agent: Twitterbot
Disallow: /

# Google AdWords & Bing Ads
User-agent: adsbot-Google
User-agent: adidxbot
Allow: /m/a/

Sitemap: https://www.heartsintrueharmony.com/sitemap.xml