# robots.txt for https://www.nurse.com/


# --- START: FACEBOOK / META CRAWLER EXCEPTIONS ---
User-agent: facebookexternalhit
User-agent: Facebot
User-agent: meta-webhooks
Allow: /cpresources/
Allow: /*?
Allow: /
# --- END: FACEBOOK / META CRAWLER EXCEPTIONS ---

# live - don't allow web crawlers to index cpresources/ or vendor/

User-agent: *

sitemap: https://www.nurse.com/sitemaps-1-sitemap.xml
Sitemap: https://www.nurse.com/sitemaps/nurse/sitemap.xml
Sitemap: https://www.nurse.com/schools/sitemap_index.xml
Sitemap: https://advertise.nurse.com/sitemap_index.xml
Sitemap: https://super-api-production.nurse.com/sitemap.xml

Disallow: /cpresources/
Disallow: /vendor/
Disallow: /.env
Disallow: /cache/

# Directories
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /pkginfo/
Disallow: /report/
Disallow: /setup/
Disallow: /update/
Disallow: /var/
Disallow: /vendor/

# Paths (clean URLs)
Disallow: /index.php/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /catalogsearch/
Disallow: /checkout/
Disallow: /control/
Disallow: /contacts/
Disallow: /customer/
Disallow: /customize/
Disallow: /newsletter/
Disallow: /review/
Disallow: /sendfriend/
Disallow: /wishlist/
Disallow: /jobs/job/

# Do not index CE author pages with no content 
Disallow: /author/
Allow: /blog/author/

# Files
Disallow: /composer.json
Disallow: /composer.lock
Disallow: /CONTRIBUTING.md
Disallow: /CONTRIBUTOR_LICENSE_AGREEMENT.html
Disallow: /COPYING.txt
Disallow: /Gruntfile.js
Disallow: /LICENSE.txt
Disallow: /LICENSE_AFL.txt
Disallow: /nginx.conf.sample
Disallow: /package.json
Disallow: /php.ini.sample
Disallow: /RELEASE_NOTES.txt

# Do not index pages that are sorted or filtered.
Disallow: /*?*product_list_mode=
Disallow: /*?*product_list_order=
Disallow: /*?*product_list_limit=
Disallow: /*?*product_list_dir=
Disallow: /*?*q=

# Do not index session ID
Disallow: /*?SID=
Disallow: /*?
Disallow: /*.php$

# CVS, SVN directory and dump files
Disallow: /*.CVS
Disallow: /*.Zip$
Disallow: /*.Svn$
Disallow: /*.Idea$
Disallow: /*.Sql$
Disallow: /*.Tgz$

# It will stop google and other search bots from crawling comments as unique pages
Disallow: *?replytocom
Disallow: /jobs/session-img/
Disallow: /jobs/invalid-request/
Disallow: /jobs/document/

Disallow: */searchjobs/*
Disallow: */jobsrss/*
Disallow: /jobsrss/*
Disallow: */jbequicksignup/*
Disallow: /your-jobs/*
Disallow: /external-redirect-registration*
Disallow: */emailjob/*

Disallow: */thank-you/*
Disallow: */thank-you-contact/*
Disallow: */veterans/thank-you/*

Disallow: /*?*jq=
Disallow: /*?*jl=
Disallow: /jobs/*?*id=

Noindex: /thank-you/
Noindex: /thank-you-contact/
Noindex: /veterans/thank-you/

User-agent: *
Crawl-delay: 5