# If the Joomla site is installed within a folder such as at www.example.com/joomla/ the robots.txt file MUST be
# moved to the site root at e.g. www.example.com/robots.txt AND the joomla folder name MUST be prefixed to the Disallowed
# path, e.g. the Disallow rule for the /administrator/ folder MUST be changed to read Disallow: /joomla/administrator/
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/orig.html
#
# ▀██▀─▄███▄─▀██─██▀██▀▀█
# ─██─███─███─██─██─██▄█
# ─██─▀██▄██▀─▀█▄█▀─██▀█
# ▄██▄▄█▀▀▀─────▀──▄██▄▄█
#
# For syntax checking, see:
# http://tool.motoricerca.info/robots-checker.phtml
#
# robots.txt file from http://www.joomla4all.nl
# 
#         ,-----.                                                      
#       ,'_/_|_\_`.                                                    
#      /<<::8[O]::>\ 
#     _|-----------|_                          
# :::|  | ====-=- |  |:::                                              
# :::|  | -=-==== |  |:::                                              
# :::\  | ::::|()||  /:::                                              
# ::::| | ....|()|| |::::                                              
#     | |_________| |                                                  
#     | |\_______/| |         ROBOT.TXT     
#    /   \ /   \ /   \                                                 
#    `---' `---' `---'        

# Sitemap: index.php?option=com_osmap&view=xml&tmpl=component&id=1
 Sitemap: http://cloud.schumm.nl/portal/cloud/sitemap.xml

# Groep 1
# All user-agents are case sensitive in robots.txt
User-agent: Googlebot # Google
User-agent: Googlebot-Image # Google Images
User-agent: Mediapartners-Google # Google Media
User-agent: Bingbot # Bing
User-agent: BingPreview # Bing
User-agent: Slurp # Yahoo
User-agent: DuckDuckBot #DuckDuckGo
User-agent: Twitterbot #Twitter
User-agent: Facebot #Facebook
user-agent: Screaming Frog SEO Spider # Screaming Frog SEO Spider
Allow: /

# Groep 2 
# Blok agents
User-agent: Baiduspider
User-agent: *
Disallow: /

# Groep 3
# Blokkeer bestanden
User-agent: *
Disallow: /*.xls$
Disallow: /*.zip
Disallow: /*.jpa
Disallow: /private_file.html
Disallow: /afbeeldingen/honden.jpg

# Groep 4 /robots.txt voor Joomla/
# Blokkeer / Allow site 
User-agent: *
Allow: /blog/
Allow: /shop/
Disallow: /portal/*/_used/
Disallow: /portal/*/administrator/
Disallow: /portal/*/bin/
Disallow: /portal/*/cache/
Disallow: /portal/*/cli/
Disallow: /portal/*/components/
Disallow: /portal/*/files/
Allow: /portal/*/images/
Disallow: /portal/*/includes/
Disallow: /portal/*/*installation*/
Disallow: /portal/*/language/
Disallow: /portal/*/layouts/
Disallow: /portal/*/libraries/
Disallow: /portal/*/logs/
Allow: /portal/*/media/
Disallow: /portal/*/modules/
Disallow: /portal/*/plugins/
Allow: /portal/*/templates/
Disallow: /portal/*/tmp/
Disallow: /portal/matomo/
Disallow: /*well-known/
Disallow: /*backups/
Disallow: /*cronjobs/
Disallow: /*include/
Disallow: /autodiscover/
Disallow: /bbclone/
Disallow: /cgi-bin/
Disallow: /downloads/
Disallow: /error/
Disallow: /policy/
Disallow: /sub/
Disallow: /tools/
Disallow: /user/

# /robots.txt voor Wordpress/
#$User-agent: *
#$Disallow: /portal/*/wp-admin/ #geen toegang tot admin sectie.
#$Disallow: /portal/*/wp-login.php #geen toegang tot admin sectie.
#$Disallow: /portal/*/search/ #geen toegang tot interne zoekresutlaat pagina's.
#$Disallow: *?s=* #geen toegang tot interne zoekresutlaat pagina's.
#$Disallow: *?p=* #geen toegang tot pagina's als permalinks niet werken.
#$Disallow: *&p=* #geen toegang tot pagina's als permalinks niet werken.
#$Disallow: *&preview=* #geen toegang tot preview pagina's.
#$Disallow: /portal/*/tag/ #geen toegang tot tag archief pagina's.
#$Disallow: /portal/*/author/ #geen toegang tot author archief pagina's.
#$Disallow: /portal/*/404-error/ #geen toegang tot de 404 pagina.
#
#