#/**
# * robots.txt
# *
# * bot control for http://clez.net
# * refer to 'Robots Exclusion Standard RFC4'
# * the use of crawlers or other automated tests on this host is forbidden for
# * any path defined by 'Disallow' directives.
# *
# * @tabstop 4
# */

# concerns any client application
User-agent: *

# no image indexing on assets
Disallow: /img/

# prevent the world from finding out the meaning of life
Disallow: *.oliver

# - i don't have them anyway, but as stated above, it's forbidden to crawl :)
Disallow: /MSADC/
Disallow: /MSOffice/
Disallow: /_vti_bin/
Disallow: /_mem_bin/
Disallow: /c/
Disallow: /d/
Disallow: /scripts/
Disallow: /%7e
Disallow: %7e

# special interest rules
User-Agent: Googlebot-Image
User-agent: Mediapartners-Google* 
User-agent: WebZIP
User-agent: WebTrends
Disallow: /

# bots a just dislike
User-agent: EmailCollector
User-agent: EmailSiphon
User-agent: EmailWolf
User-agent: WebEMailExtrac.*
User-agent: autoemailspider
User-agent: RPT-HTTPClient
Disallow: /

# archive.org
User-agent: ia_archiver
Disallow: /

User-agent: *
Sitemap: http://clez.net/sitemap.xml