yacy_search_server/htroot/robots.txt
Michael Peter Christen c0d9a3e9a7 turned HostBrowser into a admin-only page, now called IndexBrowser
This was required because spiders and bots crawled through this page and
created load on the peer without use for the user or the YaCy network.
2020-12-11 00:50:52 +01:00

71 lines
988 B
Plaintext

# robots.txt for #[clientname]#.yacy
User-agent: *
Disallow: /*query=
Disallow: /proxy.html
Disallow: /IndexBrowser_p.html
#(all)#
# dirs
#{dirs}#
Disallow: /#[dir]#
#{/dirs}#
# locked
#{locked}#
Disallow: /#[page]#
#{/locked}#
#(bookmarks)#::
# bookmarks
Disallow: /Bookmarks.html#(/bookmarks)#
#(wiki)#::
# wiki
Disallow: /Wiki.html#(/wiki)#
#(blog)#::
# blog
Disallow: /Blog.html
Disallow: /Blog.rss
Disallow: /Blog.xml#(/blog)#
#(news)#::
# news
Disallow: /News.html#(/news)#
#(status)#::
# status
Disallow: /Status.html#(/status)#
#(network)#::
# network
Disallow: /Network.html
Disallow: /Network.csv
Disallow: /Network.xml#(/network)#
#(homepage)#::
# homepage
Disallow: /www#(/homepage)#
#(fileshare)#::
# fileshare
Disallow: /share#(/fileshare)#
#(surftips)#::
# surftips
Disallow: /Surftips.html#(/surftips)#
#(profile)#::
# view profile
Disallow: /ViewProfile.html
Disallow: /ViewProfile.vcf
Disallow: /ViewProfile.xml#(/profile)#
::
# all
Disallow: /
#(/all)#