#!/opt/seen/bin/ncgi
local host = require'host'
if not host.get('primary') then
	ncgi.write([[
User-agent: *
Disallow: /
]])
	return
end

ncgi.write([[
User-agent: *
Disallow: /login
Disallow: /logout
Disallow: /register
Disallow: /reactivate
Disallow: /deactivate
Disallow: /activate
Disallow: /search
Disallow: /order
Disallow: /basket

User-agent: Googlebot
Disallow: /*?
Allow: /*?favs
Allow: /shop/artist?*

# ads
User-agent: Mediapartners-Google*
Disallow: /

# Crawlers that obey, but do not feed search engines
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

# wget recursive mode is a frequent problem.
User-agent: wget
Disallow: /

# The 'grub' distributed client has been *very* poorly behaved.
User-agent: grub-client
Disallow: /

# Doesn't follow robots.txt anyway, but...
User-agent: k2spider
Disallow: /

# Hits many times per second, not acceptable, http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit, http://www.webreaper.net/
User-agent: WebReaper
Disallow: /
]])