###############################################################################
#                                                                             #
#                     robots.txt for https://laltroweb.it                     #
#                                                                             #
#   Please note: this is optimized for my website (ipb4 in root directory)!   #
# And to exclude some bot (like Wayback Machine, Fasterfox, and many others)! #
#             Please, read carefully before using this product :)             #
#                                                                             #
###############################################################################

# Sitemap
Sitemap: http://www.austriansoccerboard.at/sitemap.php

# Crawlers that are kind enough to obey, but which we had rather not have
# unless they are feeding 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: /

# Misbehaving: requests much too fast:
User-agent: fast
Disallow: /


# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

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

#
# no 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: /

# if u want deny access to Wayback Machine:
# User-agent: ia_archiver
# Disallow: /

# and also to Fasterfox prefetching
User-agent: Fasterfox
Disallow: /

# All others...
# Added 09 April 2016, gives to many 404's
User-agent: *
Disallow: /eyeblaster
Disallow: /addineyeV2.html
Disallow: /eyeblaster/addineyeV2.html
Disallow: /adform/IFrameManager.html
Disallow: /doubleclick/adx_iframe.html
Disallow: /doubleclick/DARTIframe.html
Disallow: /eyewonder/interim.html
Disallow: /unicast/unicastIFD.html
Disallow: /flashtalking/ftlocal.html
Disallow: /flite/fif.html
Disallow: /kpsule/iframebuster.html
Disallow: /linkstorm/linkstorm_certified.html
Disallow: /mediaplex/mojofb_v9.html

# No file+directory
Allow: /applications/core/interface/font/
Disallow: /_script/
Disallow: /api/
Disallow: /applications/
Disallow: /cgi-bin/
Disallow: /datastore/
Disallow: /plugins/
Disallow: /system/
Disallow: /403error.php
Disallow: /404error.php
Disallow: /500error.php
Disallow: /Credits.txt
Disallow: /error.php
Disallow: /upgrading.html

# No also this...
Disallow: /login/
Disallow: /register/
Disallow: /lostpassword/
Disallow: /search/
Disallow: /online/
Disallow: /contact/
Disallow: /activity/
Disallow: /discover/

# ... And this!
Disallow: /?tab=*
Disallow: /index.php?*
Disallow: /*?app=*
Disallow: /*sortby=*
Disallow: /*/?do=download
Disallow: /profile/*/?do=*
Disallow: /profile/*/content/