# Name: http://www.iamwitch.com.com/robots.txt file
# Last Update: October 12, 2007
# (C) Copy and Copyright 2007  IAmAWitch.Com . All Rights Reserved.  
# You may freely copy and use this robots.txt file (just give us the credit as the source as a courtesy).
#
# We do not now or ever allow unauthorized spiders and robots. We regularly observe our logs and ban
# ip addresses that do not observe the rules. In some cases, this has also resulted in bans on entire 
# countries due to the prevalance of spamming and illegal activities being perpetrated on innocent sites.
# If the governments of certain countries would enforce their laws, such actions would not be required and 
# the web would be a better place. Just an observation. In the meantime, we're protecting our site.
#
# The Rules:
#
#  1. - Unauthorized bots will result in IP's being banned.  Agent spoofing is considered a bot.
#  2. - IP Addresses/Ranges w/o agent strings are banned in other areas of the site. Don't even waste your time trying.
#  3. - We monitor which bots don't observe robots.txt. Those who do not observe the rule meet Mr. H.T. Access.
#  4. - We do not allow traffic from Russia and it's former satellites of the Soviet Union, China, the Middle East and 
#      - most of South America due to the prevalence of spamming and illicit activities that prevail in these countries and
#      - regions of the world. Given the embedded nature of criminal activities in these countries as an accepted part of
#      - the culture, these bans are inflexible, sternly enforced and permanent until the end of time. 

# Crawl Delay set to ten seconds

User-Agent: *
Crawl-Delay: 10

# Directory specific exclusions for IAmAWitch - tune as needed for your site

User-agent: *
Disallow: /admin/
Disallow: /articles/
Disallow: /bot-trap/
Disallow: /captcha/
Disallow: /chat/
Disallow: /chatterblock/
Disallow: /cgi-bin/
Disallow: /class/
Disallow: /classes/
Disallow: /codeofisis/
Disallow: /docs/
Disallow: /fckeditor/
Disallow: /filemgmt_data/
Disallow: /galleryx_noview/
Disallow: /help/
Disallow: /images/
Disallow: /mediagallery/

# Specific files not to index  (for IAmAWitch - tune as needed for your site)
Disallow: /comment.php
Disallow: /calendar.php
Disallow: /forum/createtopic.php
Disallow: /pingback.php
Disallow: /profiles.php
Disallow: /stats.php
Disallow: /submit.php
Disallow: /trackback.php
Disallow: /users.php
Disallow: /usersettings.php

# Disallows for bad spiders

# Lower-cases (for ease of sorting via TED Notepad)

User-agent: asterias
User-agent: b2w/0.1
User-agent: cosmos
User-agent: emailCollector
User-agent: emailSiphon
User-agent: emailWolf
User-agent: grub
User-agent: grub-client
User-agent: grub-client-2.6.0
User-agent: hloader
User-agent: httplib
User-agent: humanlinks
User-agent: ia_archiver
User-agent: ia_archiver/1.6
User-agent: larbin
User-agent: libWeb/clsHTTP
User-agent: looksmart
User-agent: lwp-trivial
User-agent: lwp-trivial/1.34
User-agent: moget
User-agent: moget/2.1
User-agent: psbot
User-agent: searchpreview
User-agent: spanner
User-agent: suzuran
User-agent: toCrawl/UrlDispatcher
User-agent: turingos
User-agent: voilabot BETA 1.2

# Upper-cases and numerics

User-agent: 216.34.209.23
User-agent: Alexibot
User-agent: Aqua_Products
User-agent: BackDoorBot/1.0
User-agent: BecomeBot
User-agent: BlowFish/1.0
User-agent: Bookmark search tool
User-agent: BotALot
User-agent: BuiltBotTough
User-agent: Bullseye/1.0
User-agent: BunnySlippers
User-agent: CheeseBot
User-agent: CherryPicker
User-agent: CherryPickerElite/1.0
User-agent: CherryPickerSE/1.0
User-agent: CopyRightCheck
User-agent: Crescent
User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0
User-agent: DittoSpyder
User-agent: Entireweb*
User-agent: EroCrawler
User-agent: ExtractorPro
User-agent: FairAd Client
User-agent: Firefox/1.0 (Windows; U; Win98; en-US; Localization; rv:1.4) Gecko/20030624 Netscape/7.1 (ax)
User-agent: Flaming AttackBot
User-agent: Foobot
User-agent: Gaisbot
User-agent: GetRight/4.2
User-agent: GetRight/5.2d
User-agent: Harvest/1.5
User-agent: InfoNaviRobot
User-agent: Iron33/1.0.2
User-agent: JennyBot
User-agent: Kenjin Spider
User-agent: Keyword Density/0.9
User-agent: LNSpiderguy
User-agent: LexiBot
User-agent: LinkScan/8.1a Unix
User-agent: LinkWalker
User-agent: LinkextractorPro
User-agent: MIIxpc
User-agent: MIIxpc/4.2
User-agent: Mata Hari
User-agent: Mediapartners-Google*
User-agent: Microsoft URL Control
User-agent: Microsoft URL Control - 5.01.4511
User-agent: Microsoft URL Control - 6.00.8169
User-agent: Mister PiX
User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95)
User-agent: NICErsPRO
User-agent: NetAnts
User-agent: Offline Explorer
User-agent: Openbot
User-agent: Openfind
User-agent: Openfind data gathere
User-agent: Oracle Ultra Search
User-agent: PerMan
User-agent: ProPowerBot/2.14
User-agent: ProWebWalker
User-agent: Python-urllib
User-agent: QueryN Metasearch
User-agent: RMA
User-agent: Radiation Retriever 1.1
User-agent: RepoMonkey
User-agent: RepoMonkey Bait & Tackle/v1.01
User-agent: SiteSnagger
User-agent: SpankBot
User-agent: SurveyBot/2.3 (Whois Source)
User-agent: Szukacz/1.4
User-agent: Teleport
User-agent: TeleportPro
User-agent: Telesoft
User-agent: The Intraformant
User-agent: TheNomad
User-agent: True_Robot
User-agent: True_Robot/1.0
User-agent: TurnitinBot
User-agent: URL Control
User-agent: URL_Spider_Pro
User-agent: URLy Warning
User-agent: VCI
User-agent: VCI WebViewer VCI WebViewer Win32
User-agent: WWW-Collector-E
User-agent: Web Image Collector
User-agent: WebAuto
User-agent: WebBandit
User-agent: WebBandit/3.50
User-agent: WebCopier
User-agent: WebEnhancer
User-agent: WebSauger
User-agent: WebStripper
User-agent: WebZip
User-agent: WebZip/4.0
User-agent: WebmasterWorld Extractor
User-agent: Website Quester
User-agent: Webster Pro
User-agent: Wget
User-agent: Wget/1.5.3
User-agent: Wget/1.6
User-agent: Xenu's
User-agent: Xenu's Link Sleuth 1.1c
User-agent: Zeus
User-agent: Zeus 32297 Webster Pro V2.9 Win32
User-agent: Zeus Link Scout

Disallow: /