# $Id: robots.txt,v 1.9.2.1 2008/12/10 20:12:19 goba Exp $
#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/wc/robots.html
#
# For syntax checking, see:
# http://www.sxw.org.uk/computing/robots/check.html

User-agent: *
Crawl-delay: 12

# DISALLOW THESE QUERY STRINGS:

# DISALLOW BOOST OUTPUT FROM GETTING INDEXED:
Disallow: /boost_stats.php

# DIASLLOW LEGACY DRUPAL DIR:
Disallow: */drpl/*

# DISALLOW ICTOWIKI DIR:
Disallow: http://wiki.islamiccounterterrorism.org/a/

# DISALLOW PRINT PAGES:
Disallow: */print/*

# DISALLOW LANGUAGE PATHS:
Disallow: /en/*
Disallow: /fa/*
Disallow: /fr/*
Disallow: /ur/*
Disallow: /tr/*
#
Disallow: */en/*
Disallow: */fa/*
Disallow: */fr/*
Disallow: */ur/*
Disallow: */tr/*

# DISALLOW THESE MOBILE PATHS:
Disallow: /iphone/
Disallow: /m/
Disallow: /mobi/
Disallow: /mobile/
Disallow: /pda/

# DISALLOW THESE DRUPAL GAMES:
Disallow: /breakout
Disallow: /invaders
Disallow: /pong
Disallow: /tetris

# QURAN INSTALLATION:
### Allow: http://xn----omcoc1cd8imdfng1d.com/quran/*
Disallow: */quran/*
Disallow: /quran/*

# DISALLOW THESE DRUPAL DIRECTORIES:
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/

# DISALLOW THESE DRUPAL FILES:
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php

# PATHS (W/ CLEAN URLS):
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /contact/
Disallow: /filter/
Disallow: /logout/
Disallow: /node/add/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: */textsize/*

# PATHS (W/O CLEAN URLS):
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=contact/
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/

# DISALLOW THE FOLLOWING ROBOTS:

User-agent: IsraBot
Disallow: /

User-agent: Orthogaffe
Disallow: /

User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
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: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: wget
Disallow: /

User-agent: grub-client
Disallow: /

User-agent: k2spider
Disallow: /

User-agent: NPBot
Disallow: /

User-agent: WebReaper
Disallow: /

User-agent: twiceler
Disallow: /

User-agent: dotbot 
Disallow: /

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

User-agent: MSIECrawler
Disallow: /

user-agent: Yandex
Disallow: /

User-agent: sogou+spider
Disallow: /
User-agent: sogou spider
Disallow: /

User-agent: spbot
Disallow: /