# $Id: robots.txt, v.2.0 [typo3-specific] 2010/03/02 11:59:46 
#
# By Finees Mendez (a) rimawebsites.com - SUPPORT BY KEEPING COMMENTS
#
# 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

# Crawlers Setup
User-agent: *
Crawl-delay: 10

# Allowable Index
Allow: /
Allow: /fileadmin/user_upload/
Allow: /real-sitemap/
Allow: /real-seo-sitemap/
Allow: /apt-sitemap/
Allow: /apt-seo-sitemap/
Allow: /sell-sitemap/
Allow: /sell-seo-sitemap/
Allow: /uploads/

# Directories
Disallow: /cgi-bin/
Disallow: /fileadmin/_temp_/
Disallow: /fileadmin/templates/
Disallow: /t3lib/
Disallow: /typo3/
Disallow: /typo3_src/
Disallow: /typo3conf/
Disallow: /typo3temp/

# Paths (clean URLs)
Disallow: /index.php/ 
Disallow: /real-privacy/
Disallow: /real-terms/
Disallow: /apt-privacy/
Disallow: /apt-terms/
Disallow: /sell-privacy/
Disallow: /sell-terms/

# Files
Disallow: /clear.gif
Disallow: /error_log
Disallow: /INSTALL.tx
Disallow: /README.txt
Disallow: /RELEASE_NOTES.txt

# Paths (no clean URLs)
Disallow: /*?id=*
Disallow: /*&type=98
Disallow: /*.gz$
Disallow: /*.js$
Disallow: /*.css$
Disallow: /*.php$

# Multiple Domain Website Sitemaps
#Sitemap: http://www.heavensrealtors.com/rss.xml
Sitemap: http://www.heavensrealtors.com/real-seo-sitemap/
Sitemap: http://www.heavensapartments.com/apt-seo-sitemap/
Sitemap: http://www.shortsellmyhome.com/sell-seo-sitemap/