# $Id: robots.txt,v 1.4.4.3 2008/11/04 09:14:25 hass 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: ia_archiver 
disallow: /

User-agent: ia_archiver-web.archive.org
disallow: /

User-agent: *
Crawl-delay: 5
# Directories
Disallow: /downloader/
Disallow: /magiczoomplus/
Disallow: /catalogsearch/ajax/suggest/
Disallow: /static/factfinder/
# Files
Disallow: /LICENSE_AFL.txt
Disallow: /LICENSE.html
Disallow: /LICENSE.txt
# Paths (clean URLs)
Disallow: /admin/
Sitemap: sitemap.xml