# Define access-restrictions for robots/spiders
# http://www.robotstxt.org/wc/norobots.html



# By default we allow robots to access all areas of our site 
# already accessible to anonymous users

User-agent: *
Disallow: /Members/
Disallow: /training/
Disallow: /uol/
Disallow: /homepage-content/



# Add Googlebot-specific syntax extension to exclude forms 
# that are repeated for each piece of content in the site 
# the wildcard is only supported by Googlebot
# http://www.google.com/support/webmasters/bin/answer.py?answer=40367&ctx=sibling

User-Agent: Googlebot
Disallow: /*sendto_form$
Disallow: /*folder_factories$

Disallow: /@@*/
Disallow: /*/@@*/
Disallow: /Members/asa8/
Disallow: /offices/ssds/sd/vacancies/RSS/
Disallow: /acl_users/

# yacybot was being impolite and making 15 reqs/s
User-agent: yacybot
Disallow: /

# http://www.80legs.com/webcrawler.html hit 64 reqs/sec
User-agent: 008
Disallow: /

# yandex similarly impolite
User-agent: Yandex
Crawl-Delay: 2

User-agent: AhrefsBot
Crawl-Delay: 10

# Prevent our own GSA from crawling - should rely on feed
User-agent: gsa-crawler-uol-its
Disallow: /