robots.txt

# $Id: robots.txt,v 1.9.2.1 2015/05/05 17:12:19 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

# disallow all 
User-agent: *
Disallow: /
Crawl-delay: 600


# but allow only important bots
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Mediapartners-Google
User-agent: msnbot
User-agent: msnbot-media
User-agent: bingbot
User-agent: Slurp
User-agent: Yahoo-Blogs
User-agent: Yahoo-MMCrawler
User-agent: Applebot
User-agent: Twitterbot
User-agent: Yandexbot
User-agent: FacebookExternalHit

# Directories

# Files
Disallow: /*.py
Disallow: /*.pyc
Disallow: /*.md
Disallow: /*.sh
Disallow: /.gitignore

Disallow: /site_src/MAPSeeker*.*
Disallow: /site_src/REEFFIT*.*

# Paths (clean URLs)
Disallow: /admin/
Disallow: /login/
Disallow: /logout/
Disallow: /password/
Disallow: /register/

Disallow: /deposit/review/
Disallow: /analyze/predict/
Disallow: /api/

Disallow: /site_media/_old/
Disallow: /site_media/images/src/
Disallow: /site_data/json/
Disallow: /site_data/search/
Disallow: /site_data/tmp/

Disallow: /ping_test/
Disallow: /test/
Disallow: /cgi-bin/

# Paths (no clean URLs)
Disallow: /search/?sstring=*

Crawl-delay: 600