Search

# Directions for robots.  See this URL:
# http://www.robotstxt.org/wc/norobots.html
# for a description of the file format.

User-agent: HTTrack
User-agent: puf
User-agent: MSIECrawler
Disallow: /

# The Krugle web crawler (though based on Nutch) is OK.
User-agent: Krugle
Allow: /
Disallow: /moin
Disallow: /pypi
Disallow: /~guido/orlijn/
Disallow: /wwwstats/
Disallow: /ftpstats/

# No one should be crawling us with Nutch.
User-agent: Nutch
Disallow: /

# Hide old versions of the documentation and various large sets of files.
User-agent: *
Disallow: /~guido/orlijn/
Disallow: /wwwstats/
Disallow: /webstats/
Disallow: /ftpstats/
Disallow: /moin
Disallow: /pypi
Disallow: /dev/buildbot/