# robots.txt file for www.jraxis.com # # $Id: robots.txt,v 1.10 2005/06/12 03:38:20 jraxis Exp $ # Fetches URLs for rd.jraxis.com from www.jraxis.com instead, causing 404s # (“sherlock” …what an appropriate name for a bot that can’t find shit!): User-Agent: sherlock Disallow: / # Misparses #fragment links, stripping the “#” off, causing 404s: User-Agent: wotbox Disallow: / User-Agent: * Crawl-Delay: 30 # Only the “front page” should be indexed: Disallow: /atheism/simulator/1 Disallow: /atheism/simulator/2 Disallow: /atheism/simulator/3 Disallow: /atheism/simulator/4 Disallow: /atheism/simulator/5 Disallow: /atheism/simulator/6 Disallow: /atheism/simulator/7 Disallow: /atheism/simulator/8 Disallow: /atheism/simulator/9 Disallow: /atheism/simulator/10 Disallow: /atheism/simulator/11 Disallow: /atheism/simulator/12 Disallow: /atheism/simulator/13 Disallow: /atheism/simulator/14 Disallow: /atheism/simulator/15 Disallow: /atheism/simulator/16 Disallow: /atheism/simulator/17 Disallow: /atheism/simulator/18 # Site-wide support files: Disallow: /common Disallow: /include # The script that displays contact addresses: Disallow: /info/contact/ # The script that displays others’ search requests. If this gets indexed, # an interesting feedback loop occurs whereby more odd search requests are # attracted to the site—to this page: Disallow: /info/search-requests/ # Ephemeral content: Disallow: /tmp # Old directories marked “410 Gone.” Need to be dropped by any search engines # that currently have them indexed: Disallow: /global Disallow: /pub Disallow: /sys Disallow: /test # These pages are gone, dead, kaput. Get the hell out! Disallow: /spam