#
# robots.txt for http://bucket1.cityofpaloalto.org/
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site may be blocked.
#

# ----- TEMP

# go away
# User-agent: *
# Disallow: /

# go away google
# User-Agent: Googlebot
# Disallow: /

# User-agent: Googlebot-Image
# Disallow: /

# User-agent: Mediapartners-Google
# Disallow: /

# ----- TEMP

# Trap Bots that do not respect robots.txt
Disallow: /bot-trap/

# Direct Bots to the Site Map
Sitemap: http://www.cityofpaloalto.org/sitemap.xml

# Set delay for requests
User-agent: *
Request-rate: 1/5         # maximum rate is one page every 5 seconds
Visit-time: 0900-1100     # only visit between 1:00 AM and 3:00 AM UT (GMT)

# Don't index Lasso pages
User-Agent: *
Disallow: /*.lasso$

# Don't index javascripts or stylesheets
User-Agent: *
Disallow: /*.js$
Disallow: /*.css$

# Don't index Images
User-Agent: *
Disallow: /*.gif$
Disallow: /*.jpg$
Disallow: /*.png$

# Don't index these folders
User-Agent: *
Disallow: /*private*/
Disallow: /*trash*/
Disallow: /aspnet*/
Disallow: /*aspnet*/
Disallow: /cals/
Disallow: /custom/
Disallow: /documents/
Disallow: /dtSearch/
Disallow: /faqs/
Disallow: /flash/
Disallow: /forms/
Disallow: /forum/
Disallow: /galleries/
Disallow: /home_nav/ 
# Updated 032310 for Google RFI
Disallow: /google_rfi/ 

# Updated 091009 to comply with WAC recommendation
# Disallow: /images/
#

Disallow: /img/
Disallow: /inc/
Disallow: /mockup/
Disallow: /navdata/
Disallow: /search/
Disallow: groupcommon.asp
Disallow: /swfs/
Disallow: /templates/
Disallow: /ute/

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /

# Don't allow the wayback-machine to index pages
User-agent: ia_archiver
Disallow: /

# Frequent crawl activity
User-agent: charlotte
Disallow: /

# END OF FILE