# A list of misbehaving crawlers.
# originally from http://aardling.com/robots.txt
User-agent: DOC
Disallow: /
User-agent: Download Ninja
Disallow: /
User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy entire sites.
User-agent: Fetch
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: larbin
Disallow: /
User-agent: libwww
Disallow: /
User-agent: linko
Disallow: /
User-agent: Microsoft.URL.Control
Disallow: /
User-agent: MSIECrawler
Disallow: /
User-agent: Offline Explorer
Disallow: /
User-agent: sitecheck.internetseer.com
Disallow: /
User-agent: SiteSnagger
Disallow: /
User-agent: Teleport
Disallow: /
User-agent: TeleportPro
Disallow: /
User-agent: UbiCrawler
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: WebStripper
Disallow: /
User-agent: WebZIP
Disallow: /
User-agent: Xenu
Disallow: /
User-agent: Zealbot
Disallow: /
User-agent: ZyBORG
Disallow: /

# Wget in its recursive mode is a frequent problem.
User-agent: wget
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: /

# These rules apply to everyone else.
User-agent: *
Disallow: /*.php
Disallow: /*/?comments=true
Disallow: /*/?nomobile
Disallow: /*/?postcomment=true
Disallow: /*/?replytocom=*
Disallow: /*/feed*
Disallow: /*/feed/
Disallow: /*/trackback
Disallow: /*/trackback/
Disallow: /?cat=
Disallow: /?cat=*
Disallow: /?p=*
Disallow: /?s=*
Disallow: /author
Disallow: /edit.php?*
Disallow: /feed*
Disallow: /over*
Disallow: /statistics
Disallow: /tweets
Disallow: /tweets/
Disallow: /tweets/*
Disallow: /wp-admin
Disallow: /wp-admin/*
Disallow: /wp-login.php
Disallow: /document/
Disallow: /examples/
Disallow: /js/
Disallow: /LOG_DIR/
Disallow: /logs/
Disallow: /cgi-bin/

Sitemap: https://www.cashflowmanager.co.uk/sitemap_index.xml