## Disallow following crawlers (might also be blocked by fail2ban or similar)

# Block MJ12bot as it is just noise
User-agent: MJ12bot
Disallow: /

# Block Ahrefs
User-agent: AhrefsBot
Disallow: /

# Block Sogou
User-agent: sogou spider
Disallow: /

# Block SEOkicks
User-agent: SEOkicks-Robot
Disallow: /

# Block BlexBot
User-agent: BLEXBot
Disallow: /

# Block SISTRIX
User-agent: SISTRIX Crawler
Disallow: /
User-agent: sistrix
Disallow: /
User-agent: 007ac9
Disallow: /
User-agent: 007ac9 Crawler
Disallow: /

# Block Uptime robot
User-agent: UptimeRobot/2.0
Disallow: /

# Block Ezooms Robot
User-agent: Ezooms Robot
Disallow: /

# Block Perl LWP
User-agent: Perl LWP
Disallow: /

# Block BlexBot
User-agent: BLEXBot
Disallow: /

# Block netEstate NE Crawler (+http://www.website-datenbank.de/)
User-agent: netEstate NE Crawler (+http://www.website-datenbank.de/)
Disallow: /

# Block WiseGuys Robot
User-agent: WiseGuys Robot
Disallow: /

# Block Turnitin Robot
User-agent: Turnitin Robot
Disallow: /

# Block Heritrix
User-agent: Heritrix
Disallow: /

# Block pricepi
User-agent: pimonster
Disallow: /
User-agent: Pimonster
Disallow: /

# Block other bots (though remember they might not repect robots.txt)

User-agent: AhrefsBot
Disallow: /

User-agent: worldwebheritage.org
 disallow: /

User-agent: worldwebheritage.org/1.0
 disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: * 
## Crawl-delay parameter: number of seconds to wait between successive requests to the same server.
## Set a custom crawl rate if you're experiencing traffic problems with your server.
Crawl-delay: 60