# robots.txt for www.marquardt.com

# Block specific bots
User-agent: GPTBot
User-agent: BLEXBot
User-agent: CloudVertexBot
User-agent: ClaudeBot
User-agent: Omgili
User-agent: Omgilibot
User-agent: Webzio-Extended
User-agent: CCBot
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: DeepseekBot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: cohere-training-data-crawler
User-agent: PanguBot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: Diffbot
User-agent: Amazonbot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: ImagesiftBot
User-agent: Magpie-crawler
User-agent: Peer39_crawler
User-agent: Peer39_crawler/1.0
User-agent: MicrosoftPreview
User-agent: Baiduspider
User-agent: Baiduspider-image
User-agent: Sogou web spider
User-agent: Sogou Push Spider
User-agent: Sogou Orion spider
User-agent: Sogou inst spider
User-agent: Sogou head spider
User-agent: Sogou Pic Spider
User-agent: Sogou spider2
User-agent: 360Spider
User-agent: HaosouSpider
User-agent: YisouSpider
User-agent: YoudaoBot
User-agent: EtaoSpider
Disallow: /


# Allow all others
User-agent: *

# Only allow URLs generated with frontend routing
Disallow: /*?id=*
Disallow: /*&id=*

# L=0 is the default language
Disallow: /*?L=0*
Disallow: /*&L=0*

# Should always be protected, but you know...
Disallow: /*/Private/*
Disallow: /*/Configuration/*

# Disallow all files in /typo3temp/var/
Disallow: /typo3temp/var/*

# Disallow all files in /typo3/
Disallow: /typo3/


# SQL-Dateien (Endungen)
Disallow: /*.sql$
Disallow: /*.sql.gz$


# Prevent indexing of the 404 error page
Disallow: /404

# Allow main newsroom page
Allow: /newsroom$
Allow: /newsroom/detail/
Allow: /de/newsroom/detail/

# Disallow all filtered URLs that contain commas
Disallow: /newsroom/*,*
Disallow: /de/newsroom/*,*

# Disallow news categories filter
Disallow: /*categories=*


# sitemap files 
Sitemap: https://www.marquardt.com/sitemap.xml