# gerardo.de — robots.txt (2026)
# Shop content is crawlable by default; internal paths blocked below.

### Sitemap

Sitemap: https://www.gerardo.de/sitemaps/sitemap.xml
Sitemap: https://www.gerardo.de/sitemaps/sitemap.txt

### Default rules

User-agent: *

Disallow: /.config/
Disallow: /en/info/
Allow: /en/info/partners.php
Allow: /en/info/news.php
Allow: /en/info/verkostung.php
Disallow: /feeds/
Disallow: /info/
Allow: /info/partners.php
Allow: /info/news.php
Allow: /info/verkostung.php
Disallow: /kasse/
Disallow: /logs/
Disallow: /pages/
Disallow: /rechnung/
Disallow: /w3c/

### AI training / scraping bots

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: DeepSeek
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Copilot
Disallow: /

### SEO / aggressive crawlers

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: AliyunSecBot
Disallow: /

User-agent: CensysInspect
Disallow: /

### Mirror / ripper / archive tools

User-agent: HTTrack
Disallow: /

User-agent: Httrack
Disallow: /

User-agent: Wget
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: WebZip
Disallow: /

User-agent: Offline Explorer
Disallow: /

### Regional crawlers (non-target markets)

User-agent: Baiduspider
Disallow: /

User-agent: baiduspider
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: naverbot
Disallow: /

User-agent: yeti
Disallow: /

User-agent: Gaisbot
Disallow: /

### Legacy scrapers (still seen in logs)

User-agent: psbot
Disallow: /

User-agent: Python-urllib
Disallow: /

User-agent: curl
Disallow: /

User-agent: Foobot
Disallow: /

User-agent: larbin
Disallow: /

User-agent: grub-client
Disallow: /

User-agent: grub
Disallow: /

User-agent: looksmart
Disallow: /

User-agent: GeedoProductSearch
Disallow: /