# robots.txt for https://kolza.co.za
# (c) Kolza. All rights reserved. Text and data mining rights reserved
# (see /.well-known/tdmrep.json and https://kolza.co.za/terms/).
# Bulk copying, mirroring, cloning or AI training use is prohibited.

# --- Everyone ---------------------------------------------------------
User-agent: *
Disallow: /kz-trap/
Disallow: /api/
Disallow: /search/
Disallow: /*?q=

# --- AI training & dataset crawlers: rights reserved -----------------
User-agent: GPTBot
User-agent: CCBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Diffbot
User-agent: Omgilibot
User-agent: omgili
User-agent: Webzio-Extended
User-agent: ImagesiftBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: AI2Bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: PetalBot
User-agent: PanguBot
User-agent: Kangaroo Bot
User-agent: img2dataset
User-agent: Scrapy
Disallow: /

# --- SEO-intelligence crawlers (competitor mapping) ------------------
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: serpstatbot
User-agent: Barkrowler
Disallow: /

# --- AI search/answer engines: allowed to cite and link, not to train -
# (OAI-SearchBot, ChatGPT-User, PerplexityBot, Claude-SearchBot, Claude-User,
#  DuckAssistBot fall under "User-agent: *" above.)

Sitemap: https://kolza.co.za/sitemap.xml