# robots.txt — Nissin Foods Company Limited
# Corporate and investor relations website (Umbraco CMS)
# https://www.nissingroup.com.hk

# -----------------------------------------------------------------------------
# Default rules (all crawlers)
# -----------------------------------------------------------------------------
User-agent: *
Allow: /

# CMS, backoffice, and non-public application paths
Disallow: /umbraco/
Disallow: /App_Plugins/
Disallow: /App_Data/
Disallow: /install/

# Search result pages (avoid indexing duplicate or thin content)
Disallow: /search?

# -----------------------------------------------------------------------------
# Major search engines
# (Explicit groups for clarity; same public-site rules apply.)
# -----------------------------------------------------------------------------
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: YandexBot
User-agent: Applebot
Allow: /
Disallow: /umbraco/
Disallow: /App_Plugins/
Disallow: /App_Data/
Disallow: /install/
Disallow: /search?

# -----------------------------------------------------------------------------
# AI assistants and answer engines
# Public investor-facing content may be crawled and cited.
# Admin paths remain blocked for all agents below.
# -----------------------------------------------------------------------------
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Applebot-Extended
User-agent: cohere-ai
User-agent: CCBot

Allow: /
Disallow: /umbraco/
Disallow: /App_Plugins/
Disallow: /App_Data/
Disallow: /install/
Disallow: /search?