User-agent: *
Allow: /
Allow: /en/

# ==== 2026-06-11 安全加固 ====
Disallow: /admin/
Disallow: /private/
Disallow: /sitemap_backup/
Disallow: /blog_backup/
Disallow: /wwwroot_backup/
Disallow: /sitemap_utf8*        # 2026-07-05: publish.py 6/18 早期 bug 产物, 16KB 假 sitemap.html, 已删
Disallow: /sp.html
Disallow: /web.config-bak
Disallow: /matrix-media-*
Disallow: /*.txt$
Disallow: /_patch_*
Disallow: /_backup_*
Disallow: /_indexnow_key*
Disallow: /_bing_webmaster*
Disallow: /_yandex_webmaster*
Disallow: /_gsc_*                     # 2026-07-09: GSC Service Account JSON key, 防止泄露
Disallow: /en/en/                    # 2026-07-19: 错路径 URL（IIS rewrite 返回 200 误判）, 阻止再爬

# ==== 2026-07-09 HCU + SpamBrain 修复期 (临时) ====
# 暂停 blog 抓取, 让 Google 重新评估整站
# blog 文章已全部 meta noindex, 这里再加 robots.txt 保险
# 预计 2-4 个月修复期后逐步放开
Disallow: /blog/

# ==== 2026-06-27 引擎收录优化 ====
# 显式放行主要爬虫 (其实 User-agent: * 已经覆盖, 但显式声明提高 GEO 信任度)

# Google (含 AI 训练 Google-Extended)
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

# Bing + Microsoft (Copilot, Edge)
User-agent: Bingbot
Allow: /

User-agent: MSNBot-Media
Allow: /

# Yandex
User-agent: YandexBot
Allow: /

User-agent: YandexImages
Allow: /

# AI 引擎爬虫 (GEO 关键 - 这些 bot 不封才会被 ChatGPT/Claude/Perplexity 等 grounding 引用)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

# ==== 显式封禁有害 bot ====
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# ==== Sitemap 声明 (多引擎都读这里) ====
Sitemap: https://www.baccai.com/sitemap.xml