Bayer / robots.txt snapshot
← back to bayer.com · fetched 2026-11-04T01:20:07Z (3d ago) · HTTP 200 · 1755 bytes · sha256 5bce423051760d45 · raw
final URL: https://www.bayer.com/robots.txt
| 1 | # Bayer Global robots.txt |
| 2 | # https://www.bayer.com/ |
| 3 | |
| 4 | # Default rules for all compliant crawlers |
| 5 | User-agent: * |
| 6 | Disallow: /search/ |
| 7 | Disallow: /*? |
| 8 | |
| 9 | # OpenAI: allow ChatGPT Search |
| 10 | User-agent: OAI-SearchBot |
| 11 | Allow: / |
| 12 | Disallow: /search/ |
| 13 | Disallow: /*? |
| 14 | |
| 15 | # OpenAI: allow user-requested retrieval |
| 16 | User-agent: ChatGPT-User |
| 17 | Allow: / |
| 18 | Disallow: /search/ |
| 19 | Disallow: /*? |
| 20 | |
| 21 | # OpenAI: block model-training crawler |
| 22 | User-agent: GPTBot |
| 23 | Disallow: / |
| 24 | |
| 25 | # Anthropic: allow Claude Search |
| 26 | User-agent: Claude-SearchBot |
| 27 | Allow: / |
| 28 | Disallow: /search/ |
| 29 | Disallow: /*? |
| 30 | |
| 31 | # Anthropic: allow user-requested retrieval |
| 32 | User-agent: Claude-User |
| 33 | Allow: / |
| 34 | Disallow: /search/ |
| 35 | Disallow: /*? |
| 36 | |
| 37 | # Anthropic: block model-training crawler |
| 38 | User-agent: ClaudeBot |
| 39 | Disallow: / |
| 40 | |
| 41 | # Perplexity: allow search indexing and citations |
| 42 | User-agent: PerplexityBot |
| 43 | Allow: / |
| 44 | Disallow: /search/ |
| 45 | Disallow: /*? |
| 46 | |
| 47 | # Perplexity: allow user-requested retrieval |
| 48 | User-agent: Perplexity-User |
| 49 | Allow: / |
| 50 | Disallow: /search/ |
| 51 | Disallow: /*? |
| 52 | |
| 53 | # Mistral: allow AI search indexing |
| 54 | User-agent: MistralAI-Index |
| 55 | Allow: / |
| 56 | Disallow: /search/ |
| 57 | Disallow: /*? |
| 58 | |
| 59 | # Mistral: allow user-requested retrieval |
| 60 | User-agent: MistralAI-User |
| 61 | Allow: / |
| 62 | Disallow: /search/ |
| 63 | Disallow: /*? |
| 64 | |
| 65 | # Google: opt out of Gemini model training and grounding |
| 66 | # Does not affect Google Search, AI Overviews or AI Mode |
| 67 | User-agent: Google-Extended |
| 68 | Disallow: / |
| 69 | |
| 70 | # Apple: opt out of Apple generative-AI model training |
| 71 | # Does not block regular Applebot search crawling |
| 72 | User-agent: Applebot-Extended |
| 73 | Disallow: / |
| 74 | |
| 75 | # Meta: block model-training crawler |
| 76 | User-agent: meta-externalagent |
| 77 | Disallow: / |
| 78 | |
| 79 | # Common Crawl: block collection for public datasets |
| 80 | User-agent: CCBot |
| 81 | Disallow: / |
| 82 | |
| 83 | # ByteDance: block AI-training crawler |
| 84 | User-agent: Bytespider |
| 85 | Disallow: / |
| 86 | Sitemap: https://www.bayer.com/sitemap.xml |