[
 {
  "engine": "Google",
  "page": "developers.google.com/search/docs/appearance/ai-features",
  "note": "their AI-features guidance page",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "",
  "blocks_www": false,
  "llms": "http-404",
  "page_http": 200,
  "nojs_words": 2096,
  "title": true,
  "meta_desc": true,
  "jsonld_valid": 1,
  "jsonld_bad": 0,
  "robots_hash": "2d1ba1920a0a"
 },
 {
  "engine": "OpenAI",
  "page": "platform.openai.com/docs/bots",
  "note": "their crawler-rules page",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "",
  "blocks_www": false,
  "llms": "http-404",
  "page_http": 200,
  "nojs_words": 2052,
  "title": true,
  "meta_desc": false,
  "jsonld_valid": 0,
  "jsonld_bad": 0,
  "robots_hash": "08fe58693356"
 },
 {
  "engine": "OpenAI-www",
  "page": "openai.com/",
  "note": "corporate root",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "",
  "blocks_www": false,
  "llms": "http-403",
  "page_http": 403,
  "nojs_words": 0,
  "title": false,
  "meta_desc": false,
  "jsonld_valid": 0,
  "jsonld_bad": 0,
  "robots_hash": "c53100563b9d"
 },
 {
  "engine": "Anthropic",
  "page": "www.anthropic.com/",
  "note": "corporate root (their /claude-bot page 404s)",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "",
  "blocks_www": false,
  "llms": "http-404",
  "page_http": 200,
  "nojs_words": 697,
  "title": true,
  "meta_desc": true,
  "jsonld_valid": 0,
  "jsonld_bad": 0,
  "robots_hash": "b8bb03567cf8"
 },
 {
  "engine": "Perplexity",
  "page": "www.perplexity.ai/",
  "note": "corporate root",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "googlebot",
  "blocks_www": false,
  "llms": "http-403",
  "page_http": 403,
  "nojs_words": 0,
  "title": true,
  "meta_desc": false,
  "jsonld_valid": 0,
  "jsonld_bad": 0,
  "robots_hash": "a4b48ab940c3"
 },
 {
  "engine": "DuckDuckGo",
  "page": "duckduckgo.com/duckduckbot",
  "note": "their bot page",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "ia_archiver",
  "blocks_www": false,
  "llms": "html",
  "page_http": 200,
  "nojs_words": 2320,
  "title": true,
  "meta_desc": true,
  "jsonld_valid": 1,
  "jsonld_bad": 1,
  "robots_hash": "02fc159e8e3f",
  "jsonld_bad_corrected": 0,
  "correction_note": "jsonld_bad=1 was a measurement artifact (regex matched JSON-LD inside a Next.js payload string); retracted after re-fetch \u2014 see P5/cross-check log. Raw values kept as-collected; corrections are additive, never silent."
 },
 {
  "engine": "Bing",
  "page": "www.bing.com/webmasters/about",
  "note": "webmaster resources",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "msnbot-media,twitterbot",
  "blocks_www": false,
  "llms": "http-404",
  "page_http": 200,
  "nojs_words": 12,
  "title": true,
  "meta_desc": true,
  "jsonld_valid": 0,
  "jsonld_bad": 0,
  "robots_hash": "9a882c071677"
 },
 {
  "engine": "CommonCrawl",
  "page": "commoncrawl.org/",
  "note": "the crawler everyone reads",
  "robots_http": 200,
  "robots_html_instead": false,
  "named_bots": "indeedbot,indeedshopbot",
  "blocks_www": false,
  "llms": "http-404",
  "page_http": 200,
  "nojs_words": 459,
  "title": true,
  "meta_desc": true,
  "jsonld_valid": 0,
  "jsonld_bad": 0,
  "robots_hash": "13ac8bbfcbc8"
 }
]