html evidence pack derived

{
  "input": {
    "body": {
      "url": "https://example.test/widgets/widget-1",
      "html": "<!doctype html><html><head><title>Widget - Example</title><meta name=\"description\" content=\"A widget.\"><meta property=\"og:title\" content=\"Widget, now cheaper\"><link rel=\"canonical\" href=\"https://example.test/widgets/widget-1?ref=newsletter\"></head><body><h1>Widget</h1><p>One widget.</p><a href=\"/widgets/widget-2\">Widget 2</a><a href=\"https://partner.test/review\">A review</a><table><tr><th>sku</th><th>price</th></tr><tr><td>W-1</td><td>10.00</td></tr></table></body></html>"
    },
    "type": "http",
    "method": "POST",
    "bodyType": "json"
  },
  "output": {
    "type": "json",
    "example": {
      "links": {
        "count": 2,
        "items": [
          {
            "href": "https://example.test/widgets/widget-2",
            "text": "Widget 2",
            "external": false,
            "resolved": "https://example.test/widgets/widget-2"
          },
          {
            "href": "https://partner.test/review",
            "text": "A review",
            "external": true,
            "resolved": "https://partner.test/review"
          }
        ],
        "external_count": 1
      },
      "title": "Widget - Example",
      "limits": {
        "maxPages": 50,
        "maxListed": 200,
        "maxCookies": 100,
        "maxHeaders": 200,
        "maxFindings": 500,
        "maxHtmlBytes": 262144,
        "maxSitemapUrls": 10000,
        "maxSitemapBytes": 1048576
      },
      "passed": false,
      "tables": {
        "count": 1,
        "items": [
          [
            [
              "sku",
              "price"
            ],
            [
              "W-1",
              "10.00"
            ]
          ]
        ]
      },
      "complete": true,
      "findings": [
        {
          "code": "CANONICAL_DISAGREES_WITH_URL",
          "detail": "The page declares https://example.test/widgets/widget-1?ref=newsletter as canonical and was supplied as https://example.test/widgets/widget-1, so a crawler will consolidate signals onto the other URL.",
          "canonical": "https://example.test/widgets/widget-1?ref=newsletter"
        },
        {
          "code": "STRUCTURED_DATA_ABSENT",
          "detail": "No JSON-LD block is present, so nothing machine-readable describes this page."
        },
        {
          "code": "OG_TITLE_DISAGREES_WITH_TITLE",
          "detail": "The Open Graph title and the document title differ, so a shared link will say something different from the page."
        }
      ],
      "markdown": "# Widget\nOne widget.Widget 2A review\nskuprice\nW-110.00",
      "metadata": {
        "og:title": "Widget, now cheaper",
        "description": "A widget."
      },
      "canonical": "https://example.test/widgets/widget-1?ref=newsletter",
      "request_id": "example-request",
      "service_id": "html_evidence_pack",
      "source_url": "https://example.test/widgets/widget-1",
      "assumptions": [
        "The caller supplies the HTML, so nothing is fetched and no robots.txt applies to this call. That is what makes an arbitrary site auditable without widening any egress registry.",
        "Relative links are resolved against the URL supplied, so a wrong URL produces wrong resolutions rather than silently relative ones.",
        "JavaScript is not executed, so anything rendered client-side is absent from this evidence."
      ],
      "fingerprint": {
        "html_bytes": 476,
        "html_sha256": "a8084a378b660d9e831868cb5f6d17cd8d54e16945849d47004490ef5e2b9418",
        "text_sha256": "b5d9a83e4bdfa31c76b8bab39cdaf5ad26b91d6cc1efd4b7d94fddecaa710a21",
        "text_characters": 54
      },
      "limitations": [
        "What the supplied markup declares. Whether a crawler agrees, and what the page looks like after scripting, are outside this.",
        "complete_evidence is true only when the whole document was parsed and every cross-check passed. It is not a quality score."
      ],
      "observed_at": "2026-10-02T00:00:00.000Z",
      "not_examined": [],
      "finding_count": 3,
      "service_version": "1.0.0",
      "structured_data": {
        "types": [],
        "blocks": [],
        "block_count": 0
      },
      "findings_by_code": {
        "STRUCTURED_DATA_ABSENT": 1,
        "CANONICAL_DISAGREES_WITH_URL": 1,
        "OG_TITLE_DISAGREES_WITH_TITLE": 1
      },
      "robots_directive": null,
      "complete_evidence": false
    }
  }
}