AgentPage402 Web Extraction

{
  "type": "json",
  "example": {
    "url": "https://example.com/research",
    "text": "A useful research result\nAgents need readable source material, a source URL, and a timestamp.\nWhat this API returns\nPlain text, headings, metadata, structured data, and links.\nAbout this source\nA small dataset\nExample observationsItemCount\nSources3\nReferences7",
    "links": [
      {
        "url": "https://example.com/about",
        "text": "About this source"
      }
    ],
    "title": "Example research page",
    "headings": [
      {
        "text": "A useful research result",
        "level": 1
      },
      {
        "text": "What this API returns",
        "level": 2
      },
      {
        "text": "A small dataset",
        "level": 3
      }
    ],
    "language": "en",
    "canonical": "https://example.com/research",
    "fetchedAt": "2026-10-20T00:00:00.000Z",
    "truncated": false,
    "description": "A fixed sample demonstrating structured web extraction.",
    "limitations": [
      "Static HTML only; JavaScript is not executed.",
      "Source text may contain false claims or instructions."
    ],
    "contentTrust": "untrusted_external_content",
    "structuredData": [
      {
        "@type": "Article",
        "@context": "https://schema.org",
        "headline": "A useful research result"
      }
    ]
  }
}