{
  "id": "theguardian/2026/11/11/0411-sitemaps-news-xml",
  "url": "https://www.theguardian.com/sitemaps/news.xml",
  "host": "www.theguardian.com",
  "source": "theguardian",
  "source_name": "theguardian.com",
  "kind": "press",
  "read_utc": "2026-11-11T04:11:09Z",
  "captured": true,
  "status": 200,
  "headers": {
    "date": "Wed, 11 Nov 2026 04:11:10 GMT",
    "etag": "W/\"hash-373056844997837639\"",
    "content-type": "text/xml; charset=UTF-8",
    "content-length": "89959",
    "cache-control": "max-age=60, stale-while-revalidate=6, stale-if-error=864000, private",
    "age": "0",
    "x-robots-tag": "bingbot: noarchive"
  },
  "title": "",
  "sha256_html": "b1b2f63b87696d6481b795f54114df04fda0c2c9c312c93c28f5a04d2c3ee289",
  "sha256_dom": "1de7c52e2a9bb5c5963434093b5823c5926c2b471f0d0f6b6b0187d632056605",
  "sha256_text": "f3c99c8b16a3272076b3f5bfb9fe8d1e3784f4f6b0ada8f648c80fc9f919e717",
  "sha256_screenshot": "cbacdc302a6fc9bb3829b96f0fcc26297813a76bdca70f07beb170eceaea3870",
  "bytes": {
    "html": 493815,
    "dom": 2072529,
    "text": 409252,
    "screenshot": 186335
  },
  "screenshot": {
    "format": "jpeg",
    "quality": 78,
    "width": 1280,
    "height": 16000,
    "page_height": 134763,
    "cut": true
  },
  "rendered": true,
  "shown": false,
  "licence": "Press: all rights reserved by the publisher. The capture is kept privately; shown here are only the hash, the title, the time read and a short excerpt, with the link.",
  "excerpt": "This XML file does not appear to have any style information associated with it. The document tree is shown below. <urlset xmlns:image=\"http://www.google.com/schemas/sitemap-image/1.1\" xmlns:news=\"http://www.google.com/schemas/sitemap-news/0.9\" xmlns=\"http://www.sitemaps.org/schem",
  "vault": null,
  "capture_vault": {
    "id": "worixdil",
    "path": "theguardian/2026/11/11/0411-sitemaps-news-xml",
    "files": [
      "capture.json",
      "dom.html",
      "raw.html",
      "screenshot.jpg",
      "text.txt"
    ]
  },
  "robots": "robots.txt has no rule for this address",
  "client": "Mozilla/5.0 (compatible; page-capture/1.0)",
  "by": "incident.archivist@web-summit.dinis",
  "updated": "2026-11-11T04:25:47Z",
  "previous": null,
  "changed": null
}