{
  "id": "arquivo-pt",
  "name": "Arquivo.pt Web Crawler",
  "operator": {
    "name": "Arquivo.pt (FCCN/FCT)",
    "url": "https://arquivo.pt"
  },
  "description": "The crawler behind Arquivo.pt, Portugal's public web archive, which captures full page renders (HTML, CSS, JS, images) for long-term preservation. Built on Heritrix. Arquivo.pt publishes the ranges its crawlers operate from as a machine-readable JSON file in the JAFAR format, and recommends combining that IP check with the User-Agent check.",
  "docs": [
    "https://sobre.arquivo.pt/en/help/crawling-and-archiving-web-content/"
  ],
  "category": "archiver",
  "user_agents": {
    "patterns": [
      "Arquivo-web-crawler"
    ],
    "instances": [
      "Arquivo-web-crawler (compatible; heritrix/3.4.0-20200304 +https://arquivo.pt/faq-crawling)"
    ]
  },
  "behavior": {
    "respects_robots_txt": true,
    "robots_token": "Arquivo-web-crawler"
  },
  "verification": [
    {
      "type": "cidr_feed",
      "url": "https://arquivo.pt/crawlerips.json",
      "format": "prefixes"
    }
  ],
  "tier": 1,
  "tier_label": "Fully verifiable",
  "first_seen": "2026-07-08T19:13:49.571Z",
  "resolved_cidrs": [
    "194.210.235.0/26",
    "2001:690:a00:1039::/64"
  ]
}