{
  "slug": "warc-file-format",
  "term": "WARC file format",
  "aliases": [
    "WARC",
    "Web ARChive"
  ],
  "definition": "WARC is a container format that stores captured resources and associated information as a sequence of typed records.",
  "note": "Record boundaries: a file contains one or more records, and a segmented logical record can span several records. WARC Content-Length counts block octets, excluding the WARC header and trailing separators; an HTTP response block includes its HTTP headers. [warc11]\n\nDigest scope: block digests exclude WARC headers. Payload digests can describe content absent from a revisit record, whose profile governs interpretation. Retain referenced content as well as the referencing capture. [warc11]\n\nAccess: record-at-a-time gzip permits individual compressed records to be read by offset. A CDX index can support lookup without being part of the WARC record itself. [loc]",
  "status": "shipping",
  "advantages": [
    {
      "text": "Resources of different formats can share one archival container with associated metadata.",
      "citationIds": [
        "loc"
      ]
    }
  ],
  "limitations": [
    {
      "text": "Compression is optional; WARC defines no internal compression scheme.",
      "citationIds": [
        "warc11"
      ]
    },
    {
      "text": "Format validity does not establish complete website replay or authenticate capture history.",
      "citationIds": [
        "analysis"
      ]
    }
  ],
  "related": [
    "warc-block-digest",
    "warc-payload-digest",
    "warc-revisit-record",
    "deduplication",
    "backup-verification"
  ],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-11-21",
  "citations": [
    {
      "id": "warc11",
      "title": "IIPC WARC 1.1: file and record model, named fields, revisit, segmentation and Annex D",
      "url": "https://iipc.github.io/warc-specifications/specifications/warc-format/warc-1.1/",
      "accessed": "2026-11-21"
    },
    {
      "id": "loc",
      "title": "Library of Congress: WARC format description, aggregation, gzip and CDX indexing",
      "url": "https://www.loc.gov/preservation/digital/formats/fdd/fdd000236.shtml",
      "accessed": "2026-11-21"
    },
    {
      "id": "analysis",
      "title": "Hesela: WARC capture dependencies and bounded recovery controls",
      "url": "https://hesela.com/analyses/deduplication-restore-fragmentation/#warc-revisits",
      "accessed": "2026-11-21"
    }
  ],
  "provenance": [
    "Source synthesis for WARC 1.1; no new parser, capture or replay experiment. [warc11] [loc]",
    "Annex D is informative compression guidance, not a requirement for every WARC file. [warc11]"
  ]
}
