{
  "fileFormatID": 1673,
  "formatName": "CDX Internet Archive Index",
  "version": null,
  "formatDescription": "A CDX file consists of individual lines of text, each of which summarizes a single web document. \r\nThe first line in the file is a legend for interpreting the data, and the following lines contain the data for referencing the corresponding pages within the host. The CDX signatures use a field delimiter character which is assumed to be a space character, however please contact the PRONOM team should you encounter CDX index files where the delimiter is different.",
  "releaseDate": null,
  "binaryFileFormat": null,
  "formatNote": null,
  "lastUpdatedDate": "22 Sep 2020",
  "formatProvenance": null,
  "formatSourceDate": "14 Jan 2016",
  "formatDisclosure": null,
  "formatEnvironment": null,
  "formatRisk": null,
  "formatAliases": null,
  "formatTypes": "Text (Structured)",
  "formatFamilies": null,
  "identifiers": [
    {
      "identifierText": "fmt/869",
      "identifierType": "PUID"
    }
  ],
  "internalSignatures": [
    {
      "signatureID": 1229,
      "name": "CDX Archive Index variant 1",
      "note": "BOF: <field delimiter (usually space)>CDX<field delimiter (usually space)>, followed by CDX options as described here: https://archive.org/web/researcher/cdx_file_format.php\r\nFor signature strength we currently assume the field delimiter will be a space character (hex 0x20) rather than a wildcard, with scope to add further delimiters as they are encountered.",
      "byteSequences": [
        {
          "positionType": "Absolute from BOF",
          "offset": 0,
          "maxOffset": 0,
          "byteSequence": "2043445820",
          "endianness": null,
          "byteSequenceID": 1500
        }
      ]
    },
    {
      "signatureID": 1751,
      "name": "CDX Archive Index variant 2",
      "note": "BOF: 'CDX' <field delimiter (usually space)>, followed by CDX options as described here: https://archive.org/web/researcher/cdx_file_format.php. This format could potentially be strengthened if necessary with the inclusion of one or more of the CDX options, which are to date an alphabetic character (upper or lower case, a-z, A-Z with a few exceptions) or the hash value",
      "byteSequences": [
        {
          "positionType": "Absolute from BOF",
          "offset": 0,
          "maxOffset": 0,
          "byteSequence": "43445820",
          "endianness": null,
          "byteSequenceID": 2029
        }
      ]
    }
  ],
  "externalSignatures": [
    {
      "externalSignature": "cdx",
      "signatureType": "File extension"
    }
  ],
  "relationships": [],
  "submittedBy": [
    1
  ]
}