Get dataset

v1.0.0

Returns dataset object for given dataset ID.

This does not return dataset items, only information about the storage itself. To retrieve dataset items, use the endpoint.

:::note

Keep in mind that attributes itemCount and cleanItemCount are not propagated right away after data are pushed into a dataset.

:::

There is a short period (up to 5 seconds) during which these counters may not match with exact counts in dataset items.

Input

{
  "type": "object",
  "properties": {
    "datasetId": {
      "type": "string"
    }
  },
  "required": [
    "datasetId"
  ],
  "additionalProperties": false
}

Output

{
  "type": "object",
  "description": "Response containing dataset metadata.",
  "required": [
    "data"
  ],
  "properties": {
    "data": {
      "type": "object",
      "required": [
        "accessedAt",
        "cleanItemCount",
        "consoleUrl",
        "createdAt",
        "id",
        "itemCount",
        "modifiedAt",
        "userId"
      ],
      "properties": {
        "accessedAt": {
          "type": "string",
          "format": "date-time"
        },
        "actId": {
          "type": [
            "string",
            "null"
          ]
        },
        "actRunId": {
          "type": [
            "string",
            "null"
          ]
        },
        "cleanItemCount": {
          "type": "integer"
        },
        "consoleUrl": {
          "type": "string",
          "format": "uri"
        },
        "createdAt": {
          "type": "string",
          "format": "date-time"
        },
        "fields": {
          "type": [
            "array",
            "null"
          ],
          "items": {
            "type": "string"
          }
        },
        "generalAccess": {
          "type": "string",
          "description": "Defines the general access level for the resource.",
          "enum": [
            "ANYONE_WITH_ID_CAN_READ",
            "ANYONE_WITH_NAME_CAN_READ",
            "FOLLOW_USER_SETTING",
            "RESTRICTED"
          ]
        },
        "id": {
          "type": "string"
        },
        "itemCount": {
          "type": "integer"
        },
        "itemsPublicUrl": {
          "type": "string",
          "format": "uri",
          "description": "A public link to access the dataset items directly."
        },
        "modifiedAt": {
          "type": "string",
          "format": "date-time"
        },
        "name": {
          "type": [
            "string",
            "null"
          ]
        },
        "schema": {
          "type": [
            "object",
            "null"
          ],
          "description": "Defines the schema of items in your dataset, the full specification can be found in [Apify docs](/storage/dataset-schema)"
        },
        "stats": {
          "type": "object",
          "properties": {
            "inflatedBytes": {
              "type": "integer",
              "description": "Uncompressed size in bytes. Only returned by the dataset list endpoint."
            },
            "readCount": {
              "type": "integer"
            },
            "storageBytes": {
              "type": "integer",
              "description": "Total storage size in bytes. Only returned by the single-dataset endpoint."
            },
            "writeCount": {
              "type": "integer"
            }
          }
        },
        "urlSigningSecretKey": {
          "type": [
            "string",
            "null"
          ],
          "description": "A secret key for generating signed public URLs. It is only provided to clients with WRITE permission for the dataset."
        },
        "userId": {
          "type": "string"
        }
      }
    }
  }
}