GoNitro Extractions API

openapi: 3.0.3
info:
  title: Nitro PDF Services Public Authentication Extractions API
  description: 'REST API for Nitro PDF Services: convert, transform, extract, and generate PDF documents, plus async job status/result retrieval. Machine-to-machine OAuth 2.0 client-credentials; short-lived bearer tokens. Assembled by API Evangelist from Nitro''s published per-tool OpenAPI reference fragments; schemas preserved verbatim.'
  version: '1.0'
servers:
- url: https://api.gonitro.dev
  description: API server
security:
- BearerAuth: []
tags:
- name: Extractions
paths:
  /extractions:
    post:
      tags:
      - Extractions
      summary: Extract Fillable Form Data from PDF
      description: 'Extract the data of a PDF''s existing AcroForm — field names, current values, field types and positions — as JSON, XFDF, FDF, or CSV


        This endpoint is polymorphic: the operation performed is selected by the request body. Documented tools on this endpoint: extract-fillable-form-data, extract-invoices, forms, get-properties, pii, smart-detect-form-fields, tables, text, text-box.'
      parameters:
      - name: Accept
        in: header
        schema:
          $ref: '#/components/schemas/AcceptHeader'
      - name: Prefer
        in: header
        schema:
          $ref: '#/components/schemas/PreferHeader'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                method:
                  type: string
                  description: 'The Extractions'' endpoint method: `extract-fillable-form-data`'
                  default: extract-fillable-form-data
                  enum:
                  - extract-fillable-form-data
                params:
                  $ref: '#/components/schemas/ExtractFillableFormDataParams'
                file:
                  $ref: '#/components/schemas/FileUpload'
                delivery:
                  $ref: '#/components/schemas/DeliverySingleFileOut'
              required:
              - method
              - file
      responses:
        '200':
          description: "Returns either JSON or binary output depending on the Accept header (defaults to JSON).\n JSON responses describe the extracted form-field data for synchronous tasks, or a job status for asynchronous tasks."
          content:
            application/json:
              schema:
                oneOf:
                - $ref: '#/components/schemas/ExtractFillableFormDataResponse'
                - $ref: '#/components/schemas/AsyncJobResponse'
            application/octet-stream:
              schema:
                type: string
                format: binary
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
        '413':
          $ref: '#/components/responses/ContentTooLarge'
        '422':
          $ref: '#/components/responses/UnprocessableEntity'
        '500':
          $ref: '#/components/responses/InternalServerError'
      security:
      - BearerAuth: []
      operationId: extractFromDocument
      x-nitro-tools:
      - extract-fillable-form-data
      - extract-invoices
      - forms
      - get-properties
      - pii
      - smart-detect-form-fields
      - tables
      - text
      - text-box
components:
  schemas:
    ExtractFillableFormDataParams:
      title: Fillable Form Data
      type: object
      properties:
        format:
          type: string
          description: 'Output format for the extracted form data.

            - `json` (default): structured JSON with one `formFields` entry per form-field widget

            - `xfdf`: Adobe XFDF form-data document of field name/value pairs

            - `fdf`: Adobe FDF form-data document of field name/value pairs

            - `csv`: CSV with columns `name,value,fieldType,pageIndex,x,y,width,height`, one row per widget'
          default: json
          enum:
          - json
          - xfdf
          - fdf
          - csv
    HTTPCall:
      type: object
      properties:
        URL:
          type: string
          description: Your delivery endpoint URL
          nullable: false
          format: uri
        verb:
          type: string
          description: The HTTP method
          default: PUT
          enum:
          - GET
          - POST
          - PUT
          - DELETE
          - PATCH
        headers:
          type: array
          nullable: true
          description: Headers your file delivery endpoint might need (Optional)
          items:
            $ref: '#/components/schemas/Header'
      required:
      - URL
      - verb
    Header:
      type: object
      properties:
        name:
          type: string
        value:
          type: string
      required:
      - name
      - value
    AcceptHeader:
      type: string
      enum:
      - application/json
      - application/octet-stream
      - '*/*'
      default: '*/*'
      description: "Controls response format and behavior. See endpoint description above for detailed response combinations.\n- `application/json`: Returns JSON response with operation result\n- `application/octet-stream`: Returns binary file content \n- `*/*`: Defaults to JSON response"
    FileUpload:
      description: "The file to process. It can be provided as a binary upload or as a JSON remote file reference. \n\n"
      oneOf:
      - type: string
        format: binary
        description: "#### Binary file \n Standard multipart file binary upload field"
      - type: object
        title: Remote file
        properties:
          URL:
            type: string
            format: uri
            description: URL of the remote file to process
          contentType:
            type: string
            description: The MIME type of the remote file
            example: application/pdf
        required:
        - URL
        - contentType
        description: "#### Remote file \n JSON objects containing file URL and content type, sent with specific multipart encoding: `type` and `filename`. The playground **doesn't support** them. Plase test with an alternative tool (Ex: Postman). \n\nExample cURL file field for remote file:\n```bash\n--form 'file={\n   \"URL\":\"https://your-file.pdf\",\n   \"contentType\":\"application/pdf\"\n}\n;type=application/vnd.gonitro.url+json\n;filename=https://your-file.pdf'\n```"
    Callback:
      type: object
      description: POST endpoint that will get JOB ID and location when processing starts only on async processesing (see example above)
      properties:
        URL:
          type: string
          description: Your POST endpoint callback URL.
          nullable: false
          format: uri
        headers:
          type: array
          description: Headers your callback endpoint might need
          items:
            $ref: '#/components/schemas/Header'
      required:
      - URL
    DeliverySingleFileOut:
      type: object
      properties:
        uploadResultTo:
          $ref: '#/components/schemas/HTTPCall'
        callback:
          $ref: '#/components/schemas/Callback'
      description: "This endpoint lets you supply your own URL to receive the single-file output. The URL may point to a custom API endpoint or a pre-signed S3 URL. \n\n The HTTP method defaults to PUT, but you can change it based on your implementation needs via the `verb` parameter. You can also provide custom headers, such as authentication headers or any others required by your endpoint."
    FillableFormField:
      type: object
      description: A single form-field widget read from the PDF's existing AcroForm.
      properties:
        pageIndex:
          type: integer
          description: Zero-based index of the page the field widget is on.
          example: 0
        fieldType:
          type: string
          description: The kind of form field.
          enum:
          - TextBox
          - CheckBox
          - RadioButton
          - ComboBox
          - ListBox
          - Signature
          example: TextBox
        name:
          type: string
          description: The fully-qualified AcroForm field name. Radio-button groups produce one entry per widget, repeating the group name.
          example: text_name
        value:
          type: string
          description: The field's current value. `""` when unfilled; check boxes report `"true"` or `"false"`.
          example: John
        boundingBox:
          type: array
          description: The widget's position and size in PDF points, as `[x, y, width, height]`.
          items:
            type: number
          minItems: 4
          maxItems: 4
          example:
          - 61.2
          - 130.5
          - 240
          - 18
        choices:
          type: array
          nullable: true
          description: The available options of a `ComboBox`/`ListBox` field, or a radio-button group's export values. `null` for other field types.
          items:
            type: string
          example: null
      required:
      - pageIndex
      - fieldType
      - name
      - value
      - boundingBox
      - choices
    PreferHeader:
      type: string
      enum:
      - respond-async
      description: 'Controls synchronous vs asynchronous operation. See endpoint description above for behavior details.

        - `respond-async`: Makes request asynchronous, returns job status for polling

        - No value: Synchronous response'
    ExtractFillableFormDataResponse:
      type: object
      title: Sync - Fillable Form Data
      description: A flat list of the form-field widgets in the PDF's existing AcroForm, with their names, current values, types, and positions. Empty when the PDF has no AcroForm.
      properties:
        formFields:
          type: array
          description: The extracted form fields, one entry per widget.
          items:
            $ref: '#/components/schemas/FillableFormField'
      required:
      - formFields
      example:
        formFields:
        - pageIndex: 0
          fieldType: TextBox
          name: text_name
          value: John
          boundingBox:
          - 61.2
          - 130.5
          - 240
          - 18
          choices: null
        - pageIndex: 0
          fieldType: CheckBox
          name: checkbox_active
          value: 'true'
          boundingBox:
          - 61.2
          - 190.1
          - 12
          - 12
          choices: null
        - pageIndex: 0
          fieldType: RadioButton
          name: radio_group_app
          value: App1
          boundingBox:
          - 61.2
          - 220.7
          - 12
          - 12
          choices:
          - App1
          - App2
          - App3
    AsyncJobResponse:
      type: object
      title: Async - Job
      properties:
        jobID:
          type: string
          example: 01234567-89ab-cdef-0123-456789abcdef
        status:
          type: string
          enum:
          - running
        progress:
          type: number
          description: Progress of the job as a float between 0.0 and 1.0
          format: float
          default: 0
          example: 0
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT