Docparser Documents API

openapi: 3.2.0
info:
  title: Docparser REST Documents API
  description: The Docparser REST API provides programmatic access to document parsing and data extraction capabilities. Developers can upload documents via file upload, base64 encoding, or public URL fetch, retrieve parsed results for individual or multiple documents, manage parser configurations, and trigger re-parsing or re-integration operations. The API uses HTTP Basic Auth with the API key as the username and enforces per-minute rate limits on result retrieval endpoints.
  version: '1.0'
  contact:
    name: Docparser Support
    url: https://docparser.com
  termsOfService: https://docparser.com/terms/
  license:
    name: Proprietary
servers:
- url: https://api.docparser.com/v1
  description: Docparser API v1
- url: https://api.docparser.com/v2
  description: Docparser API v2 (selected endpoints)
security:
- basicAuth: []
- apiKeyHeader: []
- apiKeyQuery: []
tags:
- name: Documents
  description: Upload and manage documents for parsing
paths:
  /document/upload/{parserId}:
    post:
      operationId: uploadDocument
      summary: Upload a document by file
      description: Uploads a document to the specified parser using multipart form data (file upload) or base64-encoded content. The document is queued for parsing immediately upon upload.
      tags:
      - Documents
      parameters:
      - $ref: '#/components/parameters/parserId'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - file
              properties:
                file:
                  type: string
                  format: binary
                  description: The document file to upload (PDF, DOCX, image).
                file_name:
                  type: string
                  description: Optional filename override. If not provided, the original filename is used.
                remote_id:
                  type: string
                  description: Optional custom identifier to associate with the document for tracking purposes.
          application/json:
            schema:
              type: object
              required:
              - file_content
              - file_name
              properties:
                file_content:
                  type: string
                  description: Base64-encoded file content.
                file_name:
                  type: string
                  description: Filename including extension (e.g., invoice.pdf).
                remote_id:
                  type: string
                  description: Optional custom identifier for tracking.
      responses:
        '200':
          description: Document uploaded and queued for parsing
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentUploadResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
  /document/reparse/{parserId}:
    post:
      operationId: reparseDocuments
      summary: Reparse documents
      description: Reschedules parsing for previously uploaded documents under the specified parser. Useful after updating parser rules.
      tags:
      - Documents
      parameters:
      - $ref: '#/components/parameters/parserId'
      responses:
        '200':
          description: Reparse scheduled successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SuccessResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
  /document/reintegrate/{parserId}:
    post:
      operationId: reintegrateDocuments
      summary: Reintegrate documents
      description: Reschedules integration (webhook delivery / third-party push) for previously parsed documents under the specified parser.
      tags:
      - Documents
      parameters:
      - $ref: '#/components/parameters/parserId'
      responses:
        '200':
          description: Reintegration scheduled successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SuccessResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
components:
  parameters:
    parserId:
      name: parserId
      in: path
      required: true
      schema:
        type: string
      description: The unique identifier of the document parser.
      example: abc123xyz
  responses:
    BadRequest:
      description: Bad request. Check parameters and payload.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    Unauthorized:
      description: Authentication failed. Check your API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    NotFound:
      description: Resource not found. Check parserId or documentId.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Error code or short identifier.
        message:
          type: string
          description: Human-readable error description.
    SuccessResponse:
      type: object
      properties:
        msg:
          type: string
          description: Confirmation message.
    DocumentUploadResponse:
      type: object
      properties:
        id:
          type: string
          description: Unique identifier of the uploaded document.
          example: doc_abc123
        file_size:
          type: integer
          description: Size of the uploaded file in bytes.
        quota_used:
          type: integer
          description: Number of quota units consumed by this upload.
        quota_left:
          type: integer
          description: Remaining quota units in the current billing period.
  securitySchemes:
    basicAuth:
      type: http
      scheme: basic
      description: HTTP Basic Authentication. Use your API key as the username and leave the password blank.
    apiKeyHeader:
      type: apiKey
      in: header
      name: api_key
      description: API key passed as a custom request header.
    apiKeyQuery:
      type: apiKey
      in: query
      name: api_key
      description: API key passed as a URL query parameter.