Parseur Document API

openapi: 3.1.0
info:
  title: Parseur async Document API
  description: ''
  version: 1.0.0
servers:
- url: https://api.parseur.com
  description: Parseur API
security:
- TokenAuth: []
tags:
- name: Document
paths:
  /document/{id}:
    get:
      summary: Get a document
      deprecated: false
      description: ''
      tags:
      - Document
      parameters:
      - name: id
        in: path
        description: ''
        required: true
        example: '{{DOCUMENT_ID}}'
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
              example:
                attached_to: null
                id: 123456789
                match_master_template: false
                name: invoice_3.pdf
                ocr_ready_url: https://api.parseur.com/document/<secret>/ocr_ready/invoice_3.pdf
                original_document_url: https://api.parseur.com/document/<secret>/invoice_3.pdf
                parser: 98765
                processed: '2025-08-06T12:06:25.210919Z'
                received: '2025-08-06T11:59:04.717362Z'
                sample_set: []
                status_source: AI
                status: PARSEDOK
                template: null
                credits_used: 4
                conventional_credits_used: 0
                ai_credits_used: 4
                is_ai_ready: true
                is_ocr_ready: true
                is_processable: true
                is_splittable: true
                is_split: false
                json_download_url: https://api.parseur.com/document/<secret>/result/invoice_3.json
                csv_download_url: https://api.parseur.com/document/<secret>/result/invoice_3.csv
                xls_download_url: https://api.parseur.com/document/<secret>/result/invoice_3.xlsx
                result: '...Parsed data removed for brevity...'
                content: '...Content removed for brevity...'
                next_id: null
                prev_id: 123456788
                ocr_page_set:
                - image:
                    url: https://api.parseur.com/document/123456789/image/1.jpg
                    width: 1836
                    height: 2376
                    content_type: image/jpeg
                  position: 1
                  included_in_range: true
          headers: {}
        '403':
          $ref: '#/components/responses/Authentication Error'
          description: ''
        '404':
          $ref: '#/components/responses/Not Found'
          description: ''
      security:
      - TokenAuth: []
    delete:
      summary: Delete a document
      deprecated: false
      description: ''
      tags:
      - Document
      parameters:
      - name: id
        in: path
        description: ''
        required: true
        example: '{{DOCUMENT_ID}}'
        schema:
          type: string
      responses:
        '204':
          description: Deleted
          headers: {}
        '403':
          $ref: '#/components/responses/Authentication Error'
          description: ''
        '404':
          $ref: '#/components/responses/Not Found'
          description: ''
      security:
      - TokenAuth: []
  /document/{id}/log_set:
    get:
      summary: Get document logs
      deprecated: false
      description: ''
      tags:
      - Document
      parameters:
      - name: id
        in: path
        description: ''
        required: true
        example: '{{DOCUMENT_ID}}'
        schema:
          type: string
      - name: page
        in: query
        description: Page number for pagination (default is 1)
        required: false
        schema:
          type: integer
          minimum: 1
      - name: page_size
        in: query
        description: Number of results per page (default is 25)
        required: false
        schema:
          type: integer
          minimum: 1
      - name: search
        in: query
        description: Case-insensitive partial match search
        required: false
        schema:
          type: string
      - name: ordering
        in: query
        description: Field name to order by (use -prefix for descending)
        required: false
        schema:
          type: string
      responses:
        '200':
          description: List of document logs (paginated)
          content:
            application/json:
              schema:
                type: object
                properties:
                  count:
                    type: integer
                  current:
                    type: integer
                  total:
                    type: integer
                  results:
                    type: array
                    items:
                      properties:
                        id:
                          type: integer
                        created:
                          type: string
                        code:
                          type: string
                        document:
                          type: integer
                        document_name:
                          type: string
                        parser:
                          type: integer
                        parser_name:
                          type: string
                        template:
                          type: 'null'
                        template_name:
                          type: 'null'
                        status:
                          type: string
                        source:
                          type: string
                        payload:
                          type:
                          - string
                          - 'null'
                        message:
                          type: string
                      required:
                      - id
                      - created
                      - code
                      - document
                      - document_name
                      - parser
                      - parser_name
                      - template
                      - template_name
                      - status
                      - source
                      - payload
                      - message
                      $ref: '#/components/schemas/Log'
                required:
                - count
                - current
                - total
                - results
              example:
                count: 3
                current: 1
                total: 1
                results:
                - id: 2155
                  created: '2025-08-06T11:59:56.422755Z'
                  code: PARSEDOK
                  document: 123456789
                  document_name: invoice_3.pdf
                  parser: 54101
                  parser_name: API Test Mailbox
                  template: null
                  template_name: null
                  status: SUCCESS
                  source: DOCUMENT
                  payload: ..Log payload removed for brevity...
                  message: 'Processed with AI. (4 credits used), here is the final result:'
                - id: 2153
                  created: '2025-08-06T11:59:04.743875Z'
                  code: INCOMING
                  document: 123456789
                  document_name: invoice_3.pdf
                  parser: 54101
                  parser_name: API Test Mailbox
                  template: null
                  template_name: null
                  status: INFO
                  source: DOCUMENT
                  payload: null
                  message: Received
          headers: {}
        '403':
          $ref: '#/components/responses/Authentication Error'
          description: ''
        '404':
          $ref: '#/components/responses/Not Found'
          description: ''
      security:
      - TokenAuth: []
  /document/{id}/skip:
    post:
      summary: Skip a document
      deprecated: false
      description: ''
      tags:
      - Document
      parameters:
      - name: id
        in: path
        description: ''
        required: true
        example: '{{DOCUMENT_ID}}'
        schema:
          type: string
      responses:
        '200':
          description: ''
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
              example:
                attached_to: null
                id: 123456789
                match_master_template: false
                name: invoice_3.pdf
                ocr_ready_url: https://api.parseur.com/document/<secret>/ocr_ready/invoice_3.pdf
                original_document_url: https://api.parseur.com/document/<secret>/invoice_3.pdf
                parser: 98765
                processed: '2025-08-06T12:06:25.210919Z'
                received: '2025-08-06T11:59:04.717362Z'
                sample_set: []
                status_source: AI
                status: SKIPPED
                template: null
                credits_used: 4
                conventional_credits_used: 0
                ai_credits_used: 4
                is_ai_ready: true
                is_ocr_ready: true
                is_processable: true
                is_splittable: true
                is_split: false
                json_download_url: https://api.parseur.com/document/<secret>/result/invoice_3.json
                csv_download_url: https://api.parseur.com/document/<secret>/result/invoice_3.csv
                xls_download_url: https://api.parseur.com/document/<secret>/result/invoice_3.xlsx
                result: '...Parsed data removed for brevity...'
                content: '...Content removed for brevity...'
                next_id: null
                prev_id: 123456788
                ocr_page_set:
                - image:
                    url: https://api.parseur.com/document/123456789/image/1.jpg
                    width: 1836
                    height: 2376
                    content_type: image/jpeg
                  position: 1
                  included_in_range: true
          headers: {}
        '403':
          $ref: '#/components/responses/Authentication Error'
          description: ''
        '404':
          $ref: '#/components/responses/Not Found'
          description: ''
      security:
      - TokenAuth: []
components:
  responses:
    Not Found:
      description: ''
      content:
        application/json:
          schema:
            type: object
            properties:
              non_field_errors:
                type: string
            required:
            - non_field_errors
          examples:
            Document not found:
              summary: Document not found
              value:
                non_field_errors: Not found
    Authentication Error:
      description: ''
      content:
        application/json:
          schema:
            type: object
            properties:
              non_field_errors:
                type: string
            required:
            - non_field_errors
          examples:
            Not Authenticated:
              summary: Not Authenticated
              value:
                non_field_errors: Not authenticated
            Authentication failed:
              summary: Authentication failed
              value:
                non_field_errors: Authentication failed
  schemas:
    LogStatusEnum:
      type: string
      enum:
      - SUCCESS
      - ERROR
      - INFO
      - WARNING
      readOnly: true
    DocumentStatusSourceEnum:
      type:
      - string
      - 'null'
      readOnly: true
      enum:
      - AI
      - AUTO
      - CSV
      - METADATA
      - MANUAL
      - TEMPLATE
      - TRANSFORM
    OcrPage:
      type: object
      properties:
        image:
          type: object
          properties:
            url:
              type: string
              format: uri
              readOnly: true
            width:
              type: integer
              readOnly: true
            height:
              type: integer
              readOnly: true
            content_type:
              type: string
              const: image/jpeg
              readOnly: true
          required:
          - url
          - width
          - height
          - content_type
          readOnly: true
        position:
          type: integer
          readOnly: true
        included_in_range:
          type: boolean
          readOnly: true
      readOnly: true
    DocumentStatusEnum:
      type: string
      enum:
      - INCOMING
      - ANALYZING
      - PROGRESS
      - PARSEDOK
      - PARSEDKO
      - QUOTAEXC
      - SKIPPED
      - SPLIT
      - EXPORTKO
      - TRANSKO
      - INVALID
      readOnly: true
    TemplateSample:
      type:
      - object
      - 'null'
      properties:
        template_id:
          type: integer
          readOnly: true
        name:
          type: string
          readOnly: true
        sample_count:
          type: integer
          readOnly: true
      required:
      - template_id
      - name
      - sample_count
      readOnly: true
    LogSourceEnum:
      type: string
      enum:
      - DOCUMENT
      - OCRDOC
      - WEBHOOK
      readOnly: true
    Document:
      type: object
      properties:
        attached_to:
          type:
          - integer
          - 'null'
          readOnly: true
        id:
          type: integer
          readOnly: true
        match_master_template:
          type: boolean
          readOnly: true
        name:
          type: string
          readOnly: true
        ocr_ready_url:
          type:
          - string
          - 'null'
          format: uri
          readOnly: true
        original_document_url:
          type: string
          format: uri
          readOnly: true
        parser:
          type: integer
          readOnly: true
        processed:
          type: string
          format: date-time
          readOnly: true
        received:
          type: string
          format: date-time
          readOnly: true
        sample_set:
          type: array
          items:
            $ref: '#/components/schemas/TemplateSample'
          readOnly: true
        status_source:
          $ref: '#/components/schemas/DocumentStatusSourceEnum'
        status:
          $ref: '#/components/schemas/DocumentStatusEnum'
        template:
          type:
          - integer
          - 'null'
          readOnly: true
        credits_used:
          type: integer
          readOnly: true
        conventional_credits_used:
          type: integer
          readOnly: true
        ai_credits_used:
          type: integer
          readOnly: true
        is_ai_ready:
          type: boolean
          readOnly: true
        is_ocr_ready:
          type: boolean
          readOnly: true
        is_processable:
          type: boolean
          readOnly: true
        is_splittable:
          type: boolean
          readOnly: true
        is_split:
          type: boolean
          readOnly: true
        json_download_url:
          type: string
          format: uri
          readOnly: true
        csv_download_url:
          type: string
          format: uri
          readOnly: true
        xls_download_url:
          type: string
          format: uri
          readOnly: true
        result:
          type:
          - string
          - 'null'
          readOnly: true
        content:
          type: string
          readOnly: true
        next_id:
          type:
          - integer
          - 'null'
          readOnly: true
        prev_id:
          type:
          - integer
          - 'null'
          readOnly: true
        ocr_page_set:
          type: array
          items:
            properties:
              image:
                type: object
                properties:
                  url:
                    type: string
                  width:
                    type: integer
                  height:
                    type: integer
                  content_type:
                    type: string
                required:
                - url
                - width
                - height
                - content_type
              position:
                type: integer
              included_in_range:
                type: boolean
            $ref: '#/components/schemas/OcrPage'
          readOnly: true
      required:
      - id
      - match_master_template
      - name
      - parser
      - is_processable
      - is_splittable
      - is_split
      - json_download_url
      - csv_download_url
      - xls_download_url
      - result
      - content
      - next_id
      - prev_id
      - ocr_page_set
      - attached_to
      - ocr_ready_url
      - original_document_url
      - processed
      - received
      - status_source
      - status
      - template
      - credits_used
      - is_ai_ready
      - is_ocr_ready
      - conventional_credits_used
      - ai_credits_used
      - sample_set
    Log:
      type: object
      properties:
        id:
          type: integer
          readOnly: true
        created:
          type: string
          readOnly: true
          format: date-time
        code:
          type: string
          maxLength: 128
          readOnly: true
        document:
          type: integer
          readOnly: true
        document_name:
          type: string
          readOnly: true
        parser:
          type: integer
          readOnly: true
        parser_name:
          type: string
          readOnly: true
        template:
          type:
          - integer
          - 'null'
          readOnly: true
        template_name:
          type:
          - string
          - 'null'
          readOnly: true
        status:
          $ref: '#/components/schemas/LogStatusEnum'
        source:
          $ref: '#/components/schemas/LogSourceEnum'
        payload:
          type:
          - string
          - 'null'
          readOnly: true
        message:
          type: string
          readOnly: true
      required:
      - id
      - created
      - code
      - document
      - document_name
      - parser
      - template
      - template_name
      - status
      - source
      - payload
      - message
      - parser_name
  securitySchemes:
    TokenAuth:
      type: apiKey
      in: header
      name: Authorization
      description: 'Use header: Authorization: Token YOUR_API_KEY. API keys are here: https://app.parseur.com/account/api-keys'