Extraction

  • common
    Type: object
    required
    • mimeType
      Type: string | null
      required
    • size
      Type: integer | null
      required

      Integer numbers.

    • caption
      Type: string
    • chunkCount
      Type: integer

      Integer numbers.

    • infected
      Type: boolean
    • keywords
      Type: array string[]
    • thumbnail
      Type: string
  • document
    Type: object
    • author
      Type: string
    • creationDate
      Type: stringFormat: date-time

      the date-time notation as defined by RFC 3339, section 5.6, for example, 2017-07-21T17:32:28Z

    • creator
      Type: string
    • modificationDate
      Type: stringFormat: date-time

      the date-time notation as defined by RFC 3339, section 5.6, for example, 2017-07-21T17:32:28Z

    • pages
      Type: integer

      Integer numbers.

    • pdfRender
      Type: object
    • producer
      Type: string
    • security
      Type: boolean
    • subject
      Type: string
    • title
      Type: string
    • version
      Type: string
  • media
    Type: object
    • bitRate
      Type: number | null
    • channels
      Type: string | null
    • codec
      Type: string | null
    • color
      Type: object
    • device
      Type: object
    • dominantColors
      Type: array object[]
    • duration
      Type: number | null
    • frameRate
      Type: number | null
    • height
      Type: number | null
    • location
      Type: object
    • ocr
      Type: string
    • sampleRate
      Type: number | null
    • screenshot
      Type: object
    • transcript
      Type: object
    • width
      Type: number | null
  • web
    Type: object
    • description
      Type: string
    • favicon
      Type: object
    • html
      Type: object
    • image
      Type: object
    • reader
      Type: object
    • siteName
      Type: string
    • title
      Type: string
    • url
      Type: string