args:
- default: true
  description: War Room entryID of the file to read.
  name: entryID
  required: true
- description: Password for the file, if encrypted.
  name: userPassword
- defaultValue: "20"
  description: Maximum number of images to extract from the PDF file.
  name: maxImages
- auto: PREDEFINED
  defaultValue: 'true'
  description: To unescape URLs that have been escaped as part of the URLs extraction. Invalid characters will be ignored.
  name: unescape_url
  predefined:
  - 'true'
  - 'false'
comment: |-
  Load a PDF file's content and metadata into context. Supports extraction of hashes, urls, and emails when available.
commonfields:
  id: ReadPDFFileV2
  version: -1
enabled: true
name: ReadPDFFileV2
outputs:
- contextPath: Hashes.type
  description: The hash type extracted from the PDF file.
  type: String
- contextPath: Hashes.value
  description: The hash value extracted from the PDF file.
  type: String
- contextPath: URL.Data
  description: A list of URLs that were extracted from the PDF file.
  type: String
- contextPath: File.Text
  description: The text that was extracted from the PDF file.
  type: String
- contextPath: File.Producer
  description: The producer of the PDF file.
  type: String
- contextPath: File.Title
  description: The title of the PDF file.
  type: String
- contextPath: File.Author
  description: The author of the PDF file.
  type: String
- contextPath: File.ModDate
  description: The ModDate of the PDF file.
  type: Date
- contextPath: File.CreationDate
  description: The CreationDate of the PDF file.
  type: Date
- contextPath: File.Pages
  description: Number of pages in the PDF file.
  type: String
- contextPath: File.Size
  description: The file size in bytes.
  type: Number
- contextPath: File.Form
  description: PDF form type.
  type: String
- contextPath: File.Encrypted
  description: Is the file is encrypted.
  type: String
- contextPath: File.FileSize
  description: The file size in bytes.
  type: String
- contextPath: File.SHA1
  description: SHA1 hash of the file.
  type: String
- contextPath: File.PageRot
  description: Page rotation of the PDF file.
  type: String
- contextPath: File.Optimized
  description: Has the page has been optimzed.
  type: String
- contextPath: File.SHA256
  description: SHA256 hash of the file.
  type: String
- contextPath: File.PDFVersion
  description: The PDF version.
  type: String
- contextPath: File.Name
  description: The name of the PDF file.
  type: String
- contextPath: File.Creator
  description: The creator of the PDF file.
  type: String
- contextPath: File.Tagged
  description: Does the file have tagged meta-information.
  type: String
- contextPath: File.SSDeep
  description: SSDeep hash of the file.
  type: String
- contextPath: File.EntryID
  description: The Entry ID of the file.
  type: String
- contextPath: File.JavaScript
  description: Is the file in JavaScript.
  type: String
- contextPath: File.Info
  description: Additional information about the file.
  type: String
- contextPath: File.PageSize
  description: The PDF file page size.
  type: String
- contextPath: File.Type
  description: The file type.
  type: String
- contextPath: File.Suspects
  description: Indicating the presence of tag suspects.
  type: String
- contextPath: File.MD5
  description: MD5 hash of the file.
  type: String
- contextPath: File.UserProperties
  description: Indicating the presence of structure elements that contain user properties attributes.
  type: String
- contextPath: File.Extension
  description: The file's extension.
  type: String
- contextPath: Account.Email
  description: The email address of the account.
  type: String
script: "-"
subtype: python3
tags:
- Utility
- ingestion
timeout: "0"
type: python
dockerimage: demisto/readpdf:1.0.0.11193239
runas: DBotRole
tests:
- Extract Indicators From File - Generic v2 - Test
- ReadPDFFileV2-Test
fromversion: 5.0.0