Power Document Extractor icon

Power Document Extractor

Extract structured blocks from any document format locally

Actions18

Extract DOC

AI-generated

Summary

Extract DOC operation for Power Document Extractor node

Inputs

  • binaryPropertyName — Name of the binary property containing the file base64-encoded data. Defaults to 'data'.
  • structuredLevel — Level of detail in extracted blocks. Options: raw, basic, full. Defaults to 'full'.
  • libreOfficeUrl — Optional URL of a LibreOffice/unoserver instance. If empty, text extraction fallback is used.

Output shape

array

The node returns a single-item array. The item's json contains blocks (extracted content) and metadata (file details + parser metadata). pairedItem preserves the input item index.

Examples

Example 1: Process a base64-encoded DOCX file from the 'data' binary property using default settings.

binaryPropertyName='data', structuredLevel='full', libreOfficeUrl='' (fallback enabled).

Discussion