docuparse

Full-featured document parsing node for n8n — PDF, DOCX, XLSX, PPTX, images, OCR, markdown output. No native dependencies.

Package Information

Released: 3 mo ago
Downloads: 46 weekly / 1,419 monthly
Latest Version: 0.2.5
Author: raevon

Available Nodes

DocuParse icon
DocuParse
Full-featured document parsing — PDF, DOCX, XLSX, PPTX, images, OCR, markdown output. No native dependencies.

Documentation

n8n-nodes-liteparse-local

Full-featured document parsing node for n8n. No native dependencies — works in any Docker container.

Features

Operations

Operation Description
Parse Document Extract text, tables, and structure from documents
OCR Image Extract text from images using Tesseract OCR
Extract Tables Extract tables as structured JSON
Convert to Markdown Convert document to clean markdown
Merge PDFs Combine multiple PDF files into one
Split PDF Split PDF into separate pages
Extract Entities Extract emails, phones, URLs, dates from text

Supported Formats

Format Extensions Parse Tables Markdown
PDF .pdf ✅ ✅ ✅
Word .docx, .doc ✅ ❌ ✅
Excel .xlsx, .xls ✅ ✅ ❌
PowerPoint .pptx, .ppt ✅ ❌ ❌
HTML .html, .htm ✅ ❌ ✅
CSV .csv ✅ ❌ ❌
Images .png, .jpg, .tiff, .bmp, .webp ✅ OCR ❌ ❌
Text .txt, .md, .json, .xml ✅ ❌ ❌

OCR Languages

English, Arabic, Chinese (Simplified/Traditional), French, German, Hindi, Japanese, Korean, Portuguese, Russian, Spanish, Urdu

Entity Extraction

  • Email addresses
  • Phone numbers
  • URLs
  • Dates
  • IP addresses
  • Currency amounts

Installation

In n8n, go to Settings → Community Nodes and install:

n8n-nodes-liteparse-local

Usage Examples

Parse PDF to Markdown

  1. Read Binary File → point to PDF
  2. DocuParse → Operation: Parse Document, Output Format: Markdown
  3. Output: json.text contains the markdown

OCR a Scanned Document

  1. Read Binary File → point to image/PDF
  2. DocuParse → Operation: OCR Image, Language: English
  3. Output: json.text contains extracted text

Extract Tables from Excel

  1. Read Binary File → point to XLSX
  2. DocuParse → Operation: Extract Tables
  3. Output: json.tables contains array of tables

Merge Multiple PDFs

  1. Read Binary File → first PDF (field: data)
  2. Read Binary File → second PDF (field: data1)
  3. DocuParse → Operation: Merge PDFs, Additional Fields: data1
  4. Output: merged PDF in binary.merged_pdf

Dependencies (All Pure JavaScript)

  • pdfjs-dist — Mozilla's PDF.js for PDF parsing
  • tesseract.js — OCR via WebAssembly
  • mammoth — DOCX parsing
  • xlsx — Excel parsing
  • cheerio — HTML parsing
  • csv-parse — CSV parsing
  • pdf-lib — PDF manipulation (merge/split)

License

MIT

Discussion