Parse Document using n8n action

PDF4me Parse Document extracts structured data from PDF documents using AI-powered parsing templates through n8n automation workflows. Process PDFs via n8n triggers, binary data, base64 strings, or public URLs with predefined Parse IDs to automatically capture specific data fields, validate extracted information, and output structured data in JSON, XML, or CSV formats. This solution is ideal for invoice data extraction, form processing, document digitization, automated data capture, field-specific extraction, and template-based parsing workflows that require accurate field recognition with customizable extraction rules and seamless integration.

Setup

Add the PDF4me "Parse Document" node to your n8n workflow and configure the required parameters. For initial setup instructions, see our n8n Integration Guide.

Prerequisites:

• PDF4me API credentials
• n8n workflow access
• Parse ID configuration (see below)

Get Your API Key

Configuration:

1. Add PDF4me node to workflow
2. Select "Parse Document" action
3. Configure input parameters (see below)

Parameters

Complete list of parameters for the Parse Document action. Configure these parameters to control document parsing.

Important: Parameters marked with an asterisk (***) are required and must be provided for the action to function correctly.

Parameter	Type	Description	Example
Input Data Type***	String	PDF Input Format Selection • Choose the format of your PDF document input • PDF4me supports multiple input types • Options: Binary Data, Base64 String, or URL	Binary Data
Input Binary Field	Binary	Binary PDF File Input (Required if Binary Data) • Reference PDF file from previous n8n node or file upload • PDF4me processes binary PDF files with automatic format detection • Required when Input Data Type is "Binary Data"	{{ $binary.data }}
Base64 PDF Content	String	Base64 Encoded PDF Input (Required if Base64 String) • Provide PDF content as base64 encoded string • PDF4me automatically decodes and processes the PDF content • Required when Input Data Type is "Base64 String"	JVBERi0xLjQ...
PDF URL	String	Public PDF URL Input (Required if URL) • Provide a public/open permission URL to the PDF file • PDF4me downloads and processes the file from URL • Required when Input Data Type is "URL"	https://abc.com/document.pdf
Document Name***	String	Input Filename • Specify the name of the input PDF file • Used for format detection and processing optimization • Must include .pdf extension	document.pdf
Parse ID***	String	Parsing Template Identifier • Unique identifier for the parsing configuration template • References predefined parsing template that defines data fields to extract • Must be a valid Parse ID from your PDF4me account	8761-4321-4321-4321-cba
Output Format***	String	Output Data Format • Choose the format for the extracted data output • Options: JSON (structured), XML (hierarchical), CSV (tabular) • JSON is recommended for most automation workflows	JSON
Output Binary Field Name***	String	Binary Data Mapping • Define the variable name for accessing generated parsed data • Used in subsequent workflow actions • Essential for workflow data flow	data

Advanced Options

The following parameters are available in the Advanced Options section and are optional:

Parameter	Type	Description	Example
Custom Profiles	String	Custom Configuration Profiles • Set additional options using custom profiles • JSON-like format containing predefined parameters • Enables advanced parsing processing settings • Optional for specialized requirements	{ "outputDataFormat": "json", "includeMetadata": true }

Parse ID Configuration

Understanding Parse IDs

Parse IDs are unique identifiers that reference predefined parsing templates in your PDF4me account. Each Parse ID contains specific configuration for:

• Field Recognition: Which data fields to extract from documents
• Data Validation: Rules for validating extracted data
• Output Formatting: How to structure the extracted data
• Error Handling: How to handle parsing errors and exceptions

Getting Parse IDs

1. Access PDF4me Dashboard: Log into your PDF4me account
2. Navigate to Parse Templates: Go to the parsing configuration section
3. Create or Select Template: Choose an existing template or create a new one
4. Copy Parse ID: Copy the unique identifier for use in your n8n workflow

Common Parse Templates

Template Type	Use Case	Common Fields
Invoice Parsing	Extract invoice data	Invoice number, date, amount, vendor, line items
Contract Parsing	Extract contract terms	Parties, dates, terms, clauses, signatures
Form Parsing	Extract form data	Personal information, selections, responses
Receipt Parsing	Extract receipt data	Date, merchant, items, total, payment method

Output

Output Parameters

Parameter	Type	Description	Example
fileName	String	PDF4me generated filename - The complete filename of the successfully processed document with proper extension and timestamp. PDF4me ensures unique naming and validates file format compliance for seamless integration with downstream processes	parsed_document_1756999697398.json
mimeType	String	PDF4me MIME type identifier - The standardized MIME type for the extracted data file, typically application/json for JSON format, application/xml for XML format, or text/csv for CSV format. This ensures proper file handling and recognition across all systems and applications	application/json
fileSize	Number	PDF4me file size in bytes - The exact size of the extracted data file in bytes, provided for storage planning, bandwidth optimization, and file transfer monitoring. Essential for enterprise document management and workflow automation	3421
success	Boolean	PDF4me parsing status indicator - Boolean flag indicating the success or failure of the document parsing process. Returns true for successful parsing and false for any errors, enabling robust error handling in automated workflows	true
message	String	PDF4me parsing status message - Descriptive message indicating the result of the document parsing process. Provides clear status messages for successful parsing and detailed error information for troubleshooting purposes	Document parsed successfully
docName	String	PDF4me original document name reference - The original filename of the input PDF file that was processed. This reference is maintained for audit trails, debugging purposes, and tracking the source of extracted data in enterprise workflows	document.pdf

N8N Action Response

The PDF4me Parse Document API returns a response that can be viewed in multiple formats. Choose the view that best fits your needs:

JSON

JSON Response Format

The raw JSON response from the API:

{
  "fileName": "parsed_document_1756999697398.json",
  "mimeType": "application/json",
  "fileSize": 3421,
  "success": true,
  "message": "Document parsed successfully",
  "docName": "document.pdf"
}

Table

Table View

Response data in a structured table format:

Parameter	Value
fileName	parsed_document_1756999697398.json
mimeType	application/json
fileSize	3421
success	true
docName	document.pdf
message	Document parsed successfully

Schema

Schema View

The data structure and types of the response:

fileName: AB parsed_document_1756999697398.json
mimeType: AB application/json
fileSize: # 3421
success: ✓ true
docName: AB document.pdf
message: AB Document parsed successfully

Type Indicators:

• AB = String
• # = Number
• ✓ = Boolean

Binary

Binary Data View

The actual parsed data content and metadata:

data
─────────────────────────────────────────
File Name: parsed_document_1756999697398.json
File Extension: json
Mime Type: application/json
File Size: 3.3 KB

Use Cases

Invoice Processing and Accounts Payable

• Automatically extract invoice data for accounting systems
• Process vendor invoices and payment information
• Integrate with ERP systems for automated data entry

Contract Management and Legal Processing

• Extract key terms and clauses from legal documents
• Process contract renewals and compliance monitoring
• Automate legal document review and analysis

Form Processing and Data Entry

• Extract data from application forms and surveys
• Process customer onboarding documents
• Automate data entry for business processes

Get Help

n8n Integration Guiden8n SampleGetting Started