n8n Workflow: Parse and Extract Invoice Data with Nanonets OCR and Export to Excel

This n8n workflow demonstrates how to process invoice data using a simulated OCR service (Nanonets is implied by the directory name, but the JSON uses generic HTTP requests) and then export the extracted information into an Excel file. It provides a basic framework for automating the extraction of structured data from documents.

What it does

This workflow performs the following steps:

1. Receives a Webhook Trigger: The workflow starts when it receives an incoming HTTP request via a webhook. This webhook is expected to contain the data needed to initiate the OCR process.
2. Simulates OCR Request: An "HTTP Request" node is used to simulate sending data to an OCR service (e.g., Nanonets API). This node would typically send the invoice document (or a reference to it) and receive the parsed data in return.
3. Waits for Processing: A "Wait" node introduces a delay, simulating the time it takes for the OCR service to process the document and return results. This is useful for asynchronous OCR APIs.
4. Processes OCR Response (Code): A "Code" node is used to parse and transform the data received from the simulated OCR service. This is where you would extract specific fields like invoice number, date, line items, total amount, etc., from the OCR output.
5. Converts to Excel File: The processed data from the "Code" node is then converted into an Excel (.xlsx) file using the "Convert to File" node.
6. Responds to Webhook: Finally, the workflow sends a response back to the initial webhook caller, potentially including a link to the generated Excel file or a confirmation message.

Prerequisites/Requirements

• n8n Instance: A running instance of n8n.
• Webhook Integration: An external system or application that can send HTTP requests to the n8n webhook.
• OCR Service (Conceptual): While the workflow uses a generic "HTTP Request" node, in a real-world scenario, you would need an account and API key for an OCR service like Nanonets, Google Document AI, Amazon Textract, etc. The HTTP Request node would be configured to interact with that specific service.
• Basic JavaScript Knowledge: For customizing the data extraction logic within the "Code" node.

Setup/Usage

1. Import the Workflow:
   • Copy the provided JSON code.
   • In your n8n instance, click on "Workflows" in the left sidebar.
   • Click "New" and then "Import from JSON".
   • Paste the JSON code and click "Import".
2. Configure the Webhook:
   • Click on the "Webhook" node.
   • Note down the "Webhook URL" displayed in the node settings. This is the URL you will send your trigger requests to.
   • You can set the "HTTP Method" and "Response Mode" as needed for your integration.
3. Configure the HTTP Request Node:
   • Click on the "HTTP Request" node.
   • Method: Set this to the appropriate HTTP method for your OCR API (e.g., POST).
   • URL: Replace the placeholder with the actual API endpoint of your OCR service (e.g., Nanonets API endpoint).
   • Headers/Body: Configure the headers (e.g., Authorization with your API key) and the request body to send the invoice document or its URL to the OCR service.
4. Customize the Code Node:
   • Click on the "Code" node.
   • Modify the JavaScript code to parse the specific JSON structure returned by your chosen OCR service.
   • Extract the relevant invoice fields and structure them into an array of objects, which will be used to generate the Excel file.
5. Activate the Workflow:
   • Once configured, click the "Activate" toggle in the top right corner of the n8n editor to enable the workflow.
6. Trigger the Workflow:
   • Send an HTTP request to the Webhook URL you obtained in step 2. The body of this request should contain any initial data required by your workflow (e.g., a document URL or base64 encoded file).
   • The workflow will then execute, process the invoice, and generate an Excel file. The "Respond to Webhook" node will send a response back to your calling system.