N8n is a strong automation platform for developers and technical teams, but it has a real gap when it comes to document parsing. Its built-in Read PDF node extracts plain text from clean PDFs. It has no OCR, no table extraction, and no way to handle scanned documents. For anything more complex, n8n users end up writing custom JavaScript, piping pdftotext through an Execute Command node, or calling external APIs just to get structured data out of a PDF.
Parseur removes all of that. It uses AI to extract structured fields from emails, PDFs, and scanned documents, then sends clean JSON directly into your n8n workflow. You configure what to extract in Parseur, and n8n handles the rest.
Key Takeaways
N8n's native PDF node is text-only with no OCR. Parseur adds AI extraction, scanned document support, and structured table parsing that n8n can't do on its own.
Parseur sends structured JSON to n8n on document events: Document Processed, Flattened Tables, Table Item Processed, and Export Failed.
The Parseur connector is available for n8n Cloud. Self-hosted n8n users can connect via generic webhook, which is production-ready today.
No coding is required to set up the extraction in Parseur. N8n handles the routing and any additional logic you need.
Both Parseur and n8n have free plans you can use to test the full workflow.
What n8n can't do natively with documents
Parseur and n8n integration
N8n's approach to PDF processing requires workarounds that add maintenance overhead:
The Read PDF node extracts raw text but loses all table structure
Scanned PDFs and image-based documents need an external OCR service
Extracting specific fields like invoice numbers or totals requires custom JavaScript or regex
Line items in a table come out as a text block that needs further parsing before it's usable
Parseur handles all of that before the data reaches n8n. Fields like invoice date, vendor name, line items, and totals arrive in your n8n workflow as clean, named JSON properties. No command-line tools, no custom functions, no regex maintenance.
What you can build with Parseur and n8n
Once Parseur and n8n are connected, the extraction layer is handled automatically. Your n8n workflows receive clean, structured data and can focus on routing and logic:
Invoice to ERP or Google Sheets: Automatically extract vendor name, invoice date, subtotal, tax, total, and line items from supplier invoices. Push each invoice as a new record in your ERP or add rows to Google Sheets for reporting. See the invoice processing guide.
Order emails to a database: Capture order IDs, customer details, and product information from incoming order emails, then insert the data into Postgres or MySQL. Your records stay current without manual entry. See the e-commerce parsing guide.
Shipping notices to Slack: Get instant Slack alerts when a shipping notification arrives or when a document export fails. Keep your team informed in real time.
Attachments to Drive with metadata to CRM: Store PDFs in Google Drive while sending extracted details like invoice number, customer name, and payment amount straight into your CRM. See the lead email guide.
Real estate listings to database: Parsed property listing emails can route directly into a tracking sheet or CRM. See the real estate use case.
How the integration works
The setup has three steps:
A new email or document arrives in your Parseur mailbox
Parseur extracts the structured fields you defined and sends clean JSON to n8n via the connector or webhook
N8n runs your workflow, routing the data to whichever apps or databases you've connected
You configure the extraction in Parseur once. N8n handles the routing from there.
Parseur sends structured JSON to n8n, which routes it to your apps
Step-by-step: Connect Parseur to n8n
Step 1: Forward your documents to Parseur
Each Parseur mailbox has a dedicated email address. Forward a sample email or PDF to it. The document appears in your mailbox within seconds, including any attachments.
Set up an auto-forwarding rule in Gmail or Outlook to handle new incoming documents automatically.
Step 2: Define the fields you want to extract
For supported formats, Parseur extracts data automatically using its pre-built templates.
For custom documents, create a template by highlighting the fields you want to capture and naming each one. Parseur applies that logic to every future document of the same type. Table rows like line items are extracted as separate structured objects without any extra configuration.
Step 3: Add the Parseur node in n8n
Log in to n8n, start a new workflow, and search for the Parseur node. Connect it to your Parseur account using your API key, then choose your trigger event:
Document Processed: standard event with full JSON payload
Flattened Tables: useful when your documents contain multi-row tables
Table Item Processed: fires separately for each row in a table field
Export Failed: good for error notifications and Slack alerts
Step 4: Process a document and map your fields
Go to your Parseur mailbox and re-process a document. The parsed results appear in your n8n execution log. From there, add any action nodes you need (Google Sheets, Slack, Postgres, a CRM) and map the Parseur fields using {{ $json.field_name }}.
For the full setup walkthrough with screenshots, follow the official guide: Connecting Parseur to n8n.
Parseur connector vs generic webhook
Two options are available for connecting Parseur to n8n, and the right one depends on your setup:
Option
Best for
Advantages
Things to note
Parseur Connector (Recommended)
n8n Cloud users
Quick to set up, event-aware, purpose-built for Parseur
Still rolling out in beta. May not be available in every instance yet
Generic Webhook
Self-hosted n8n or users who want flexibility
Works everywhere, simple setup, full control over headers and routing
All three work with Parseur. N8n is the best fit for developer and technical teams who want to self-host, need custom JavaScript logic in their workflows, or are connecting to databases and APIs that require more flexibility. Make is better for complex multi-step visual workflows without self-hosting. Zapier is the fastest path for simple two-app connections with no technical overhead. For a detailed breakdown, see the Zapier vs Make vs n8n comparison.
Free tools for related document types
If you need to convert standalone documents without setting up a full workflow, these free tools work in the browser with no account required:
If the same document type arrives regularly by email, the full Parseur and n8n integration processes each one automatically as it arrives.
What is Parseur?
Parseur is a powerful document processing software to extract text from emails, PDFs and documents and automate your workflow.
All Parseur features.
What is n8n?
N8N is a workflow automation platform that connects different apps and services without heavy coding. It gives users a visual editor to design workflows, making it easier to move data, trigger actions, and streamline processes across tools.
Common questions about connecting Parseur to n8n for automated email and document parsing workflows.
N8n has a basic Read PDF node that extracts plain text from native (non-scanned) PDFs. It has no OCR, no table extraction, and no way to handle scanned documents. For anything beyond simple text extraction, you need an external tool. Parseur fills that gap: it handles native PDFs, scanned documents, images, and structured tables, then sends the clean JSON to n8n automatically.
Yes. Self-hosted n8n users can connect Parseur using a generic webhook node. Make sure your n8n instance is publicly accessible so Parseur can reach the webhook endpoint. The Parseur connector works for n8n Cloud setups.
Set up Parseur as the trigger in n8n using the Parseur connector or a webhook. Then add a Google Sheets node as the next step in your workflow. Map the Parseur JSON fields to the spreadsheet columns using n8n's field mapping interface. Every new document processed by Parseur will add a row to your sheet automatically.
No. Parseur is a no-code extraction tool where you point at the data you want and name each field. The Parseur connector in n8n connects with your API key and no custom code. If you want to add logic or transformations to your n8n workflow, JavaScript is available but not required for the basic setup.
Yes. Parseur sends data to your n8n endpoint over HTTPS. With the webhook method, you can add headers or shared secrets for additional validation. Self-hosted users can keep sensitive workflows entirely within their own infrastructure.
Yes, an official Parseur connector is available in n8n. A community-built node is also available. If you don't see the connector in your instance, you can use the webhook method instead, which works with both n8n Cloud and self-hosted setups and is production-ready today.
Parseur supports four trigger events for n8n. "Document Processed" fires with a standard JSON payload when a document is extracted. "Flattened Tables" is useful when your documents contain table data. "Table Item Processed" triggers separately for each row in a table field. "Export Failed" is good for error monitoring and Slack alerts.
Yes. Parseur extracts line items as structured table data and sends each row as a separate JSON object to n8n. You can then use n8n's Postgres, MySQL, or other database nodes to insert each line item as a separate record. This works for invoices, purchase orders, and any other document with repeating table rows.
The Parseur connector is event-aware and purpose-built for Parseur. It exposes the different trigger events directly in the n8n interface, making setup faster. The generic webhook method works everywhere, including self-hosted instances where the connector may not be available, and gives you full control over headers and routing.
N8n is the best fit if your team wants to self-host the automation platform, needs custom JavaScript logic in the workflow, or is working with databases and APIs that require more flexibility than Zapier or Make provide. Zapier is faster to set up for simple two-app flows. Make is better for complex multi-step visual workflows without self-hosting.
