Drop a Parse node into any workflow and every invoice, receipt or statement comes back with the same fields, in the same shape. No parsing code, no regular expressions, no per-supplier templates.
The node is published as a community package, so n8n installs it for you.
In n8n, go to Settings, then Community Nodes, then select Install.
Paste n8n-nodes-parse-conversiontools and confirm the install.
Create an API key in your Parse dashboard under API Keys, then paste it into a new Parse credential. Testing the connection is free and never uses a page.
n8n-nodes-parse-conversiontoolsSelf-hosted n8n only. Community nodes are not available on n8n Cloud starter plans.
Parse is the step in the middle. The trigger is whatever already brings documents to you.
Watch a folder, extract every invoice against one schema, append a row. The columns never move, because the schema decides them rather than the document.
Google Drive → Parse → Google Sheets
Pull attachments as they arrive, extract the fields your system expects, post them on. Filter on a value first if you only want some of them.
Gmail → Parse → Filter → HTTP Request
Statements arrive as PDFs and need to become rows. One schema covers every statement from the same bank.
Dropbox → Parse → Postgres
Five operations, all against your own account.
The node loads your saved schemas into a dropdown, so you choose one instead of pasting an ID. A schema is what guarantees the same fields for every document of a type, which is what makes the rest of the workflow safe to build.
Extraction happens in the background and the node waits for the result on your behalf. Turn waiting off to get the ID immediately and collect the result later, or point a webhook at your own endpoint.
An identical document extracted against the same fields is served from cache. It does not count against your page allowance, so a workflow that retries is not a workflow that overspends.
Community nodes require a self-hosted n8n instance, or a Cloud plan that permits them. On any self-hosted instance the install takes a minute.
PDF, PNG, JPG and HEIC, including scans and photographs taken on a phone. If a person can read the document, it is worth trying.
No. You can describe the fields inline for a one-off extraction. Saving a schema is what makes the output consistent across documents, so it is worth doing as soon as you are extracting the same type twice.
The free tier includes 100 pages per month, which is enough to build and test a workflow. Paid plans start at 500 pages per month.
Yes. The node is marked as usable as a tool, so an AI Agent node can call it directly and decide for itself when a document needs extracting.
A free account includes 100 pages a month. No card, and the connection test costs nothing.
The same schema-driven API works across every document type. Define a schema once, extract from thousands of files.
Extract structured JSON from any document with custom schemas.
Parse any PDF into structured JSON, scanned or digital.
Vendor, line items, totals, tax, and dates from invoices.
Store, items, totals, and payment method from receipts.
PO number, vendor, buyer, and SKU-level line items.
Transactions, running balances, and dates for reconciliation.
Box-level data from W-2, 1099, and other tax forms.
Parties, dates, governing law, and key clauses.
Carrier, parties, ports, containers, and cargo.
Credit amounts matched back to the original invoice.
Payments split across invoices for cash application.
Meter readings, charges, and totals from any provider.
Line items and periods from balance sheets and reports.
Vendor quotes in one shape so you can compare them.
Earnings, deductions, taxes, and year-to-date totals.
Experience, education, and skills from any CV layout.
Fields and MRZ from passports and ID cards.
Rent, term, deposits, and renewal deadlines.
Claim and policy numbers, dates, and claimed amounts.
Packages and SKU-level lines for receiving.
Ordered versus delivered quantities and sign-off.