Import and Export License Extractor

Extract the exporter, consignee, EORI numbers, license validity, commodity codes, and declared value from an import or export license PDF into structured data.

The full guide: Dual-use export license CN code and validity window

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Import and Export License Extractor.

Which parties and identifiers does the extractor read?

The exporter and consignee names and addresses, and the EORI or tax identification numbers of the exporter, importer, declarant, and representative, plus the issuing authority and the declaration type (IM, EX, CO, or EU).

Does it read the license validity and status?

Yes. The document date, the expiration date after which the license is no longer valid for clearance, and the license status are each read, along with the additional declaration type.

Are the goods returned as a table?

The goods items table returns one row per item with its commodity code (Combined Nomenclature or HS), product description, country of origin and preferential origin, CUS code, preference, valuation method, item price, declared value, currency, net mass, package type and count, and statistical value.

Which trade and movement details come out?

The incoterms, the countries of origin, preferential origin, destination, and dispatch or export, the location of goods, the transport charges method of payment, and references to previous and supporting documents, following the EU Customs Data Model (EUCDM) catalogue.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The license is processed via the Talonic API for extraction, is not retained for training, and is not shared.

Doing this to one file, or to ten thousand?

The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.

See PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.