Dangerous Goods Declaration Extractor

Extract the UN numbers, proper shipping names, hazard classes, packing groups, quantities, and transport details from a dangerous goods declaration PDF.

The full guide: UN number, hazard class and packing group for hazmat

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 Dangerous Goods Declaration Extractor.

What does the dangerous goods declaration extractor read?

The declaration number and date, the shipper, consignee, notify party, and carrier with their addresses, the transport mode (air, sea, road, rail, or multimodal), the vessel name and voyage number, the ports of loading and discharge, the place of delivery, the declarant name, and the signature date.

Are the hazardous items returned as a table?

Yes. The dangerous goods items table returns one row per substance with its UN number, proper shipping name, hazard class, packing group, quantity, quantity unit, packaging type, technical name, subsidiary hazard class, and marine-pollutant flag, so a multi-substance consignment comes back as rows.

How are the UN number, hazard class, and packing group captured?

The four-digit UN classification number, the official proper shipping name, the hazard class (Class 1–9), and the packing group (I great danger, II medium, III minor) come back both as header fields and per line item, following the IMDG Code and IATA Dangerous Goods Regulations conventions.

Does it capture container, emergency, and handling details?

The container number, container type, and seal number, the emergency contact for hazmat incidents, and the special handling instructions come back as fields, and a transport details table returns the transport mode, vessel name, voyage number, container number and type, seal number, and the ports of loading and discharge.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The declaration 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.