SEC 8-K Report Extractor

Extract the issuer, CIK, event date, Item codes, and the event narratives, exhibits, and signatories from an SEC 8-K current report PDF.

The full guide: Item codes and event dates on an SEC Form 8-K

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 SEC 8-K Report Extractor.

What does the 8-K extractor read?

The SEC accession number (document number) and filing date, the issuer name, CIK (Central Index Key), and ticker symbol, the event date the material event occurred, and the array of Item codes reported (such as 1.01, 2.01, 5.01, 5.02, 8.01, and 9.01).

How does an 8-K differ from a 10-K or 10-Q?

An 8-K is a current report that discloses a single material event — an acquisition, a bankruptcy, a change in control, or an executive departure — usually within four business days, rather than a period full financial statements. The extractor captures the event Items; for the periodic financials use the 10-K or 10-Q extractor.

Which event narratives come out as fields?

The business combination (Item 1.01), the bankruptcy (Item 2.01) and debtor bankruptcy (Item 3.01), the change in control (Item 5.01), the costs associated with exit or disposal activities (Item 5.02, as a number), and the other events (Item 8.01) each come back as their own field.

Are the exhibits and signatories returned as tables?

Yes. The financial statements table returns each statement type, period end date, line item, amount, and currency; the exhibits table returns the exhibit number, description, document type, and filed-herewith flag; and separate signatories and transaction parties tables come back too.

What are the file limits and privacy terms?

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