Extract a shipping manifest PDF to JSON
Everything below is the response the live API returned for a shipping manifest, generated when this page was built. Not a description of what it would return — the output itself, including what it scored low on.
Who this is for
Freight forwarders and customs brokers keying manifests that arrive as PDF from a carrier portal.
The job, in the words people search for: “read a container manifest into a freight system”.
What makes this shape awkward
Wide table with eight columns and a page break in the middle, header repeated on the second page. The repeated header is proof the first row is a header — and it is also a row of data waiting to be filed if the stitching does not drop it.
The measured result
| Pages read | 1 |
| Time | 10 ms (10 ms/page) |
| Labelled fields found unprompted | 6 |
| Tables | 1 (30 rows) |
| Input | shipping-manifest.pdf (33 KB — synthetic, generated from a spec in the repo; real documents of this type cannot be published) |
Fields, with a schema
Ask for the fields you want by the label printed on the page. Each answer carries the text exactly as printed (raw), the value coerced to the type you asked for, a confidence, and a bounding box you can draw on the page to check it.
curl -X POST https://api.pdfcraft.dev/v1/extract \
-H "Authorization: Bearer $PDFCRAFT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"file": "<base64 of your shipping manifest>",
"schema": {
"manifest_number": "string",
"container": "string",
"eta": "date"
}
}'What came back
| Field | raw | value | confidence |
|---|---|---|---|
manifest_number | MAN-2026-90114 | "MAN-2026-90114" | 60% |
container | MSKU 441 7223 | "MSKU 441 7223" | 60% |
eta | 2026-04-02 | "2026-04-02" | 70% |
Every label it found without being asked
Send no schema and you get all of these, keyed by the label as printed. Useful for discovering what a new supplier’s layout actually contains before you write a schema against it.
Manifest Number, Vessel, Container, Port of Loading, Port of Discharge, ETA
Tables
Line · Marks · Packages · Description · HS code · Gross kg · Net kg · CBM · 30 rows × 8 columns · page 1
Table confidence 100%. Header confidence 100% — the first row was promoted out of the data.
| Line | Marks | Packages | Description | HS code | Gross kg | Net kg | CBM |
|---|---|---|---|---|---|---|---|
| 1 | MK-100 | 12 | Machine parts | 8400.10 | 430 | 396 | 2.35 |
| 2 | MK-101 | 39 | Textiles | 8401.11 | 407 | 374 | 1.79 |
| 3 | MK-102 | 15 | Ceramics | 8402.12 | 498 | 458 | 1.80 |
First 3 of 30 rows.
With options.rows_as_objects, the same row keyed by its header:
{
"Line": "1",
"Marks": "MK-100",
"Packages": "12",
"Description": "Machine parts",
"HS code": "8400.10",
"Gross kg": "430",
"Net kg": "396",
"CBM": "2.35"
}What this does not do
- No OCR. This reads the PDF’s text layer. A scanned or photographed shipping manifest has no text layer and returns
422 extraction_failedwith the page numbers that were blank — deliberately, and quickly, so you can route it somewhere that does OCR rather than waiting on a guess. - No model. Run the same file twice and you get the same bytes back. That is the trade: it cannot infer a field that is not printed, and it cannot hallucinate one either.
- Ambiguity is reported, not resolved. A date like 03/04/2026 stays a string, and a bare
$returns a null currency, because guessing wrong on either is not something you can recover from downstream.
Try it on your own shipping manifest
The playground takes a file and shows the same JSON, with every bounding box drawn over the page. No key and no signup for the first few; a free key gives you 100 pages a month.