# Show HN: Parse - define the fields once, get the same JSON from every PDF

> Source: <https://parse.conversiontools.io>
> Published: 2026-09-30 13:37:21+00:00

AI-powered document parsing that understands your data. Upload a PDF, get structured data back as JSON, CSV, or Excel.

```
================================
     TRADER JOE'S  #502
1800 N Vermont Ave
Los Angeles, CA 90027
================================
02/20/2026  3:42 PM   Reg: 03
Cashier: MARIA     #4821
--------------------------------
ORG BANANAS          0.99
WHOLE MILK 1GAL      4.29
SOURDOUGH BREAD      4.49
EVERYTHING BAGELS    3.99
SPARKLING WATER      1.29
OLIVE OIL 500ML      6.99
PENNE PASTA          1.29
CRUSHED TOMATOES     1.99
--------------------------------
SUBTOTAL            25.32
TAX  9.5%            2.41
TOTAL               27.73
VISA ***4829        27.73
--------------------------------
THANK YOU FOR SHOPPING
     AT TRADER JOE'S!
================================
```

Try with your own document

Click to upload or drag and drop - no signup needed

No credit card required · 100 pages/month free

The async contract

Extraction does not hold your request open. Parse answers straight away with an id, reads the document in the background, and hands back structured JSON when it is ready. Here is one sample three-page invoice going through it, second by second.

No credit card required - 30 pages/month free

Submit the file, keep the id, and ask for it until the status changes. Everything else - schemas, exports, webhooks - is built on those two calls.

```
# 1. submit - the call returns straight away
curl -X POST https://api-parse.conversiontools.io/v1/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@invoice.pdf"

# 202  { "id": "ext_9f2c41d7", "status": "processing" }

# 2. poll that id until it stops saying "processing"
curl https://api-parse.conversiontools.io/v1/extractions/ext_9f2c41d7 \
  -H "Authorization: Bearer YOUR_API_KEY"

# 200  { "status": "completed", "data": { ... } }
```

Built by developers, for developers. We handle the complexity so you don't have to.

Parse integrates into any pipeline where documents need to become data.

You Got the Data Out. Why Is It Still a Mess?

Parsing a document is the easy part now. The real work is turning that output into the same clean fields every time - here is the gap that breaks pipelines, and how to close it.

Read more
How I prepare my VAT report from a pile of supplier invoices

A founder walkthrough: define the fields once, then turn every supplier PDF invoice into the same structured JSON for a VAT return - no manual re-typing.

Read more
