OCR API JavaScript: Extract Text and Data from PDFs in Node.js

import { readFile } from "node:fs/promises";

const API_KEY = "YOUR_API_KEY";
const BASE = "https://docuocr.com/api/documents";
const auth = { Authorization: `Bearer ${API_KEY}` };

// 1. Upload the PDF or image, get a file_id
const form = new FormData();
form.append("file", new Blob([await readFile("invoice.pdf")]), "invoice.pdf");
const up = await fetch(`${BASE}/upload`, { method: "POST", headers: auth, body: form });
const { file_id } = await up.json();

// 2. Start extraction, get a job hash
const job = await fetch(`${BASE}/extract`, {
  method: "POST",
  headers: { ...auth, "Content-Type": "application/json" },
  body: JSON.stringify({ file_id }),
});
const { extraction_hash } = await job.json();

// 3. Poll until the JSON is ready
let res;
do {
  await new Promise(r => setTimeout(r, 2000));
  res = await (await fetch(`${BASE}/extraction/${extraction_hash}`, { headers: auth })).json();
} while (res.status !== "completed");

// res.fields and res.tables are ready to use
for (const field of res.fields) {
  console.log(field.name, field.value, field.confidence);
}