DocuOCR API Reference

# 1, Upload the document
curl -X POST https://docuocr.com/api/documents/upload \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "document=@/path/to/invoice-q1-2026.pdf"

# → {"success":true,"data":{"file_id":1234,"name":"invoice-q1-2026.pdf"}}

# 2, Start extraction (document_type_id optional)
curl -X POST https://docuocr.com/api/documents/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"file_id": 1234, "document_type_id": 5678}'

# → {"success":true,"data":{"extraction_id":9876,"extraction_hash":"abc123-def456"}}

# 3, Retrieve structured results
curl -X GET https://docuocr.com/api/documents/extraction/abc123-def456 \
  -H "Authorization: Bearer YOUR_API_KEY"

<?php

$apiKey     = 'YOUR_API_KEY';
$baseUrl    = 'https://docuocr.com/api';
$filePath   = '/path/to/invoice-q1-2026.pdf';

// 1, Upload
$ch = curl_init("$baseUrl/documents/upload");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST           => true,
    CURLOPT_HTTPHEADER     => ["Authorization: Bearer $apiKey"],
    CURLOPT_POSTFIELDS     => ['document' => new CURLFile($filePath)],
]);
$upload = json_decode(curl_exec($ch), true);
curl_close($ch);

if (!$upload['success']) {
    die("Upload failed: " . $upload['message']);
}
$fileId = $upload['data']['file_id'];

// 2, Extract
$ch = curl_init("$baseUrl/documents/extract");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST           => true,
    CURLOPT_HTTPHEADER     => [
        "Authorization: Bearer $apiKey",
        "Content-Type: application/json",
    ],
    CURLOPT_POSTFIELDS => json_encode([
        'file_id'          => $fileId,
        'document_type_id' => 5678, // optional
    ]),
]);
$extract = json_decode(curl_exec($ch), true);
curl_close($ch);

if (!$extract['success']) {
    die("Extraction failed: " . $extract['message']);
}
$hash = $extract['data']['extraction_hash'];

// 3, Poll for results
do {
    sleep(2);
    $ch = curl_init("$baseUrl/documents/extraction/$hash");
    curl_setopt_array($ch, [
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_HTTPHEADER     => ["Authorization: Bearer $apiKey"],
    ]);
    $result = json_decode(curl_exec($ch), true);
    curl_close($ch);
} while (in_array($result['data']['status'], ['pending', 'processing'], true));

if ($result['data']['status'] !== 'completed') {
    throw new RuntimeException($result['data']['status'] . ': ' . $result['data']['message']);
}

foreach ($result['data']['fields'] as $field) {
    echo $field['content'] . ': ' . $field['value'] . "\n";
}

const API_KEY  = 'YOUR_API_KEY';
const BASE_URL = 'https://docuocr.com/api';

async function uploadDocument(file) {
  const form = new FormData();
  form.append('document', file);

  const res = await fetch(`${BASE_URL}/documents/upload`, {
    method: 'POST',
    headers: { 'Authorization': `Bearer ${API_KEY}` },
    body: form,
  });
  const json = await res.json();
  if (!json.success) throw new Error(json.message);
  return json.data.file_id;
}

async function startExtraction(fileId, documentTypeId = null) {
  const payload = { file_id: fileId };
  if (documentTypeId) payload.document_type_id = documentTypeId;

  const res = await fetch(`${BASE_URL}/documents/extract`, {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${API_KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify(payload),
  });
  const json = await res.json();
  if (!json.success) throw new Error(json.message);
  return json.data.extraction_hash;
}

async function pollResults(hash, intervalMs = 2000) {
  while (true) {
    const res  = await fetch(`${BASE_URL}/documents/extraction/${hash}`, {
      headers: { 'Authorization': `Bearer ${API_KEY}` },
    });
    const json = await res.json();
    if (json.data.status === 'completed') return json.data;
    if (!['pending', 'processing'].includes(json.data.status)) {
      throw new Error(`${json.data.status}: ${json.data.message}`);
    }
    await new Promise(r => setTimeout(r, intervalMs));
  }
}

// Usage
const fileInput = document.querySelector('input[type="file"]');
const fileId    = await uploadDocument(fileInput.files[0]);
const hash      = await startExtraction(fileId, 5678);
const data      = await pollResults(hash);
console.log('Extracted fields:', data.fields);

import time
import requests

API_KEY  = "YOUR_API_KEY"
BASE_URL = "https://docuocr.com/api"
HEADERS  = {"Authorization": f"Bearer {API_KEY}"}

def upload_document(file_path: str) -> int:
    with open(file_path, "rb") as f:
        resp = requests.post(
            f"{BASE_URL}/documents/upload",
            headers=HEADERS,
            files={"document": f},
        )
    data = resp.json()
    if not data["success"]:
        raise RuntimeError(data["message"])
    return data["data"]["file_id"]

def start_extraction(file_id: int, document_type_id: int | None = None) -> str:
    payload = {"file_id": file_id}
    if document_type_id:
        payload["document_type_id"] = document_type_id
    resp = requests.post(
        f"{BASE_URL}/documents/extract",
        headers={**HEADERS, "Content-Type": "application/json"},
        json=payload,
    )
    data = resp.json()
    if not data["success"]:
        raise RuntimeError(data["message"])
    return data["data"]["extraction_hash"]

def poll_results(extraction_hash: str, interval: float = 2.0) -> dict:
    url = f"{BASE_URL}/documents/extraction/{extraction_hash}"
    while True:
        data = requests.get(url, headers=HEADERS).json()["data"]
        if data["status"] == "completed":
            return data
        if data["status"] not in ("pending", "processing"):
            raise RuntimeError(f"{data['status']}: {data['message']}")
        time.sleep(interval)

# Usage
file_id  = upload_document("/path/to/invoice-q1-2026.pdf")
ex_hash  = start_extraction(file_id, document_type_id=5678)
result   = poll_results(ex_hash)

for field in result["fields"]:
    print(f"{field['content']}  (page={field['page']})")