Document OCR

Article summary

Did you find this summary helpful?

Thank you for your feedback

Available in Classic and VPC

This document introduces the Document OCR API examples of the CLOVA OCR service.

For `Content-Type: multipart/form-data`

This section describes the API examples when the request header's Content-Type is multipart/form-data.

Java

The following is a Java-based sample code for the API.

import java.io.BufferedReader;
import java.io.DataOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.UUID;

import org.json.JSONArray;
import org.json.JSONObject;

public class OCRAPIDemo {

	public static void main(String[] args) {
		String apiURL = "YOUR_API_URL";
		String secretKey = "YOUR_SECRET_KEY";
		String imageFile = "YOUR_IMAGE_FILE";

		try {
			URL url = new URL(apiURL);
			HttpURLConnection con = (HttpURLConnection)url.openConnection();
			con.setUseCaches(false);
			con.setDoInput(true);
			con.setDoOutput(true);
			con.setReadTimeout(30000);
			con.setRequestMethod("POST");
			String boundary = "----" + UUID.randomUUID().toString().replaceAll("-", "");
			con.setRequestProperty("Content-Type", "multipart/form-data; boundary=" + boundary);
			con.setRequestProperty("X-OCR-SECRET", secretKey);

			JSONObject json = new JSONObject();
			json.put("version", "V2");
			json.put("requestId", UUID.randomUUID().toString());
			json.put("timestamp", System.currentTimeMillis());
			JSONObject image = new JSONObject();
			image.put("format", "jpg");
			image.put("name", "demo");
			JSONArray images = new JSONArray();
			images.put(image);
			json.put("images", images);
			String postParams = json.toString();

			con.connect();
			DataOutputStream wr = new DataOutputStream(con.getOutputStream());
			long start = System.currentTimeMillis();
			File file = new File(imageFile);
			writeMultiPart(wr, postParams, file, boundary);
			wr.close();

			int responseCode = con.getResponseCode();
			BufferedReader br;
			if (responseCode == 200) {
				br = new BufferedReader(new InputStreamReader(con.getInputStream()));
			} else {
				br = new BufferedReader(new InputStreamReader(con.getErrorStream()));
			}
			String inputLine;
			StringBuffer response = new StringBuffer();
			while ((inputLine = br.readLine()) != null) {
				response.append(inputLine);
			}
			br.close();

			System.out.println(response);
		} catch (Exception e) {
			System.out.println(e);
		}
	}

	private static void writeMultiPart(OutputStream out, String jsonMessage, File file, String boundary) throws
		IOException {
		StringBuilder sb = new StringBuilder();
		sb.append("--").append(boundary).append("\r\n");
		sb.append("Content-Disposition:form-data; name=\"message\"\r\n\r\n");
		sb.append(jsonMessage);
		sb.append("\r\n");

		out.write(sb.toString().getBytes("UTF-8"));
		out.flush();

		if (file != null && file.isFile()) {
			out.write(("--" + boundary + "\r\n").getBytes("UTF-8"));
			StringBuilder fileString = new StringBuilder();
			fileString
				.append("Content-Disposition:form-data; name=\"file\"; filename=");
			fileString.append("\"" + file.getName() + "\"\r\n");
			fileString.append("Content-Type: application/octet-stream\r\n\r\n");
			out.write(fileString.toString().getBytes("UTF-8"));
			out.flush();

			try (FileInputStream fis = new FileInputStream(file)) {
				byte[] buffer = new byte[8192];
				int count;
				while ((count = fis.read(buffer)) != -1) {
					out.write(buffer, 0, count);
				}
				out.write("\r\n".getBytes());
			}

			out.write(("--" + boundary + "--\r\n").getBytes("UTF-8"));
		}
		out.flush();
	}
}

Python

The following is a Python-based sample code for the API.

import requests
import uuid
import time
import json

api_url = 'YOUR_API_URL'
secret_key = 'YOUR_SECRET_KEY'
image_file = 'YOUR_IMAGE_FILE'

request_json = {
    'images': [
        {
            'format': 'jpg',
            'name': 'demo'
        }
    ],
    'requestId': str(uuid.uuid4()),
    'version': 'V2',
    'timestamp': int(round(time.time() * 1000))
}

payload = {'message': json.dumps(request_json).encode('UTF-8')}
files = [
  ('file', open(image_file,'rb'))
]
headers = {
  'X-OCR-SECRET': secret_key
}

response = requests.request("POST", api_url, headers=headers, data = payload, files = files)

print(response.text.encode('utf8'))

PHP

The following is a PHP-based sample code for the API.

<?php
  $client_secret = "YOUR_SECRET_KEY";
  $url = "YOUR_API_URL";
  $image_file = "YOUR_IMAGE_FILE";

  $params->version = "V2";
  $params->requestId = uniqid();
  $params->timestamp = time();
  $image->format = "jpg";
  $image->name = "demo";
  $images = array($image);
  $params->images = $images;
  $json = json_encode($params);
  
  $boundary = uniqid();
  $is_post = true;
  $ch = curl_init();
  curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
  curl_setopt($ch, CURLOPT_URL, $url);
  curl_setopt($ch, CURLOPT_POST, $is_post);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  $post_form = array("message" => $json, "file" => new CURLFILE($image_file));
  curl_setopt($ch, CURLOPT_POSTFIELDS, $post_form);
  $headers = array();
  $headers[] = "X-OCR-SECRET: ".$client_secret;
  curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
  $response = curl_exec($ch);
  $err = curl_error($ch);
  $status_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
  curl_close ($ch);

  echo $status_code;
  if($status_code == 200) {
    echo $response;
  } else {
    echo "ERROR: ".$response;
  }
?>

For `Content-Type: application/json`

This section describes the API examples when the request header's Content-Type is application/json.

Java

The following is a Java-based sample code for the API.

import java.io.BufferedReader;
import java.io.DataOutputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.UUID;

import org.json.JSONArray;
import org.json.JSONObject;

public class OCRGeneralAPIDemo {

	public static void main(String[] args) {
		String apiURL = "YOUR_API_URL";
		String secretKey = "YOUR_SECRET_KEY";

		try {
			URL url = new URL(apiURL);
			HttpURLConnection con = (HttpURLConnection)url.openConnection();
			con.setUseCaches(false);
			con.setDoInput(true);
			con.setDoOutput(true);
			con.setRequestMethod("POST");
			con.setRequestProperty("Content-Type", "application/json; charset=utf-8");
			con.setRequestProperty("X-OCR-SECRET", secretKey);

			JSONObject json = new JSONObject();
			json.put("version", "V2");
			json.put("requestId", UUID.randomUUID().toString());
			json.put("timestamp", System.currentTimeMillis());
			JSONObject image = new JSONObject();
			image.put("format", "jpg");
			image should be public, otherwise, should use data
			FileInputStream inputStream = new FileInputStream("YOUR_IMAGE_FILE");
			byte[] buffer = new byte[inputStream.available()];
			inputStream.read(buffer);
			inputStream.close();
			image.put("data", buffer);
			image.put("name", "demo");
			JSONArray images = new JSONArray();
			images.put(image);
			json.put("images", images);
			String postParams = json.toString();

			DataOutputStream wr = new DataOutputStream(con.getOutputStream());
			wr.writeBytes(postParams);
			wr.flush();
			wr.close();

			int responseCode = con.getResponseCode();
			BufferedReader br;
			if (responseCode == 200) {
				br = new BufferedReader(new InputStreamReader(con.getInputStream()));
			} else {
				br = new BufferedReader(new InputStreamReader(con.getErrorStream()));
			}
			String inputLine;
			StringBuffer response = new StringBuffer();
			while ((inputLine = br.readLine()) != null) {
				response.append(inputLine);
			}
			br.close();

			System.out.println(response);
		} catch (Exception e) {
			System.out.println(e);
		}
	}

}

Python

The following is a Python-based sample code for the API.

import requests
import uuid
import time
import base64
import json

api_url = 'YOUR_API_URL'
secret_key = 'YOUR_SECRET_KEY'
image_file = 'YOUR_IMAGE_FILE'
with open(image_file,'rb') as f:
file_data = f.read()

request_json = {
    'images': [
        {
            'format': 'jpg',
            'name': 'demo',
            'data': base64.b64encode(file_data).decode()
        }
    ],
    'requestId': str(uuid.uuid4()),
    'version': 'V2',
    'timestamp': int(round(time.time() * 1000))
}

payload = json.dumps(request_json).encode('UTF-8')
headers = {
  'X-OCR-SECRET': secret_key,
  'Content-Type': 'application/json'
}

response = requests.request("POST", api_url, headers=headers, data = payload)

print(response.text)

PHP

The following is a PHP-based sample code for the API.

<?php
  $client_secret = "YOUR_SECRET_KEY";
  $url = "YOUR_API_URL";
  $image_file = "YOUR_IMAGE_FILE";

  $params->version = "V2";
  $params->requestId = "uuid";
  $params->timestamp = time();
  $image->format = "jpg";
  $image->data = base64_encode(file_get_contents($image_file));
  $image->name = "demo";
  $images = array($image);
  $params->images = $images;
  $json = json_encode($params);

  $is_post = true;
  $ch = curl_init();
  curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
  curl_setopt($ch, CURLOPT_URL, $url);
  curl_setopt($ch, CURLOPT_POST, $is_post);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch, CURLOPT_POSTFIELDS, $json);
  $headers = array();
  $headers[] = "X-OCR-SECRET: ".$client_secret;
  $headers[] = "Content-Type:application/json; charset=utf-8";
  curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
  $response = curl_exec($ch);
  $err = curl_error($ch);
  $status_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
  curl_close ($ch);

  echo $status_code;
  if($status_code == 200) {
    echo $response;
  } else {
    echo "ERROR: ".$response;
  }
?>

Was this article helpful?

What's Next

CLOVA OCR Release Notes

Table of contents

For Content-Type: multipart/form-data
For Content-Type: application/json

Document OCR

For Content-Type: multipart/form-data

Java

Python

PHP

For Content-Type: application/json

Java

Python

PHP

What's Next

For `Content-Type: multipart/form-data`

For `Content-Type: application/json`