Getting Started
The following section will walk you through how to best make use of all the functionality the OCR API provides.
The Basics of OCR
Let’s start with the basics. The OCR API allows you to take files in any supported format and make any text in them selectable and searchable. This is useful for images and scanned documents. To learn more about OCR itself, see here.
For our first example, we’ll run OCR on a single image file. To do this, add a page1.jpg
file to
the same folder as your code. You can use any image containing text, or use our provided
sample page.
Run the code, and you’ll get a result.pdf
with your page OCRed. Our example sets the OCR language
to English. If your content is in a different language, make sure to update the language
property
accordingly. You can find a list of all supported languages at the
bottom of this page.
Code to perform OCR:
curl -X POST https://api.nutrient.io/build \
-H "Authorization: Bearer your_api_key_here" \
-o result.pdf \
--fail \
-F page1.jpg=@/path/to/page1.jpg \
-F instructions='{
"parts": [
{
"file": "page1.jpg"
}
],
"actions": [
{
"type": "ocr",
"language": "english"
}
]
}'
curl -X POST https://api.nutrient.io/build ^
-H "Authorization: Bearer your_api_key_here" ^
-o result.pdf ^
--fail ^
-F page1.jpg=@/path/to/page1.jpg ^
-F instructions="{\"parts\": [{\"file\": \"page1.jpg\"}], \"actions\": [{\"type\": \"ocr\", \"language\": \"english\"}]}"
package com.example.pspdfkit;
import java.io.File;
import java.io.IOException;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.StandardCopyOption;
import org.json.JSONArray;
import org.json.JSONObject;
import okhttp3.MediaType;
import okhttp3.MultipartBody;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;
public final class PspdfkitApiExample {
public static void main(final String[] args) throws IOException {
final RequestBody body = new MultipartBody.Builder()
.setType(MultipartBody.FORM)
.addFormDataPart(
"page1.jpg",
"/path/to/page1.jpg",
RequestBody.create(
MediaType.parse("image/jpeg"),
new File("/path/to/page1.jpg")
)
)
.addFormDataPart(
"instructions",
new JSONObject()
.put("parts", new JSONArray()
.put(new JSONObject()
.put("file", "page1.jpg")
)
)
.put("actions", new JSONArray()
.put(new JSONObject()
.put("type", "ocr")
.put("language", "english")
)
).toString()
)
.build();
final Request request = new Request.Builder()
.url("https://api.nutrient.io/build")
.method("POST", body)
.addHeader("Authorization", "Bearer your_api_key_here")
.build();
final OkHttpClient client = new OkHttpClient()
.newBuilder()
.build();
final Response response = client.newCall(request).execute();
if (response.isSuccessful()) {
Files.copy(
response.body().byteStream(),
FileSystems.getDefault().getPath("result.pdf"),
StandardCopyOption.REPLACE_EXISTING
);
} else {
// Handle the error
throw new IOException(response.body().string());
}
}
}
using System;
using System.IO;
using System.Net;
using RestSharp;
namespace PspdfkitApiDemo
{
class Program
{
static void Main(string[] args)
{
var client = new RestClient("https://api.nutrient.io/build");
var request = new RestRequest(Method.POST)
.AddHeader("Authorization", "Bearer your_api_key_here")
.AddFile("page1.jpg", "/path/to/page1.jpg")
.AddParameter("instructions", new JsonObject
{
["parts"] = new JsonArray
{
new JsonObject
{
["file"] = "page1.jpg"
}
},
["actions"] = new JsonArray
{
new JsonObject
{
["type"] = "ocr",
["language"] = "english"
}
}
}.ToString());
request.AdvancedResponseWriter = (responseStream, response) =>
{
if (response.StatusCode == HttpStatusCode.OK)
{
using (responseStream)
{
using var outputFileWriter = File.OpenWrite("result.pdf");
responseStream.CopyTo(outputFileWriter);
}
}
else
{
var responseStreamReader = new StreamReader(responseStream);
Console.Write(responseStreamReader.ReadToEnd());
}
};
client.Execute(request);
}
}
}
// This code requires Node.js. Do not run this code directly in a web browser.
const axios = require('axios')
const FormData = require('form-data')
const fs = require('fs')
const formData = new FormData()
formData.append('instructions', JSON.stringify({
parts: [
{
file: "page1.jpg"
}
],
actions: [
{
type: "ocr",
language: "english"
}
]
}))
formData.append('page1.jpg', fs.createReadStream('/path/to/page1.jpg'))
;(async () => {
try {
const response = await axios.post('https://api.nutrient.io/build', formData, {
headers: formData.getHeaders({
'Authorization': 'Bearer your_api_key_here'
}),
responseType: "stream"
})
response.data.pipe(fs.createWriteStream("result.pdf"))
} catch (e) {
const errorString = await streamToString(e.response.data)
console.log(errorString)
}
})()
function streamToString(stream) {
const chunks = []
return new Promise((resolve, reject) => {
stream.on("data", (chunk) => chunks.push(Buffer.from(chunk)))
stream.on("error", (err) => reject(err))
stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8")))
})
}
import requests
import json
response = requests.request(
'POST',
'https://api.nutrient.io/build',
headers = {
'Authorization': 'Bearer your_api_key_here'
},
files = {
'page1.jpg': open('/path/to/page1.jpg', 'rb')
},
data = {
'instructions': json.dumps({
'parts': [
{
'file': 'page1.jpg'
}
],
'actions': [
{
'type': 'ocr',
'language': 'english'
}
]
})
},
stream = True
)
if response.ok:
with open('result.pdf', 'wb') as fd:
for chunk in response.iter_content(chunk_size=8096):
fd.write(chunk)
else:
print(response.text)
exit()
<?php
$FileHandle = fopen('result.pdf', 'w+');
$curl = curl_init();
curl_setopt_array($curl, array(
CURLOPT_URL => 'https://api.nutrient.io/build',
CURLOPT_CUSTOMREQUEST => 'POST',
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => '',
CURLOPT_POSTFIELDS => array(
'instructions' => '{
"parts": [
{
"file": "page1.jpg"
}
],
"actions": [
{
"type": "ocr",
"language": "english"
}
]
}',
'page1.jpg' => new CURLFILE('/path/to/page1.jpg')
),
CURLOPT_HTTPHEADER => array(
'Authorization: Bearer your_api_key_here'
),
CURLOPT_FILE => $FileHandle,
));
$response = curl_exec($curl);
curl_close($curl);
fclose($FileHandle);
POST https://api.nutrient.io/build HTTP/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here
--customboundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json
{
"parts": [
{
"file": "page1.jpg"
}
],
"actions": [
{
"type": "ocr",
"language": "english"
}
]
}
--customboundary
Content-Disposition: form-data; name="page1.jpg"; filename="/path/to/page1.jpg"
Content-Type: image/jpeg
(page1.jpg data)
--customboundary--
Advanced OCR
While running OCR on a single page is useful, often you’ll have a folder full of scanned pages that you want to both run OCR on and merge into a single searchable PDF.
Luckily, this is easy; pass in multiple images — one for each page in your request — and Nutrient DWS API will merge all of them into a PDF before running OCR on it.
Add more files in the same folder as your code and run the updated code. You can duplicate and rename the existing file you have, or you can add some other images containing text.
Code to perform OCR on multiple pages:
curl -X POST https://api.nutrient.io/build \
-H "Authorization: Bearer your_api_key_here" \
-o result.pdf \
--fail \
-F page1.jpg=@/path/to/page1.jpg \
-F page2.jpg=@/path/to/page2.jpg \
-F page3.jpg=@/path/to/page3.jpg \
-F page4.jpg=@/path/to/page4.jpg \
-F instructions='{
"parts": [
{
"file": "page1.jpg"
},
{
"file": "page2.jpg"
},
{
"file": "page3.jpg"
},
{
"file": "page4.jpg"
}
],
"actions": [
{
"type": "ocr",
"language": "english"
}
]
}'
curl -X POST https://api.nutrient.io/build ^
-H "Authorization: Bearer your_api_key_here" ^
-o result.pdf ^
--fail ^
-F page1.jpg=@/path/to/page1.jpg ^
-F page2.jpg=@/path/to/page2.jpg ^
-F page3.jpg=@/path/to/page3.jpg ^
-F page4.jpg=@/path/to/page4.jpg ^
-F instructions="{\"parts\": [{\"file\": \"page1.jpg\"}, {\"file\": \"page2.jpg\"}, {\"file\": \"page3.jpg\"}, {\"file\": \"page4.jpg\"}], \"actions\": [{\"type\": \"ocr\", \"language\": \"english\"}]}"
package com.example.pspdfkit;
import java.io.File;
import java.io.IOException;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.StandardCopyOption;
import org.json.JSONArray;
import org.json.JSONObject;
import okhttp3.MediaType;
import okhttp3.MultipartBody;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;
public final class PspdfkitApiExample {
public static void main(final String[] args) throws IOException {
final RequestBody body = new MultipartBody.Builder()
.setType(MultipartBody.FORM)
.addFormDataPart(
"page1.jpg",
"/path/to/page1.jpg",
RequestBody.create(
MediaType.parse("image/jpeg"),
new File("/path/to/page1.jpg")
)
)
.addFormDataPart(
"page2.jpg",
"/path/to/page2.jpg",
RequestBody.create(
MediaType.parse("image/jpeg"),
new File("/path/to/page2.jpg")
)
)
.addFormDataPart(
"page3.jpg",
"/path/to/page3.jpg",
RequestBody.create(
MediaType.parse("image/jpeg"),
new File("/path/to/page3.jpg")
)
)
.addFormDataPart(
"page4.jpg",
"/path/to/page4.jpg",
RequestBody.create(
MediaType.parse("image/jpeg"),
new File("/path/to/page4.jpg")
)
)
.addFormDataPart(
"instructions",
new JSONObject()
.put("parts", new JSONArray()
.put(new JSONObject()
.put("file", "page1.jpg")
)
.put(new JSONObject()
.put("file", "page2.jpg")
)
.put(new JSONObject()
.put("file", "page3.jpg")
)
.put(new JSONObject()
.put("file", "page4.jpg")
)
)
.put("actions", new JSONArray()
.put(new JSONObject()
.put("type", "ocr")
.put("language", "english")
)
).toString()
)
.build();
final Request request = new Request.Builder()
.url("https://api.nutrient.io/build")
.method("POST", body)
.addHeader("Authorization", "Bearer your_api_key_here")
.build();
final OkHttpClient client = new OkHttpClient()
.newBuilder()
.build();
final Response response = client.newCall(request).execute();
if (response.isSuccessful()) {
Files.copy(
response.body().byteStream(),
FileSystems.getDefault().getPath("result.pdf"),
StandardCopyOption.REPLACE_EXISTING
);
} else {
// Handle the error
throw new IOException(response.body().string());
}
}
}
using System;
using System.IO;
using System.Net;
using RestSharp;
namespace PspdfkitApiDemo
{
class Program
{
static void Main(string[] args)
{
var client = new RestClient("https://api.nutrient.io/build");
var request = new RestRequest(Method.POST)
.AddHeader("Authorization", "Bearer your_api_key_here")
.AddFile("page1.jpg", "/path/to/page1.jpg")
.AddFile("page2.jpg", "/path/to/page2.jpg")
.AddFile("page3.jpg", "/path/to/page3.jpg")
.AddFile("page4.jpg", "/path/to/page4.jpg")
.AddParameter("instructions", new JsonObject
{
["parts"] = new JsonArray
{
new JsonObject
{
["file"] = "page1.jpg"
},
new JsonObject
{
["file"] = "page2.jpg"
},
new JsonObject
{
["file"] = "page3.jpg"
},
new JsonObject
{
["file"] = "page4.jpg"
}
},
["actions"] = new JsonArray
{
new JsonObject
{
["type"] = "ocr",
["language"] = "english"
}
}
}.ToString());
request.AdvancedResponseWriter = (responseStream, response) =>
{
if (response.StatusCode == HttpStatusCode.OK)
{
using (responseStream)
{
using var outputFileWriter = File.OpenWrite("result.pdf");
responseStream.CopyTo(outputFileWriter);
}
}
else
{
var responseStreamReader = new StreamReader(responseStream);
Console.Write(responseStreamReader.ReadToEnd());
}
};
client.Execute(request);
}
}
}
// This code requires Node.js. Do not run this code directly in a web browser.
const axios = require('axios')
const FormData = require('form-data')
const fs = require('fs')
const formData = new FormData()
formData.append('instructions', JSON.stringify({
parts: [
{
file: "page1.jpg"
},
{
file: "page2.jpg"
},
{
file: "page3.jpg"
},
{
file: "page4.jpg"
}
],
actions: [
{
type: "ocr",
language: "english"
}
]
}))
formData.append('page1.jpg', fs.createReadStream('/path/to/page1.jpg'))
formData.append('page2.jpg', fs.createReadStream('/path/to/page2.jpg'))
formData.append('page3.jpg', fs.createReadStream('/path/to/page3.jpg'))
formData.append('page4.jpg', fs.createReadStream('/path/to/page4.jpg'))
;(async () => {
try {
const response = await axios.post('https://api.nutrient.io/build', formData, {
headers: formData.getHeaders({
'Authorization': 'Bearer your_api_key_here'
}),
responseType: "stream"
})
response.data.pipe(fs.createWriteStream("result.pdf"))
} catch (e) {
const errorString = await streamToString(e.response.data)
console.log(errorString)
}
})()
function streamToString(stream) {
const chunks = []
return new Promise((resolve, reject) => {
stream.on("data", (chunk) => chunks.push(Buffer.from(chunk)))
stream.on("error", (err) => reject(err))
stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8")))
})
}
import requests
import json
response = requests.request(
'POST',
'https://api.nutrient.io/build',
headers = {
'Authorization': 'Bearer your_api_key_here'
},
files = {
'page1.jpg': open('/path/to/page1.jpg', 'rb'),
'page2.jpg': open('/path/to/page2.jpg', 'rb'),
'page3.jpg': open('/path/to/page3.jpg', 'rb'),
'page4.jpg': open('/path/to/page4.jpg', 'rb')
},
data = {
'instructions': json.dumps({
'parts': [
{
'file': 'page1.jpg'
},
{
'file': 'page2.jpg'
},
{
'file': 'page3.jpg'
},
{
'file': 'page4.jpg'
}
],
'actions': [
{
'type': 'ocr',
'language': 'english'
}
]
})
},
stream = True
)
if response.ok:
with open('result.pdf', 'wb') as fd:
for chunk in response.iter_content(chunk_size=8096):
fd.write(chunk)
else:
print(response.text)
exit()
<?php
$FileHandle = fopen('result.pdf', 'w+');
$curl = curl_init();
curl_setopt_array($curl, array(
CURLOPT_URL => 'https://api.nutrient.io/build',
CURLOPT_CUSTOMREQUEST => 'POST',
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => '',
CURLOPT_POSTFIELDS => array(
'instructions' => '{
"parts": [
{
"file": "page1.jpg"
},
{
"file": "page2.jpg"
},
{
"file": "page3.jpg"
},
{
"file": "page4.jpg"
}
],
"actions": [
{
"type": "ocr",
"language": "english"
}
]
}',
'page1.jpg' => new CURLFILE('/path/to/page1.jpg'),
'page2.jpg' => new CURLFILE('/path/to/page2.jpg'),
'page3.jpg' => new CURLFILE('/path/to/page3.jpg'),
'page4.jpg' => new CURLFILE('/path/to/page4.jpg')
),
CURLOPT_HTTPHEADER => array(
'Authorization: Bearer your_api_key_here'
),
CURLOPT_FILE => $FileHandle,
));
$response = curl_exec($curl);
curl_close($curl);
fclose($FileHandle);
POST https://api.nutrient.io/build HTTP/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here
--customboundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json
{
"parts": [
{
"file": "page1.jpg"
},
{
"file": "page2.jpg"
},
{
"file": "page3.jpg"
},
{
"file": "page4.jpg"
}
],
"actions": [
{
"type": "ocr",
"language": "english"
}
]
}
--customboundary
Content-Disposition: form-data; name="page1.jpg"; filename="/path/to/page1.jpg"
Content-Type: image/jpeg
(page1.jpg data)
--customboundary
Content-Disposition: form-data; name="page2.jpg"; filename="/path/to/page2.jpg"
Content-Type: image/jpeg
(page2.jpg data)
--customboundary
Content-Disposition: form-data; name="page3.jpg"; filename="/path/to/page3.jpg"
Content-Type: image/jpeg
(page3.jpg data)
--customboundary
Content-Disposition: form-data; name="page4.jpg"; filename="/path/to/page4.jpg"
Content-Type: image/jpeg
(page4.jpg data)
--customboundary--
Supported Languages
Finally, here’s a listing of all supported languages:
Croatian
Czech
Danish
Dutch
English
Finnish
French
German
Indonesian
Italian
Malay
Norwegian
Polish
Portuguese
Serbian
Slovak
Slovenian