OCR PDF

Use built-in optical character recognition (OCR) to convert images to text and enable fully text searchable documents for archiving and creation of searchable indexes.

REST API

See our public API Reference for OCR PDF

Text recognition (OCR)

Optical character recognition (OCR) converts images to text so that you and your users can fully interact with the PDF file. After performing OCR, the PDF may be fully editable and searchable. The input format must be application/pdf.

This sample defaults to the en-us locale. For other languages, see OCR with explicit language.

Please refer the API usage guide to understand how to use our APIs.

Java

.NET

Node JS

REST API

// Get the samples from https://www.adobe.com/go/pdftoolsapi_java_samples
// Run the sample:
// mvn -f pom.xml exec:java -Dexec.mainClass=com.adobe.pdfservices.operation.samples.ocrpdf.OcrPDF
 
public class OcrPDF {
 
  // Initialize the logger.
  private static final Logger LOGGER = LoggerFactory.getLogger(OcrPDF.class);
 
  public static void main(String[] args) {
        try (InputStream inputStream = Files.newInputStream(new File("src/main/resources/ocrInput.pdf").toPath())) {
             // Initial setup, create credentials instance
            Credentials credentials = new ServicePrincipalCredentials(
                    System.getenv("PDF_SERVICES_CLIENT_ID"),
                    System.getenv("PDF_SERVICES_CLIENT_SECRET"));

            // Creates a PDF Services instance
            PDFServices pdfServices = new PDFServices(credentials);

            // Creates an asset(s) from source file(s) and upload
            Asset asset = pdfServices.upload(inputStream, PDFServicesMediaType.PDF.getMediaType());

            // Creates a new job instance
            OCRJob ocrJob = new OCRJob(asset);

            // Submit the job and gets the job result
            String location = pdfServices.submit(ocrJob);
            PDFServicesResponse<OCRResult> pdfServicesResponse = pdfServices.getJobResult(location, OCRResult.class);

            // Get content from the resulting asset(s)
            Asset resultAsset = pdfServicesResponse.getResult().getAsset();
            StreamAsset streamAsset = pdfServices.getContent(resultAsset);

            // Creates an output stream and copy stream asset's content to it
            Files.createDirectories(Paths.get("output/"));
            OutputStream outputStream = Files.newOutputStream(new File("output/ocrOutput.pdf").toPath());
            LOGGER.info("Saving asset at output/ocrOutput.pdf");
            IOUtils.copy(streamAsset.getInputStream(), outputStream); 
            outputStream.close();
       } catch (ServiceApiException | IOException | SDKException | ServiceUsageException ex) {
        LOGGER.error("Exception encountered while executing operation", ex);
       }
  }
}
Copied to your clipboard
1// Get the samples from https://www.adobe.com/go/pdftoolsapi_java_samples
2// Run the sample:
3// mvn -f pom.xml exec:java -Dexec.mainClass=com.adobe.pdfservices.operation.samples.ocrpdf.OcrPDF
4 
5public class OcrPDF {
6 
7  // Initialize the logger.
8  private static final Logger LOGGER = LoggerFactory.getLogger(OcrPDF.class);
9 
10  public static void main(String[] args) {
11        try (InputStream inputStream = Files.newInputStream(new File("src/main/resources/ocrInput.pdf").toPath())) {
12             // Initial setup, create credentials instance
13            Credentials credentials = new ServicePrincipalCredentials(
14                    System.getenv("PDF_SERVICES_CLIENT_ID"),
15                    System.getenv("PDF_SERVICES_CLIENT_SECRET"));
16
17            // Creates a PDF Services instance
18            PDFServices pdfServices = new PDFServices(credentials);
19
20            // Creates an asset(s) from source file(s) and upload
21            Asset asset = pdfServices.upload(inputStream, PDFServicesMediaType.PDF.getMediaType());
22
23            // Creates a new job instance
24            OCRJob ocrJob = new OCRJob(asset);
25
26            // Submit the job and gets the job result
27            String location = pdfServices.submit(ocrJob);
28            PDFServicesResponse<OCRResult> pdfServicesResponse = pdfServices.getJobResult(location, OCRResult.class);
29
30            // Get content from the resulting asset(s)
31            Asset resultAsset = pdfServicesResponse.getResult().getAsset();
32            StreamAsset streamAsset = pdfServices.getContent(resultAsset);
33
34            // Creates an output stream and copy stream asset's content to it
35            Files.createDirectories(Paths.get("output/"));
36            OutputStream outputStream = Files.newOutputStream(new File("output/ocrOutput.pdf").toPath());
37            LOGGER.info("Saving asset at output/ocrOutput.pdf");
38            IOUtils.copy(streamAsset.getInputStream(), outputStream); 
39            outputStream.close();
40       } catch (ServiceApiException | IOException | SDKException | ServiceUsageException ex) {
41        LOGGER.error("Exception encountered while executing operation", ex);
42       }
43  }
44}

// Get the samples from https://www.adobe.com/go/pdftoolsapi_net_samples
// Run the sample:
// cd OcrPDF/
// dotnet run OcrPDF.csproj

 namespace OcrPDF
 {
   class Program
   {
     private static readonly ILog log = LogManager.GetLogger(typeof(Program));
     static void Main()
     {
       //Configure the logging
       ConfigureLogging();
       try
       {
           // Initial setup, create credentials instance.
           Credentials credentials = Credentials.ServicePrincipalCredentialsBuilder()
                .WithClientId("PDF_SERVICES_CLIENT_ID")
                .WithClientSecret("PDF_SERVICES_CLIENT_SECRET")
                .Build();

         //Create an ExecutionContext using credentials and create a new operation instance.
         ExecutionContext executionContext = ExecutionContext.Create(credentials);
         OCROperation ocrOperation = OCROperation.CreateNew();

         // Set operation input from a source file.
         FileRef sourceFileRef = FileRef.CreateFromLocalFile(@"ocrInput.pdf");
         ocrOperation.SetInput(sourceFileRef);

         // Execute the operation.
         FileRef result = ocrOperation.Execute(executionContext);

         // Save the result to the specified location.
         result.SaveAs(Directory.GetCurrentDirectory() + "/output/ocrOperationOutput.pdf");
       }
       catch (ServiceUsageException ex)
       {
         log.Error("Exception encountered while executing operation", ex);
       }
       // Catch more errors here. . .
     }

     static void ConfigureLogging()
     {
       ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
       XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
     }
   }
 }
Copied to your clipboard
1// Get the samples from https://www.adobe.com/go/pdftoolsapi_net_samples
2// Run the sample:
3// cd OcrPDF/
4// dotnet run OcrPDF.csproj
5
6 namespace OcrPDF
7 {
8   class Program
9   {
10     private static readonly ILog log = LogManager.GetLogger(typeof(Program));
11     static void Main()
12     {
13       //Configure the logging
14       ConfigureLogging();
15       try
16       {
17           // Initial setup, create credentials instance.
18           Credentials credentials = Credentials.ServicePrincipalCredentialsBuilder()
19                .WithClientId("PDF_SERVICES_CLIENT_ID")
20                .WithClientSecret("PDF_SERVICES_CLIENT_SECRET")
21                .Build();
22
23         //Create an ExecutionContext using credentials and create a new operation instance.
24         ExecutionContext executionContext = ExecutionContext.Create(credentials);
25         OCROperation ocrOperation = OCROperation.CreateNew();
26
27         // Set operation input from a source file.
28         FileRef sourceFileRef = FileRef.CreateFromLocalFile(@"ocrInput.pdf");
29         ocrOperation.SetInput(sourceFileRef);
30
31         // Execute the operation.
32         FileRef result = ocrOperation.Execute(executionContext);
33
34         // Save the result to the specified location.
35         result.SaveAs(Directory.GetCurrentDirectory() + "/output/ocrOperationOutput.pdf");
36       }
37       catch (ServiceUsageException ex)
38       {
39         log.Error("Exception encountered while executing operation", ex);
40       }
41       // Catch more errors here. . .
42     }
43
44     static void ConfigureLogging()
45     {
46       ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
47       XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
48     }
49   }
50 }

// Get the samples from http://www.adobe.com/go/pdftoolsapi_node_sample
// Run the sample:
// node src/ocr/ocr-pdf.js

const {
    ServicePrincipalCredentials,
    PDFServices,
    MimeType,
    OCRJob,
    OCRResult,
    SDKError,
    ServiceUsageError,
    ServiceApiError
} = require("@adobe/pdfservices-node-sdk");
const fs = require("fs");

(async () => {
    let readStream;
    try {
        // Initial setup, create credentials instance
        const credentials = new ServicePrincipalCredentials({
            clientId: process.env.PDF_SERVICES_CLIENT_ID,
            clientSecret: process.env.PDF_SERVICES_CLIENT_SECRET
        });

        // Creates a PDF Services instance
        const pdfServices = new PDFServices({credentials});

        // Creates an asset(s) from source file(s) and upload
        readStream = fs.createReadStream("./ocrInput.pdf");
        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

        // Creates a new job instance
        const job = new OCRJob({inputAsset});

        // Submit the job and get the job result
        const pollingURL = await pdfServices.submit({job});
        const pdfServicesResponse = await pdfServices.getJobResult({
            pollingURL,
            resultType: OCRResult
        });

        // Get content from the resulting asset(s)
        const resultAsset = pdfServicesResponse.result.asset;
        const streamAsset = await pdfServices.getContent({asset: resultAsset});

        // Creates a write stream and copy stream asset's content to it
        const outputFilePath = "./ocrOutput.pdf";
        console.log(`Saving asset at ${outputFilePath}`);

        const writeStream = fs.createWriteStream(outputFilePath);
        streamAsset.readStream.pipe(writeStream);
    } catch (err) {
        if (err instanceof SDKError || err instanceof ServiceUsageError || err instanceof ServiceApiError) {
            console.log("Exception encountered while executing operation", err);
        } else {
            console.log("Exception encountered while executing operation", err);
        }
    } finally {
        readStream?.destroy();
    }
})();
Copied to your clipboard
1// Get the samples from http://www.adobe.com/go/pdftoolsapi_node_sample
2// Run the sample:
3// node src/ocr/ocr-pdf.js
4
5const {
6    ServicePrincipalCredentials,
7    PDFServices,
8    MimeType,
9    OCRJob,
10    OCRResult,
11    SDKError,
12    ServiceUsageError,
13    ServiceApiError
14} = require("@adobe/pdfservices-node-sdk");
15const fs = require("fs");
16
17(async () => {
18    let readStream;
19    try {
20        // Initial setup, create credentials instance
21        const credentials = new ServicePrincipalCredentials({
22            clientId: process.env.PDF_SERVICES_CLIENT_ID,
23            clientSecret: process.env.PDF_SERVICES_CLIENT_SECRET
24        });
25
26        // Creates a PDF Services instance
27        const pdfServices = new PDFServices({credentials});
28
29        // Creates an asset(s) from source file(s) and upload
30        readStream = fs.createReadStream("./ocrInput.pdf");
31        const inputAsset = await pdfServices.upload({
32            readStream,
33            mimeType: MimeType.PDF
34        });
35
36        // Creates a new job instance
37        const job = new OCRJob({inputAsset});
38
39        // Submit the job and get the job result
40        const pollingURL = await pdfServices.submit({job});
41        const pdfServicesResponse = await pdfServices.getJobResult({
42            pollingURL,
43            resultType: OCRResult
44        });
45
46        // Get content from the resulting asset(s)
47        const resultAsset = pdfServicesResponse.result.asset;
48        const streamAsset = await pdfServices.getContent({asset: resultAsset});
49
50        // Creates a write stream and copy stream asset's content to it
51        const outputFilePath = "./ocrOutput.pdf";
52        console.log(`Saving asset at ${outputFilePath}`);
53
54        const writeStream = fs.createWriteStream(outputFilePath);
55        streamAsset.readStream.pipe(writeStream);
56    } catch (err) {
57        if (err instanceof SDKError || err instanceof ServiceUsageError || err instanceof ServiceApiError) {
58            console.log("Exception encountered while executing operation", err);
59        } else {
60            console.log("Exception encountered while executing operation", err);
61        }
62    } finally {
63        readStream?.destroy();
64    }
65})();

// Please refer our REST API docs for more information 
// https://developer.adobe.com/document-services/docs/apis/#tag/Ocr

curl --location --request POST 'https://pdf-services.adobe.io/operation/ocr' \
--header 'x-api-key: {{Placeholder for client_id}}' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {{Placeholder for token}}' \
--data-raw '{
    "assetID": "urn:aaid:AS:UE1:23c30ee0-2e4d-46d6-87f2-087832fca718"
}'
Copied to your clipboard
1// Please refer our REST API docs for more information 
2// https://developer.adobe.com/document-services/docs/apis/#tag/Ocr
3
4curl --location --request POST 'https://pdf-services.adobe.io/operation/ocr' \
5--header 'x-api-key: {{Placeholder for client_id}}' \
6--header 'Content-Type: application/json' \
7--header 'Authorization: Bearer {{Placeholder for token}}' \
8--data-raw '{
9    "assetID": "urn:aaid:AS:UE1:23c30ee0-2e4d-46d6-87f2-087832fca718"
10}'

OCR with explicit language

You can perform OCR on files in other languages, including German, French, Danish, and other languages. Refer to OCRSupportedLocale and OCRSupportedType in the API docs for a list of supported OCR locales and OCR types.

As shown in the OcrPDFWithOptions sample, when you make a PDF file searchable, you specify both the locale (language) and the type. There are two types which produce a different result:

One type ensures that text is searchable and selectable, but modifies the original image during the cleanup process (for example, deskews it) before placing an invisible text layer over it. This type removes unwanted artifacts and may result in a more readable document in some scenarios.
The second (EXACT) type, also overlays a searchable text layer over the original image, but in this case, the original image is unchanged. This type produces maximum fidelity to the original image.

Please refer the API usage guide to understand how to use our APIs.

Java

.NET

Node JS

REST API

// Get the samples from https://www.adobe.com/go/pdftoolsapi_java_samples
// Run the sample:
// mvn -f pom.xml exec:java Dexec.mainClass=com.adobe.pdfservices.operation.samples.ocrpdf.OcrPDFWithOptions
 
  public class OcrPDFWithOptions {
    // Initialize the logger.
    private static final Logger LOGGER = LoggerFactory.getLogger(OcrPDFWithOptions.class);
 
    public static void main(String[] args) {
 
        try (InputStream inputStream = Files.newInputStream(new File("src/main/resources/ocrInput.pdf").toPath())) {
            // Initial setup, create credentials instance
            Credentials credentials = new ServicePrincipalCredentials(
                    System.getenv("PDF_SERVICES_CLIENT_ID"),
                    System.getenv("PDF_SERVICES_CLIENT_SECRET"));

            // Creates a PDF Services instance
            PDFServices pdfServices = new PDFServices(credentials);

            // Creates an asset(s) from source file(s) and upload
            Asset asset = pdfServices.upload(inputStream, PDFServicesMediaType.PDF.getMediaType());

            // Create parameters for the job
            OCRParams ocrParams = OCRParams.ocrParamsBuilder()
                    .withOCRLocale(OCRSupportedLocale.EN_US)
                    .withOCRType(OCRSupportedType.SEARCHABLE_IMAGE_EXACT)
                    .build();

            // Creates a new job instance
            OCRJob ocrJob = new OCRJob(asset).setParams(ocrParams);

            // Submit the job and gets the job result
            String location = pdfServices.submit(ocrJob);
            PDFServicesResponse<OCRResult> pdfServicesResponse = pdfServices.getJobResult(location, OCRResult.class);

            // Get content from the resulting asset(s)
            Asset resultAsset = pdfServicesResponse.getResult().getAsset();
            StreamAsset streamAsset = pdfServices.getContent(resultAsset);

            // Creates an output stream and copy stream asset's content to it
            Files.createDirectories(Paths.get("output/"));
            OutputStream outputStream = Files.newOutputStream(new File("output/ocrWithOptionsOutput.pdf").toPath());
            LOGGER.info("Saving asset at output/ocrWithOptionsOutput.pdf");
            IOUtils.copy(streamAsset.getInputStream(), outputStream); 
            outputStream.close();
        } catch (ServiceApiException | IOException | SDKException | ServiceUsageException ex) {
            LOGGER.error("Exception encountered while executing operation", ex);
        }
    }
  }
Copied to your clipboard
1// Get the samples from https://www.adobe.com/go/pdftoolsapi_java_samples
2// Run the sample:
3// mvn -f pom.xml exec:java Dexec.mainClass=com.adobe.pdfservices.operation.samples.ocrpdf.OcrPDFWithOptions
4 
5  public class OcrPDFWithOptions {
6    // Initialize the logger.
7    private static final Logger LOGGER = LoggerFactory.getLogger(OcrPDFWithOptions.class);
8 
9    public static void main(String[] args) {
10 
11        try (InputStream inputStream = Files.newInputStream(new File("src/main/resources/ocrInput.pdf").toPath())) {
12            // Initial setup, create credentials instance
13            Credentials credentials = new ServicePrincipalCredentials(
14                    System.getenv("PDF_SERVICES_CLIENT_ID"),
15                    System.getenv("PDF_SERVICES_CLIENT_SECRET"));
16
17            // Creates a PDF Services instance
18            PDFServices pdfServices = new PDFServices(credentials);
19
20            // Creates an asset(s) from source file(s) and upload
21            Asset asset = pdfServices.upload(inputStream, PDFServicesMediaType.PDF.getMediaType());
22
23            // Create parameters for the job
24            OCRParams ocrParams = OCRParams.ocrParamsBuilder()
25                    .withOCRLocale(OCRSupportedLocale.EN_US)
26                    .withOCRType(OCRSupportedType.SEARCHABLE_IMAGE_EXACT)
27                    .build();
28
29            // Creates a new job instance
30            OCRJob ocrJob = new OCRJob(asset).setParams(ocrParams);
31
32            // Submit the job and gets the job result
33            String location = pdfServices.submit(ocrJob);
34            PDFServicesResponse<OCRResult> pdfServicesResponse = pdfServices.getJobResult(location, OCRResult.class);
35
36            // Get content from the resulting asset(s)
37            Asset resultAsset = pdfServicesResponse.getResult().getAsset();
38            StreamAsset streamAsset = pdfServices.getContent(resultAsset);
39
40            // Creates an output stream and copy stream asset's content to it
41            Files.createDirectories(Paths.get("output/"));
42            OutputStream outputStream = Files.newOutputStream(new File("output/ocrWithOptionsOutput.pdf").toPath());
43            LOGGER.info("Saving asset at output/ocrWithOptionsOutput.pdf");
44            IOUtils.copy(streamAsset.getInputStream(), outputStream); 
45            outputStream.close();
46        } catch (ServiceApiException | IOException | SDKException | ServiceUsageException ex) {
47            LOGGER.error("Exception encountered while executing operation", ex);
48        }
49    }
50  }

// Get the samples from https://www.adobe.com/go/pdftoolsapi_net_samples
// Run the sample:
// cd OcrPDFWithOptions
// dotnet run OcrPDFWithOptions.csproj

 namespace OcrPDFWithOptions
 {
  class Program
  {
    private static readonly ILog log = LogManager.GetLogger(typeof(Program));
    static void Main()
    {
      //Configure the logging
      ConfigureLogging();
      try
      {
          // Initial setup, create credentials instance.
          Credentials credentials = Credentials.ServicePrincipalCredentialsBuilder()
                .WithClientId("PDF_SERVICES_CLIENT_ID")
                .WithClientSecret("PDF_SERVICES_CLIENT_SECRET")
                .Build();
 
        //Create an ExecutionContext using credentials and create a new operation instance.
        ExecutionContext executionContext = ExecutionContext.Create(credentials);
        OCROperation ocrOperation = OCROperation.CreateNew();
 
        // Set operation input from a source file.
        FileRef sourceFileRef = FileRef.CreateFromLocalFile(@"ocrWithOptionsInput.pdf");
        ocrOperation.SetInput(sourceFileRef);
        // Build OCR options from supported locales and OCR-types and set them into the operation
        OCROptions ocrOptions = OCROptions.OCROptionsBuilder()
            .WithOcrLocale(OCRSupportedLocale.EN_US)
            .WithOcrType(OCRSupportedType.SEARCHABLE_IMAGE_EXACT)
            .Build();
        ocrOperation.SetOptions(ocrOptions);
 
        // Execute the operation.
        FileRef result = ocrOperation.Execute(executionContext);
 
        // Save the result to the specified location.
        result.SaveAs(Directory.GetCurrentDirectory() + "/output/ocrOperationWithOptionsOutput.pdf");
      }
      catch (ServiceUsageException ex)
      {
        log.Error("Exception encountered while executing operation", ex);
      }
      // Catch more errors here . . .
    }
 
    static void ConfigureLogging()
    {
      ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
      XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
    }
  }
 }
Copied to your clipboard
1// Get the samples from https://www.adobe.com/go/pdftoolsapi_net_samples
2// Run the sample:
3// cd OcrPDFWithOptions
4// dotnet run OcrPDFWithOptions.csproj
5
6 namespace OcrPDFWithOptions
7 {
8  class Program
9  {
10    private static readonly ILog log = LogManager.GetLogger(typeof(Program));
11    static void Main()
12    {
13      //Configure the logging
14      ConfigureLogging();
15      try
16      {
17          // Initial setup, create credentials instance.
18          Credentials credentials = Credentials.ServicePrincipalCredentialsBuilder()
19                .WithClientId("PDF_SERVICES_CLIENT_ID")
20                .WithClientSecret("PDF_SERVICES_CLIENT_SECRET")
21                .Build();
22 
23        //Create an ExecutionContext using credentials and create a new operation instance.
24        ExecutionContext executionContext = ExecutionContext.Create(credentials);
25        OCROperation ocrOperation = OCROperation.CreateNew();
26 
27        // Set operation input from a source file.
28        FileRef sourceFileRef = FileRef.CreateFromLocalFile(@"ocrWithOptionsInput.pdf");
29        ocrOperation.SetInput(sourceFileRef);
30        // Build OCR options from supported locales and OCR-types and set them into the operation
31        OCROptions ocrOptions = OCROptions.OCROptionsBuilder()
32            .WithOcrLocale(OCRSupportedLocale.EN_US)
33            .WithOcrType(OCRSupportedType.SEARCHABLE_IMAGE_EXACT)
34            .Build();
35        ocrOperation.SetOptions(ocrOptions);
36 
37        // Execute the operation.
38        FileRef result = ocrOperation.Execute(executionContext);
39 
40        // Save the result to the specified location.
41        result.SaveAs(Directory.GetCurrentDirectory() + "/output/ocrOperationWithOptionsOutput.pdf");
42      }
43      catch (ServiceUsageException ex)
44      {
45        log.Error("Exception encountered while executing operation", ex);
46      }
47      // Catch more errors here . . .
48    }
49 
50    static void ConfigureLogging()
51    {
52      ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
53      XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
54    }
55  }
56 }

// Get the samples from http://www.adobe.com/go/pdftoolsapi_node_sample
// Run the sample:
// node src/ocr/ocr-pdf-with-options.js

const {
    ServicePrincipalCredentials,
    PDFServices,
    MimeType,
    OCRJob,
    OCRParams,
    OCRSupportedLocale,
    OCRSupportedType,
    OCRResult,
    SDKError,
    ServiceUsageError,
    ServiceApiError
} = require("@adobe/pdfservices-node-sdk");
const fs = require("fs");

(async () => {
    let readStream;
    try {
        // Initial setup, create credentials instance
        const credentials = new ServicePrincipalCredentials({
            clientId: process.env.PDF_SERVICES_CLIENT_ID,
            clientSecret: process.env.PDF_SERVICES_CLIENT_SECRET
        });

        // Creates a PDF Services instance
        const pdfServices = new PDFServices({credentials});

        // Creates an asset(s) from source file(s) and upload
        readStream = fs.createReadStream("./ocrInput.pdf");
        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

        // Create parameters for the job
        const params = new OCRParams({
            ocrLocale: OCRSupportedLocale.EN_US,
            ocrType: OCRSupportedType.SEARCHABLE_IMAGE_EXACT
        });

        // Creates a new job instance
        const job = new OCRJob({inputAsset, params});

        // Submit the job and get the job result
        const pollingURL = await pdfServices.submit({job});
        const pdfServicesResponse = await pdfServices.getJobResult({
            pollingURL,
            resultType: OCRResult
        });

        // Get content from the resulting asset(s)
        const resultAsset = pdfServicesResponse.result.asset;
        const streamAsset = await pdfServices.getContent({asset: resultAsset});

        // Creates a write stream and copy stream asset's content to it
        const outputFilePath = "./ocrWithOptionsOutput.pdf";
        console.log(`Saving asset at ${outputFilePath}`);

        const writeStream = fs.createWriteStream(outputFilePath);
        streamAsset.readStream.pipe(writeStream);
    } catch (err) {
        if (err instanceof SDKError || err instanceof ServiceUsageError || err instanceof ServiceApiError) {
            console.log("Exception encountered while executing operation", err);
        } else {
            console.log("Exception encountered while executing operation", err);
        }
    } finally {
        readStream?.destroy();
    }
})();
Copied to your clipboard
1// Get the samples from http://www.adobe.com/go/pdftoolsapi_node_sample
2// Run the sample:
3// node src/ocr/ocr-pdf-with-options.js
4
5const {
6    ServicePrincipalCredentials,
7    PDFServices,
8    MimeType,
9    OCRJob,
10    OCRParams,
11    OCRSupportedLocale,
12    OCRSupportedType,
13    OCRResult,
14    SDKError,
15    ServiceUsageError,
16    ServiceApiError
17} = require("@adobe/pdfservices-node-sdk");
18const fs = require("fs");
19
20(async () => {
21    let readStream;
22    try {
23        // Initial setup, create credentials instance
24        const credentials = new ServicePrincipalCredentials({
25            clientId: process.env.PDF_SERVICES_CLIENT_ID,
26            clientSecret: process.env.PDF_SERVICES_CLIENT_SECRET
27        });
28
29        // Creates a PDF Services instance
30        const pdfServices = new PDFServices({credentials});
31
32        // Creates an asset(s) from source file(s) and upload
33        readStream = fs.createReadStream("./ocrInput.pdf");
34        const inputAsset = await pdfServices.upload({
35            readStream,
36            mimeType: MimeType.PDF
37        });
38
39        // Create parameters for the job
40        const params = new OCRParams({
41            ocrLocale: OCRSupportedLocale.EN_US,
42            ocrType: OCRSupportedType.SEARCHABLE_IMAGE_EXACT
43        });
44
45        // Creates a new job instance
46        const job = new OCRJob({inputAsset, params});
47
48        // Submit the job and get the job result
49        const pollingURL = await pdfServices.submit({job});
50        const pdfServicesResponse = await pdfServices.getJobResult({
51            pollingURL,
52            resultType: OCRResult
53        });
54
55        // Get content from the resulting asset(s)
56        const resultAsset = pdfServicesResponse.result.asset;
57        const streamAsset = await pdfServices.getContent({asset: resultAsset});
58
59        // Creates a write stream and copy stream asset's content to it
60        const outputFilePath = "./ocrWithOptionsOutput.pdf";
61        console.log(`Saving asset at ${outputFilePath}`);
62
63        const writeStream = fs.createWriteStream(outputFilePath);
64        streamAsset.readStream.pipe(writeStream);
65    } catch (err) {
66        if (err instanceof SDKError || err instanceof ServiceUsageError || err instanceof ServiceApiError) {
67            console.log("Exception encountered while executing operation", err);
68        } else {
69            console.log("Exception encountered while executing operation", err);
70        }
71    } finally {
72        readStream?.destroy();
73    }
74})();

// Please refer our REST API docs for more information 
// https://developer.adobe.com/document-services/docs/apis/#tag/Ocr

curl --location --request POST 'https://pdf-services.adobe.io/operation/ocr' \
--header 'x-api-key: {{Placeholder for client_id}}' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {{Placeholder for token}}' \
--data-raw '{
    "assetID": "ce8fe9da-99f2-4d01-999e-42b9ce22ec5f",
    "ocrLang": "en-US"
}'
Copied to your clipboard
1// Please refer our REST API docs for more information 
2// https://developer.adobe.com/document-services/docs/apis/#tag/Ocr
3
4curl --location --request POST 'https://pdf-services.adobe.io/operation/ocr' \
5--header 'x-api-key: {{Placeholder for client_id}}' \
6--header 'Content-Type: application/json' \
7--header 'Authorization: Bearer {{Placeholder for token}}' \
8--data-raw '{
9    "assetID": "ce8fe9da-99f2-4d01-999e-42b9ce22ec5f",
10    "ocrLang": "en-US"
11}'

Combine PDF Files

Compress PDFs

Last updated 4/9/2024

Was this helpful?

Yes

OCR PDF

REST API.css-83mclq{margin-left:var(--spectrum-global-dimension-size-100);}

Text recognition (OCR)

OCR with explicit language

REST API