PDF Accessibility Auto-Tag API

Copy
// Get the samples from https://github.com/adobe/pdfservices-java-sdk-samples
// Run the sample:
// mvn -f pom.xml exec:java -Dexec.mainClass=com.adobe.pdfservices.operation.samples.autotagpdf.AutotagPDF

public class AutotagPDF {
    // Initialize the logger.
    private static final Logger LOGGER = LoggerFactory.getLogger(AutotagPDF.class);

    public static void main(String[] args) {

        try (InputStream inputStream = Files.newInputStream(new File("src/main/resources/autotagPDFInput.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
            AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset);
        
            // Submit the job and gets the job result
            String location = pdfServices.submit(autotagPDFJob);
            PDFServicesResponse<AutotagPDFResult> pdfServicesResponse = pdfServices.getJobResult(location, AutotagPDFResult.class);
        
            // Get content from the resulting asset(s)
            Asset resultAsset = pdfServicesResponse.getResult().getTaggedPDF();
            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/autotagPDFOutput.pdf").toPath());
            LOGGER.info("Saving asset at output/autotagPDFOutput.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
// Get the samples from https://github.com/adobe/pdfservices-java-sdk-samples
// Run the sample:
// mvn -f pom.xml exec:java -Dexec.mainClass=com.adobe.pdfservices.operation.samples.autotagpdf.AutotagPDF

public class AutotagPDF {
    // Initialize the logger.
    private static final Logger LOGGER = LoggerFactory.getLogger(AutotagPDF.class);

    public static void main(String[] args) {

        try (InputStream inputStream = Files.newInputStream(new File("src/main/resources/autotagPDFInput.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
            AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset);
        
            // Submit the job and gets the job result
            String location = pdfServices.submit(autotagPDFJob);
            PDFServicesResponse<AutotagPDFResult> pdfServicesResponse = pdfServices.getJobResult(location, AutotagPDFResult.class);
        
            // Get content from the resulting asset(s)
            Asset resultAsset = pdfServicesResponse.getResult().getTaggedPDF();
            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/autotagPDFOutput.pdf").toPath());
            LOGGER.info("Saving asset at output/autotagPDFOutput.pdf");
            IOUtils.copy(streamAsset.getInputStream(), outputStream);
            outputStream.close();
        } catch (ServiceApiException | IOException | SDKException | ServiceUsageException ex) {
            LOGGER.error("Exception encountered while executing operation", ex);
        }
    }

Copy
// Get the samples from https://github.com/adobe/PDFServices.NET.SDK.Samples
// Run the sample:
// cd AutotagPDF/
// dotnet run AutotagPDF.csproj


namespace AutotagPDF
{
    class Program
    {
        private static readonly ILog log = LogManager.GetLogger(typeof(Program));

        static void Main()
        {
            // Configure the logging
            ConfigureLogging();
            try
            {
                // Initial setup, create credentials instance
                ICredentials credentials = new ServicePrincipalCredentials(
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_ID"),
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_SECRET"));

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

                // Creates an asset(s) from source file(s) and upload
                using Stream inputStream = File.OpenRead(@"autotagPdfInput.pdf");
                IAsset asset = pdfServices.Upload(inputStream, PDFServicesMediaType.PDF.GetMIMETypeValue());

                // Creates a new job instance
                AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset);

                // Submits the job and gets the job result
                String location = pdfServices.Submit(autotagPDFJob);
                PDFServicesResponse<AutotagPDFResult> pdfServicesResponse =
                    pdfServices.GetJobResult<AutotagPDFResult>(location, typeof(AutotagPDFResult));

                // Get content from the resulting asset(s)
                IAsset resultAsset = pdfServicesResponse.Result.TaggedPDF;
                StreamAsset streamAsset = pdfServices.GetContent(resultAsset);

                // Creating output streams and copying stream asset's content to it
                String outputFilePath = "/output/autotagPDFOutput.pdf";
                new FileInfo(Directory.GetCurrentDirectory() + outputFilePath).Directory.Create();
                Stream outputStream = File.OpenWrite(Directory.GetCurrentDirectory() + outputFilePath);
                streamAsset.Stream.CopyTo(outputStream);
                outputStream.Close();
            }
            catch (ServiceUsageException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (ServiceApiException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (SDKException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (IOException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (Exception ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
        }

        static void ConfigureLogging()
        {
            ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
            XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
        }
    }
}
Copied to your clipboard
// Get the samples from https://github.com/adobe/PDFServices.NET.SDK.Samples
// Run the sample:
// cd AutotagPDF/
// dotnet run AutotagPDF.csproj


namespace AutotagPDF
{
    class Program
    {
        private static readonly ILog log = LogManager.GetLogger(typeof(Program));

        static void Main()
        {
            // Configure the logging
            ConfigureLogging();
            try
            {
                // Initial setup, create credentials instance
                ICredentials credentials = new ServicePrincipalCredentials(
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_ID"),
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_SECRET"));

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

                // Creates an asset(s) from source file(s) and upload
                using Stream inputStream = File.OpenRead(@"autotagPdfInput.pdf");
                IAsset asset = pdfServices.Upload(inputStream, PDFServicesMediaType.PDF.GetMIMETypeValue());

                // Creates a new job instance
                AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset);

                // Submits the job and gets the job result
                String location = pdfServices.Submit(autotagPDFJob);
                PDFServicesResponse<AutotagPDFResult> pdfServicesResponse =
                    pdfServices.GetJobResult<AutotagPDFResult>(location, typeof(AutotagPDFResult));

                // Get content from the resulting asset(s)
                IAsset resultAsset = pdfServicesResponse.Result.TaggedPDF;
                StreamAsset streamAsset = pdfServices.GetContent(resultAsset);

                // Creating output streams and copying stream asset's content to it
                String outputFilePath = "/output/autotagPDFOutput.pdf";
                new FileInfo(Directory.GetCurrentDirectory() + outputFilePath).Directory.Create();
                Stream outputStream = File.OpenWrite(Directory.GetCurrentDirectory() + outputFilePath);
                streamAsset.Stream.CopyTo(outputStream);
                outputStream.Close();
            }
            catch (ServiceUsageException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (ServiceApiException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (SDKException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (IOException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (Exception ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
        }

        static void ConfigureLogging()
        {
            ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
            XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
        }
    }
}

Copy
// Get the samples from https://github.com/adobe/pdfservices-node-sdk-samples
// Run the sample:
// node src/autotagpdf/autotag-pdf.js

const {
    ServicePrincipalCredentials,
    PDFServices,
    MimeType,
    AutotagPDFJob,
    AutotagPDFResult,
    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("./autotagPDFInput.pdf");
        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

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

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

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

        // Creates an output stream and copy stream asset's content to it
        const outputFilePath = "./autotag-tagged.pdf";
        console.log(`Saving asset at ${outputFilePath}`);

        let 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
// Get the samples from https://github.com/adobe/pdfservices-node-sdk-samples
// Run the sample:
// node src/autotagpdf/autotag-pdf.js

const {
    ServicePrincipalCredentials,
    PDFServices,
    MimeType,
    AutotagPDFJob,
    AutotagPDFResult,
    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("./autotagPDFInput.pdf");
        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

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

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

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

        // Creates an output stream and copy stream asset's content to it
        const outputFilePath = "./autotag-tagged.pdf";
        console.log(`Saving asset at ${outputFilePath}`);

        let 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();
    }
})();

Copy
# Get the samples from https://github.com/adobe/pdfservices-python-sdk-samples
# Run the sample:
# python src/autotagpdf/autotag_pdf.py

# Initialize the logger
logging.basicConfig(level=logging.INFO)

class AutoTagPDF:
    def __init__(self):
        try:
            file = open('autotagPDFInput.pdf', 'rb')
            input_stream = file.read()
            file.close()

            # Initial setup, create credentials instance
            credentials = ServicePrincipalCredentials(
                client_id=os.getenv('PDF_SERVICES_CLIENT_ID'),
                client_secret=os.getenv('PDF_SERVICES_CLIENT_SECRET')
            )

            # Creates a PDF Services instance
            pdf_services = PDFServices(credentials=credentials)

            # Creates an asset(s) from source file(s) and upload
            input_asset = pdf_services.upload(input_stream=input_stream,
                                              mime_type=PDFServicesMediaType.PDF)

            # Creates a new job instance
            autotag_pdf_job = AutotagPDFJob(input_asset)

            # Submit the job and gets the job result
            location = pdf_services.submit(autotag_pdf_job)
            pdf_services_response = pdf_services.get_job_result(location, AutotagPDFResult)

            # Get content from the resulting asset(s)
            result_asset: CloudAsset = pdf_services_response.get_result().get_tagged_pdf()
            stream_asset: StreamAsset = pdf_services.get_content(result_asset)

            # Creates an output stream and copy stream asset's content to it
            output_file_path = 'autoTagPDFOutput.pdf'
            with open(output_file_path, "wb") as file:
                file.write(stream_asset.get_input_stream())

        except (ServiceApiException, ServiceUsageException, SdkException) as e:
            logging.exception(f'Exception encountered while executing operation: {e}')


if __name__ == "__main__":
    AutoTagPDF()

Copied to your clipboard
# Get the samples from https://github.com/adobe/pdfservices-python-sdk-samples
# Run the sample:
# python src/autotagpdf/autotag_pdf.py

# Initialize the logger
logging.basicConfig(level=logging.INFO)

class AutoTagPDF:
    def __init__(self):
        try:
            file = open('autotagPDFInput.pdf', 'rb')
            input_stream = file.read()
            file.close()

            # Initial setup, create credentials instance
            credentials = ServicePrincipalCredentials(
                client_id=os.getenv('PDF_SERVICES_CLIENT_ID'),
                client_secret=os.getenv('PDF_SERVICES_CLIENT_SECRET')
            )

            # Creates a PDF Services instance
            pdf_services = PDFServices(credentials=credentials)

            # Creates an asset(s) from source file(s) and upload
            input_asset = pdf_services.upload(input_stream=input_stream,
                                              mime_type=PDFServicesMediaType.PDF)

            # Creates a new job instance
            autotag_pdf_job = AutotagPDFJob(input_asset)

            # Submit the job and gets the job result
            location = pdf_services.submit(autotag_pdf_job)
            pdf_services_response = pdf_services.get_job_result(location, AutotagPDFResult)

            # Get content from the resulting asset(s)
            result_asset: CloudAsset = pdf_services_response.get_result().get_tagged_pdf()
            stream_asset: StreamAsset = pdf_services.get_content(result_asset)

            # Creates an output stream and copy stream asset's content to it
            output_file_path = 'autoTagPDFOutput.pdf'
            with open(output_file_path, "wb") as file:
                file.write(stream_asset.get_input_stream())

        except (ServiceApiException, ServiceUsageException, SdkException) as e:
            logging.exception(f'Exception encountered while executing operation: {e}')


if __name__ == "__main__":
    AutoTagPDF()

Copy
// Please refer our REST API docs for more information 
// https://developer.adobe.com/document-services/docs/apis/#tag/PDF-Accessibility-Auto-Tag

curl --location --request POST 'https://pdf-services.adobe.io/operation/autotag' \
--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
// Please refer our REST API docs for more information 
// https://developer.adobe.com/document-services/docs/apis/#tag/PDF-Accessibility-Auto-Tag

curl --location --request POST 'https://pdf-services.adobe.io/operation/autotag' \
--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"
}'

Copy
// Get the samples from https://github.com/adobe/pdfservices-java-sdk-samples
// Run the sample:
// mvn -f pom.xml exec:java -Dexec.mainClass=com.adobe.pdfservices.operation.samples.autotagpdf.AutotagPDFParamaterised

public class AutotagPDFParameterised {

    private static final org.slf4j.Logger LOGGER = LoggerFactory.getLogger(AutotagPDFParameterised.class);

    public static void main(String[] args) {
        LOGGER.info("--input " + getInputFilePathFromCmdArgs(args));
        LOGGER.info("--output " + getOutputFilePathFromCmdArgs(args));
        LOGGER.info("--report " + getGenerateReportFromCmdArgs(args));
        LOGGER.info("--shift_headings " + getShiftHeadingsFromCmdArgs(args));
        
        try (InputStream inputStream = Files.newInputStream(new File(getInputFilePathFromCmdArgs(args)).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
            AutotagPDFParams autotagPDFParams = getOptionsFromCmdArgs(args);
        
            // Creates a new job instance
            AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset)
                .setParams(autotagPDFParams);
        
            // Submit the job and gets the job result
            String location = pdfServices.submit(autotagPDFJob);
            PDFServicesResponse<AutotagPDFResult> pdfServicesResponse = pdfServices.getJobResult(location, AutotagPDFResult.class);
        
            // Get content from the resulting asset(s)
            Asset resultAsset = pdfServicesResponse.getResult().getTaggedPDF();
            Asset resultAssetReport = pdfServicesResponse.getResult().getReport();
            StreamAsset streamAsset = pdfServices.getContent(resultAsset);
            StreamAsset streamAssetReport = (autotagPDFParams != null && autotagPDFParams.isGenerateReport()) ?
                pdfServices.getContent(resultAssetReport) : null;
        
            // Creating output streams and copying stream assets' content to it
            Files.createDirectories(Paths.get("output/"));
            String outputPath = getOutputFilePathFromCmdArgs(args);
            OutputStream outputStream = Files.newOutputStream(new File(outputPath + "autotagPDFInput-tagged.pdf").toPath());
            LOGGER.info("Saving asset at " + outputPath + "autotagPDFInput-tagged.pdf");
            IOUtils.copy(streamAsset.getInputStream(), outputStream);
            if(streamAssetReport != null) {
                OutputStream outputStreamReport = Files.newOutputStream(new File(outputPath + "autotagPDFInput-report.xlsx").toPath());
                LOGGER.info("Saving asset at " + outputPath + "autotagPDFInput-report.xlsx");
                IOUtils.copy(streamAssetReport.getInputStream(), outputStreamReport);
                outputStreamReport.close();
            }
        } catch (ServiceApiException | IOException | SDKException | ServiceUsageException e) {
            LOGGER.error("Exception encountered while executing operation", e);
        }
    }

    private static AutotagPDFParams getOptionsFromCmdArgs(String[] args) {
        Boolean generateReport = getGenerateReportFromCmdArgs(args);
        Boolean shiftHeadings = getShiftHeadingsFromCmdArgs(args);
        AutotagPDFParams.Builder autotagPDFParamsBuilder = AutotagPDFParams.autotagPDFParamsBuilder();
    
        if (generateReport)
            autotagPDFParamsBuilder.generateReport();
        if (shiftHeadings)
            autotagPDFParamsBuilder.shiftHeadings();
    
        return autotagPDFParamsBuilder.build();
    }
    
    private static Boolean getShiftHeadingsFromCmdArgs(String[] args) {
        return Arrays.asList(args).contains("--shift_headings");
    }
    
    private static Boolean getGenerateReportFromCmdArgs(String[] args) {
        return Arrays.asList(args).contains("--report");
    }
    
    private static String getInputFilePathFromCmdArgs(String[] args) {
        String inputFilePath = "src/main/resources/autotagPDFInput.pdf";
        int inputFilePathIndex = Arrays.asList(args).indexOf("--input");
        if (inputFilePathIndex >= 0 && inputFilePathIndex < args.length - 1) {
            inputFilePath = args[inputFilePathIndex + 1];
        } else
            LOGGER.info("input file not specified, using default value : autotagPDFInput.pdf");
    
        return inputFilePath;
    }
    
    private static String getOutputFilePathFromCmdArgs(String[] args) {
        String outputFilePath = "output/AutotagPDFParameterised/";
        int outputFilePathIndex = Arrays.asList(args).indexOf("--output");
        if (outputFilePathIndex >= 0 && outputFilePathIndex < args.length - 1) {
            outputFilePath = args[outputFilePathIndex + 1];
        } else
            LOGGER.info("output path not specified, using default value : " + outputFilePath);
    
        return outputFilePath;
    }
}

Copied to your clipboard
// Get the samples from https://github.com/adobe/pdfservices-java-sdk-samples
// Run the sample:
// mvn -f pom.xml exec:java -Dexec.mainClass=com.adobe.pdfservices.operation.samples.autotagpdf.AutotagPDFParamaterised

public class AutotagPDFParameterised {

    private static final org.slf4j.Logger LOGGER = LoggerFactory.getLogger(AutotagPDFParameterised.class);

    public static void main(String[] args) {
        LOGGER.info("--input " + getInputFilePathFromCmdArgs(args));
        LOGGER.info("--output " + getOutputFilePathFromCmdArgs(args));
        LOGGER.info("--report " + getGenerateReportFromCmdArgs(args));
        LOGGER.info("--shift_headings " + getShiftHeadingsFromCmdArgs(args));
        
        try (InputStream inputStream = Files.newInputStream(new File(getInputFilePathFromCmdArgs(args)).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
            AutotagPDFParams autotagPDFParams = getOptionsFromCmdArgs(args);
        
            // Creates a new job instance
            AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset)
                .setParams(autotagPDFParams);
        
            // Submit the job and gets the job result
            String location = pdfServices.submit(autotagPDFJob);
            PDFServicesResponse<AutotagPDFResult> pdfServicesResponse = pdfServices.getJobResult(location, AutotagPDFResult.class);
        
            // Get content from the resulting asset(s)
            Asset resultAsset = pdfServicesResponse.getResult().getTaggedPDF();
            Asset resultAssetReport = pdfServicesResponse.getResult().getReport();
            StreamAsset streamAsset = pdfServices.getContent(resultAsset);
            StreamAsset streamAssetReport = (autotagPDFParams != null && autotagPDFParams.isGenerateReport()) ?
                pdfServices.getContent(resultAssetReport) : null;
        
            // Creating output streams and copying stream assets' content to it
            Files.createDirectories(Paths.get("output/"));
            String outputPath = getOutputFilePathFromCmdArgs(args);
            OutputStream outputStream = Files.newOutputStream(new File(outputPath + "autotagPDFInput-tagged.pdf").toPath());
            LOGGER.info("Saving asset at " + outputPath + "autotagPDFInput-tagged.pdf");
            IOUtils.copy(streamAsset.getInputStream(), outputStream);
            if(streamAssetReport != null) {
                OutputStream outputStreamReport = Files.newOutputStream(new File(outputPath + "autotagPDFInput-report.xlsx").toPath());
                LOGGER.info("Saving asset at " + outputPath + "autotagPDFInput-report.xlsx");
                IOUtils.copy(streamAssetReport.getInputStream(), outputStreamReport);
                outputStreamReport.close();
            }
        } catch (ServiceApiException | IOException | SDKException | ServiceUsageException e) {
            LOGGER.error("Exception encountered while executing operation", e);
        }
    }

    private static AutotagPDFParams getOptionsFromCmdArgs(String[] args) {
        Boolean generateReport = getGenerateReportFromCmdArgs(args);
        Boolean shiftHeadings = getShiftHeadingsFromCmdArgs(args);
        AutotagPDFParams.Builder autotagPDFParamsBuilder = AutotagPDFParams.autotagPDFParamsBuilder();
    
        if (generateReport)
            autotagPDFParamsBuilder.generateReport();
        if (shiftHeadings)
            autotagPDFParamsBuilder.shiftHeadings();
    
        return autotagPDFParamsBuilder.build();
    }
    
    private static Boolean getShiftHeadingsFromCmdArgs(String[] args) {
        return Arrays.asList(args).contains("--shift_headings");
    }
    
    private static Boolean getGenerateReportFromCmdArgs(String[] args) {
        return Arrays.asList(args).contains("--report");
    }
    
    private static String getInputFilePathFromCmdArgs(String[] args) {
        String inputFilePath = "src/main/resources/autotagPDFInput.pdf";
        int inputFilePathIndex = Arrays.asList(args).indexOf("--input");
        if (inputFilePathIndex >= 0 && inputFilePathIndex < args.length - 1) {
            inputFilePath = args[inputFilePathIndex + 1];
        } else
            LOGGER.info("input file not specified, using default value : autotagPDFInput.pdf");
    
        return inputFilePath;
    }
    
    private static String getOutputFilePathFromCmdArgs(String[] args) {
        String outputFilePath = "output/AutotagPDFParameterised/";
        int outputFilePathIndex = Arrays.asList(args).indexOf("--output");
        if (outputFilePathIndex >= 0 && outputFilePathIndex < args.length - 1) {
            outputFilePath = args[outputFilePathIndex + 1];
        } else
            LOGGER.info("output path not specified, using default value : " + outputFilePath);
    
        return outputFilePath;
    }
}

Copy
// Get the samples from https://github.com/adobe/PDFServices.NET.SDK.Samples
// Run the sample:
// cd AutotagPDFParameterised/
// dotnet run AutotagPDFParameterised.csproj

namespace AutotagPDFParameterised
{
    class Program
    {
        private static readonly ILog log = LogManager.GetLogger(typeof(Program));

        private static AutotagPDFParams GetParamsFromCmdArgs(String[] args)
        {
            Boolean generateReport = GetGenerateReportFromCmdArgs(args);
            Boolean shiftHeadings = GetShiftHeadingsFromCmdArgs(args);

            AutotagPDFParams.Builder builder = AutotagPDFParams.AutotagPDFParamsBuilder();

            if (generateReport) builder.GenerateReport();
            if (shiftHeadings) builder.ShiftHeadings();

            return builder.Build();
        }

        private static Boolean GetShiftHeadingsFromCmdArgs(String[] args)
        {
            return Array.Exists(args, element => element == "--shift_headings");
        }

        private static Boolean GetGenerateReportFromCmdArgs(String[] args)
        {
            return Array.Exists(args, element => element == "--report");
        }

        private static String GetInputFilePathFromCmdArgs(String[] args)
        {
            String inputFilePath = @"autotagPdfInput.pdf";
            int inputFilePathIndex = Array.IndexOf(args, "--input");
            if (inputFilePathIndex >= 0 && inputFilePathIndex < args.Length - 1)
            {
                inputFilePath = args[inputFilePathIndex + 1];
            }
            else
                log.Info("input file not specified, using default value : autotagPdfInput.pdf");

            return inputFilePath;
        }

        private static String GetOutputFilePathFromCmdArgs(String[] args)
        {
            String outputFilePath = Directory.GetCurrentDirectory() + "/output/";
            int outputFilePathIndex = Array.IndexOf(args, "--output");
            if (outputFilePathIndex >= 0 && outputFilePathIndex < args.Length - 1)
            {
                outputFilePath = args[outputFilePathIndex + 1];
            }
            else
                log.Info("output path not specified, using default value : /output/");

            return outputFilePath;
        }

        static void Main(String[] args)
        {
            // Configure the logging
            ConfigureLogging();

            log.Info("--input " + GetInputFilePathFromCmdArgs(args));
            log.Info("--output " + GetOutputFilePathFromCmdArgs(args));
            log.Info("--report " + GetGenerateReportFromCmdArgs(args));
            log.Info("--shift_headings " + GetShiftHeadingsFromCmdArgs(args));

            try
            {
                // Initial setup, create credentials instance
                ICredentials credentials = new ServicePrincipalCredentials(
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_ID"),
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_SECRET"));

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

                // Creates an asset(s) from source file(s) and upload
                using Stream inputStream = File.OpenRead(GetInputFilePathFromCmdArgs(args));
                IAsset asset = pdfServices.Upload(inputStream, PDFServicesMediaType.PDF.GetMIMETypeValue());

                // Create parameters for the job
                AutotagPDFParams autotagPDFParams = GetParamsFromCmdArgs(args);

                // Creates a new job instance
                AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset).SetParams(autotagPDFParams);

                // Submits the job and gets the job result
                String location = pdfServices.Submit(autotagPDFJob);
                PDFServicesResponse<AutotagPDFResult> pdfServicesResponse =
                    pdfServices.GetJobResult<AutotagPDFResult>(location, typeof(AutotagPDFResult));

                // Get content from the resulting asset(s)
                IAsset resultAsset = pdfServicesResponse.Result.TaggedPDF;
                StreamAsset streamAsset = pdfServices.GetContent(resultAsset);

                // Creating output streams and copying stream asset's content to it
                String outputPath = GetOutputFilePathFromCmdArgs(args);
                Stream outputStream = File.OpenWrite(outputPath + "autotagPDFInput-tagged.pdf");
                streamAsset.Stream.CopyTo(outputStream);
                outputStream.Close();

                if (autotagPDFParams != null && autotagPDFParams.IsGenerateReport)
                {
                    // Get content from the resulting asset(s)
                    IAsset resultAssetReport = pdfServicesResponse.Result.Report;
                    StreamAsset streamAssetReport = pdfServices.GetContent(resultAssetReport);

                    // Creating output streams and copying stream asset's content to it
                    Stream outputStreamReport =
                        File.OpenWrite(outputPath + "autotagPDFInput-report.xlsx");
                    streamAssetReport.Stream.CopyTo(outputStreamReport);
                    outputStreamReport.Close();
                }
            }
            catch (ServiceUsageException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (ServiceApiException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (SDKException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (IOException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (Exception ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
        }

        static void ConfigureLogging()
        {
            ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
            XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
        }
    }
}
Copied to your clipboard

// Get the samples from https://github.com/adobe/PDFServices.NET.SDK.Samples
// Run the sample:
// cd AutotagPDFParameterised/
// dotnet run AutotagPDFParameterised.csproj

namespace AutotagPDFParameterised
{
    class Program
    {
        private static readonly ILog log = LogManager.GetLogger(typeof(Program));

        private static AutotagPDFParams GetParamsFromCmdArgs(String[] args)
        {
            Boolean generateReport = GetGenerateReportFromCmdArgs(args);
            Boolean shiftHeadings = GetShiftHeadingsFromCmdArgs(args);

            AutotagPDFParams.Builder builder = AutotagPDFParams.AutotagPDFParamsBuilder();

            if (generateReport) builder.GenerateReport();
            if (shiftHeadings) builder.ShiftHeadings();

            return builder.Build();
        }

        private static Boolean GetShiftHeadingsFromCmdArgs(String[] args)
        {
            return Array.Exists(args, element => element == "--shift_headings");
        }

        private static Boolean GetGenerateReportFromCmdArgs(String[] args)
        {
            return Array.Exists(args, element => element == "--report");
        }

        private static String GetInputFilePathFromCmdArgs(String[] args)
        {
            String inputFilePath = @"autotagPdfInput.pdf";
            int inputFilePathIndex = Array.IndexOf(args, "--input");
            if (inputFilePathIndex >= 0 && inputFilePathIndex < args.Length - 1)
            {
                inputFilePath = args[inputFilePathIndex + 1];
            }
            else
                log.Info("input file not specified, using default value : autotagPdfInput.pdf");

            return inputFilePath;
        }

        private static String GetOutputFilePathFromCmdArgs(String[] args)
        {
            String outputFilePath = Directory.GetCurrentDirectory() + "/output/";
            int outputFilePathIndex = Array.IndexOf(args, "--output");
            if (outputFilePathIndex >= 0 && outputFilePathIndex < args.Length - 1)
            {
                outputFilePath = args[outputFilePathIndex + 1];
            }
            else
                log.Info("output path not specified, using default value : /output/");

            return outputFilePath;
        }

        static void Main(String[] args)
        {
            // Configure the logging
            ConfigureLogging();

            log.Info("--input " + GetInputFilePathFromCmdArgs(args));
            log.Info("--output " + GetOutputFilePathFromCmdArgs(args));
            log.Info("--report " + GetGenerateReportFromCmdArgs(args));
            log.Info("--shift_headings " + GetShiftHeadingsFromCmdArgs(args));

            try
            {
                // Initial setup, create credentials instance
                ICredentials credentials = new ServicePrincipalCredentials(
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_ID"),
                    Environment.GetEnvironmentVariable("PDF_SERVICES_CLIENT_SECRET"));

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

                // Creates an asset(s) from source file(s) and upload
                using Stream inputStream = File.OpenRead(GetInputFilePathFromCmdArgs(args));
                IAsset asset = pdfServices.Upload(inputStream, PDFServicesMediaType.PDF.GetMIMETypeValue());

                // Create parameters for the job
                AutotagPDFParams autotagPDFParams = GetParamsFromCmdArgs(args);

                // Creates a new job instance
                AutotagPDFJob autotagPDFJob = new AutotagPDFJob(asset).SetParams(autotagPDFParams);

                // Submits the job and gets the job result
                String location = pdfServices.Submit(autotagPDFJob);
                PDFServicesResponse<AutotagPDFResult> pdfServicesResponse =
                    pdfServices.GetJobResult<AutotagPDFResult>(location, typeof(AutotagPDFResult));

                // Get content from the resulting asset(s)
                IAsset resultAsset = pdfServicesResponse.Result.TaggedPDF;
                StreamAsset streamAsset = pdfServices.GetContent(resultAsset);

                // Creating output streams and copying stream asset's content to it
                String outputPath = GetOutputFilePathFromCmdArgs(args);
                Stream outputStream = File.OpenWrite(outputPath + "autotagPDFInput-tagged.pdf");
                streamAsset.Stream.CopyTo(outputStream);
                outputStream.Close();

                if (autotagPDFParams != null && autotagPDFParams.IsGenerateReport)
                {
                    // Get content from the resulting asset(s)
                    IAsset resultAssetReport = pdfServicesResponse.Result.Report;
                    StreamAsset streamAssetReport = pdfServices.GetContent(resultAssetReport);

                    // Creating output streams and copying stream asset's content to it
                    Stream outputStreamReport =
                        File.OpenWrite(outputPath + "autotagPDFInput-report.xlsx");
                    streamAssetReport.Stream.CopyTo(outputStreamReport);
                    outputStreamReport.Close();
                }
            }
            catch (ServiceUsageException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (ServiceApiException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (SDKException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (IOException ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
            catch (Exception ex)
            {
                log.Error("Exception encountered while executing operation", ex);
            }
        }

        static void ConfigureLogging()
        {
            ILoggerRepository logRepository = LogManager.GetRepository(Assembly.GetEntryAssembly());
            XmlConfigurator.Configure(logRepository, new FileInfo("log4net.config"));
        }
    }
}

Copy
// Get the samples from https://github.com/adobe/pdfservices-node-sdk-samples
// Run the sample:
// node src/autotag/autoag-pdf-parameterised.js

const {
    ServicePrincipalCredentials,
    PDFServices,
    MimeType,
    AutotagPDFParams,
    AutotagPDFJob,
    AutotagPDFResult,
    SDKError,
    ServiceUsageError,
    ServiceApiError
} = require("@adobe/pdfservices-node-sdk");
const fs = require("fs");
const args = process.argv;

(async () => {
    let readStream;
    try {
        console.log("--input " + getInputFilePathFromCmdArgs(args));
        console.log("--output " + getOutputFilePathFromCmdArgs(args));
        console.log("--report " + getGenerateReportFromCmdArgs(args));
        console.log("--shift_headings " + getShiftHeadingsFromCmdArgs(args));

        // 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(getInputFilePathFromCmdArgs(args));
        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

        // Create parameters for the job
        const params = new AutotagPDFParams({
            generateReport: getGenerateReportFromCmdArgs(args),
            shiftHeadings: getShiftHeadingsFromCmdArgs(args)
        });

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

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

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

        // Creates an output stream and copy stream asset's content to it
        const outputPath = getOutputFilePathFromCmdArgs(args);
        const outputFilePath = outputPath + "autotagPDFInput-tagged.pdf";
        console.log(`Saving asset at ${outputFilePath}`);

        const writeStream = fs.createWriteStream(outputFilePath);
        streamAsset.readStream.pipe(writeStream);
        if (resultAssetReport) {
            const outputFileReportPath = outputPath + "autotagPDFInput-report.xlsx";
            console.log(`Saving asset at ${outputFileReportPath}`);

            const writeStream = fs.createWriteStream(outputFileReportPath);
            streamAssetReport.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();
    }
})();

function getInputFilePathFromCmdArgs(args) {
    let inputFilePath = "resources/autotagPdfInput.pdf";
    let inputFilePathIndex = args.indexOf("--input");
    if (inputFilePathIndex >= 0 && inputFilePathIndex < args.length - 1) {
        inputFilePath = args[inputFilePathIndex + 1];
    } else
        console.log("input file not specified, using default value : autotagPdfInput.pdf");
    return inputFilePath;
}

function getOutputFilePathFromCmdArgs(args) {
    let outputFilePath = "output/";
    let outputFilePathIndex = args.indexOf("--output");
    if (outputFilePathIndex >= 0 && outputFilePathIndex < args.length - 1) {
        outputFilePath = args[outputFilePathIndex + 1];
    } else {
        console.log("output path not specified, using default value :" + outputFilePath);
        fs.mkdirSync(outputFilePath, {recursive: true});
    }
    return outputFilePath;
}

function getGenerateReportFromCmdArgs(args) {
    return args.includes("--report");
}

function getShiftHeadingsFromCmdArgs(args) {
    return args.includes("--shift_headings");
}
Copied to your clipboard
// Get the samples from https://github.com/adobe/pdfservices-node-sdk-samples
// Run the sample:
// node src/autotag/autoag-pdf-parameterised.js

const {
    ServicePrincipalCredentials,
    PDFServices,
    MimeType,
    AutotagPDFParams,
    AutotagPDFJob,
    AutotagPDFResult,
    SDKError,
    ServiceUsageError,
    ServiceApiError
} = require("@adobe/pdfservices-node-sdk");
const fs = require("fs");
const args = process.argv;

(async () => {
    let readStream;
    try {
        console.log("--input " + getInputFilePathFromCmdArgs(args));
        console.log("--output " + getOutputFilePathFromCmdArgs(args));
        console.log("--report " + getGenerateReportFromCmdArgs(args));
        console.log("--shift_headings " + getShiftHeadingsFromCmdArgs(args));

        // 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(getInputFilePathFromCmdArgs(args));
        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

        // Create parameters for the job
        const params = new AutotagPDFParams({
            generateReport: getGenerateReportFromCmdArgs(args),
            shiftHeadings: getShiftHeadingsFromCmdArgs(args)
        });

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

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

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

        // Creates an output stream and copy stream asset's content to it
        const outputPath = getOutputFilePathFromCmdArgs(args);
        const outputFilePath = outputPath + "autotagPDFInput-tagged.pdf";
        console.log(`Saving asset at ${outputFilePath}`);

        const writeStream = fs.createWriteStream(outputFilePath);
        streamAsset.readStream.pipe(writeStream);
        if (resultAssetReport) {
            const outputFileReportPath = outputPath + "autotagPDFInput-report.xlsx";
            console.log(`Saving asset at ${outputFileReportPath}`);

            const writeStream = fs.createWriteStream(outputFileReportPath);
            streamAssetReport.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();
    }
})();

function getInputFilePathFromCmdArgs(args) {
    let inputFilePath = "resources/autotagPdfInput.pdf";
    let inputFilePathIndex = args.indexOf("--input");
    if (inputFilePathIndex >= 0 && inputFilePathIndex < args.length - 1) {
        inputFilePath = args[inputFilePathIndex + 1];
    } else
        console.log("input file not specified, using default value : autotagPdfInput.pdf");
    return inputFilePath;
}

function getOutputFilePathFromCmdArgs(args) {
    let outputFilePath = "output/";
    let outputFilePathIndex = args.indexOf("--output");
    if (outputFilePathIndex >= 0 && outputFilePathIndex < args.length - 1) {
        outputFilePath = args[outputFilePathIndex + 1];
    } else {
        console.log("output path not specified, using default value :" + outputFilePath);
        fs.mkdirSync(outputFilePath, {recursive: true});
    }
    return outputFilePath;
}

function getGenerateReportFromCmdArgs(args) {
    return args.includes("--report");
}

function getShiftHeadingsFromCmdArgs(args) {
    return args.includes("--shift_headings");
}

Copy
# Get the samples from https://github.com/adobe/pdfservices-python-sdk-samples
# Run the sample:
# python src/autotagpdf/autotag_pdf_parameterised.py --report --shift_headings --input resources/autotagPdfInput.pdf --output output/

# Initialize the logger
logging.basicConfig(level=logging.INFO)

class AutotagPDFParameterised:
    _input_path: str
    _output_path: str
    _generate_report: bool
    _shift_headings: bool

    def __init__(self):
        pass

    def execute(self, *args: str) -> None:
        args = self.parse_args(*args)
        self._input_path = args.input if args.input else self.get_default_input_file_path()
        self._output_path = args.output if args.output else self.get_default_output_file_path()
        self._generate_report = args.report
        self._shift_headings = args.shift_headings

        self.autotag_pdf()

    def autotag_pdf(self):
        try:
            file = open(self._input_path, 'rb')
            input_stream = file.read()
            file.close()

            # Initial setup, create credentials instance
            credentials = ServicePrincipalCredentials(
                client_id=os.getenv('PDF_SERVICES_CLIENT_ID'),
                client_secret=os.getenv('PDF_SERVICES_CLIENT_SECRET')
            )

            # Creates a PDF Services instance
            pdf_services = PDFServices(credentials=credentials)

            # Creates an asset(s) from source file(s) and upload
            input_asset = pdf_services.upload(input_stream=input_stream,
                                              mime_type=PDFServicesMediaType.PDF)

            # Create parameters for the job
            autotag_pdf_params = self.get_autotag_pdf_options()

            # Creates a new job instance
            autotag_pdf_job = AutotagPDFJob(input_asset=input_asset,
                                            autotag_pdf_params=autotag_pdf_params)

            # Submit the job and gets the job result
            location = pdf_services.submit(autotag_pdf_job)
            pdf_services_response = pdf_services.get_job_result(location, AutotagPDFResult)

            # Get content from the resulting asset(s)
            result_asset: CloudAsset = pdf_services_response.get_result().get_tagged_pdf()
            stream_asset: StreamAsset = pdf_services.get_content(result_asset)

            # Create output directory if not present
            self.create_output_file_path(self._output_path)

            # Creates an output stream and copy stream asset's content to it
            with open(f'{self._output_path}/autotagPDFInput-tagged.pdf', "wb") as file:
                file.write(stream_asset.get_input_stream())

            if self._generate_report:
                result_asset_report: CloudAsset = pdf_services_response.get_result().get_report()
                stream_asset_report: StreamAsset = pdf_services.get_content(result_asset_report)
                with open(f'{self._output_path}/autotagPDFInput-report.xlsx', "wb") as file:
                    file.write(stream_asset_report.get_input_stream())

        except (ServiceApiException, ServiceUsageException, SdkException) as e:
            logging.exception(f'Exception encountered while executing operation: {e}')

    @staticmethod
    def parse_args(*args: str):
        if not args:
            args = sys.argv[1:]
        parser = argparse.ArgumentParser(description='Autotag PDF')

        parser.add_argument('--input', help='Input file path', type=Path, metavar='input')
        parser.add_argument('--output', help='Output path', type=Path, dest='output')
        parser.add_argument('--report', dest='report', action='store_true', help='Generate report(in XLSX format)',
                            default=False)
        parser.add_argument('--shift_headings', dest='shift_headings', action='store_true', help='Shift headings',
                            default=False)

        return parser.parse_args(args)

    @staticmethod
    def get_default_input_file_path() -> str:
        return 'autotagPdfInput.pdf'

    @staticmethod
    def get_default_output_file_path() -> str:
        now = datetime.now()
        time_stamp = now.strftime("%Y-%m-%dT%H-%M-%S")
        os.makedirs("output/AutotagPDFParameterised", exist_ok=True)
        return f"output/AutotagPDFParameterised/autotag-tagged{time_stamp}"

    @staticmethod
    def create_output_file_path(path) -> None:
        os.makedirs(path, exist_ok=True)

    def get_autotag_pdf_options(self) -> AutotagPDFParams:
        return AutotagPDFParams(
            shift_headings=self._shift_headings,
            generate_report=self._generate_report
        )


if __name__ == "__main__":
    autotag_pdf_parameterised = AutotagPDFParameterised()
    autotag_pdf_parameterised.execute()
Copied to your clipboard
# Get the samples from https://github.com/adobe/pdfservices-python-sdk-samples
# Run the sample:
# python src/autotagpdf/autotag_pdf_parameterised.py --report --shift_headings --input resources/autotagPdfInput.pdf --output output/

# Initialize the logger
logging.basicConfig(level=logging.INFO)

class AutotagPDFParameterised:
    _input_path: str
    _output_path: str
    _generate_report: bool
    _shift_headings: bool

    def __init__(self):
        pass

    def execute(self, *args: str) -> None:
        args = self.parse_args(*args)
        self._input_path = args.input if args.input else self.get_default_input_file_path()
        self._output_path = args.output if args.output else self.get_default_output_file_path()
        self._generate_report = args.report
        self._shift_headings = args.shift_headings

        self.autotag_pdf()

    def autotag_pdf(self):
        try:
            file = open(self._input_path, 'rb')
            input_stream = file.read()
            file.close()

            # Initial setup, create credentials instance
            credentials = ServicePrincipalCredentials(
                client_id=os.getenv('PDF_SERVICES_CLIENT_ID'),
                client_secret=os.getenv('PDF_SERVICES_CLIENT_SECRET')
            )

            # Creates a PDF Services instance
            pdf_services = PDFServices(credentials=credentials)

            # Creates an asset(s) from source file(s) and upload
            input_asset = pdf_services.upload(input_stream=input_stream,
                                              mime_type=PDFServicesMediaType.PDF)

            # Create parameters for the job
            autotag_pdf_params = self.get_autotag_pdf_options()

            # Creates a new job instance
            autotag_pdf_job = AutotagPDFJob(input_asset=input_asset,
                                            autotag_pdf_params=autotag_pdf_params)

            # Submit the job and gets the job result
            location = pdf_services.submit(autotag_pdf_job)
            pdf_services_response = pdf_services.get_job_result(location, AutotagPDFResult)

            # Get content from the resulting asset(s)
            result_asset: CloudAsset = pdf_services_response.get_result().get_tagged_pdf()
            stream_asset: StreamAsset = pdf_services.get_content(result_asset)

            # Create output directory if not present
            self.create_output_file_path(self._output_path)

            # Creates an output stream and copy stream asset's content to it
            with open(f'{self._output_path}/autotagPDFInput-tagged.pdf', "wb") as file:
                file.write(stream_asset.get_input_stream())

            if self._generate_report:
                result_asset_report: CloudAsset = pdf_services_response.get_result().get_report()
                stream_asset_report: StreamAsset = pdf_services.get_content(result_asset_report)
                with open(f'{self._output_path}/autotagPDFInput-report.xlsx', "wb") as file:
                    file.write(stream_asset_report.get_input_stream())

        except (ServiceApiException, ServiceUsageException, SdkException) as e:
            logging.exception(f'Exception encountered while executing operation: {e}')

    @staticmethod
    def parse_args(*args: str):
        if not args:
            args = sys.argv[1:]
        parser = argparse.ArgumentParser(description='Autotag PDF')

        parser.add_argument('--input', help='Input file path', type=Path, metavar='input')
        parser.add_argument('--output', help='Output path', type=Path, dest='output')
        parser.add_argument('--report', dest='report', action='store_true', help='Generate report(in XLSX format)',
                            default=False)
        parser.add_argument('--shift_headings', dest='shift_headings', action='store_true', help='Shift headings',
                            default=False)

        return parser.parse_args(args)

    @staticmethod
    def get_default_input_file_path() -> str:
        return 'autotagPdfInput.pdf'

    @staticmethod
    def get_default_output_file_path() -> str:
        now = datetime.now()
        time_stamp = now.strftime("%Y-%m-%dT%H-%M-%S")
        os.makedirs("output/AutotagPDFParameterised", exist_ok=True)
        return f"output/AutotagPDFParameterised/autotag-tagged{time_stamp}"

    @staticmethod
    def create_output_file_path(path) -> None:
        os.makedirs(path, exist_ok=True)

    def get_autotag_pdf_options(self) -> AutotagPDFParams:
        return AutotagPDFParams(
            shift_headings=self._shift_headings,
            generate_report=self._generate_report
        )


if __name__ == "__main__":
    autotag_pdf_parameterised = AutotagPDFParameterised()
    autotag_pdf_parameterised.execute()