使用亞馬遜 Textract 和AWSSDK

    public static String startDocAnalysisS3 (TextractClient textractClient, String bucketName, String docName) {

        try {

            List<FeatureType> myList = new ArrayList<FeatureType>();
            myList.add(FeatureType.TABLES);
            myList.add(FeatureType.FORMS);

            S3Object s3Object = S3Object.builder()
                    .bucket(bucketName)
                    .name(docName)
                    .build();

            DocumentLocation location = DocumentLocation.builder()
                    .s3Object(s3Object)
                    .build();

            StartDocumentAnalysisRequest documentAnalysisRequest = StartDocumentAnalysisRequest.builder()
                    .documentLocation(location)
                    .featureTypes(myList)
                    .build();

            StartDocumentAnalysisResponse response = textractClient.startDocumentAnalysis(documentAnalysisRequest);

            // Get the job ID
            String jobId = response.jobId();
            return jobId;

        } catch (TextractException e) {

            System.err.println(e.getMessage());
            System.exit(1);
        }
        return "" ;
    }

    private static String getJobResults(TextractClient textractClient, String jobId) {

        boolean finished = false;
        int index = 0 ;
        String status = "" ;

       try {
        while (!finished) {
            GetDocumentAnalysisRequest analysisRequest = GetDocumentAnalysisRequest.builder()
                    .jobId(jobId)
                    .maxResults(1000)
                    .build();

            GetDocumentAnalysisResponse response = textractClient.getDocumentAnalysis(analysisRequest);
            status = response.jobStatus().toString();

            if (status.compareTo("SUCCEEDED") == 0)
                finished = true;
            else {
                System.out.println(index + " status is: " + status);
                Thread.sleep(1000);
            }
            index++ ;
        }
        return status;

       } catch( InterruptedException e) {
           System.out.println(e.getMessage());
           System.exit(1);
       }
       return "";
    }

啟動異步作業以分析文檔。

class TextractWrapper:
    """Encapsulates Textract functions."""
    def __init__(self, textract_client, s3_resource, sqs_resource):
        """
        :param textract_client: A Boto3 Textract client.
        :param s3_resource: A Boto3 Amazon S3 resource.
        :param sqs_resource: A Boto3 Amazon SQS resource.
        """
        self.textract_client = textract_client
        self.s3_resource = s3_resource
        self.sqs_resource = sqs_resource

    def start_analysis_job(
            self, bucket_name, document_file_name, feature_types, sns_topic_arn,
            sns_role_arn):
        """
        Starts an asynchronous job to detect text and additional elements, such as
        forms or tables, in an image stored in an Amazon S3 bucket. Textract publishes
        a notification to the specified Amazon SNS topic when the job completes.
        The image must be in PNG, JPG, or PDF format.

        :param bucket_name: The name of the Amazon S3 bucket that contains the image.
        :param document_file_name: The name of the document image stored in Amazon S3.
        :param feature_types: The types of additional document features to detect.
        :param sns_topic_arn: The Amazon Resource Name (ARN) of an Amazon SNS topic
                              where job completion notification is published.
        :param sns_role_arn: The ARN of an AWS Identity and Access Management (IAM)
                             role that can be assumed by Textract and grants permission
                             to publish to the Amazon SNS topic.
        :return: The ID of the job.
        """
        try:
            response = self.textract_client.start_document_analysis(
                DocumentLocation={
                    'S3Object': {'Bucket': bucket_name, 'Name': document_file_name}},
                NotificationChannel={
                    'SNSTopicArn': sns_topic_arn, 'RoleArn': sns_role_arn},
                FeatureTypes=feature_types)
            job_id = response['JobId']
            logger.info(
                "Started text analysis job %s on %s.", job_id, document_file_name)
        except ClientError:
            logger.exception("Couldn't analyze text in %s.", document_file_name)
            raise
        else:
            return job_id