AWS SDK または CLI GetDocumentAnalysisで使用する

複数ページのドキュメントの非同期テキスト分析の結果を取得するには

次の get-document-analysis の例は、複数ページのドキュメントの非同期テキスト分析の結果を取得します。

aws textract get-document-analysis \
    --job-id df7cf32ebbd2a5de113535fcf4d921926a701b09b4e7d089f3aebadb41e0712b \
    --max-results 1000

出力:

{
    "Blocks": [
        {
            "Geometry": {
                "BoundingBox": {
                    "Width": 1.0,
                    "Top": 0.0,
                    "Left": 0.0,
                    "Height": 1.0
                },
                "Polygon": [
                    {
                        "Y": 0.0,
                        "X": 0.0
                    },
                    {
                        "Y": 0.0,
                        "X": 1.0
                    },
                    {
                        "Y": 1.0,
                        "X": 1.0
                    },
                    {
                        "Y": 1.0,
                        "X": 0.0
                    }
                ]
            },
            "Relationships": [
                {
                    "Type": "CHILD",
                    "Ids": [
                        "75966e64-81c2-4540-9649-d66ec341cd8f",
                        "bb099c24-8282-464c-a179-8a9fa0a057f0",
                        "5ebf522d-f9e4-4dc7-bfae-a288dc094595"
                    ]
                }
            ],
            "BlockType": "PAGE",
            "Id": "247c28ee-b63d-4aeb-9af0-5f7ea8ba109e",
            "Page": 1
        }
    ],
    "NextToken": "cY1W3eTFvoB0cH7YrKVudI4Gb0H8J0xAYLo8xI/JunCIPWCthaKQ+07n/ElyutsSy0+1VOImoTRmP1zw4P0RFtaeV9Bzhnfedpx1YqwB4xaGDA==",
    "DocumentMetadata": {
        "Pages": 1
    },
    "JobStatus": "SUCCEEDED"
}

詳細については、「Amazon Textract デベロッパーガイド」の「複数ページドキュメント内のテキストの検出または分析」を参照してください。

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 get_analysis_job(self, job_id):
        """
        Gets data for a previously started detection job that includes additional
        elements.

        :param job_id: The ID of the job to retrieve.
        :return: The job data, including a list of blocks that describe elements
                 detected in the image.
        """
        try:
            response = self.textract_client.get_document_analysis(JobId=job_id)
            job_status = response["JobStatus"]
            logger.info("Job %s status is %s.", job_id, job_status)
        except ClientError:
            logger.exception("Couldn't get data for job %s.", job_id)
            raise
        else:
            return response

    "Gets the results for an Amazon Textract"
    "asynchronous operation that analyzes text in a document."
    TRY.
        oo_result = lo_tex->getdocumentanalysis( iv_jobid = iv_jobid ).    "oo_result is returned for testing purposes."
        WHILE oo_result->get_jobstatus( ) <> 'SUCCEEDED'.
          IF sy-index = 10.
            EXIT.               "Maximum 300 seconds.
          ENDIF.
          WAIT UP TO 30 SECONDS.
          oo_result = lo_tex->getdocumentanalysis( iv_jobid = iv_jobid ).
        ENDWHILE.

        DATA(lt_blocks) = oo_result->get_blocks( ).
        LOOP AT lt_blocks INTO DATA(lo_block).
          IF lo_block->get_text( ) = 'INGREDIENTS: POWDERED SUGAR* (CANE SUGAR,'.
            MESSAGE 'Found text in the doc: ' && lo_block->get_text( ) TYPE 'I'.
          ENDIF.
        ENDLOOP.
        MESSAGE 'Document analysis retrieved.' TYPE 'I'.
      CATCH /aws1/cx_texaccessdeniedex.
        MESSAGE 'You do not have permission to perform this action.' TYPE 'E'.
      CATCH /aws1/cx_texinternalservererr.
        MESSAGE 'Internal server error.' TYPE 'E'.
      CATCH /aws1/cx_texinvalidjobidex.
        MESSAGE 'Job ID is not valid.' TYPE 'E'.
      CATCH /aws1/cx_texinvalidkmskeyex.
        MESSAGE 'AWS KMS key is not valid.' TYPE 'E'.
      CATCH /aws1/cx_texinvalidparameterex.
        MESSAGE 'Request has non-valid parameters.' TYPE 'E'.
      CATCH /aws1/cx_texinvalids3objectex.
        MESSAGE 'Amazon S3 object is not valid.' TYPE 'E'.
      CATCH /aws1/cx_texprovthruputexcdex.
        MESSAGE 'Provisioned throughput exceeded limit.' TYPE 'E'.
      CATCH /aws1/cx_texthrottlingex.
        MESSAGE 'The request processing exceeded the limit.' TYPE 'E'.
    ENDTRY.