Amazon Textract とAWSSDK

ドキュメント内のテキストを検出する非同期ジョブを開始します。

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_detection_job(
            self, bucket_name, document_file_name, sns_topic_arn, sns_role_arn):
        """
        Starts an asynchronous job to detect text elements 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 sns_topic_arn: The Amazon Resource Name (ARN) of an Amazon SNS topic
                              where the 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_text_detection(
                DocumentLocation={
                    'S3Object': {'Bucket': bucket_name, 'Name': document_file_name}},
                NotificationChannel={
                    'SNSTopicArn': sns_topic_arn, 'RoleArn': sns_role_arn})
            job_id = response['JobId']
            logger.info(
                "Started text detection job %s on %s.", job_id, document_file_name)
        except ClientError:
            logger.exception("Couldn't detect text in %s.", document_file_name)
            raise
        else:
            return job_id