Textract / Client / start_lending_analysis



Starts the classification and analysis of an input document. StartLendingAnalysis initiates the classification and analysis of a packet of lending documents. StartLendingAnalysis operates on a document file located in an Amazon S3 bucket.

StartLendingAnalysis can analyze text in documents that are in one of the following formats: JPEG, PNG, TIFF, PDF. Use DocumentLocation to specify the bucket name and the file name of the document.

StartLendingAnalysis returns a job identifier ( JobId) that you use to get the results of the operation. When the text analysis is finished, Amazon Textract publishes a completion status to the Amazon Simple Notification Service (Amazon SNS) topic that you specify in NotificationChannel. To get the results of the text analysis operation, first check that the status value published to the Amazon SNS topic is SUCCEEDED. If the status is SUCCEEDED you can call either GetLendingAnalysis or GetLendingAnalysisSummary and provide the JobId to obtain the results of the analysis.

If using OutputConfig to specify an Amazon S3 bucket, the output will be contained within the specified prefix in a directory labeled with the job-id. In the directory there are 3 sub-directories:

  • detailedResponse (contains the GetLendingAnalysis response)

  • summaryResponse (for the GetLendingAnalysisSummary response)

  • splitDocuments (documents split across logical boundaries)

See also: AWS API Documentation

Request Syntax

response = client.start_lending_analysis(
        'S3Object': {
            'Bucket': 'string',
            'Name': 'string',
            'Version': 'string'
        'SNSTopicArn': 'string',
        'RoleArn': 'string'
        'S3Bucket': 'string',
        'S3Prefix': 'string'
  • DocumentLocation (dict) –


    The Amazon S3 bucket that contains the document to be processed. It’s used by asynchronous operations.

    The input document can be an image file in JPEG or PNG format. It can also be a file in PDF format.

    • S3Object (dict) –

      The Amazon S3 bucket that contains the input document.

      • Bucket (string) –

        The name of the S3 bucket. Note that the # character is not valid in the file name.

      • Name (string) –

        The file name of the input document. Synchronous operations can use image files that are in JPEG or PNG format. Asynchronous operations also support PDF and TIFF format files.

      • Version (string) –

        If the bucket has versioning enabled, you can specify the object version.

  • ClientRequestToken (string) – The idempotent token that you use to identify the start request. If you use the same token with multiple StartLendingAnalysis requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidentally started more than once. For more information, see Calling Amazon Textract Asynchronous Operations.

  • JobTag (string) – An identifier that you specify to be included in the completion notification published to the Amazon SNS topic. For example, you can use JobTag to identify the type of document that the completion notification corresponds to (such as a tax form or a receipt).

  • NotificationChannel (dict) –

    The Amazon Simple Notification Service (Amazon SNS) topic to which Amazon Textract publishes the completion status of an asynchronous document operation.

    • SNSTopicArn (string) – [REQUIRED]

      The Amazon SNS topic that Amazon Textract posts the completion status to.

    • RoleArn (string) – [REQUIRED]

      The Amazon Resource Name (ARN) of an IAM role that gives Amazon Textract publishing permissions to the Amazon SNS topic.

  • OutputConfig (dict) –

    Sets whether or not your output will go to a user created bucket. Used to set the name of the bucket, and the prefix on the output file.

    OutputConfig is an optional parameter which lets you adjust where your output will be placed. By default, Amazon Textract will store the results internally and can only be accessed by the Get API operations. With OutputConfig enabled, you can set the name of the bucket the output will be sent to the file prefix of the results where you can download your results. Additionally, you can set the KMSKeyID parameter to a customer master key (CMK) to encrypt your output. Without this parameter set Amazon Textract will encrypt server-side using the AWS managed CMK for Amazon S3.

    Decryption of Customer Content is necessary for processing of the documents by Amazon Textract. If your account is opted out under an AI services opt out policy then all unencrypted Customer Content is immediately and permanently deleted after the Customer Content has been processed by the service. No copy of of the output is retained by Amazon Textract. For information about how to opt out, see Managing AI services opt-out policy.

    For more information on data privacy, see the Data Privacy FAQ.

    • S3Bucket (string) – [REQUIRED]

      The name of the bucket your output will go to.

    • S3Prefix (string) –

      The prefix of the object key that the output will be saved to. When not enabled, the prefix will be “textract_output”.

  • KMSKeyId (string) – The KMS key used to encrypt the inference results. This can be in either Key ID or Key Alias format. When a KMS key is provided, the KMS key will be used for server-side encryption of the objects in the customer bucket. When this parameter is not enabled, the result will be encrypted server side, using SSE-S3.

Return type:



Response Syntax

    'JobId': 'string'

Response Structure

  • (dict) –

    • JobId (string) –

      A unique identifier for the lending or text-detection job. The JobId is returned from StartLendingAnalysis. A JobId value is only valid for 7 days.


  • Textract.Client.exceptions.InvalidParameterException

  • Textract.Client.exceptions.InvalidS3ObjectException

  • Textract.Client.exceptions.InvalidKMSKeyException

  • Textract.Client.exceptions.UnsupportedDocumentException

  • Textract.Client.exceptions.DocumentTooLargeException

  • Textract.Client.exceptions.BadDocumentException

  • Textract.Client.exceptions.AccessDeniedException

  • Textract.Client.exceptions.ProvisionedThroughputExceededException

  • Textract.Client.exceptions.InternalServerError

  • Textract.Client.exceptions.IdempotentParameterMismatchException

  • Textract.Client.exceptions.ThrottlingException

  • Textract.Client.exceptions.LimitExceededException