Having difficulties using the QUERY option in "textract" start document analisys with boto3 python

Question

My problem is that textract asynchronous method start_document_analysis, has an option for the type of analysis you want to perform, but when I try to use the "Queries" feature =>

FeatureTypes=[
        'TABLES'|'FORMS'|'QUERIES',
    ], 

you would have to pass another parameter with the queries list =>

QueriesConfig={
        'Queries': [
            {
                'Text': 'string',
                'Alias': 'string',
                'Pages': [
                    'string',
                ]
            },
        ]
    }

once I pass this parameter, boto3 throws an exception that Queries config is not recognized as one of the parameters accepted, have anyone used this feature with python before?

Answer 1

You can use by this way:

def getJobResults(jobId):

    pages = []
    client = boto3.client('textract')
    response = client.get_document_analysis(JobId=jobId)
    pages.append(response)
    print("Resultset page recieved: {}".format(len(pages)))
    nextToken = None
    if('NextToken' in response):
        nextToken = response['NextToken']
    while(nextToken):
        response = client.get_document_analysis(JobId=jobId, NextToken=nextToken)
        pages.append(response)
        print("Resultset page recieved: {}".format(len(pages)))
        nextToken = None
        if('NextToken' in response):
            nextToken = response['NextToken']
    return pages


def get_kv_map(s3BucketName, documentName):

    client = boto3.client('textract')
    response = client.start_document_analysis(
        DocumentLocation={
            'S3Object': {
                'Bucket': s3BucketName,
                'Name': documentName
            }
        },
        FeatureTypes=['QUERIES'],
        QueriesConfig={
            'Queries': [
                {
                    "Text": "is 1. A. checkbox seleted"
                }
                
            ]
        }
    )
    
    job_id = response['JobId']
    response = client.get_document_analysis(JobId=job_id)
    status = response["JobStatus"]
    
    while(status == "IN_PROGRESS"):
        time.sleep(3)
        response = client.get_document_analysis(JobId=job_id)
        status = response["JobStatus"]
        print("Job status2: {}".format(status))
        
    response = getJobResults(job_id)    
    return response


def query_extraction():

    s3BucketName = "bucket-name"
    documentName = "xyz.pdf"

    data = get_kv_map(s3BucketName, documentName)
    
    return data

data = query_extraction()

Hope this will solve your issue