如何使用python和amazon-textract检索PDF格式的表单数据(键值对)？

import boto3

def retrieve_form_data_from_pdf(pdf_bucket, pdf_key):
    # 创建Amazon Textract客户端
    textract_client = boto3.client('textract', region_name='your_region', aws_access_key_id='your_access_key', aws_secret_access_key='your_secret_key')

    # 提交PDF文件
    response = textract_client.start_document_text_detection(
        DocumentLocation={
            'S3Object': {
                'Bucket': pdf_bucket,
                'Name': pdf_key
            }
        }
    )

    # 获取分析结果
    job_id = response['JobId']
    response = textract_client.get_document_text_detection(JobId=job_id)

    # 解析分析结果
    form_data = {}
    for item in response['Blocks']:
        if item['BlockType'] == 'KEY_VALUE_SET':
            key_block = item['KeyValuePairs'][0]['Key']
            value_block = item['KeyValuePairs'][0]['Value']
            key = get_text_from_block(key_block)
            value = get_text_from_block(value_block)
            form_data[key] = value

    return form_data

def get_text_from_block(block):
    text = ''
    if 'Text' in block:
        text = block['Text']
    if 'Relationships' in block:
        for relationship in block['Relationships']:
            if relationship['Type'] == 'CHILD':
                for child_id in relationship['Ids']:
                    child_block = next(item for item in response['Blocks'] if item['Id'] == child_id)
                    text += get_text_from_block(child_block)
    return text

# 使用示例
pdf_bucket = 'your_pdf_bucket'
pdf_key = 'your_pdf_key'
form_data = retrieve_form_data_from_pdf(pdf_bucket, pdf_key)
print(form_data)