amazon-textract-textractor

import os from textractor import Textractor from textractor.data.constants import TextractFeatures # Ensure AWS credentials are configured (e.g., via AWS CLI, env vars, IAM roles) # textractor uses boto3, which automatically picks up credentials. # Example: os.environ['AWS_ACCESS_KEY_ID'] = 'YOUR_ACCESS_KEY' # os.environ['AWS_SECRET_ACCESS_KEY'] = 'YOUR_SECRET_KEY' # os.environ['AWS_DEFAULT_REGION'] = 'us-east-1' # Initialize Textractor client # Make sure the region matches your S3 bucket and Textract service availability tractor = Textractor(region_name=os.environ.get('AWS_DEFAULT_REGION', 'us-east-1')) # Example: Process a document from an S3 path s3_path = "s3://amazon-textract-public-content/samples/sample.pdf" print(f"Processing document: {s3_path}") document = tractor.start_document_analysis( file_source=s3_path, features=[TextractFeatures.FORMS, TextractFeatures.TABLES] ) # Print extracted forms print("\n--- Forms ---") for key_value in document.key_values: print(f"{key_value.key}: {key_value.value}") # Print extracted tables print("\n--- Tables ---") for i, table in enumerate(document.tables): print(f"Table {i+1}:\n{table.to_csv(include_box=False)}\n")