AWS Code Sample
Catalog

The AWS Documentation website is getting a new look!
Try it now and let us know what you think. Switch to the new look >>

You can return to the original look by selecting English in the language selector above.

textract_python_kv_parser.py

textract_python_kv_parser.py demonstrates how to extract key-value pairs in form documents.

# Copyright 2010-2019 Amazon.com, Inc. or its affiliates. All Rights Reserved. # # This file is licensed under the Apache License, Version 2.0 (the "License"). # You may not use this file except in compliance with the License. A copy of the # License is located at # # http://aws.amazon.com/apache2.0/ # # This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS # OF ANY KIND, either express or implied. See the License for the specific # language governing permissions and limitations under the License. import boto3 import sys import re import json def get_kv_map(file_name): with open(file_name, 'rb') as file: img_test = file.read() bytes_test = bytearray(img_test) print('Image loaded', file_name) # process using image bytes client = boto3.client('textract') response = client.analyze_document(Document={'Bytes': bytes_test}, FeatureTypes=['FORMS']) # Get the text blocks blocks=response['Blocks'] # get key and value maps key_map = {} value_map = {} block_map = {} for block in blocks: block_id = block['Id'] block_map[block_id] = block if block['BlockType'] == "KEY_VALUE_SET": if 'KEY' in block['EntityTypes']: key_map[block_id] = block else: value_map[block_id] = block return key_map, value_map, block_map def get_kv_relationship(key_map, value_map, block_map): kvs = {} for block_id, key_block in key_map.items(): value_block = find_value_block(key_block, value_map) key = get_text(key_block, block_map) val = get_text(value_block, block_map) kvs[key] = val return kvs def find_value_block(key_block, value_map): for relationship in key_block['Relationships']: if relationship['Type'] == 'VALUE': for value_id in relationship['Ids']: value_block = value_map[value_id] return value_block def get_text(result, blocks_map): text = '' if 'Relationships' in result: for relationship in result['Relationships']: if relationship['Type'] == 'CHILD': for child_id in relationship['Ids']: word = blocks_map[child_id] if word['BlockType'] == 'WORD': text += word['Text'] + ' ' if word['BlockType'] == 'SELECTION_ELEMENT': if word['SelectionStatus'] == 'SELECTED': text += 'X ' return text def print_kvs(kvs): for key, value in kvs.items(): print(key, ":", value) def search_value(kvs, search_key): for key, value in kvs.items(): if re.search(search_key, key, re.IGNORECASE): return value def main(file_name): key_map, value_map, block_map = get_kv_map(file_name) # Get Key Value relationship kvs = get_kv_relationship(key_map, value_map, block_map) print("\n\n== FOUND KEY : VALUE pairs ===\n") print_kvs(kvs) # Start searching a key value while input('\n Do you want to search a value for a key? (enter "n" for exit) ') != 'n': search_key = input('\n Enter a search key:') print('The value is:', search_value(kvs, search_key)) if __name__ == "__main__": file_name = sys.argv[1] main(file_name)

Sample Details

Service: textract

Last tested: 2019-01-3

Author: reesch (AWS)

Type: full-example

On this page: