amazon_textract_textractor_document_analysis_tables_and_forms.py

1from textractor import Textractor
2from textractor.visualizers.entitylist import EntityList
3from textractor.data.constants import TextractFeatures
4
5# Initialize the Textractor client
6extractor = Textractor(region_name="us-east-1")
7
8# Call Amazon Textract to analyze a document
9# Note: Replace 'path/to/document.png' with your actual file path
10document = extractor.analyze_document(
11    file_source="path/to/document.png",
12    features=[TextractFeatures.TABLES, TextractFeatures.FORMS]
13)
14
15# Print the extracted text
16print(document.text)
17
18# Print any tables found in the document
19for table in document.tables:
20    print(table.to_pandas())
21
22# Print any forms (key-value pairs) found in the document
23for kv in document.key_values:
24    print(f"Key: {kv.key}, Value: {kv.value}")