docstrange/example.py at main · NanoNets/docstrange · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
from docstrange import DocumentExtractor

file_path = "sample_documents/invoice.pdf"

extractor = DocumentExtractor()

result = extractor.extract(file_path).extract_data(specified_fields=[
        "total_amount",
        "date",
        "vendor_name",
        "invoice_number"
    ])

print(result)


exit()


print("📝=============================== JSON Output:===============================")
result = extractor.extract(file_path).extract_data()
print(result)


print("\n📝=============================== Specific Field :===============================")
result = extractor.extract(file_path)
specific_fields = result.extract_data(specified_fields=[
        "total_amount",
        "date",
        "vendor_name",
        "invoice_number"
    ])
print(specific_fields)


print("\n📝=============================== JSON Schema Extraction:===============================")
schema = {
        "invoice_number": "string",
        "total_amount": "number",
        "vendor_name": "string",
        "items": [{
            "description": "string",
            "amount": "number"
        }]
    }

structured_data = result.extract_data(json_schema=schema)
print(structured_data)