google_cloud_document_ai_pdf_text_extraction_quickstart.py

1from google.api_core.client_options import ClientOptions
2from google.cloud import documentai  # type: ignore
3
4# TODO(developer): Fill these variables before running the sample.
5project_id = "YOUR_PROJECT_ID"
6location = "us"  # Format is 'us' or 'eu'
7processor_id = "YOUR_PROCESSOR_ID"  # Create processor before running sample
8file_path = "path/to/local/pdf"
9mime_type = "application/pdf"  # Refer to https://cloud.google.com/document-ai/docs/file-types for supported file types
10
11def process_document_sample(
12    project_id: str, location: str, processor_id: str, file_path: str, mime_type: str
13):
14    # You must set the api_endpoint if you use a location other than 'us'.
15    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")
16
17    client = documentai.DocumentProcessorServiceClient(client_options=opts)
18
19    # The full resource name of the processor, e.g.:
20    # projects/project_id/locations/location/processor/processor_id
21    name = client.processor_path(project_id, location, processor_id)
22
23    # Read the file into memory
24    with open(file_path, "rb") as image:
25        image_content = image.read()
26
27    # Load Binary Data into Document AI RawDocument Object
28    raw_document = documentai.RawDocument(content=image_content, mime_type=mime_type)
29
30    # Configure the process request
31    request = documentai.ProcessRequest(name=name, raw_document=raw_document)
32
33    result = client.process_document(request=request)
34
35    # For a full list of Document object attributes, please reference this page:
36    # https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.Document
37    document = result.document
38
39    # Read the text recognition output from the processor
40    print("The document contains the following text:")
41    print(document.text)
42
43process_document_sample(project_id, location, processor_id, file_path, mime_type)