google_cloud_documentai_local_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/file.pdf"
9mime_type = "application/pdf"  # Refer to https://cloud.google.com/document-ai/docs/file-types for supported file types
10
11
12def quickstart(
13    project_id: str,
14    location: str,
15    processor_id: str,
16    file_path: str,
17    mime_type: str,
18):
19    # You must set the `api_endpoint` if you use a location other than "us".
20    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")
21
22    client = documentai.DocumentProcessorServiceClient(client_options=opts)
23
24    # The full resource name of the processor, e.g.:
25    # `projects/{project_id}/locations/{location}/processors/{processor_id}`
26    name = client.processor_path(project_id, location, processor_id)
27
28    # Read the file into memory
29    with open(file_path, "rb") as image:
30        image_content = image.read()
31
32    # Load binary data
33    raw_document = documentai.RawDocument(content=image_content, mime_type=mime_type)
34
35    # Configure the process request
36    # `processor_display_name` is not required but is used to show which processor is being used
37    request = documentai.ProcessRequest(name=name, raw_document=raw_document)
38
39    result = client.process_document(request=request)
40
41    # For a full list of `Document` object attributes, please reference this page:
42    # https://cloud.google.com/document-ai/docs/reference/rest/v1/Document
43    document = result.document
44
45    # Read the text recognition output from the processor
46    print("The document contains the following text:")
47    print(document.text)