from adobe.pdfservices.operation.auth.credentials import Credentials
from adobe.pdfservices.operation.exception.exceptions import ServiceApiException, ServiceUsageException, SdkException
from adobe.pdfservices.operation.pdfops.options.extractpdf.extract_pdf_options import ExtractPDFOptions
from adobe.pdfservices.operation.pdfops.options.extractpdf.extract_element_type import ExtractElementType
from adobe.pdfservices.operation.pdfops.options.extractpdf.extract_renditions_element_type import \
    ExtractRenditionsElementType
from adobe.pdfservices.operation.pdfops.options.extractpdf.table_structure_type import TableStructureType
from adobe.pdfservices.operation.execution_context import ExecutionContext
from adobe.pdfservices.operation.io.file_ref import FileRef
from adobe.pdfservices.operation.pdfops.extract_pdf_operation import ExtractPDFOperation

import os.path
import zipfile
import json

output_zip = "./ExtractTextInfoFromPDF.zip"

if os.path.isfile(output_zip):
    os.remove(output_zip)

input_pdf = "C:/Users/stand/PDFExtractTest/venv/Docshospitals.pdf"

try:

    #Initial setup, create credentials instance.
    credentials = Credentials.service_account_credentials_builder()\
        .from_file("C:/Users/stand/PDFExtractTest/venv/pdfservices-api-credentials.json") \
        .build()

    #Create an ExecutionContext using credentials and create a new operation instance.
    execution_context = ExecutionContext.create(credentials)
    extract_pdf_operation = ExtractPDFOperation.create_new()

    #Set operation input from a source file.
    source = FileRef.create_from_local_file(input_pdf)
    extract_pdf_operation.set_input(source)

    # Build ExtractPDF options and set them into the operation
    extract_pdf_options: ExtractPDFOptions = ExtractPDFOptions.builder() \
        .with_elements_to_extract([ExtractElementType.TEXT, ExtractElementType.TABLES]) \
        .with_element_to_extract_renditions(ExtractRenditionsElementType.TABLES) \
        .with_table_structure_format(TableStructureType.CSV) \
        .build()
    extract_pdf_operation.set_options(extract_pdf_options)
    
     #Build ExtractPDF options and set them into the operation
    #extract_pdf_options: ExtractPDFOptions = ExtractPDFOptions.builder() \
     #   .with_element_to_extract(ExtractElementType.TEXT) \
     #   .build()
   # extract_pdf_operation.set_options(extract_pdf_options)

    #Execute the operation.
    result: FileRef = extract_pdf_operation.execute(execution_context)

    #Save the result to the specified location.
    result.save_as(output_zip)

    print("Successfully extracted information from PDF. Printing H1 Headers:\n");

    archive = zipfile.ZipFile(output_zip, 'r')
    jsonentry = archive.open('structuredData.json')
    jsondata = jsonentry.read()
    data = json.loads(jsondata)
    for element in data["elements"]:
        if(element["Path"].endswith("/H1")):
            print(element["Text"])

except (ServiceApiException, ServiceUsageException, SdkException):
    logging.exception("Exception encountered while executing operation")

(Feb-23-2023, 06:48 PM)deanhystad Wrote: You need to activate your virtual environment. If you are using a IDE, you might have set the python interpreter.

What is your system? What OS are you using? If using an IDE, which one? Do you python from the command line?