通过 Python SDK 将 PDF 解析为 XML 格式的表单字段

import shutil
import json
import logging
from pathlib import Path
from asposepdfcloud import ApiClient, PdfApi
import logging

# Configure logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")


class ExportFormToXML:
    """Class for extracting PDF form fields into XML using Aspose PDF Cloud API."""
    def __init__(self):
        self.pdf_api = PdfApi(ApiClient(APP_KEY, APP_SID)

    def uploadDocument(self, documentName: str, localFolder: str, remoteFolder: str):
        """Upload a PDF document to the Aspose Cloud server."""
        if self.pdf_api:
            file_path = localFolder / documentName
            try:
                if remoteFolder == None:
                    self.pdf_api.upload_file(documentName, str(file_path))
                else:
                    opts = { "folder": remoteFolder }
                    self.pdf_api.upload_file(remoteFolder + '/' + documentName, file_path)
                logging.info(f"File {documentName} uploaded successfully.")
            except Exception as e:
                logging.error(f"Failed to upload file: {e}")

    def downloadFile(self, document: str, outputDocument: str, localFolder: Path, remoteFolder: str,  output_prefix: str):
        """Download the processed PDF document from the Aspose Cloud server."""
        if self.pdf_api:
            try:
                temp_file = self.pdf_api.download_file(remoteFolder + '/' + document)
                local_path = localFolder / ( output_prefix + outputDocument )
                shutil.move(temp_file, str(local_path))
                logging.info(f"download_result(): File successfully downloaded: {local_path}")
            except Exception as e:
                logging.error(f"download_result(): Failed to download file: {e}")


    def Extract(self, documentName: str, outputXMLName: str, localFolder: Path, remoteFolder: str ):
        self.uploadDocument(documentName, remoteFolder)

        XMLPath = str(Path.joinpath(Path(remoteFolder), outputXMLName))
        opts = {
            "folder": remoteFolder
        }
        response = self.pdf_put_export_fields_from_pdf_to_xml_in_storage(documentName, XMLPath, **opts)
        if response.code != 200:
            logging.error("ExportFormToXML(): Unexpected error!")
        else:
            logging.info(f"ExportFormToXML(): Pdf document '{documentName}' form fields successfully exported to '{outputXMLName}' file.")
            self.downloadFile(outputXMLName, outputXMLName, localFolder, remoteFolder, "")