通过 Python SDK 解析 PDF 以按名称提取文本

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 ParseExtractTextBox:
    """Class for extracting text box from PDF document using Aspose PDF Cloud API."""
    def __init__(self):
        self.pdf_api = PdfApi(ApiClient(APP_KEY, APP_SID)

    def upload_document(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 Extract(self, documentName: str, texxtboxName: str, localFolder: Path, remoteFolder: Path):
        self.upload_document(documentName, remoteFolder)

        opts = {
            "folder": remoteFolder
        }
	response = self.pdf_api.get_text_box_field(documentName, textboxName, **opts)
        if response.code != 200:
            logging.error("ParseExtractTextBox(): Unexpected error!")
        else:
	    logging.info(f"ParseExtractTextBox(): TextBox field '{textboxName}' successfully extracted from the document '{documentName}'.")
            localJsonFile = str(Path.joinpath(localFolder, "text_box_objects.json"))
            with open(localJsonFile, "w", encoding="utf-8") as localFile:            
               jsText = json.dumps(response.field.__dict__, ensure_ascii=False, default=str, indent=4)
               localFile.write(jsText)