使用 Python SDK 解析 PDF 以提取图像

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 ParseExtractImages:
    """Class for extracting images from PDF document page 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, pageNumber: int, localFolder: Path, remoteFolder: Path):
        self.upload_document(documentName, remoteFolder)

        opts = {
            "folder": remoteFolder
        }
        respImages = self.pdf_api.get_images(documentName, pageNumber, **opts)
        if respImages.code != 200:
            logging.error("ParseExtractImages(): Unexpected error!")
        else:
            for img in respImages.images.list:
                response = self.pdf_api.get_image_extract_as_png(documentName, img.id, **opts)

                logging.info(f"ParseExtractImages(): Image '{img.id}' successfully extracted from the document '{documentName}'.")
                local_path = localFolder / ( img.id + '.png' )
                shutil.move(response, str(local_path))