تحليل PDF لاستخراج النصوص في مجموعة أدوات جافا

    import java.io.File;
    import java.nio.file.Files;
    import java.nio.file.OpenOption;
    import java.nio.file.StandardOpenOption;
    import java.nio.file.Path;
    import com.google.gson.Gson;

    import com.aspose.asposecloudpdf.api.PdfApi;
    import com.aspose.asposecloudpdf.model.TextBoxField;
    import com.aspose.asposecloudpdf.model.TextBoxFieldsResponse;

    public class ParseGetTextBoxes {
        public static void extract() {
            String REMOTE_FOLDER   = "Your_Temp_Pdf_Cloud";
	    String LOCAL_FOLDER    = "c:\\Samples";
	    String PDF_DOCUMENT    = "sample.pdf";
	    String OUTPUT_FILE     = "parsed_text_box_fields_output.json";

            try {
                PdfApi pdfApi = new PdfApi(API_KEY, API_SECRET);

                // upload local PDF file to remote storage
                File file = new File(Path.of(LOCAL_FOLDER, PDF_DOCUMENT).toString());
                pdfApi.uploadFile(Path.of(REMOTE_FOLDER , PDF_DOCUMENT).toString(), file, null);
                System.out.println(String.format("File '%s' successfully uploaded!", Path.of(LOCAL_FOLDER, PDF_DOCUMENT).toString()));

                // perform action
                TextBoxFieldsResponse response = pdfApi.getDocumentTextBoxFields(PDF_DOCUMENT, null,  REMOTE_FOLDER);
                System.out.println("TextBox fields extracted status: " + response.getStatus());

                String jsonResult = "[\n";
                for (TextBoxField fieldDef : response.getFields().getList()) {
                    String jsonFiled = new Gson().toJson(fieldDef);
                    jsonResult += jsonFiled + ",\n\n";
                }
                jsonResult +="]";

                // save json
                Path path = Path.of(LOCAL_FOLDER, OUTPUT_FILE);
                byte[] strToBytes = jsonResult.getBytes();
                Files.write(path, strToBytes, new OpenOption[] { StandardOpenOption.WRITE, StandardOpenOption.CREATE, StandardOpenOption.TRUNCATE_EXISTING });
		
                System.out.println("TextBox fields successfully extracted to: '" + path + "'");
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }