Link Search Menu Expand Document

Advanced Conversion Options - Java

PDF To XLS sample in Java demonstrating ‘Advanced Conversion Options’

import okhttp3.*;

import java.nio.file.Path;
import java.nio.file.Paths;

public class Main
    // The authentication key (API Key).
    // Get your own by registering at
    final static String API_KEY = "***********************************";

    // Direct URL of source PDF file.
    // You can also upload your own file into and use it as url. Check "Upload File" samples for code snippets:    
    final static String SourceFileUrl = "";
    // Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
    final static String Pages = "";
    // PDF document password. Leave empty for unprotected documents.
    final static String Password = "";
    // Destination XLS file name
    final static Path DestinationFile = Paths.get(".\\result.xls");

    public static void main(String[] args) throws IOException
        // Create HTTP client instance
        OkHttpClient webClient = new OkHttpClient();

        Some of advanced options available through profiles:
        (JSON can be single/double-quoted and contain comments.)
            "profiles": [
                    "profile1": {
                        "NumberDecimalSeparator": "", // Allows to customize decimal separator in numbers.
                        "NumberGroupSeparator": "", // Allows to customize thousands separator.
                        "AutoDetectNumbers": true, // Whether to detect numbers. Values: true / false
                        "RichTextFormatting": true, // Whether to keep text style and fonts. Values: true / false
                        "PageToWorksheet": true, // Whether to create separate worksheet for each page of PDF document. Values: true / false
                        "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
                        "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
                        "LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows"
                        "ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables"
                        "Unwrap": false, // Unwrap grouped text in table cells. Values: true / false
                        "ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false
                        "DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection.
                        "CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction.
                        "CheckPermissions": true, // Ignore document permissions. Values: true / false
        // Sample profile that sets advanced conversion options.
        // Advanced options are properties of XLSExtractor class from ByteScout PDF Extractor SDK used in the back-end:
        String Profiles = "{ 'profiles': [ { 'profile1': { 'RichTextFormatting': false, 'PageToWorksheet': false } } ] }";

        // Prepare URL for `PDF To XLS` API call
        String query = "";

        // Make correctly escaped (encoded) URL
        URL url = null;
            url = new URI(null, query, null).toURL();
        catch (URISyntaxException e)

        // Create JSON payload
		String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\", \"profiles\": \"%s\"}",

        // Prepare request body
        RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
        // Prepare request
        Request request = new Request.Builder()
            .addHeader("x-api-key", API_KEY) // (!) Set API Key
            .addHeader("Content-Type", "application/json")
        // Execute request
        Response response = webClient.newCall(request).execute();

        if (response.code() == 200)
            // Parse JSON response
            JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();

            boolean error = json.get("error").getAsBoolean();
            if (!error)
                // Get URL of generated XLS file
                String resultFileUrl = json.get("url").getAsString();

                // Download XLS file
                downloadFile(webClient, resultFileUrl, DestinationFile.toFile());

                System.out.printf("Generated XLS file saved as \"%s\" file.", DestinationFile.toString());
                // Display service reported error
            // Display request error
            System.out.println(response.code() + " " + response.message());

    public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
        // Prepare request
        Request request = new Request.Builder()
        // Execute request
        Response response = webClient.newCall(request).execute();

        byte[] fileBytes = response.body().bytes();

        // Save downloaded bytes to file
        OutputStream output = new FileOutputStream(destinationFile);

} Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.

Get your API key here!

Download Source Code (.zip)

return to the previous page explore PDF To XLS endpoint