Link Search Menu Expand Document

Convert PDF To HTML From Uploaded File - Java

PDF to HTML sample in Java demonstrating ‘Convert PDF To HTML From Uploaded File’

Main.java
package com.company;

import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;

import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;

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

    // Source PDF file
    final static Path SourceFile = Paths.get(".\\sample.pdf");
    // 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 HTML file name
    final static Path DestinationFile = Paths.get(".\\result.html");
    // Set to `true` to get simplified HTML without CSS. Default is the rich HTML keeping the document design.
    final static boolean PlainHtml = false;
    // Set to `true` if your document has the column layout like a newspaper.
    final static boolean ColumnLayout = false;

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

        // 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
        // * If you already have a direct file URL, skip to the step 3.

        // Prepare URL for `Get Presigned URL` API call
        String query = String.format(
                "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
                SourceFile.getFileName());

        // Prepare request
        Request request = new Request.Builder()
                .url(query)
                .addHeader("x-api-key", API_KEY) // (!) Set API Key
                .build();
        // 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 to use for the file upload
                String uploadUrl = json.get("presignedUrl").getAsString();
                // Get URL of uploaded file to use with later API calls
                String uploadedFileUrl = json.get("url").getAsString();

                // 2. UPLOAD THE FILE TO CLOUD.

                if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
                {
                    // 3. CONVERT UPLOADED PDF FILE TO HTML

                    PdfToHtml(webClient, API_KEY, DestinationFile, Password, Pages, PlainHtml, ColumnLayout, uploadedFileUrl);
                }
            }
            else
            {
                // Display service reported error
                System.out.println(json.get("message").getAsString());
            }
        }
        else
        {
            // Display request error
            System.out.println(response.code() + " " + response.message());
        }
    }

    public static void PdfToHtml(OkHttpClient webClient, String apiKey, Path destinationFile,
        String password, String pages, boolean plainHtml, boolean columnLayout, String uploadedFileUrl) throws IOException
    {
        // Prepare URL for `PDF To HTML` API call
        String query = "https://api.pdf.co/v1/pdf/convert/to/html";

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

        // Create JSON payload
		String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"simple\": \"%s\", \"columns\": \"%s\", \"url\": \"%s\"}",
                destinationFile.getFileName(),
                password,
                pages,
                plainHtml,
                columnLayout,
                uploadedFileUrl);

        // Prepare request body
        RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
        
        // Prepare request
        Request request = new Request.Builder()
            .url(url)
            .addHeader("x-api-key", API_KEY) // (!) Set API Key
            .addHeader("Content-Type", "application/json")
            .post(body)
            .build();
        
        // 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 HTML file
                String resultFileUrl = json.get("url").getAsString();

                // Download HTML file
                downloadFile(webClient, resultFileUrl, destinationFile.toFile());

                System.out.printf("Generated HTML file saved as \"%s\" file.", destinationFile.toString());
            }
            else
            {
                // Display service reported error
                System.out.println(json.get("message").getAsString());
            }
        }
        else
        {
            // Display request error
            System.out.println(response.code() + " " + response.message());
        }
    }

    public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
    {
        // Prepare request body
        RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());

        // Prepare request
        Request request = new Request.Builder()
                .url(url)
                .addHeader("x-api-key", apiKey) // (!) Set API Key
                .addHeader("content-type", "application/octet-stream")
                .put(body)
                .build();

        // Execute request
        Response response = webClient.newCall(request).execute();

        return (response.code() == 200);
    }

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

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

        // Save downloaded bytes to file
        OutputStream output = new FileOutputStream(destinationFile);
        output.write(fileBytes);
        output.flush();
        output.close();

        response.close();
    }
}

PDF.co 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 PDF.co API key here!

Download Source Code (.zip)

return to the previous page explore PDF to HTML endpoint