Link Search Menu Expand Document

PDF Table Search from Uploaded File Asynchronously - Java

PDF Find Table sample in Java demonstrating ‘PDF Table Search from Uploaded File Asynchronously’

Main.java
package com.company;

import com.google.gson.JsonArray;
import com.google.gson.JsonElement;
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;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;

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

    // Source file name
    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 = "";

    // (!) Make asynchronous job
    final static  boolean Async = true;


    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, uploadUrl, SourceFile.toFile()))
                {
                    // 3. SEARCH TABLE FROM UPLOADED PDF FILE

                    searchTableFromPDF(webClient, 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 searchTableFromPDF(OkHttpClient webClient, String uploadedFileUrl) throws IOException {

        // Prepare URL for PDF Table Search API call.
        // See documentation: https://apidocs.pdf.co
        String query = "https://api.pdf.co/v1/pdf/find/table";

        // 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("{\"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\", \"async\": \"%s\"}",
                Password,
                Pages,
                uploadedFileUrl,
                Async);
        // 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();
        
        DateTimeFormatter dtf = DateTimeFormatter.ofPattern("MM/dd/yyyy HH:mm:ss");

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

            boolean error = json.get("error").getAsBoolean();
            if (!error)
            {
                // Asynchronous job ID
                String jobId = json.get("jobId").getAsString();

                System.out.println("Job#" + jobId + ": has been created. - " + dtf.format(LocalDateTime.now()));

                // URL of generated json file that will available after the job completion
                String resultFileUrl = json.get("url").getAsString();

                // Check the job status in a loop.
                // If you don't want to pause the main thread you can rework the code
                // to use a separate thread for the status checking and completion.
                do {
                    String status = CheckJobStatus(webClient, jobId);  // Possible statuses: "working", "failed", "aborted", "success".

                    System.out.println("Job#" + jobId + ": " + status + " - " + dtf.format(LocalDateTime.now()));

                    if(status.compareToIgnoreCase("success") == 0){

                        // Build request for job url
                        request = new Request.Builder()
                                .url(resultFileUrl)
                                .build();

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

                        System.out.println(response.body().string());

                        break;
                    }
                    else if (status.compareToIgnoreCase("working") == 0){
                        // Pause for a few seconds
                        try{
                            Thread.sleep(3000);
                        }
                        catch (InterruptedException ex){
                            Thread.currentThread().interrupt(); // restore interrupted status
                        }
                    }
                    else{
                        System.out.println(status);
                        break;
                    }
                }while (true);
            }
            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 url, File sourceFile) throws IOException
    {
        // Prepare request body
        RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile);

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

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

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

    // Check Job Status
    private  static String CheckJobStatus(OkHttpClient webClient, String jobId) throws IOException {

        String url = "https://api.pdf.co/v1/job/check?jobid=" + jobId;

        // Prepare request
        Request request = new Request.Builder()
                .url(url)
                .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();

            return json.get("status").getAsString();
        }
        else
        {
            // Display request error
            System.out.println(response.code() + " " + response.message());
        }

        return "Failed";
    }

}

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 Find Table endpoint