Link Search Menu Expand Document

PDF Text Search from URL - Java

PDF Search Text sample in Java demonstrating ‘PDF Text Search from URL’

Main.java
package com.company;

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

import java.io.*;
import java.net.*;

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

    // Direct URL of source PDF file.
    // You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/    
    final static String SourceFileURL = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/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 = "";

    // Search string.
	final static String SearchString = "\\d{1,}\\.\\d\\d"; // Regular expression to find numbers like '100.00'
    // Note: do not use `+` char in regex, but use `{1,}` instead.
    // `+` char is valid for URL and will not be escaped, and it will become a space char on the server side.

    // Enable regular expressions (Regex)
    final static boolean RegexSearch = true;

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

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

        // 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\", \"searchString\": \"%s\", \"regexSearch\": \"%s\"}",
                Password,
                Pages,
                SourceFileURL,
                SearchString,
                RegexSearch);

        // 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)
            {
                // Display found items in console
                for (JsonElement element : json.get("body").getAsJsonArray())
                {
                    JsonObject item = (JsonObject) element;
                    System.out.println("Found text " + item.get("text") + " at coordinates " + item.get("left") + ", "+ item.get("top"));
                }
            }
            else
            {
                // Display service reported error
                System.out.println(json.get("message").getAsString());
            }
        }
        else
        {
            // Display request error
            System.out.println(response.code() + " " + response.message());
        }
    }
}

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 Search Text endpoint