Link Search Menu Expand Document

PDF Text Search from URL Asynchronously - C#

PDF Search Text sample in C# demonstrating ‘PDF Text Search from URL Asynchronously’

Program.cs
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
using System;
using System.Collections.Generic;
using System.Net;
using System.Threading;

namespace ByteScoutWebApiExample
{
    class Program
    {
        // The authentication key (API Key).
        // Get your own by registering at https://app.pdf.co
        const 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/
        const 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-'.
        const string Pages = "";

        // PDF document password. Leave empty for unprotected documents.
        const string Password = "";

        // Search string. 
        const 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) 
        const bool RegexSearch = true;

        // (!) Make asynchronous job
        const bool Async = true;


        static void Main(string[] args)
        {
            // Create standard .NET web client instance
            WebClient webClient = new WebClient();

            // Set API Key
            webClient.Headers.Add("x-api-key", API_KEY);

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

            // Prepare requests params as JSON
            Dictionary<string, object> parameters = new Dictionary<string, object>();
            parameters.Add("password", Password);
            parameters.Add("pages", Pages);
            parameters.Add("url", SourceFileUrl);
            parameters.Add("searchString", SearchString);
            parameters.Add("regexSearch", RegexSearch);
            parameters.Add("async", Async);

            // Convert dictionary of params to JSON
            string jsonPayload = JsonConvert.SerializeObject(parameters);

            try
            {
                // Execute POST request with JSON payload
                string response = webClient.UploadString(url, jsonPayload);

                // Parse JSON response
                JObject json = JObject.Parse(response);

                if (json["error"].ToObject<bool>() == false)
                {
                    // Asynchronous job ID
                    string jobId = json["jobId"].ToString();

                    // URL of generated json file that will available after the job completion
                    string resultFileUrl = json["url"].ToString();

                    // 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(jobId); // Possible statuses: "working", "failed", "aborted", "success".

                        // Display timestamp and status (for demo purposes)
                        Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status);

                        if (status == "success")
                        {
                            // Execute request
                            string respFileJson = webClient.DownloadString(resultFileUrl);

                            // Parse JSON response
                            JArray jsonFoundInformation = JArray.Parse(respFileJson);

                            // Display found information in console
                            foreach (JToken item in jsonFoundInformation)
                            {
                                Console.WriteLine($"Found text \"{item["text"]}\" at coordinates {item["left"]}, {item["top"]}");
                            }

                            break;
                        }
                        else if (status == "success")
                        {
                            // Pause for a few seconds
                            Thread.Sleep(3000);
                        }
                        else
                        {
                            Console.WriteLine(status);
                            break;
                        }
                    }
                    while (true);
                }
                else
                {
                    Console.WriteLine(json["message"].ToString());
                }
            }
            catch (WebException e)
            {
                Console.WriteLine(e.ToString());
            }

            webClient.Dispose();

            Console.WriteLine();
            Console.WriteLine("Press any key...");
            Console.ReadKey();
        }


        static string CheckJobStatus(string jobId)
        {
            using (WebClient webClient = new WebClient())
            {
                // Set API Key
                webClient.Headers.Add("x-api-key", API_KEY);

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

                string response = webClient.DownloadString(url);
                JObject json = JObject.Parse(response);

                return Convert.ToString(json["status"]);
            }
        }

    }
}

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