Convert PDF to CSV with SharePoint and PDF.co

Convert PDF to CSV – Source Code Snippets

Check out the markup for Web Part visual control.

VisualWebPart1UserControl.ascx

<%@ Assembly Name="$SharePoint.Project.AssemblyFullName$" %>
<%@ Assembly Name="Microsoft.Web.CommandUI, Version=15.0.0.0, Culture=neutral, PublicKeyToken=71e9bce111e9429c" %> 
<%@ Register Tagprefix="SharePoint" Namespace="Microsoft.SharePoint.WebControls" Assembly="Microsoft.SharePoint, Version=15.0.0.0, Culture=neutral, PublicKeyToken=71e9bce111e9429c" %> 
<%@ Register Tagprefix="Utilities" Namespace="Microsoft.SharePoint.Utilities" Assembly="Microsoft.SharePoint, Version=15.0.0.0, Culture=neutral, PublicKeyToken=71e9bce111e9429c" %>
<%@ Register Tagprefix="asp" Namespace="System.Web.UI" Assembly="System.Web.Extensions, Version=4.0.0.0, Culture=neutral, PublicKeyToken=31bf3856ad364e35" %>
<%@ Import Namespace="Microsoft.SharePoint" %> 
<%@ Register Tagprefix="WebPartPages" Namespace="Microsoft.SharePoint.WebPartPages" Assembly="Microsoft.SharePoint, Version=15.0.0.0, Culture=neutral, PublicKeyToken=71e9bce111e9429c" %>
<%@ Control Language="C#" AutoEventWireup="true" CodeBehind="VisualWebPart1UserControl.ascx.cs" Inherits="PDFcoWebPart.VisualWebPart1.VisualWebPart1UserControl" %>
Chose file to convert<br />
<asp:FileUpload ID="FileUpload1" runat="server" Width="600px" />
<br />
<br />
<asp:Button ID="StartButton" runat="server" OnClick="StartButton_Click" Text="Convert to CSV" style="width: 610px; padding-left: 0px; margin-left: 0px; padding-right: 0px; padding-right: 0px;"/>
<br />
<br />
Log<br />
<asp:TextBox ID="LogTextBox" runat="server" Height="80px" TextMode="MultiLine" Width="600px"></asp:TextBox>
<br />
<br />
Result<br />
<asp:TextBox ID="ResultTextBox" runat="server" Height="500px" TextMode="MultiLine" Width="600px"></asp:TextBox>

This is code behind for Web Part User Control.

VisualWebPart1UserControl.ascx.cs

using System;
using System.Collections.Generic;
using System.Net;
using System.Threading;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;

namespace PDFcoWebPart.VisualWebPart1
{
    public partial class VisualWebPart1UserControl : UserControl
    {
        string API_KEY = Utils.API_KEY;

        // 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 = "";
        const bool Async = true;

        protected void Page_Load(object sender, EventArgs e)
        {
        }

        protected void StartButton_Click(object sender, EventArgs e)
        {
            var fileData = FileUpload1.FileBytes;

            // Create standard .NET web client instance
            ServicePointManager.Expect100Continue = true;
            ServicePointManager.SecurityProtocol = SecurityProtocolType.Tls12;
            WebClient webClient = new WebClient();

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

            // 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 = Uri.EscapeUriString(string.Format(
                "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
                FileUpload1.FileName));

            try
            {
                // Execute request
                string response = webClient.DownloadString(query);

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

                if (json["status"].ToString() != "error")
                {
                    // Get URL to use for the file upload
                    string uploadUrl = json["presignedUrl"].ToString();
                    string uploadedFileUrl = json["url"].ToString();

                    // 2. UPLOAD THE FILE TO CLOUD.
                    webClient.Headers.Add("content-type", "application/octet-stream");
                    //webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
                    webClient.UploadData(uploadUrl, "PUT", fileData); // You can use UploadData() instead if your file is byte[] or Stream
                    webClient.Headers.Remove("content-type");

                    // 3. CONVERT UPLOADED PDF FILE TO CSV

                    // URL for `PDF To CSV` API call
                    var url = "https://api.pdf.co/v1/pdf/convert/to/csv";

                    // Prepare requests params as JSON
                    Dictionary<string, object> parameters = new Dictionary<string, object>();
                    parameters.Add("name", FileUpload1.FileName);
                    parameters.Add("password", Password);
                    parameters.Add("pages", Pages);
                    parameters.Add("url", uploadedFileUrl);
                    parameters.Add("async", Async);

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

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

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

                        if (json["status"].ToString() != "error")
                        {
                            // Asynchronous job ID
                            string jobId = json["jobId"].ToString();
                            // URL of generated CSV 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)
                                LogTextBox.Text += DateTime.Now.ToLongTimeString() + ": " + status;

                                if (status == "success")
                                {
                                    // Download CSV file
                                    var csvText = webClient.DownloadString(resultFileUrl);

                                    LogTextBox.Text += "Generated CSV.";
                                    ResultTextBox.Text += csvText;
                                    break;
                                }
                                else if (status == "working")
                                {
                                    // Pause for a few seconds
                                    Thread.Sleep(3000);
                                }
                                else
                                {
                                    LogTextBox.Text += status;
                                    break;
                                }
                            }
                            while (true);
                        }
                        else
                        {
                            LogTextBox.Text += json["message"].ToString();
                        }
                    }
                    catch (WebException ex)
                    {
                        LogTextBox.Text += ex.ToString();
                    }
                }
                else
                {
                    LogTextBox.Text += json["message"].ToString();
                }
            }
            catch (Exception ex)
            {
                LogTextBox.Text += ex.ToString();
            }

            webClient.Dispose();

            LogTextBox.Text += "";
            LogTextBox.Text += "Done...";

        }

        protected 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"]);
            }
        }
    }
}

Source Code at GitHub

You can explore the full source code for this sample at this GitHub link.

Convert PDF to CSV – Sample Screenshots