using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using System.Windows.Forms;
using System.Net;
using System.IO;
using HtmlAgilityPack;
using mshtml;
using System.Text.RegularExpressions;
namespace Extract_Images
{
public partial class Form1 : Form
{
private string[] linkstoextract;
private int numberoflinks;
private int currentLinkNumber = 0;
private string mainlink;
private WebClient client;
private WebBrowser webBrowser1;
private string htmlCode;
private bool pagesorimages = false;
public Form1()
{
InitializeComponent();
webBrowser1 = new WebBrowser();
webBrowser1.ScriptErrorsSuppressed = true;
webBrowser1.DocumentCompleted += webBrowser1_DocumentCompleted;
label1.Text = "Number of links: ";
mainlink = "http://www.test.com/";
numberoflinks = 13;
backgroundWorker1.RunWorkerAsync();
}
private void ProcessNextLink()
{
if (currentLinkNumber < numberoflinks)
{
currentLinkNumber++;
string linktonav = mainlink + "index"+currentLinkNumber.ToString() + ".html";
pagesorimages = false;
backgroundWorker1.ReportProgress(0,currentLinkNumber);
webBrowser1.Navigate(linktonav);
}
}
int count = 0;
void webBrowser1_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
{
mshtml.HTMLDocument objHtmlDoc = (mshtml.HTMLDocument)webBrowser1.Document.DomDocument;
string pageSource = objHtmlDoc.documentElement.innerHTML;
List<string> links = new List<string>();
string[] hrefs = this.webBrowser1.Document.Links.Cast<HtmlElement>()
.Select(a => a.GetAttribute("href")).Where(h => h.Contains(".jpg")).ToArray();
foreach(string a in hrefs)
{
using (WebClient client = new WebClient())
{
client.DownloadFile(a, @"C:\Images\file" + count + ".jpg");
}
count ++;
pagesorimages = true;
backgroundWorker1.ReportProgress(0, count);
}
//ProcessNextLink();
}
private void Form1_Load(object sender, EventArgs e)
{
}
private void backgroundWorker1_DoWork(object sender, DoWorkEventArgs e)
{
ProcessNextLink();
}
private void backgroundWorker1_ProgressChanged(object sender, ProgressChangedEventArgs e)
{
if (pagesorimages == false)
{
label1.Text = e.UserState.ToString();
}
if (pagesorimages == true)
{
label2.Text = e.UserState.ToString();
}
}
private void backgroundWorker1_RunWorkerCompleted(object sender, RunWorkerCompletedEventArgs e)
{
}
}
}
The exception is on the second ReportProgress:
backgroundWorker1.ReportProgress(0, count);
This operation has already had OperationCompleted called on it and further calls are illegal
What i want to do is to report first the current page number in this case it's 1 to label1. And then to report the number of downloaded images in this page to label2.
Then to move to the next page with the method ProcessNextLink(); and again report the page number it should be 2 and then to report the number of images downloaded in page 2.
But i'm getting this exception already on the first page.
It was working fine without the backgroundworker in the event webBrowser1_DocumentCompleted i called ProcessNextLink(); in the bottom and it was working fine. But with the backgroundworker it's not working.