Question

I have this code:

private void ToLocalSiteOnlyToolStripMenuItem_Click(object sender, EventArgs e)
        {
            if (buttonSwitch == true)
            {
                ToLocalSiteOnlyToolStripMenuItem.ForeColor = Color.Red;
                buttonSwitch = false;
                removeExt = true;
            }
            else
            {
                ToLocalSiteOnlyToolStripMenuItem.ForeColor = Color.Black;
                buttonSwitch = true;
                removeExt = false;
            }
        }



private void removeExternals(List<string> externals)
    {

        for (int i = 0; i < externals.Count; i++)
        {
            if (!externals[i].StartsWith(mainUrl))
            {
                externals.RemoveAt(i);
            }
        }
    }

When i click the menu and its red then im calling the function removeExternals in here:

private List<string> test(string url, int levels,DoWorkEventArgs eve)
        {

            HtmlWeb hw = new HtmlWeb();
            List<string> webSites;
            try
            {
                doc = hw.Load(url);
                webSites = getLinks(doc);
                removeDupes(webSites);
                if (removeExt == true)
                {
                    removeExternals(webSites);
                }

Now the webSites List contain links of sites like for example:

www.ynet.co.il
www.hot.co.il
www.walla.co.il

Now the variable mainUrl is http://www.ynet.co.il
I want each iertion im calling the test function and then webSites each time have a different List of links to remove all the links that not start with http://www.ynet.co.il

So in the end each time i will come up in webSites with links that only start with: http://www.ynet.co.il

But it seems that my removeExternals function does not working good as i wanted.

Where is the problem and how to repair it ? Thanks.

Answer 1

The problem is in your loop:

  for (int i = 0; i < externals.Count; i++)
  {
      if (!externals[i].StartsWith(mainUrl))
      {
          externals.RemoveAt(i);
      }
  }

Every time you call RemoveAt(), you’re changing all the indexes. If you call RemoveAt(1), then everything after 1 is shifted down. I’d recommend looping through in reverse order, like:

  for (int i = externals.Count - 1; i >= 0; i--)
  {
      if (!externals[i].StartsWith(mainUrl))
      {
          externals.RemoveAt(i);
      }
  }