public static void TestRemoveNodeFromUrl()
{
String url = "http://www.bbc.co.uk/news/";
HtmlSanitiser sn = new HtmlSanitiser(url);
RemoveNode rn1 = new RemoveNode("script", null, null);
sn.RemoveNodes(new RemoveNode[] { rn1 });
string htmlout = sn.Html;
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(htmlout);
bool foundNode = false;
if (doc.DocumentNode.Name == "script")
foundNode = true;
if(doc.DocumentNode.HasChildNodes)
{
foreach(HtmlNode cNode in doc.DocumentNode.ChildNodes)
if (cNode.Name == "script")
{
foundNode = true;
}
}
if (htmlout.Contains("<script"))
{
foundNode = true;
}
Assert.AreEqual(foundNode, false);
}
public void Download()
{
HtmlSanitiser sanity = new HtmlSanity.HtmlSanitiser(link);
sanity.RemoveNodes(RemoveNodes.ToArray());
string pathFile = path + FileName;
DownloadImages dn = new DownloadImages(link, path + @"images\");
dn.Download(sanity.Html);
StreamWriter sw = System.IO.File.CreateText(pathFile);
dn.Document.Save(sw);
sw.Flush();
sw.Close();
}
