public ContentExtractionUsingMiBAT(string urlString)
{
NonDispBrowser wb = new NonDispBrowser();
wb.NavigateAndWait(urlString);
HtmlDocument doc = wb.Document;
//_Node = doc.Body;
_Node = doc.GetElementsByTagName("html")[0];
foreach (HtmlElement node in _Node.All)
{
HashSet <HtmlElement> contentNodeSet = MiBAT(node);
foreach (HtmlElement contentNode in contentNodeSet)
{
ContentNodeSet.Add(contentNode);
}
}
}
public ContentExtractionUsingLossRatio(string urlString, int thresholdTextLength = 0)
{
if (thresholdTextLength > 0)
{
ThresholdTextLength = thresholdTextLength;
}
NonDispBrowser wb = new NonDispBrowser();
wb.NavigateAndWait(urlString);
HtmlDocument doc = wb.Document;
//_Node = doc.Body;
_Node = doc.GetElementsByTagName("html")[0];
CreateNodeProperty(_Node);
CreateLossRatio(_Node);
FindContentNode();
FindSeparator();
}
