Wednesday, November 14, 2012

How to parse html tag by HTML Agility pack?

 http://www.codeplex.com/htmlagilitypack
 
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(@"<html><body><p><table id=""foo""><tr><th>hello</th></tr><tr><td>world</td></tr></table></body></html>");
 
foreach (HtmlNode table in doc.DocumentNode.SelectNodes("//table")) {
    Console.WriteLine("Found: " + table.Id);
    foreach (HtmlNode row in table.SelectNodes("tr")) {
        Console.WriteLine("row");
        foreach (HtmlNode cell in row.SelectNodes("th|td")) {
            Console.WriteLine("cell: " + cell.InnerText);
        }
    }

No comments:

Post a Comment