示例#1
0
        protected void ParseWebPage(string url, string content, ElementToParseCollection elements)
        {
            trucker.Tell(new ParseStarted(url));

            System.Diagnostics.Stopwatch timer = new System.Diagnostics.Stopwatch();
            timer.Start();

            HtmlAgilityPack.HtmlDocument document = new HtmlAgilityPack.HtmlDocument();
            document.LoadHtml(content);

            var parsedElements = new ElementParsedCollection();

            foreach (var element in elements)
            {
                var node = document.DocumentNode.SelectSingleNode(element.Path);
                parsedElements.Add(new ElementParsed(element.Path, node.InnerText));
            }

            timer.Stop();

            trucker.Tell(new ParseFinished(url, timer.ElapsedMilliseconds));
            Sender.Tell(parsedElements);
        }
示例#2
0
 public WebPageToParse(string url, string content, ElementToParseCollection elements)
 {
     Url      = url;
     Content  = content;
     Elements = elements;
 }