I don't know what you're supposed to get out from the em. But I will give you all the data you say you need to figure it out.
First we load the HTML.
string html = "<tr>" +
"<td>" +
"<div onmouseover = \"toggle('clue_J_1_1', 'clue_J_1_1_stuck', '<em class="correct_response">Obama</em><br/><br/><table width="100%"><tr><td class="right">Kailyn</td></tr></table>')\" onmouseout = \"toggle('clue_J_1_1', 'clue_J_1_1_stuck', 'Michelle LaVaughn Robinson')\" onclick = \"togglestick('clue_J_1_1_stuck')\"></div></td></tr>";
HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);
//Console.WriteLine(doc.DocumentNode.OuterHtml);
Then we get the value of the attribute, onmouseover.
string toggle = doc.DocumentNode.SelectSingleNode("//tr//td/div[@onmouseover]").GetAttributeValue("onmouseover", "FAILED");
It will return FAILED if it failed to find an attribute named "onmouseover". Now we get the parameters of the toggle method where each are enclosed by two '(apostrophe).
//Get Variables from toggle()
List<string> toggleVariables = new List<string>();
bool flag = false; string temp = "";
for(int i=0; i<toggle.Length; i++)
{
if (toggle[i] == '\'' && flag== true)
{
toggleVariables.Add(temp);
temp = "";
flag = false;
}
else if (flag)
{
temp += toggle[i];
}
else if (toggle[i] == '\'')
{
flag = true;
}
}
After that we have a list with 3 entities. In this case it will contain the following.
- clue_J_1_1
- clue_J_1_1_stuck
- <em class="correct_response">Obama</em><br/><br/><table width="100%"><tr><td class="right">Kailyn</td></tr></table>;
Now we can create a new HtmlDocument with the HTML code from the third parameter. But first we have to convert it into workable HTML since the third parameter contains escape characters from HTML.
//Make it into workable HTML
toggleVariables[2] = HttpUtility.HtmlDecode(toggleVariables[2]);
//New HtmlDocument
HtmlDocument htmlInsideToggle = new HtmlDocument();
htmlInsideToggle.LoadHtml(toggleVariables[2]);
Console.WriteLine(htmlInsideToggle.DocumentNode.OuterHtml);
And done. The code in it's entirety is below from here.
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using HtmlAgilityPack;
using System.Web;
namespace test
{
class Program
{
public static void Main(string[] args)
{
string html = "<tr>" +
"<td>" +
"<div onmouseover = \"toggle('clue_J_1_1', 'clue_J_1_1_stuck', '<em class="correct_response">Obama</em><br/><br/><table width="100%"><tr><td class="right">Kailyn</td></tr></table>')\" onmouseout = \"toggle('clue_J_1_1', 'clue_J_1_1_stuck', 'Michelle LaVaughn Robinson')\" onclick = \"togglestick('clue_J_1_1_stuck')\"></div></td></tr>";
HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);
//Console.WriteLine(doc.DocumentNode.OuterHtml);
string toggle = doc.DocumentNode.SelectSingleNode("//tr//td/div[@onmouseover]").GetAttributeValue("onmouseover", "FAILED");
//Clean up string
//Console.WriteLine(toggle);
//Get Variables from toggle()
List<string> toggleVariables = new List<string>();
bool flag = false; string temp = "";
for(int i=0; i<toggle.Length; i++)
{
if (toggle[i] == '\'' && flag== true)
{
toggleVariables.Add(temp);
temp = "";
flag = false;
}
else if (flag)
{
temp += toggle[i];
}
else if (toggle[i] == '\'')
{
flag = true;
}
}
//Make it into workable HTML
toggleVariables[2] = HttpUtility.HtmlDecode(toggleVariables[2]);
//New HtmlDocument
HtmlDocument htmlInsideToggle = new HtmlDocument();
htmlInsideToggle.LoadHtml(toggleVariables[2]);
Console.WriteLine(htmlInsideToggle.DocumentNode.OuterHtml);
//You're on your own from here
Console.ReadKey();
}
}