Using HtmlAgilityPack to GET and POST web forms - Part 2

In my previous post I showed how to post a html form using HtmlAgilityPack. My FormElementCollection class only worked with simple <input> tags like text and hidden fields. In this post I am going to extend this class to handle checkboxes, radio buttons, drop downs and textareas.

To review, this is the FormElementCollection from last post:

public class FormElementCollection : Dictionary<string, string>
{
    public FormElementCollection(HtmlDocument htmlDoc)
    {
        var inputs = htmlDoc.DocumentNode.Descendants("input");
        foreach (var element in inputs)
        {
            string name = element.GetAttributeValue("name", "undefined");
            string value = element.GetAttributeValue("value", "");
            if (!name.Equals("undefined")) Add(name, value);
        }
    }

    public string AssemblePostPayload()
    {
        // Not changing. Same as before
    }
}

The constructor parses the HtmlDocument to get all form input elements. We just have to extend this to parse for the other types as well:

public class FormElementCollection : Dictionary<string, string>
{
    public FormElementCollection(HtmlDocument htmlDoc)
    {
        var inputs = htmlDoc.DocumentNode.Descendants("input");
        foreach (var element in inputs)
        {
            AddInputElement(element); 
        }

        var menus = htmlDoc.DocumentNode.Descendants("select");
        foreach (var element in menus)
        {
            AddMenuElement(element); 
        }

        var textareas = htmlDoc.DocumentNode.Descendants("textarea");
        foreach (var element in textareas)
        {
            AddTextareaElement(element);
        }
    }
}

The AddInputElement method parses the <input> nodes. It looks at the "type" attribute to special handle the checkboxes and radio buttons.

private void AddInputElement(HtmlNode element)
{
    string name = element.GetAttributeValue("name", "");
    string value = element.GetAttributeValue("value", "");
    string type = element.GetAttributeValue("type", "");            

    if (string.IsNullOrEmpty(name)) return;

    switch (type.ToLower())
    {
        case "checkbox": 
        case "radio":
            if (!ContainsKey(name)) Add(name, "");
            string isChecked = element.GetAttributeValue("checked", "unchecked"); 
            if (!isChecked.Equals("unchecked")) this[name] = value;
            break; 
        default: 
            Add(name, value); 
            break;
    }            
}

The AddMenuElement method parses the dropdown elements (the <select> nodes).

private void AddMenuElement(HtmlNode element)
{
    string name = element.GetAttributeValue("name", "");
    var options = element.Descendants("option");

    if (string.IsNullOrEmpty(name)) return;

    // choose the first option as default
    var firstOp = options.First();
    string defaultValue = firstOp.GetAttributeValue("value", firstOp.NextSibling.InnerText); 

    Add(name, defaultValue); 

    // check if any option is selected
    foreach (var option in options)
    {
        string selected = option.GetAttributeValue("selected", "notSelected");
        if (!selected.Equals("notSelected"))
        {
            string selectedValue = option.GetAttributeValue("value", option.NextSibling.InnerText);
            this[name] = selectedValue;
        }
    }
}

And finally, the AddTextareaElement method parses the the <textarea> nodes.

private void AddTextareaElement(HtmlNode element)
{
    string name = element.GetAttributeValue("name", "");
    if (string.IsNullOrEmpty(name)) return;
    Add(name, element.InnerText);
}

Now we can use this to post data for different kinds of form elements:

BrowserSession b = new BrowserSession();
b.Get("http://my.site.com/myForm.aspx");
b.FormElements["NameTextBox"] = "my name";
b.FormElements["MaleFemaleRadioButton"] = "male";
b.FormElements["CommentTextArea"] = "blah blah ...";
b.FormElements["StateDropDown"] = "WA";
string response = b.Post("http://my.site.com/myForm.aspx");