/// <summary>
/// Parse input html page for form containing specified fragment and create HtmlForm from it
/// </summary>
/// <param name="page">html page</param>
/// <param name="url">url of the input html page</param>
/// <param name="fragment">part of html code that contained by the form. Can be null.</param>
/// <returns>object presenting found and parsed form</returns>
public HtmlForm ParseForm(string page, string url, string fragment)
{
HtmlForm hf = null;
try
{
Match m = Regex.Match(page, @"<form\s.*?</form.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
if (fragment == null || m.Result("$0").Contains(fragment))
{
hf = new HtmlForm();
break;
}
m = m.NextMatch();
}
if (hf == null)
return null;
string form = m.Result("$0");
m = Regex.Match(form, @"<form[^>]*?\smethod=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m.Success && m.Result("$2").ToUpper() == HttpRequest.RequestMethod.POST.ToString())
{
hf.Method = HttpRequest.RequestMethod.POST;
}
m = Regex.Match(form, @"<form[^>]*?\saction=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m.Success)
{
Uri ubase = new Uri(url, UriKind.Absolute);
string link = HttpUtility.HtmlDecode(m.Result("$2"));
Uri ulink = new Uri(ubase, link);
hf.Url = ulink.AbsoluteUri.Trim();
}
else
{
hf.Url = url;
}
m = Regex.Match(form, @"<input\s[^>]+?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
string input_element = m.Result("$0");
Match m2 = Regex.Match(input_element, @"\sname=(['""]?)(.+?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
{
m = m.NextMatch();
continue;
}
string name = m2.Result("$2");
string type = "";
m2 = Regex.Match(input_element, @"\stype=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m2.Success)
{
type = m2.Result("$2");
}
type = type.ToUpper().Trim();
bool ignore_value = false;
if (type == "CHECKBOX")
{
m2 = Regex.Match(input_element, @"\s(['""]?)checked\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
ignore_value = true;
}
string value = null;
m2 = Regex.Match(input_element, @"\svalue=(['""]?)(.*?)\1", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
m2 = Regex.Match(input_element, @"\svalue(=)(.*?)[\s>]", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m2.Success)
{
if (!ignore_value)
value = m2.Result("$2");
}
if (type == HtmlForm.ParameterType.HIDDEN.ToString())
hf.Create(name, HtmlForm.ParameterType.HIDDEN, value);
else if (type == "" || type == HtmlForm.ParameterType.TEXT.ToString())
hf.Create(name, HtmlForm.ParameterType.TEXT, value);
else if (type == HtmlForm.ParameterType.CHECKBOX.ToString())
hf.Create(name, HtmlForm.ParameterType.CHECKBOX, value);
else if (type == HtmlForm.ParameterType.RADIO.ToString())
hf.Create(name, HtmlForm.ParameterType.RADIO, value);
else if (type == HtmlForm.ParameterType.SUBMIT.ToString())
hf.Create(name, HtmlForm.ParameterType.SUBMIT, value);
else if (type == HtmlForm.ParameterType.RESET.ToString())
hf.Create(name, HtmlForm.ParameterType.RESET, value);
else if (type == HtmlForm.ParameterType.BUTTON.ToString())
hf.Create(name, HtmlForm.ParameterType.BUTTON, value);
else if (type == HtmlForm.ParameterType.PASSWORD.ToString())
hf.Create(name, HtmlForm.ParameterType.PASSWORD, value);
else if (type == HtmlForm.ParameterType.FILE.ToString())
hf.Create(name, HtmlForm.ParameterType.FILE, value);
else
hf.Create(name, HtmlForm.ParameterType.OTHER, value);
m = m.NextMatch();
}
m = Regex.Match(form, @"<textarea(\s[^>]*?)>(.*?)</textarea", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
Match m2 = Regex.Match(m.Result("$1"), @"\sname=['""]?(.*?)['""\s>]", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
continue;
string name = m2.Result("$1");
string value = m.Result("$2");
hf.Create(name, HtmlForm.ParameterType.TEXTAREA, value);
m = m.NextMatch();
}
m = Regex.Match(form, @"<select(\s[^>]*?>)(.*?)</select", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
Match m2 = Regex.Match(m.Result("$1"), @"[\s""']name=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
continue;
string name = m2.Result("$2");
hf.Create(name, HtmlForm.ParameterType.SELECT);
m2 = Regex.Match(m.Result("$2"), @"<OPTION(.*?>)(.*?)</OPTION", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m2.Success)
{
if (Regex.IsMatch(m2.Result("$1"), @" selected", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase))
{
string value = null;
Match m3 = Regex.Match(m2.Result("$1"), @"\svalue=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m3.Success)
value = m3.Result("$2");
else
value = m2.Result("$2");
hf.Add(name, value);
}
m2 = m2.NextMatch();
}
m = m.NextMatch();
}
return hf;
}
catch (ThreadAbortException)
{
}
catch (Exception e)
{
LogMessage.Error(e);
}
return null;
}
/// <summary>
/// Submit form. /*//NOTICE: parameters with null value will not submitted.*/
/// </summary>
/// <param name="form">parsed form</param>
/// <param name="send_cookies">defines whether cookies should be sent</param>
/// <returns>true if received success response</returns>
public bool SubmitForm(HtmlForm form, bool send_cookies)
{
return Do(new HttpRequest(form), send_cookies);
}
/// <summary>
/// Submit form with sending cookies. /*//NOTICE: parameters with null value will not submitted.*/
/// </summary>
/// <param name="form">parsed form</param>
/// <param name="send_cookies">defines whether cookies should be sent</param>
/// <returns>true if received success response</returns>
public bool SubmitForm(HtmlForm form)
{
return Do(new HttpRequest(form), true);
}
/// <summary>
/// Parse input html page for form containing specified fragment and create HtmlForm from it
/// </summary>
/// <param name="page">html page</param>
/// <param name="url">url of the input html page</param>
/// <param name="fragment">part of html code that contained by the form. Can be null.</param>
/// <returns>object presenting found and parsed form</returns>
public HtmlForm ParseForm(string page, string url, string fragment)
{
HtmlForm hf = null;
try
{
Match m = Regex.Match(page, @"<form\s.*?</form.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
if (fragment == null || m.Result("$0").Contains(fragment))
{
hf = new HtmlForm();
break;
}
m = m.NextMatch();
}
if (hf == null)
{
return(null);
}
string form = m.Result("$0");
m = Regex.Match(form, @"<form[^>]*?\smethod=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m.Success && m.Result("$2").ToUpper() == HttpRequest.RequestMethod.POST.ToString())
{
hf.Method = HttpRequest.RequestMethod.POST;
}
m = Regex.Match(form, @"<form[^>]*?\saction=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m.Success)
{
Uri ubase = new Uri(url, UriKind.Absolute);
string link = HttpUtility.HtmlDecode(m.Result("$2"));
Uri ulink = new Uri(ubase, link);
hf.Url = ulink.AbsoluteUri.Trim();
}
else
{
hf.Url = url;
}
m = Regex.Match(form, @"<input\s[^>]+?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
string input_element = m.Result("$0");
Match m2 = Regex.Match(input_element, @"\sname=(['""]?)(.+?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
{
m = m.NextMatch();
continue;
}
string name = m2.Result("$2");
string type = "";
m2 = Regex.Match(input_element, @"\stype=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m2.Success)
{
type = m2.Result("$2");
}
type = type.ToUpper().Trim();
bool ignore_value = false;
if (type == "CHECKBOX")
{
m2 = Regex.Match(input_element, @"\s(['""]?)checked\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
{
ignore_value = true;
}
}
string value = null;
m2 = Regex.Match(input_element, @"\svalue=(['""]?)(.*?)\1", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
{
m2 = Regex.Match(input_element, @"\svalue(=)(.*?)[\s>]", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
}
if (m2.Success)
{
if (!ignore_value)
{
value = m2.Result("$2");
}
}
if (type == HtmlForm.ParameterType.HIDDEN.ToString())
{
hf.Create(name, HtmlForm.ParameterType.HIDDEN, value);
}
else if (type == "" || type == HtmlForm.ParameterType.TEXT.ToString())
{
hf.Create(name, HtmlForm.ParameterType.TEXT, value);
}
else if (type == HtmlForm.ParameterType.CHECKBOX.ToString())
{
hf.Create(name, HtmlForm.ParameterType.CHECKBOX, value);
}
else if (type == HtmlForm.ParameterType.RADIO.ToString())
{
hf.Create(name, HtmlForm.ParameterType.RADIO, value);
}
else if (type == HtmlForm.ParameterType.SUBMIT.ToString())
{
hf.Create(name, HtmlForm.ParameterType.SUBMIT, value);
}
else if (type == HtmlForm.ParameterType.RESET.ToString())
{
hf.Create(name, HtmlForm.ParameterType.RESET, value);
}
else if (type == HtmlForm.ParameterType.BUTTON.ToString())
{
hf.Create(name, HtmlForm.ParameterType.BUTTON, value);
}
else if (type == HtmlForm.ParameterType.PASSWORD.ToString())
{
hf.Create(name, HtmlForm.ParameterType.PASSWORD, value);
}
else if (type == HtmlForm.ParameterType.FILE.ToString())
{
hf.Create(name, HtmlForm.ParameterType.FILE, value);
}
else
{
hf.Create(name, HtmlForm.ParameterType.OTHER, value);
}
m = m.NextMatch();
}
m = Regex.Match(form, @"<textarea(\s[^>]*?)>(.*?)</textarea", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
Match m2 = Regex.Match(m.Result("$1"), @"\sname=['""]?(.*?)['""\s>]", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
{
continue;
}
string name = m2.Result("$1");
string value = m.Result("$2");
hf.Create(name, HtmlForm.ParameterType.TEXTAREA, value);
m = m.NextMatch();
}
m = Regex.Match(form, @"<select(\s[^>]*?>)(.*?)</select", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m.Success)
{
Match m2 = Regex.Match(m.Result("$1"), @"[\s""']name=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (!m2.Success)
{
continue;
}
string name = m2.Result("$2");
hf.Create(name, HtmlForm.ParameterType.SELECT);
m2 = Regex.Match(m.Result("$2"), @"<OPTION(.*?>)(.*?)</OPTION", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
while (m2.Success)
{
if (Regex.IsMatch(m2.Result("$1"), @" selected", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase))
{
string value = null;
Match m3 = Regex.Match(m2.Result("$1"), @"\svalue=(['""]?)(.*?)\1.*?>", RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.IgnoreCase);
if (m3.Success)
{
value = m3.Result("$2");
}
else
{
value = m2.Result("$2");
}
hf.Add(name, value);
}
m2 = m2.NextMatch();
}
m = m.NextMatch();
}
return(hf);
}
catch (ThreadAbortException)
{
}
catch (Exception e)
{
LogMessage.Error(e);
}
return(null);
}
/// <summary>
/// Submit form with sending cookies. /*//NOTICE: parameters with null value will not submitted.*/
/// </summary>
/// <param name="form">parsed form</param>
/// <param name="send_cookies">defines whether cookies should be sent</param>
/// <returns>true if received success response</returns>
public bool SubmitForm(HtmlForm form)
{
return(Do(new HttpRequest(form), true));
}
/// <summary>
/// Submit form. /*//NOTICE: parameters with null value will not submitted.*/
/// </summary>
/// <param name="form">parsed form</param>
/// <param name="send_cookies">defines whether cookies should be sent</param>
/// <returns>true if received success response</returns>
public bool SubmitForm(HtmlForm form, bool send_cookies)
{
return(Do(new HttpRequest(form), send_cookies));
}
public HttpRequest(HtmlForm html_form, Dictionary<string, string> headers = null)
{
if (headers != null)
foreach (KeyValuePair<string, string> h in headers)
Headers[h.Key] = h.Value;
Url = html_form.Url;
string query = "";
foreach (string parameter in html_form.Names)
{
if (html_form.GetType(parameter) == HtmlForm.ParameterType.RESET)
continue;
foreach (string value in html_form[parameter])
query += "&" + HttpUtility.UrlEncode(parameter) + "=" + HttpUtility.UrlEncode(value);
}
Method = html_form.Method;
if (Method == RequestMethod.POST)
{
post_string = query;
PostData = Encoding.UTF8.GetBytes(post_string);
Headers["Content-Type"] = "application/x-www-form-urlencoded";
}
else
{
if (Url.Contains("?"))
Url += query;
else
Url += "?" + query.Substring(1);
}
}
/// <summary>
/// Downloads web page by POST.
/// </summary>
/// <param name="form">form with parameters. /*//NOTICE: parameters with null value will not be submitted.*/</param>
/// <param name="send_cookies">defines if cookies should be sent</param>
/// <returns>reqest status</returns>
public bool PostPage(HtmlForm form, bool send_cookies = true)
{
return Do(new HttpRequest(form, new Dictionary<string, string>() { { "Accept", Settings.Web.TextModeHttpRequestAcceptHeader } }), send_cookies);
}