/// <summary>
/// Gets the title out of the HTML head section.
/// </summary>
/// <param name="url">The URL of the page</param>
/// <param name="defaultIfNoMatch">string to return, if no match was found</param>
/// <param name="credentials">Credentials for authenticating the request</param>
/// <param name="proxy">Proxy server to direct the request through</param>
/// <returns></returns>
//dup to FindTitle2() - which one we should use?
public static string FindTitle(string url, string defaultIfNoMatch, IWebProxy proxy, ICredentials credentials)
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
request.AllowAutoRedirect = true;
request.Proxy = proxy;
request.Credentials = credentials;
request.Timeout = 5 * 1000 /* 5 second timeout */;
if (FeedSource.SetCookies)
{
HttpCookieManager.SetCookies(request);
}
/* use bogus user agent since some sites will bounce you to unsupported browser page otherwise */
request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1;)";
string title = defaultIfNoMatch;
Stream stream = null;
try
{
stream = request.GetResponse().GetResponseStream();
SgmlReader reader = new SgmlReader();
reader.InputStream = new StreamReader(stream);
while (reader.Read())
{
if ((reader.NodeType == XmlNodeType.Element) && (reader.Name.ToLower().Equals("title")))
{
title = reader.ReadElementContentAsString();
stream.Flush();
break;
}
} //while
}
catch (Exception e)
{
_log.Debug("Error retrieving title from HTML page at " + url, e);
}
finally
{
if (stream != null)
{
stream.Close();
}
}
return(title);
}
//dup to FindTitle() - which one we should use?
public static string FindTitle2(string url, string defaultIfNoMatch, IWebProxy proxy, ICredentials credentials)
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
request.AllowAutoRedirect = true;
request.Proxy = proxy;
request.Credentials = credentials;
request.Timeout = 5 * 1000 /* 5 second timeout */;
if (FeedSource.SetCookies)
{
HttpCookieManager.SetCookies(request);
}
/* use bogus user agent since some sites will bounce you to unsupported browser page otherwise */
request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1;)";
string title = defaultIfNoMatch;
using (HttpWebResponse response = (HttpWebResponse)request.GetResponse())
{
using (FastSgmlXPathReader sgmlReader = new FastSgmlXPathReader())
{
using (StreamReader inputStreamReader = new StreamReader(response.GetResponseStream()))
{
try
{
sgmlReader.InputStream = inputStreamReader;
sgmlReader.DocType = "HTML";
sgmlReader.CaseFolding = CaseFolding.ToLower;
bool done = false;
while (!done && sgmlReader.Read())
{
if (sgmlReader.NodeType == XmlNodeType.Element)
{
switch (sgmlReader.XPath)
{
case "//html/title":
title = sgmlReader.ReadElementContentAsString(); // .ReadInnerXml();
done = true;
break;
case "//html/head/title":
title = sgmlReader.ReadElementContentAsString(); // .ReadInnerXml();
done = true;
break;
case "//html/body":
done = true;
break;
}
}
} //while
}
catch (Exception e)
{
_log.Debug("Error retrieving title from HTML page at " + url, e);
}
}
}
}
return(title);
}
