/// <summary>
/// Removes all HTML comments from a string.
/// </summary>
/// <param name="strString">The string.</param>
/// <returns>Comment-free version of string.</returns>
public static string RemoveComments(string strString)
{
// Return comment-free version of string
string strCommentFreeString = "";
string strSegment = "";
HTMLStringHelper parser = new HTMLStringHelper(strString);
while (parser.ExtractTo("<!--", ref strSegment))
{
strCommentFreeString += strSegment;
if (!parser.SkipToEndOf("-->"))
{
return(strString);
}
}
parser.ExtractToEnd(ref strSegment);
strCommentFreeString += strSegment;
return(strCommentFreeString);
}
/// <summary>
/// Retrieves the collection of HTML links in a string.
/// </summary>
/// <param name="strString">The string.</param>
/// <param name="strRootUrl">Root url (may be null).</param>
/// <param name="documents">Collection of document link strings.</param>
/// <param name="images">Collection of image link strings.</param>
public static void GetLinks(string strString, string strRootUrl, ref ArrayList documents, ref ArrayList images)
{
// Remove comments and JavaScript and fix links
strString = HTMLStringHelper.RemoveComments(strString);
strString = HTMLStringHelper.RemoveScripts(strString);
HTMLStringHelper parser = new HTMLStringHelper(strString);
parser.ReplaceEvery("\'", "\"");
// Set root url
string rootUrl = "";
if (strRootUrl != null)
{
rootUrl = strRootUrl.Trim();
}
if ((rootUrl.Length > 0) && !rootUrl.EndsWith("/"))
{
rootUrl += "/";
}
// Extract HREF targets
string strUrl = "";
parser.ResetPosition();
while (parser.SkipToEndOfNoCase("href=\""))
{
if (parser.ExtractTo("\"", ref strUrl))
{
strUrl = strUrl.Trim();
if (strUrl.Length > 0)
{
if (strUrl.IndexOf("mailto:") == -1)
{
// Get fully qualified url (best guess)
if (!strUrl.StartsWith("http://") && !strUrl.StartsWith("ftp://"))
{
try
{
UriBuilder uriBuilder = new UriBuilder(rootUrl);
uriBuilder.Path = strUrl;
strUrl = uriBuilder.Uri.ToString();
}
catch (Exception)
{
strUrl = "http://" + strUrl;
}
}
// Add url to document list if not already present
if (!documents.Contains(strUrl))
{
documents.Add(strUrl);
}
}
}
}
}
// Extract SRC targets
parser.ResetPosition();
while (parser.SkipToEndOfNoCase("src=\""))
{
if (parser.ExtractTo("\"", ref strUrl))
{
strUrl = strUrl.Trim();
if (strUrl.Length > 0)
{
// Get fully qualified url (best guess)
if (!strUrl.StartsWith("http://") && !strUrl.StartsWith("ftp://"))
{
try
{
UriBuilder uriBuilder = new UriBuilder(rootUrl);
uriBuilder.Path = strUrl;
strUrl = uriBuilder.Uri.ToString();
}
catch (Exception)
{
strUrl = "http://" + strUrl;
}
}
// Add url to images list if not already present
if (!images.Contains(strUrl))
{
images.Add(strUrl);
}
}
}
}
}