public static string removeScripts(string strString)
{
string text = "";
string text2 = "";
StringParser stringParser = new StringParser(strString);
while (stringParser.extractToNoCase("<script", ref text2))
{
text += text2;
if (!stringParser.skipToEndOfNoCase("</script>"))
{
stringParser.Content = text;
return(strString);
}
}
stringParser.extractToEnd(ref text2);
return(text + text2);
}
public static void getLinks(string strString, string strRootUrl, ref ArrayList documents, ref ArrayList images)
{
strString = StringParser.removeComments(strString);
strString = StringParser.removeScripts(strString);
StringParser stringParser = new StringParser(strString);
stringParser.replaceEvery("'", "\"");
string text = "";
if (strRootUrl != null)
{
text = strRootUrl.Trim();
}
if (text.Length > 0 && !text.EndsWith("/"))
{
text += "/";
}
string text2 = "";
stringParser.resetPosition();
while (stringParser.skipToEndOfNoCase("href=\""))
{
if (stringParser.extractTo("\"", ref text2))
{
text2 = text2.Trim();
if (text2.Length > 0 && text2.IndexOf("mailto:") == -1)
{
if (!text2.StartsWith("http://") && !text2.StartsWith("ftp://"))
{
try
{
UriBuilder uriBuilder = new UriBuilder(text);
uriBuilder.Path =text2;
text2 = uriBuilder.Uri.ToString();
}
catch (Exception)
{
text2 = "http://" + text2;
}
}
if (!documents.Contains(text2))
{
documents.Add(text2);
}
}
}
}
stringParser.resetPosition();
while (stringParser.skipToEndOfNoCase("src=\""))
{
if (stringParser.extractTo("\"", ref text2))
{
text2 = text2.Trim();
if (text2.Length > 0)
{
if (!text2.StartsWith("http://") && !text2.StartsWith("ftp://"))
{
try
{
UriBuilder uriBuilder2 = new UriBuilder(text);
uriBuilder2.Path = text2;
text2 = uriBuilder2.Uri.ToString();
}
catch (Exception)
{
text2 = "http://" + text2;
}
}
if (!images.Contains(text2))
{
images.Add(text2);
}
}
}
}
}
public static string removeScripts(string strString)
{
string text = "";
string text2 = "";
StringParser stringParser = new StringParser(strString);
while (stringParser.extractToNoCase("<script", ref text2))
{
text += text2;
if (!stringParser.skipToEndOfNoCase("</script>"))
{
stringParser.Content = text;
return strString;
}
}
stringParser.extractToEnd(ref text2);
return text + text2;
}
public static void getLinks(string strString, string strRootUrl, ref ArrayList documents, ref ArrayList images)
{
strString = StringParser.removeComments(strString);
strString = StringParser.removeScripts(strString);
StringParser stringParser = new StringParser(strString);
stringParser.replaceEvery("'", "\"");
string text = "";
if (strRootUrl != null)
{
text = strRootUrl.Trim();
}
if (text.Length > 0 && !text.EndsWith("/"))
{
text += "/";
}
string text2 = "";
stringParser.resetPosition();
while (stringParser.skipToEndOfNoCase("href=\""))
{
if (stringParser.extractTo("\"", ref text2))
{
text2 = text2.Trim();
if (text2.Length > 0 && text2.IndexOf("mailto:") == -1)
{
if (!text2.StartsWith("http://") && !text2.StartsWith("ftp://"))
{
try
{
UriBuilder uriBuilder = new UriBuilder(text);
uriBuilder.Path = text2;
text2 = uriBuilder.Uri.ToString();
}
catch (Exception)
{
text2 = "http://" + text2;
}
}
if (!documents.Contains(text2))
{
documents.Add(text2);
}
}
}
}
stringParser.resetPosition();
while (stringParser.skipToEndOfNoCase("src=\""))
{
if (stringParser.extractTo("\"", ref text2))
{
text2 = text2.Trim();
if (text2.Length > 0)
{
if (!text2.StartsWith("http://") && !text2.StartsWith("ftp://"))
{
try
{
UriBuilder uriBuilder2 = new UriBuilder(text);
uriBuilder2.Path = text2;
text2 = uriBuilder2.Uri.ToString();
}
catch (Exception)
{
text2 = "http://" + text2;
}
}
if (!images.Contains(text2))
{
images.Add(text2);
}
}
}
}
}