public static string removeScripts(string strString)
{
string str = "";
string strExtract = "";
StringParser parser = new StringParser(strString);
while (parser.extractToNoCase("<script", ref strExtract))
{
str = str + strExtract;
if (!parser.skipToEndOfNoCase("</script>"))
{
parser.Content = str;
return(strString);
}
}
parser.extractToEnd(ref strExtract);
return(str + strExtract);
}
public static void getLinks(string strString, string strRootUrl, ref ArrayList documents, ref ArrayList images)
{
strString = removeComments(strString);
strString = removeScripts(strString);
StringParser parser = new StringParser(strString);
parser.replaceEvery("'", "\"");
string uri = "";
if (strRootUrl != null)
{
uri = strRootUrl.Trim();
}
if ((uri.Length > 0) && !uri.EndsWith("/"))
{
uri = uri + "/";
}
string strExtract = "";
parser.resetPosition();
while (parser.skipToEndOfNoCase("href=\""))
{
if (parser.extractTo("\"", ref strExtract))
{
strExtract = strExtract.Trim();
if ((strExtract.Length > 0) && (strExtract.IndexOf("mailto:") == -1))
{
if (!strExtract.StartsWith("http://") && !strExtract.StartsWith("ftp://"))
{
try
{
UriBuilder builder = new UriBuilder(uri);
builder.Path = strExtract;
strExtract = builder.Uri.ToString();
}
catch (Exception)
{
strExtract = "http://" + strExtract;
}
}
if (!documents.Contains(strExtract))
{
documents.Add(strExtract);
}
}
}
}
parser.resetPosition();
while (parser.skipToEndOfNoCase("src=\""))
{
if (parser.extractTo("\"", ref strExtract))
{
strExtract = strExtract.Trim();
if (strExtract.Length > 0)
{
if (!strExtract.StartsWith("http://") && !strExtract.StartsWith("ftp://"))
{
try
{
UriBuilder builder2 = new UriBuilder(uri);
builder2.Path = strExtract;
strExtract = builder2.Uri.ToString();
}
catch (Exception)
{
strExtract = "http://" + strExtract;
}
}
if (!images.Contains(strExtract))
{
images.Add(strExtract);
}
}
}
}
}
public static string removeScripts(string strString)
{
string str = "";
string strExtract = "";
StringParser parser = new StringParser(strString);
while (parser.extractToNoCase("<script", ref strExtract))
{
str = str + strExtract;
if (!parser.skipToEndOfNoCase("</script>"))
{
parser.Content = str;
return strString;
}
}
parser.extractToEnd(ref strExtract);
return (str + strExtract);
}
public static void getLinks(string strString, string strRootUrl, ref ArrayList documents, ref ArrayList images)
{
strString = removeComments(strString);
strString = removeScripts(strString);
StringParser parser = new StringParser(strString);
parser.replaceEvery("'", "\"");
string uri = "";
if (strRootUrl != null)
{
uri = strRootUrl.Trim();
}
if ((uri.Length > 0) && !uri.EndsWith("/"))
{
uri = uri + "/";
}
string strExtract = "";
parser.resetPosition();
while (parser.skipToEndOfNoCase("href=\""))
{
if (parser.extractTo("\"", ref strExtract))
{
strExtract = strExtract.Trim();
if ((strExtract.Length > 0) && (strExtract.IndexOf("mailto:") == -1))
{
if (!strExtract.StartsWith("http://") && !strExtract.StartsWith("ftp://"))
{
try
{
UriBuilder builder = new UriBuilder(uri);
builder.Path = strExtract;
strExtract = builder.Uri.ToString();
}
catch (Exception)
{
strExtract = "http://" + strExtract;
}
}
if (!documents.Contains(strExtract))
{
documents.Add(strExtract);
}
}
}
}
parser.resetPosition();
while (parser.skipToEndOfNoCase("src=\""))
{
if (parser.extractTo("\"", ref strExtract))
{
strExtract = strExtract.Trim();
if (strExtract.Length > 0)
{
if (!strExtract.StartsWith("http://") && !strExtract.StartsWith("ftp://"))
{
try
{
UriBuilder builder2 = new UriBuilder(uri);
builder2.Path = strExtract;
strExtract = builder2.Uri.ToString();
}
catch (Exception)
{
strExtract = "http://" + strExtract;
}
}
if (!images.Contains(strExtract))
{
images.Add(strExtract);
}
}
}
}
}