/// <summary>
/// Parses the fetched content.
/// </summary>
protected override void parseContent()
{
// Initialize the scraper
this.Translation = string.Empty;
string strContent = this.Content;
StringParser parser = new StringParser (strContent);
// Scrape the translation
string strTranslation = string.Empty;
if (parser.skipToEndOf ("<span id=result_box")) {
if (parser.skipToEndOf ("onmouseout=\"this.style.backgroundColor='#fff'\">")) {
if (parser.extractTo("</span>", ref strTranslation)) {
strTranslation = StringParser.removeHtml (strTranslation);
}
}
}
#region Fix up the translation
int startClean = 0;
int endClean = 0;
int i=0;
while (i < strTranslation.Length) {
if (Char.IsLetterOrDigit (strTranslation[i])) {
startClean = i;
break;
}
i++;
}
i = strTranslation.Length - 1;
while (i > 0) {
char ch = strTranslation[i];
if (Char.IsLetterOrDigit (ch) ||
(Char.IsPunctuation (ch) && (ch != '\"'))) {
endClean = i;
break;
}
i--;
}
this.Translation = strTranslation.Substring (startClean, endClean - startClean + 1).Replace ("\"", "");
#endregion
}
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 removeHtml(string strString)
{
Hashtable hashtable = new Hashtable();
hashtable.Add(" ", " ");
hashtable.Add("&", "&");
hashtable.Add("å", "");
hashtable.Add("ä", "");
hashtable.Add("é", "");
hashtable.Add("í", "");
hashtable.Add("ì", "");
hashtable.Add("ò", "");
hashtable.Add("ö", "");
hashtable.Add(""", "\"");
hashtable.Add("ß", "");
StringParser stringParser = new StringParser(strString);
IEnumerator enumerator = hashtable.Keys.GetEnumerator();
try
{
while (enumerator.MoveNext())
{
string text = (string)enumerator.Current;
string strReplacement = hashtable[text] as string;
if (strString.IndexOf(text) != -1)
{
stringParser.replaceEveryExact(text, strReplacement);
}
}
}
finally
{
IDisposable disposable = enumerator as IDisposable;
if (disposable != null)
{
disposable.Dispose();
}
}
stringParser.replaceEveryExact("�", "&#");
stringParser.replaceEveryExact("'", "'");
stringParser.replaceEveryExact("</", " <~/");
stringParser.replaceEveryExact("<~/", "</");
hashtable.Clear();
hashtable.Add("<br>", " ");
hashtable.Add("<p>", " ");
enumerator = hashtable.Keys.GetEnumerator();
try
{
while (enumerator.MoveNext())
{
string text2 = (string)enumerator.Current;
string strReplacement2 = hashtable[text2] as string;
if (strString.IndexOf(text2) != -1)
{
stringParser.replaceEvery(text2, strReplacement2);
}
}
}
finally
{
IDisposable disposable = enumerator as IDisposable;
if (disposable != null)
{
disposable.Dispose();
}
}
strString = stringParser.Content;
string text3 = "";
int num = 0;
int num2;
while ((num2 = strString.IndexOf("<", num)) != -1)
{
string text4 = strString.Substring(num, num2 - num);
text3 += text4;
num = num2 + 1;
int num3 = strString.IndexOf(">", num);
if (num3 == -1)
{
break;
}
num = num3 + 1;
}
if (num < strString.Length)
{
text3 += strString.Substring(num, strString.Length - num);
}
strString = text3;
stringParser.Content = strString;
stringParser.replaceEveryExact(" ", " ");
strString = stringParser.Content.Trim();
return strString;
}
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 string removeComments(string strString)
{
string text = "";
string text2 = "";
StringParser stringParser = new StringParser(strString);
while (stringParser.extractTo("<!--", ref text2))
{
text += text2;
if (!stringParser.skipToEndOf("-->"))
{
return strString;
}
}
stringParser.extractToEnd(ref text2);
return text + text2;
}
