/// <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 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);
}
/// <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 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;
}
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);
}
}
}
}
}