html = StringEscapeUtils.unescapeHtml(html);
final HashSet<String> outlinkSet = extractOutlinks(html, site);
String title = extractTitle(html);
String extractedLargestText = extractor.getText(html);
return new ContentFetchResult(site, outlinkSet, title,
extractedLargestText);
} catch (ParserException pEx) {
// ignore parser exceptions, they contain mostly garbage
} catch (RuntimeException rEx) {
rEx.printStackTrace();