// The result of parsing the html-content
setCleanedContent(cleanedContent);
// Extract links
LinkVisitor linkVisitor = new LinkVisitor();
if (isContentCutted) {
// This means a new parser run which is expensive but neccessary
htmlPage = new Page(rawDocument.getContentAsString(), "UTF-8");
parser = new Parser(new Lexer(htmlPage));
} else {
parser.reset();
}
try {
// Parse the content
parser.visitAllNodesWith(linkVisitor);
ArrayList<Tag> links = linkVisitor.getLinks();
htmlPage.setBaseUrl(rawDocument.getUrl());
// Iterate over all links found
Iterator linksIter = links.iterator();
while (linksIter.hasNext()) {