页面抓取特定链接

public static List<CmsLinkParser> getHtmlUrls(String url, String pageEncoding,String include) {
  List<CmsLinkParser> listClp = new ArrayList<CmsLinkParser>();
  StringFiltes stringFiltes = new StringFiltes();
  NodeList nodelist = null;
//  String filte = "/baidu";
  try {
   Parser parser = new Parser(url);
   parser.setEncoding(pageEncoding);
   nodelist = parser.parse(new NodeClassFilter(LinkTag.class));
  } catch (ParserException e) {
   e.printStackTrace();
  }
  System.out.println(nodelist.size());
  if (nodelist != null && nodelist.size() > 0) {

   for (int i = 0; i < nodelist.size(); i++){
    String urlLink = ((LinkTag)nodelist.elementAt(i)).extractLink().trim();
    String linkName = ((LinkTag)nodelist.elementAt(i)).getLinkText().trim();
    if (urlLink.indexOf("http") == 0 && linkName.trim().length() != 0&&urlLink.indexOf(include)>=0&&linkName.indexOf(CommonConstant.NOT_INCLUDE)<0){
     int num = 0;
     System.out.println(stringFiltes.replaceString(linkName) + ":" + urlLink);
     CmsLinkParser clp = new CmsLinkParser();
     clp.setLinkTitle(stringFiltes.replaceString(linkName));
     clp.setLinkSrc(urlLink);
     clp.setCreateTime(new Date());
     listClp.add(num, clp);
     num +=1;
   }
  }
  }
  return listClp;
 }