初试htmlCleaner结合Xpath

//import java.io.File;
import java.io.IOException;
import java.net.URL;
import org.htmlcleaner.CleanerProperties;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.PrettyXmlSerializer;
import org.htmlcleaner.TagNode;
import org.htmlcleaner.XPatherException;
//import com.sun.xml.internal.txw2.output.XmlSerializer;

/**
 * 数据抓取
 */
public class HtmlClean {

	@SuppressWarnings("deprecation")
	/**
	 * 数据抓取
	 */
	public void cleanHtml(String htmlurl, String xmlurl, String xpath) throws XPatherException {
		try {
			//将目标网址内容抓取下来存到本地的XML文件中（格式化）
			//long start = System.currentTimeMillis();
			HtmlCleaner cleaner = new HtmlCleaner();
			CleanerProperties props = cleaner.getProperties();
			props.setUseCdataForScriptAndStyle(true);
			props.setRecognizeUnicodeChars(true);
			props.setUseEmptyElementTags(true);
			props.setAdvancedXmlEscape(true);
			props.setTranslateSpecialEntities(true);
			props.setBooleanAttributeValues("empty");
			TagNode node = cleaner.clean(new URL(htmlurl));
//			System.out.println(in);
			//System.out.println(((TagNode) ns[0]).getText());
			//System.out.println("vreme:" + (System.currentTimeMillis() - start));
			new PrettyXmlSerializer(props).writeXmlToFile(node, xmlurl);//格式化保存
			String result = new PrettyXmlSerializer(props).getXmlAsString(node);
			//System.out.println("vreme:" + (System.currentTimeMillis() - start));
			System.out.println("*********************************************************");
			//
			//
			//TagNode Xmlnode = cleaner.clean(new URL(xmlurl));//从已经格式化的XML文件中取出所要的数据
			TagNode Xmlnode = cleaner.clean(new String(result));//从已格式化的String中取出所要的数据
			Object[] ns = Xmlnode.getElementsByName("title", true); // 标题
			if (ns.length > 0) {
				System.out.println("title=" + ((TagNode) ns[0]).getText());
			}
			ns = Xmlnode.evaluateXPath(xpath); // 选取class为指定dixian1的所有td标签
//			for (int i = 0; i < ns.length; i++) {
//				String in = cleaner.getInnerHtml((TagNode) ns[i]);
//				System.out.println("<span>" + in + "</span>");
//			}
			System.out.println("*********************************************************");
			String in = cleaner.getInnerHtml((TagNode) ns[0]);
			for(int i=0 ;i<ns.length ;i++){
				in = cleaner.getInnerHtml((TagNode) ns[i]);
				System.out.println(in);
				if((i+1)%8==0){
					System.out.println("*********************************************************");
				}
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

	public static void main(String[] args) throws XPatherException {
		HtmlClean cleaner = new HtmlClean();
		cleaner.cleanHtml("http://app.sipo.gov.cn:8080/sipo2008/searchfee/searchfee_action.jsp?sqh=01351345.1", "E://text/test.xml","//td[@class='dixian1']");
	}
}