htmlParser解析提取html文件内容

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;

import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.util.NodeList;
import org.htmlparser.visitors.TextExtractingVisitor;


/**
*
*/

/**
* @author Administrator
*
*/
public class htmlparser {

/**
* @param args
*/
public String openFile(String file){
try {
BufferedReader bis = new BufferedReader(new InputStreamReader(new FileInputStream(new File(file))));
String htmlContent="";
String temp="";
temp=bis.readLine();
while(temp!=null){
htmlContent+=temp+"\n";
temp=bis.readLine();
}
bis.close();
/*System.out.println(htmlContent);*/
return htmlContent;
} catch (Exception e) {
// TODO: handle exception
System.out.print(e.toString());
return "";
}
}
public void? parsehtml(){
String htmlContent=openFile("D:\\temp\\61891.html");
try {
System.out.println("Parsing .....");
Parser parser=new Parser(htmlContent);
parser.setEncoding("GB2312");
/*TextExtractingVisitor vistor=new TextExtractingVisitor();*/
NodeFilter textFilter=new NodeClassFilter(TextNode.class);
NodeList nodes=parser.extractAllNodesThatMatch(textFilter);
for(int i=0;i<nodes.size();i++){
TextNode textNode=(TextNode)nodes.elementAt(i);
String lineString=textNode.toPlainTextString().trim();
if(lineString.equals(""))
continue;
System.out.println(lineString);
}
/*parser.visitAllNodesWith(vistor);
System.out.println(vistor.getExtractedText());*/
} catch (Exception e) {
// TODO: handle exception
System.out.print(e.toString());
}
}
public static void main(String[] args) {
// TODO Auto-generated method stub
htmlparser test=new htmlparser();
test.parsehtml();
}
}