htmlparser.java

搜索引擎的预处理部分的代码

package test;

import java.io.*;
import org.htmlparser.*;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.NodeVisitor;
import org.htmlparser.visitors.TextExtractingVisitor;
public class HtmlParser extends NodeVisitor{

	public String HParser(String inputFilePath){
		try {
			Parser parser=new Parser(inputFilePath);
			parser.setEncoding("UTF-8");
			TextExtractingVisitor tev=new TextExtractingVisitor();
			parser.visitAllNodesWith(tev);
			String body=tev.getExtractedText();
			return body.trim();
		} catch (ParserException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			return null;
		}
	}
}