import org.htmlparser.beans.StringBean; //导入依赖的package包/类
public static String getPlainText(String htmlStr) {
    Parser parser = new Parser();
    String plainText = "";
    try {
        parser.setInputHTML(htmlStr);

        StringBean stringBean = new StringBean();
        // 设置不需要得到页面所包含的链接信息
        stringBean.setLinks(false);
        // 设置将不间断空格由正规空格所替代
        stringBean.setReplaceNonBreakingSpaces(true);
        // 设置将一序列空格由单一空格替代
        stringBean.setCollapse(true);

        parser.visitAllNodesWith(stringBean);
        plainText = stringBean.getStrings();

    } catch (ParserException e) {
        e.printStackTrace();
    }

    return plainText;
}
 

import org.htmlparser.beans.StringBean; //导入依赖的package包/类
/**
 * Converts an HTML document into plain text.
 * 
 * @param html HTML document
 * @return plain text or <code>null</code> if the conversion failed
 */
public static synchronized String html2text(String html) {
	// convert HTML document
	StringBean sb = new StringBean();
	sb.setLinks(false);  // no links
	sb.setReplaceNonBreakingSpaces (true); // replace non-breaking spaces
    sb.setCollapse(true);  // replace sequences of whitespaces
	Parser parser = new Parser();
	try {
		parser.setInputHTML(html);
		parser.visitAllNodesWith(sb);
	} catch (ParserException e) {
		return null;
	}
	String docText = sb.getStrings();
	
	if (docText == null) docText = "";  // no content
	
	return docText;
}
 

import org.htmlparser.beans.StringBean; //导入依赖的package包/类
/**
 * Reads an HTML document from a file and converts it into plain text.
 * 
 * @param filename name of file containing HTML documents
 * @return plain text or <code>null</code> if the reading or conversion failed
 */
public static synchronized String file2text(String filename) {
	// read from file and convert HTML document
	StringBean sb = new StringBean();
	sb.setLinks(false);  // no links
	sb.setReplaceNonBreakingSpaces (true); // replace non-breaking spaces
    sb.setCollapse(true);  // replace sequences of whitespaces
	Parser parser = new Parser();
	try {
		parser.setResource(filename);
		parser.visitAllNodesWith(sb);
	} catch (ParserException e) {
		return null;
	}
	String docText = sb.getStrings();
	
	return docText;
}
 

import org.htmlparser.beans.StringBean; //导入依赖的package包/类
/**
 * Fetches an HTML document from a URL and converts it into plain text.
 * 
 * @param url URL of HTML document
 * @return plain text or <code>null</code> if the fetching or conversion failed
 */
public static synchronized String url2text(String url) throws SocketTimeoutException {
	// connect to URL
	URLConnection conn = null;
	try {
		conn = (new URL(url)).openConnection();
		if (!(conn instanceof HttpURLConnection)) return null;  // only allow HTTP connections
	} catch (IOException e) {
		return null;
	}
	conn.setRequestProperty("User-agent","Mozilla/4.0");  // pretend to be a browser
	conn.setConnectTimeout(TIMEOUT);
	conn.setReadTimeout(TIMEOUT);
	
	// fetch URL and convert HTML document
	StringBean sb = new StringBean();
	sb.setLinks(false);  // no links
	sb.setReplaceNonBreakingSpaces(true); // replace non-breaking spaces
    sb.setCollapse(true);  // replace sequences of whitespaces
	sb.setConnection(conn);
	String docText = sb.getStrings();
	
	return docText;
}