jsoup 和nekohtml，htmlparser解析html
仅以此文章表达介绍下将html解析成纯文本的多种方式
1.jsoup 是一款 Java 的HTML 解析器，可直接解析某个URL地址、HTML文本内容。
可参考：http://www.iteye.com/topic/1010581
public void parse(String urlStr) {// 返回结果初始化。Document doc = null;try {doc = Jsoup.connect(urlStr).userAgent("Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.2.15)") // 设置User-Agent.timeout(5000) // 设置连接超时时间.get();} catch (MalformedURLException e) {log.error( e);return ;} catch (IOException e) {if (e instanceof SocketTimeoutException) {log.error( e); return ;}if(e instanceof UnknownHostException){log.error(e);return ;}log.error( e);return ;}system.out.println(doc.title());Element head = doc.head();Elements metas = head.select("meta");for (Element meta : metas) {String content = meta.attr("content");if ("content-type".equalsIgnoreCase(meta.attr("http-equiv"))&& !StringUtils.startsWith(content, "text/html")) {log.debug( urlStr);return ;}if ("description".equalsIgnoreCase(meta.attr("name"))) {system.out.println(meta.attr("content"));}}Element body = doc.body();for (Element img : body.getElementsByTag("img")) {String imageUrl = img.attr("abs:src");//获得绝对路径for (String suffix : IMAGE_TYPE_ARRAY) {if(imageUrl.indexOf("?")>0){imageUrl=imageUrl.substring(0,imageUrl.indexOf("?"));}if (StringUtils.endsWithIgnoreCase(imageUrl, suffix)) {imgSrcs.add(imageUrl);break;}}}}import java.io.BufferedReader;import java.io.FileReader;import org.cyberneko.html.parsers.DOMParser;import org.w3c.dom.Document;import org.w3c.dom.Element;import org.w3c.dom.Node;import org.w3c.dom.NodeList;import org.xml.sax.InputSource;public class Demo {public static String TextExtractor(Node root){ //若是文本节点的话，直接返回 if (root.getNodeType() == Node.TEXT_NODE) { return root.getNodeValue().trim(); } if(root.getNodeType() == Node.ELEMENT_NODE) { Element elmt = (Element) root; //抛弃脚本 if (elmt.getTagName().equals("STYLE") || elmt.getTagName().equals("SCRIPT")) return ""; NodeList children = elmt.getChildNodes(); StringBuilder text = new StringBuilder(); for (int i = 0; i < children.getLength(); i++) { text.append(TextExtractor(children.item(i))); } return text.toString(); } //对其它类型的节点，返回空值 return "";}public static void main(String[] args) throws Exception{ //生成html parser DOMParser parser = new DOMParser(); //设置网页的默认编码 parser.setProperty( "http://cyberneko.org/html/properties/default-encoding ", "gb18030"); //input file BufferedReader in = new BufferedReader(new FileReader("input.htm")); parser.parse(new InputSource(in)); Document doc = parser.getDocument(); //获得body节点，以此为根，计算其文本内容 Node body = doc.getElementsByTagName("BODY").item(0); System.out.println(TextExtractor(body));}}