用htmlparser截取html摘要实现源码

import java.io.BufferedReader; import java.io.File; import java.io.FileReader; import java.io.IOException; import java.io.UnsupportedEncodingException; import org.htmlparser.Node; import org.htmlparser.NodeFilter; import org.htmlparser.Parser; import org.htmlparser.PrototypicalNodeFactory; import org.htmlparser.tags.BrTag; import org.htmlparser.tags.CompositeTag; import org.htmlparser.tags.FontTag; import org.htmlparser.tags.LinkTypeTag; import org.htmlparser.tags.PtypeTag; import org.htmlparser.tags.WbrTag; import org.htmlparser.util.NodeList; import org.htmlparser.util.ParserException; public class TestNew { public static String readFileByLines(String filename) { File file = new File(filename); BufferedReader reader = null; try { reader = new BufferedReader(new FileReader(file)); String tempString = ""; StringBuffer sb = new StringBuffer(); while ((tempString = reader.readLine()) != null) { tempString = new String(tempString.getBytes(),"utf-8"); sb.append(tempString+"\n"); } return sb.toString(); } catch (Exception e) { // TODO Auto-generated catch block return ""; } } /*public static String extractText(String file) throws Exception { StringBuffer text = new StringBuffer(); Parser parser = new Parser(file); parser.setEncoding("utf-8"); NodeList nodes = parser.extractAllNodesThatMatch(new NodeFilter() { public boolean accept(Node node) { return true; } }); for (int i=0;i<nodes.size();i++){ Node nodet = nodes.elementAt(i); text.append(new String(nodet.toPlainTextString().getBytes())); } return text.toString(); }*/ public static String readWithTag(String filename,int length) throws IOException { String content = readFileByLines(filename); int pos = 0,len = 0,count = 0; String s = ""; StringBuffer sb = new StringBuffer(); while(true) { if(count >= length) break; s = content.substring(pos, pos+1); if(s.equals("<")) { len = content.indexOf(">", pos)-pos; for(int i=0;i<len;i++) { s = content.substring(pos+i, pos+i+1); sb.append(s); } pos += len; } else { if(count < length) { if(s.equals(">")) { sb.append(s); pos++; } else{ sb.append(s); count++; pos++; } } } } return sb.toString(); } public static String cutContent(String file,int len) { try{ /*String temp = readFileByLines(file); String content = extractText(file); content = content.substring(0, len); String tmp1 = content.substring(content.length()-2, content.length()); String html = temp.substring(0, temp.indexOf(tmp1));*/ String html = readWithTag(file,len); Parser parser = Parser.createParser(new String(html.getBytes(),"8859_1"),""); //注册自定义的新结点解析器,这是必要的... PrototypicalNodeFactory factory = new PrototypicalNodeFactory (); factory.registerTag(new LinkTypeTag ()); factory.registerTag(new BrTag ()); factory.registerTag(new FontTag ()); factory.registerTag(new PtypeTag ()); factory.registerTag(new WbrTag ()); parser.setNodeFactory(factory); NodeList nodelist = parser.extractAllNodesThatMatch(new NodeFilter(){ public boolean accept(Node node) { if(node instanceof CompositeTag) return true; return false; } }); String str = ""; String tmp = ""; for (int i = 0; i < nodelist.size(); i++) { CompositeTag testTag = (CompositeTag)nodelist.elementAt(i); if (testTag.getParent() == null) { tmp = new String(testTag.toHtml().getBytes("8859_1")); str += tmp + "\n"; } } return str; } catch(Exception e) { return ""; } } /** * @param args * @throws Exception */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub String str = cutContent("c:/双卫,医学社区---文章阅读.htm",200); System.out.println(str); } }