testhtmlparser.java

来自「cwbbs 云网论坛源码」· Java 代码 · 共 175 行

package cn.js.fan.test;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.tags.*;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;
import org.htmlparser.visitors.TextExtractingVisitor;



public class TestHtmlParser {
    public static void main(String[] args) throws Exception {
        String aFile = "c:/rjcs.html";
        
        String content = "大家好！<a href='ddd.jsp'>GOOD！</a><img src='http://www.cloudwe";
        
        
        test2(content);
        
        
        
        
        
        
        
        
        
        
    }

    
    public static void test5(String resource) throws Exception {
        Parser myParser = new Parser(resource);
        
        myParser.setEncoding("GBK");
        HtmlPage visitor = new HtmlPage(myParser);
        myParser.visitAllNodesWith(visitor);
        String textInPage = visitor.getTitle();
        System.out.println(textInPage);
    }

    
    public static void test4(String content) throws Exception {
        Parser myParser;
        myParser = Parser.createParser(content, "GBK");
        HtmlPage visitor = new HtmlPage(myParser);
        myParser.visitAllNodesWith(visitor);
        String textInPage = visitor.getTitle();
        System.out.println(textInPage);
    }

    
    public static void test3(String content) throws Exception {
        Parser myParser;
        myParser = Parser.createParser(content, "GBK");
        TextExtractingVisitor visitor = new TextExtractingVisitor();
        myParser.visitAllNodesWith(visitor);
        String textInPage = visitor.getExtractedText();
        System.out.println(textInPage);
    }

    
    public static void test2(String content) throws ParserException {
        Parser myParser;
        NodeList nodeList = null;
        myParser = Parser.createParser(content, "utf-8");
        NodeFilter textFilter = new NodeClassFilter(TextNode.class);
        NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
        NodeFilter imgFilter = new NodeClassFilter(ImageTag.class);
        
        
        OrFilter lastFilter = new OrFilter();
        lastFilter.setPredicates(new NodeFilter[] {textFilter, linkFilter, imgFilter});
        nodeList = myParser.parse(lastFilter);
        Node[] nodes = nodeList.toNodeArray();
        for (int i = 0; i < nodes.length; i++) {
            Node anode = (Node) nodes[i];
            String line = "";
            if (anode instanceof TextNode) {
                TextNode textnode = (TextNode) anode;
                
                line = textnode.getText();
            } else if (anode instanceof LinkTag) {
                LinkTag linknode = (LinkTag) anode;
                line = linknode.toHtml();
                
                
                
            } else if (anode instanceof AppletTag) {
                AppletTag appletnode = (AppletTag) anode;
                line = appletnode.getAppletClass() + " " +
                       appletnode.getArchive();
            } else if (anode instanceof ImageTag) {
                ImageTag imagenode = (ImageTag) anode;
                
                line = imagenode.toHtml();
                
            }
            if (isTrimEmpty(line))
                continue;
            System.out.println(line);
        }
    }

    
    public static void test1(String content) throws ParserException {
        Parser myParser;
        Node[] nodes = null;
        myParser = Parser.createParser(content, null);
        
        nodes = (myParser.extractAllNodesThatMatch(new NodeClassFilter(TextNode.class))).
                toNodeArray();
        for (int i = 0; i < nodes.length; i++) {
            TextNode textnode = (TextNode) nodes[i];
            String line = textnode.toPlainTextString().trim();
            if (line.equals(""))
                continue;
            System.out.println(line);
        }
    }

    
    public static String readTextFile(String sFileName, String sEncode) {
        StringBuffer sbStr = new StringBuffer();
        try {
            File ff = new File(sFileName);
            InputStreamReader read = new InputStreamReader(new FileInputStream(
                    ff),
                    sEncode);
            BufferedReader ins = new BufferedReader(read);
            String dataLine = "";
            while (null != (dataLine = ins.readLine())) {
                sbStr.append(dataLine);
                sbStr.append("\r\n");
            }
            ins.close();
        } catch (Exception e) {
            
        }
        return sbStr.toString();
    }

    
    public static boolean isTrimEmpty(String astr) {
        if ((null == astr) || (astr.length() == 0)) {
            return true;
        }
        if (isBlank(astr.trim())) {
            return true;
        }
        return false;
    }

    
    public static boolean isBlank(String astr) {
        if ((null == astr) || (astr.length() == 0)) {
            return true;
        } else {
            return false;
        }
    }
}