htmlparser示例

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.filters.TagNameFilter;  
import org.htmlparser.nodes.TextNode;  
import org.htmlparser.tags.LinkTag;  
import org.htmlparser.util.NodeList;  
import org.htmlparser.util.ParserException;  
import org.htmlparser.visitors.HtmlPage;  
import org.htmlparser.visitors.TextExtractingVisitor;  

/** 
* 演示了Html Parse的應用. 
* 
*/  
public class ParseHtmlTest {  

    public static void main(String[] args) throws Exception {  
        String aFile = "F:\\百度一下，你就知道.htm";  

        String content = readTextFile(aFile, "GBK");  

        test1(content);  
        System.out.println("====================================");  

        test2(content);  
        System.out.println("====================================");  

        test3(content);  
        System.out.println("====================================");  

        test4(content);  
        System.out.println("====================================");  

        test5(aFile);  
        System.out.println("====================================");  

        //訪問外部資源,相對慢  
        test5("http://www.baidu.com");  
        System.out.println("====================================");  

    }  

    /** 
     * 讀取文件的方式來分析內容. 
     * filePath也可以是一個Url. 
     * 
     * @param resource 文件/Url 
     */  
    public static void test5(String resource) throws Exception {  
        Parser myParser = new Parser(resource);  

        //設置編碼  
        myParser.setEncoding("GBK");  

        HtmlPage visitor = new HtmlPage(myParser);  

        myParser.visitAllNodesWith(visitor);  

        String textInPage = visitor.getTitle();  

        System.out.println("test5 html title = " + textInPage);  
    }  

    /** 
     * 按頁面方式處理.對一個標準的Html頁面,推薦使用此種方式. 
     */  
    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("test4 html title = " + textInPage);  
    }  

    /** 
     * 利用Visitor模式解析html頁面. 
     * 
     * 小優點:翻譯了<>等符號 
     * 缺點:好多空格,無法提取link 
     *  
     */  
    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("test3 = " + textInPage);  
    }  

    /** 
     * 得到普通文本和鏈接的內容. 
     * 
     * 使用了過濾條件. 
     */  
    public static void test2(String content) throws ParserException {  
        Parser myParser;  
        NodeList nodeList = null;  

        myParser = Parser.createParser(content, "GBK");  

        NodeFilter textFilter = new NodeClassFilter(TextNode.class);  
        NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);  

        //暫時不處理 meta  
        //NodeFilter metaFilter = new NodeClassFilter(MetaTag.class);  

        OrFilter lastFilter = new OrFilter();  
        lastFilter.setPredicates(new NodeFilter[] { textFilter, linkFilter });  

        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.toPlainTextString().trim();  
                line = textnode.getText();  
            } else if (anode instanceof LinkTag) {  
                LinkTag linknode = (LinkTag) anode;  

                line = linknode.getLink();  
                //@todo 過濾jsp標籤:可以自己實現這個函數  
                //line = StringFunc.replace(line, "<%.*%>", "");  
            }  

            if (isTrimEmpty(line))  
                continue;  

            System.out.println("test2 = " + line);  
        }  
    }  

    /** 
     * 解析普通文本節點. 
     * 
     * @param content 
     * @throws ParserException 
     */  
    public static void test1(String content) throws ParserException {  
        Parser myParser;  
        Node[] nodes = null;  

        myParser = Parser.createParser(content, null);  
        NodeFilter nodeFilter = new TagNameFilter(TextNode.class.getName());  
        nodes = myParser.extractAllNodesThatMatch(nodeFilter).toNodeArray(); //exception could be thrown here  

        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("test1 = " + line);  
        }  

    }  

    /** 
     * 讀取一個文件到字符串裏. 
     * 
     * @param sFileName 文件名 
     * @param sEncode   String 
     * @return 文件內容 
     */  
    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) {  
            System.out.println("read Text File Error");  
            e.printStackTrace();  
        }  

        return sbStr.toString();  
    }  

    /** 
     * 去掉左右空格後字符串是否爲空 
     * @param astr String 
     * @return boolean 
     */  
    public static boolean isTrimEmpty(String astr) {  
        if ((null == astr) || (astr.length() == 0)) {  
            return true;  
        }  
        if (isBlank(astr.trim())) {  
            return true;  
        }  
        return false;  
    }  

    /** 
     * 字符串是否爲空:null或者長度爲0. 
     * @param astr 源字符串. 
     * @return boolean 
     */  
    public static boolean isBlank(String astr) {  
        if ((null == astr) || (astr.length() == 0)) {  
            return true;  
        } else {  
            return false;  
        }  
    }  

}