JTidy转换html到xml

现在的位置: 首页 > 综合 > 正文

JTidy转换html到xml

2013年10月14日 ⁄ 综合 ⁄ 共 3182字 ⁄ 字号小中大 ⁄ 评论关闭

JTidy转换html到xml

方法一：现无法解决乱码

package spide; 
import java.io.PrintWriter; 
import java.io.FileInputStream; 
import java.io.IOException; 
import org.w3c.dom.Attr; 
import org.w3c.dom.Document; 
import org.w3c.dom.NamedNodeMap; 
import org.w3c.dom.Node; 
import org.w3c.dom.NodeList; 
import org.w3c.tidy.Tidy; 
import java.io.FileOutputStream; 
/** 
* A sample DOM writer. This sample program illustrates how to 
* traverse a DOM tree in order to print a document that is parsed. 
* 
*/ 
public class TestDOM { 
protected PrintWriter out; 
public TestDOM() { 
try 
{ 
FileOutputStream outxml=new FileOutputStream("D:/test.xml"); 
out = new PrintWriter(outxml); 
} 
catch(Exception e) 
{ 
 e.printStackTrace(); 
 } 
} 
/** Prints the specified node, recursively. */ 
public void print(Node node) { 
if ( node == null ) { 
return; 
} 
int type = node.getNodeType(); 
switch ( type ) { 
case Node.DOCUMENT_NODE:
out.println("<?xml version=/"1.0/" encoding=/"GBK/"?>"); 
print(((Document)node).getDocumentElement()); 
out.flush(); 
break; 
case Node.ELEMENT_NODE: 
out.print('<'); 
out.print(node.getNodeName()); 
NamedNodeMap attrs = node.getAttributes(); 
for ( int i = 0; i < attrs.getLength(); i++ ) { 
out.print(' '); 
out.print(attrs.item(i).getNodeName()); 
out.print("=/""); 
out.print(attrs.item(i).getNodeValue()); 
out.print('"'); 
} 
out.print('>'); 
out.println(); // HACK 
NodeList children = node.getChildNodes(); 
if ( children != null ) { 
int len = children.getLength(); 
for ( int i = 0; i < len; i++ ) { 
print(children.item(i)); 
} 
} 
break; 
case Node.TEXT_NODE: 
out.print(node.getNodeValue()); 
break; 
} 
if ( type == Node.ELEMENT_NODE ) { 
out.print("</"); 
out.print(node.getNodeName()); 
out.print('>'); 
out.println(); // HACK 
} 
out.flush(); 
} 
public static void main(String args[]) { 
 String conf="D:/tidy.properties"; 
FileInputStream in;
Tidy tidy = new Tidy(); 
tidy.setConfigurationFromFile(conf); 
TestDOM t = new TestDOM(); 
try { 
in = new FileInputStream("D:/speed.html"); 
tidy.setMakeClean(true); 
tidy.setXmlTags(true); 
t.print(tidy.parseDOM(in, null)); 
} 
catch ( IOException e ) { 
System.err.println( e.toString() ); 
} 
} 
}

方法二：可以解决乱码，解析时出现 White spaces are required between publicId and systemId错误

package spide; 
import java.io.BufferedInputStream; 
import java.io.BufferedOutputStream; 
import java.io.BufferedWriter; 
import java.io.FileInputStream; 
import java.io.FileOutputStream; 
import java.io.FileWriter; 
import java.io.IOException; 
import java.io.PrintWriter; 
import org.w3c.tidy.Tidy; 
public class Test17 implements Runnable { 
 private String srcFileName; 
 private String outFileName; 
 private String errOutFileName; 
 private String configFileName; 
 public Test17(String srcFileName, String outFileName,??? String confName) { 
 this.srcFileName = srcFileName; 
 this.outFileName = outFileName; 
 this.configFileName= confName; 
 } 
 public void run() { 
 BufferedInputStream in; 
 FileOutputStream out; 
 Tidy tidy = new Tidy(); 
 tidy.setConfigurationFromFile(configFileName); 
 try { 
 // tidy.setErrout(new PrintWriter(new FileWriter(errOutFileName), true)); 
 in = new BufferedInputStream(new FileInputStream(srcFileName)); 
 out = new FileOutputStream(outFileName); 
 String head = "<?xml version=/"1.0/" encoding=/"GBK/"?>"; 
 byte[] bytes = head.getBytes(); 
 out.write(bytes, 0, bytes.length);
 tidy.parse(in, out); 
 } catch (IOException e) { 
 System.out.println(this.toString() + e.toString()); 
 } 
 } 
 public static void main(String[] args) { 
 String src="D:/speed.html"; 
 String out="D:/result.xml"; 
 String err="D:/err.txt"; 
 String conf="D:/tidy.properties"; 
 Test17 t1 = new Test17(src,out,conf); 
 Thread th1 = new Thread(t1); 
 th1.start(); 
 } 
}

【上篇】qtopia文件系统 nfs 挂载启动出错 unable to mount root fs on unknown-block
【下篇】asp.net中session的原理及应用

作者: chenggong265168

该日志由 chenggong265168 于11年前发表在综合分类下，最后更新于 2013年10月14日.
转载请注明: JTidy转换html到xml | 学步园 +复制链接

抱歉!评论已关闭.

学步园