javax w3c 网页解析（二）_w3c解析doc-优快云博客

本文提供了一个使用Java HTMLEditorKit解析HTML文档的示例代码。该代码从指定URL加载HTML内容，并通过HTMLEditorKit读取并解析到Document对象中。接着遍历文档中的所有A标签元素，提取每个元素的href属性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package test;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Reader;
import java.net.HttpURLConnection;
import java.net.URL;

import javax.swing.text.AttributeSet;
import javax.swing.text.Document;
import javax.swing.text.EditorKit;
import javax.swing.text.Element;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLDocument;
import javax.swing.text.html.HTMLEditorKit;

public class javahtml {

   public static void main(String[] args)
    throws Exception
   {
    EditorKit kit = new HTMLEditorKit();
    Document doc = kit.createDefaultDocument();

    // The Document class does not yet handle charset's properly.
    doc.putProperty("IgnoreCharsetDirective", Boolean.TRUE);

    // Create a reader on the HTML content.

    Reader rd = getReader("http://hexun.com/kangojian/default.html");

    // Parse the HTML.

    kit.read(rd, doc, 0);

    // The HTML text is now stored in the document

    HTMLDocument.Iterator it = ((HTMLDocument) doc).getIterator(HTML.Tag.A);


    while(it.isValid())
    {

     /****************************************************
      * 属性添加比如 id name
      *
      * Element   ele   =   ((HTMLDocument) doc).getElement("button");
      * AttributeSet s = it.getAttributes();
      * String href = (String)((AttributeSet) ele).getAttribute(HTML.Attribute.HREF);
      *
      ****************************************************/

     Element   ele   =   ((HTMLDocument) doc).getElement("id");
     //AttributeSet s = it.getAttributes();
     //AttributeSet s =it.getAttributes();
     String href = (String)((AttributeSet) ele).getAttribute(HTML.Attribute.HREF);
     System.out.println(href);
     it.next();
    }

   }

   // Returns a reader on the HTML data. If 'uri' begins
   // with "http:", it's treated as a URL; otherwise,
   // it's assumed to be a local filename.

   static Reader getReader(String uri)
    throws IOException
   {
    // Retrieve from Internet.
    if (uri.startsWith("http:"))
    {
     HttpURLConnection conn = (HttpURLConnection) new URL(uri).openConnection();
     return new InputStreamReader(conn.getInputStream());
    }
    // Retrieve from file.
    else
    {
     return new FileReader(uri);
    }
   }
    }