如何使用 HTMLDocument 查找属性？

Question

可能 HTML 的术语与 XML 的术语不同，但这里有一个 HTML 文档，可以从中检索属性。这里的属性 a1、a2、a3 是 Body 标签的一部分。

<html>
  <head>
      Hello World
  </head>
  <body a1="ABC" a2="3974" a3="A1B2">     <------These attributes
    <H1>Start Here<H1>
    <p>This is the body</p>
  </body>
</html>

使用下面的文件解析上面的HTML文件。

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.Reader;

import javax.swing.text.AttributeSet;
import javax.swing.text.Element;
import javax.swing.text.ElementIterator;
import javax.swing.text.StyleConstants;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLDocument;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;

public class HTMLParserTest
{

  public static void main(String args[]) throws Exception {

    Reader reader = new FileReader("C:/Downloads/DeleteMe/Example1.html");
    BufferedReader br = new BufferedReader(reader );

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);
    
    // Parse
    ElementIterator iterator = new ElementIterator(htmlDoc);
    Element element;
    while ((element = iterator.next()) != null) 
    {
      System.out.println("Element : " + element);
      AttributeSet attributes = element.getAttributes();
      Object name = attributes.getAttribute(StyleConstants.NameAttribute);
      if ((name instanceof HTML.Tag))
          //&& ((name == HTML.Tag.H1) || (name == HTML.Tag.H2) || (name == HTML.Tag.H3))) 
        {
        // Build up content text as it may be within multiple elements
        StringBuffer text = new StringBuffer();
        int count = element.getElementCount();
        for (int i = 0; i < count; i++) {
          Element child = element.getElement(i);
          AttributeSet childAttributes = child.getAttributes();
          System.out.println("Element : " + child);
          System.out.println("     Attribute count : " + childAttributes.getAttributeCount());
          System.out.println("     a1 exists : " + childAttributes.isDefined("a1"));
          
            int startOffset = child.getStartOffset();
            int endOffset = child.getEndOffset();
            int length = endOffset - startOffset;
            text.append(htmlDoc.getText(startOffset, length));
        }
        
      }
    }
    System.exit(0);
  }
}

输出在这里。

Element : BranchElement(html) 0,1

Element : BranchElement(body) 0,1

     Attribute count : 1
     a1 exists : false                    <-----expected true here.
Element : BranchElement(body) 0,1

Element : BranchElement(p) 0,1

     Attribute count : 3
     a1 exists : false
Element : BranchElement(p) 0,1

Element : LeafElement(content) 0,1

     Attribute count : 1
     a1 exists : false
Element : LeafElement(content) 0,1

期望“a1 存在”检查应该返回 true 一次，但它没有。最终将搜索所有 3 (a1, a2, a3)。

上面的代码是正确的实现还是在 HTML 解析器中不可行？

Answer 1

我不知道 HtmlKit 但你可以使用正则表达式获得类似的结果

public static void main(String[] args) throws UnirestException {
    String html = "<html>\r\n" + 
            "  <head>\r\n" + 
            "      Hello World\r\n" + 
            "  </head>\r\n" + 
            "  <body a1=\"ABC\" a2=\"3974\" a3=\"A1B2\">\r\n" + 
            "    <H1>Start Here<H1>\r\n" + 
            "    <p>This is the body</p>\r\n" + 
            "  </body>\r\n" + 
            "</html>";
    Pattern regexBodyPattern = Pattern.compile("<body[^>]*>", Pattern.MULTILINE);
    Matcher matcher = regexBodyPattern.matcher(html);
    
    while(matcher.find()) {
        String bodyTag = matcher.group();
        Pattern regexBodyAttrPattern = Pattern.compile("(\S*)=(\\"\w*\\")", Pattern.MULTILINE);
        Matcher attrMatcher = regexBodyAttrPattern.matcher(bodyTag);
        while(attrMatcher.find()) {
            System.out.println("Key :: "+attrMatcher.group(1)+" , Value "+attrMatcher.group(2));
        }
    }       
}

输出

Key :: a1 , Value "ABC"
Key :: a2 , Value "3974"
Key :: a3 , Value "A1B2"

Answer 2

也许这会有所帮助：

import java.io.*;
import java.net.*;
import java.util.*;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;

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

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

        try
        {
            // Create a reader on the HTML content.
            Reader rd = getReader(args[0]);

            // Parse the HTML.
            kit.read(rd, doc, 0);

            // Iterate through the elements of the HTML document.

            ElementIterator it = new ElementIterator(doc);
            Element elem = null;

            while ( (elem = it.next()) != null )
            {
                if (elem.getName().equals("body"))
                {

                    AttributeSet as = elem.getAttributes();

                    Enumeration enum1 = as.getAttributeNames();

                    while( enum1.hasMoreElements() )
                    {
                        Object name = enum1.nextElement();
                        Object value = as.getAttribute( name );

                        System.out.println( "\t" + name + " : " + value );
                    }

                }
            }

        }
        catch (Exception e)
        {
            e.printStackTrace();
        }

        System.exit(1);
    }

    // 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:"))
        {
            URLConnection conn = new URL(uri).openConnection();
            return new InputStreamReader(conn.getInputStream());
        }
        // Retrieve from file.
        else
        {
            return new FileReader(uri);
        }
    }
}

测试使用：

java AttributeHTML yourFile.html

Answer 3

要检索属性，您可以提供自己的 ParserCallback

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.List;

import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML.Tag;
import javax.swing.text.html.HTMLEditorKit.ParserCallback;
import javax.swing.text.html.parser.ParserDelegator;

public class HTMLParserTest2
{

  public static void main(String args[]) throws Exception {

    Reader reader = new FileReader("d:/temp/Example.html");
    BufferedReader br = new BufferedReader(reader);
    
    System.out.println(HTMLParserTest2.extractTagsAttributes(br));
    // output :  [title-_implied_=true, body-a1=ABC, body-a2=3974, body-a3=A1B2]
    System.exit(0);
  }
  
  public static List<String> extractTagsAttributes(Reader r) throws IOException {
     final ArrayList<String> list = new ArrayList<String>();

     ParserDelegator parserDelegator = new ParserDelegator();
     ParserCallback parserCallback = new ParserCallback() {
       @Override
      public void handleText(final char[] data, final int pos) {  }
       @Override
      public void handleStartTag(Tag tag, MutableAttributeSet attribute, int pos) { 
          Enumeration<?> e=attribute.getAttributeNames();
          while(e.hasMoreElements()) {
             Object name=e.nextElement();
             Object value=attribute.getAttribute(name);
             list.add(tag.toString() + "-" + name + "=" +value);
          }
       }
      @Override
      public void handleEndTag(Tag t, final int pos) {  }
      @Override
      public void handleSimpleTag(Tag t, MutableAttributeSet a, final int pos) { }
      @Override
      public void handleComment(final char[] data, final int pos) { }
      @Override
      public void handleError(final java.lang.String errMsg, final int pos) { }
     };
     parserDelegator.parse(r, parserCallback, true);
     return list;
  }
}

如何使用 HTMLDocument 查找属性？

How to find an attribute using HTMLDocument?

html

java

attributes

dom