本文目录导读：
我来为您详细解释如何使用JEditorPane和HTMLEditorKit进行HTML解析和替换操作。
基本替换操作
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
import java.io.*;
public class HTMLReplaceExample {
public static void main(String[] args) {
JFrame frame = new JFrame("HTML Replace Example");
JEditorPane editorPane = new JEditorPane();
editorPane.setContentType("text/html");
editorPane.setEditable(true);
// 设置HTML内容
String htmlContent = "<html><body>" +
"<h1>原始标题</h1>" +
"<p>这是一段文本内容</p>" +
"<p>包含需要替换的文本</p>" +
"<a href='http://example.com'>链接文本</a>" +
"</body></html>";
editorPane.setText(htmlContent);
// 创建按钮进行替换
JButton replaceButton = new JButton("替换文本");
replaceButton.addActionListener(e -> {
// 执行替换操作
replaceInHTMLEditor(editorPane, "替换", "已替换");
});
frame.add(new JScrollPane(editorPane));
frame.add(replaceButton, java.awt.BorderLayout.SOUTH);
frame.setSize(600, 400);
frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
frame.setVisible(true);
}
}
高级HTML解析和替换
import javax.swing.text.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
import java.util.*;
public class AdvancedHTMLReplace {
/**
* 替换HTML中的指定文本
*/
public static void replaceInHTMLEditor(JEditorPane editor,
String oldText,
String newText) {
try {
Document doc = editor.getDocument();
String content = doc.getText(0, doc.getLength());
// 替换文本
content = content.replaceAll(
Pattern.quote(oldText),
Matcher.quoteReplacement(newText)
);
// 更新文档
editor.setText(content);
} catch (BadLocationException e) {
e.printStackTrace();
}
}
/**
* 使用正则表达式替换HTML内容
*/
public static void replaceWithRegex(JEditorPane editor,
String regex,
String replacement) {
try {
Document doc = editor.getDocument();
String content = doc.getText(0, doc.getLength());
// 使用正则替换
content = content.replaceAll(regex, replacement);
// 更新文档
editor.setText(content);
} catch (BadLocationException e) {
e.printStackTrace();
}
}
/**
* 替换特定HTML标签内的文本
*/
public static void replaceInTag(JEditorPane editor,
String tag,
String oldText,
String newText) {
try {
Document doc = editor.getDocument();
String content = doc.getText(0, doc.getLength());
// 使用正则匹配特定标签内的内容
String regex = "(<" + tag + "[^>]*>)(.*?)(" + Pattern.quote(oldText) + ")(.*?</" + tag + ">)";
String replacement = "$1$2" + Matcher.quoteReplacement(newText) + "$4";
content = content.replaceAll(regex, replacement);
// 更新文档
editor.setText(content);
} catch (BadLocationException e) {
e.printStackTrace();
}
}
/**
* 批量替换多个文本
*/
public static void batchReplace(JEditorPane editor,
Map<String, String> replacements) {
try {
Document doc = editor.getDocument();
String content = doc.getText(0, doc.getLength());
for (Map.Entry<String, String> entry : replacements.entrySet()) {
content = content.replaceAll(
Pattern.quote(entry.getKey()),
Matcher.quoteReplacement(entry.getValue())
);
}
// 更新文档
editor.setText(content);
} catch (BadLocationException e) {
e.printStackTrace();
}
}
}
使用HTMLEditorKit进行解析
import javax.swing.text.html.*;
import javax.swing.text.*;
import java.awt.event.*;
public class HTMLEditorKitParserExample {
public static void main(String[] args) {
JFrame frame = new JFrame("HTMLEditorKit Parser Example");
JEditorPane editorPane = new JEditorPane();
// 设置HTML编辑器套件
HTMLEditorKit kit = new HTMLEditorKit();
editorPane.setEditorKit(kit);
editorPane.setEditable(true);
// 设置初始HTML内容
String html = "<html><body>" +
"<h1>标题</h1>" +
"<p>段落文本 <b>加粗文本</b> 普通文本</p>" +
"<ul><li>列表项1</li><li>列表项2</li></ul>" +
"</body></html>";
editorPane.setText(html);
JButton parseButton = new JButton("解析和替换");
parseButton.addActionListener(e -> {
// 使用HTMLEditorKit解析
HTMLDocument doc = (HTMLDocument) editorPane.getDocument();
HTMLDocument.Iterator iterator = doc.getIterator(
HTML.Tag.CONTENT
);
while (iterator.isValid()) {
try {
int start = iterator.getStartOffset();
int end = iterator.getEndOffset();
String text = doc.getText(start, end - start);
// 执行替换逻辑
if (text.contains("原始文本")) {
// 替换文本
doc.replace(start, end - start, "新文本", null);
}
} catch (BadLocationException ex) {
ex.printStackTrace();
}
iterator.next();
}
});
JPanel panel = new JPanel();
panel.add(parseButton);
frame.add(new JScrollPane(editorPane));
frame.add(panel, java.awt.BorderLayout.SOUTH);
frame.setSize(600, 400);
frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
frame.setVisible(true);
}
}
完整的替换工具类
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
import java.util.regex.*;
public class HTMLEditorReplaceUtil {
/**
* 简单文本替换（替换纯文本内容，不涉及HTML标签）
*/
public static void simpleTextReplace(JEditorPane editor,
String oldText,
String newText) {
try {
HTMLDocument doc = (HTMLDocument) editor.getDocument();
String content = getTextContent(doc);
// 替换文本
content = content.replace(oldText, newText);
// 重新设置内容
editor.setText(content);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 智能替换（保留HTML结构）
*/
public static void smartReplace(JEditorPane editor,
String oldText,
String newText) {
try {
HTMLDocument doc = (HTMLDocument) editor.getDocument();
String html = getHTMLContent(doc);
// 仅替换不在标签内的文本
html = replaceTextInContent(html, oldText, newText);
// 更新编辑器内容
editor.setText(html);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 替换指定标签内的文本
*/
public static void replaceInSpecifiedTag(JEditorPane editor,
String tagName,
String oldText,
String newText) {
try {
HTMLDocument doc = (HTMLDocument) editor.getDocument();
String html = getHTMLContent(doc);
// 匹配指定标签内的内容
String pattern = "<" + tagName + "[^>]*>([^<]*" +
Pattern.quote(oldText) + "[^<]*)</" + tagName + ">";
html = html.replaceAll(pattern,
"<" + tagName + ">$1</" + tagName + ">".replace(oldText, newText));
editor.setText(html);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 获取文本内容（不含HTML标签）
*/
private static String getTextContent(HTMLDocument doc) throws BadLocationException {
StringBuilder sb = new StringBuilder();
ElementIterator iterator = new ElementIterator(doc);
Element element;
while ((element = iterator.next()) != null) {
if (element.getName().equals("content")) {
int start = element.getStartOffset();
int end = element.getEndOffset();
sb.append(doc.getText(start, end - start));
}
}
return sb.toString();
}
/**
* 获取完整的HTML内容
*/
private static String getHTMLContent(HTMLDocument doc) throws BadLocationException {
return doc.getText(0, doc.getLength());
}
/**
* 替换文本内容（保留HTML标签）
*/
private static String replaceTextInContent(String html,
String oldText,
String newText) {
StringBuilder result = new StringBuilder();
boolean inTag = false;
StringBuilder currentText = new StringBuilder();
for (int i = 0; i < html.length(); i++) {
char c = html.charAt(i);
if (c == '<') {
// 处理之前累积的文本
if (currentText.length() > 0) {
String processed = currentText.toString()
.replace(oldText, newText);
result.append(processed);
currentText = new StringBuilder();
}
inTag = true;
result.append(c);
} else if (c == '>') {
inTag = false;
result.append(c);
} else if (!inTag) {
currentText.append(c);
} else {
result.append(c);
}
}
// 处理最后剩余的文本
if (currentText.length() > 0) {
result.append(currentText.toString().replace(oldText, newText));
}
return result.toString();
}
/**
* 使用示例
*/
public static void main(String[] args) {
JFrame frame = new JFrame("HTML Replace Utility");
JEditorPane editorPane = new JEditorPane();
editorPane.setContentType("text/html");
// 设置示例HTML
String html = "<html><body>" +
"<h1>Hello World</h1>" +
"<p>This is a <b>Hello</b> example</p>" +
"<p>Another Hello text</p>" +
"</body></html>";
editorPane.setText(html);
// 创建各种替换按钮
JPanel buttonPanel = new JPanel();
JButton simpleReplace = new JButton("简单替换");
simpleReplace.addActionListener(e ->
simpleTextReplace(editorPane, "Hello", "Hi")
);
JButton smartReplace = new JButton("智能替换");
smartReplace.addActionListener(e ->
smartReplace(editorPane, "Hello", "Hi")
);
JButton replaceInTag = new JButton("替换在p标签内");
replaceInTag.addActionListener(e ->
replaceInSpecifiedTag(editorPane, "p", "Hello", "Hi")
);
buttonPanel.add(simpleReplace);
buttonPanel.add(smartReplace);
buttonPanel.add(replaceInTag);
frame.add(new JScrollPane(editorPane));
frame.add(buttonPanel, java.awt.BorderLayout.SOUTH);
frame.setSize(600, 400);
frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
frame.setVisible(true);
}
}
- 直接替换：使用
editorPane.setText()重新设置整个HTML内容 - 保留结构：使用正则表达式匹配非标签内的文本进行替换
- 解析替换：使用
HTMLDocument和ElementIterator遍历元素进行替换 - 性能考虑：对于大型文档，建议使用
HTMLDocument的迭代器方法
这些方法可以满足大多数HTML内容替换的需求,根据具体场景选择合适的替换策略。
