本文目录导读：
我来详细解释一下 JEditorPane、HTMLEditorKit 中的解析器方法模式匹配。
核心组件
JEditorPane
JEditorPane editor = new JEditorPane();
editor.setContentType("text/html");
editor.setText("<html><body><p>Hello World</p></body></html>");
HTMLEditorKit
HTMLEditorKit kit = new HTMLEditorKit(); editor.setEditorKit(kit);
解析器相关类
HTMLEditorKit.ParserHTMLEditorKit.ParserCallback
模式匹配方法
基本解析器模式匹配示例
import javax.swing.text.html.parser.*;
import javax.swing.text.html.*;
import javax.swing.text.*;
import java.io.*;
public class HTMLParserPattern {
public static void main(String[] args) {
String html = "<html><body>" +
"<h1>标题</h1>" +
"<p>段落文本</p>" +
"<a href='http://example.com'>链接</a>" +
"<img src='image.jpg' alt='图片'/>" +
"</body></html>";
try {
// 方法1: 使用HTMLEditorKit的解析器
parseWithHTMLEditorKit(html);
// 方法2: 使用ParserDelegator
parseWithParserDelegator(html);
} catch (Exception e) {
e.printStackTrace();
}
}
// 方法1: HTMLEditorKit方式
static void parseWithHTMLEditorKit(String html) throws Exception {
HTMLEditorKit kit = new HTMLEditorKit();
HTMLEditorKit.Parser parser = kit.getParser();
StringReader reader = new StringReader(html);
parser.parse(reader, new HTMLEditorKit.ParserCallback() {
@Override
public void handleText(char[] data, int pos) {
String text = new String(data);
System.out.println("文本: " + text);
// 模式匹配示例
if (text.matches(".*标题.*")) {
System.out.println(" -> 匹配标题模式");
}
if (text.contains("段落")) {
System.out.println(" -> 包含段落关键词");
}
}
@Override
public void handleStartTag(HTML.Tag tag, MutableAttributeSet attrs, int pos) {
System.out.println("开始标签: " + tag);
// 标签模式匹配
if (tag == HTML.Tag.A) {
String href = (String) attrs.getAttribute(HTML.Attribute.HREF);
if (href != null && href.matches("https?://.*")) {
System.out.println(" -> 匹配URL模式: " + href);
}
}
if (tag == HTML.Tag.IMG) {
String src = (String) attrs.getAttribute(HTML.Attribute.SRC);
if (src != null && src.matches(".*\\.(jpg|png|gif)$")) {
System.out.println(" -> 匹配图片路径模式: " + src);
}
}
}
}, false);
}
// 方法2: ParserDelegator方式
static void parseWithParserDelegator(String html) throws Exception {
ParserDelegator parser = new ParserDelegator();
StringReader reader = new StringReader(html);
parser.parse(reader, new ParserDelegator.HTMLParserCallback() {
@Override
public void handleSimpleTag(HTML.Tag tag, MutableAttributeSet attrs, int pos) {
System.out.println("自闭合标签: " + tag);
// 模式匹配
if (tag == HTML.Tag.IMG) {
String alt = (String) attrs.getAttribute(HTML.Attribute.ALT);
if (alt != null && !alt.isEmpty()) {
System.out.println(" -> 图片描述: " + alt);
}
}
}
}, true);
}
}
高级模式匹配示例
正则表达式模式匹配
public class RegexPatternMatcher {
// 匹配HTML标签
private static final Pattern TAG_PATTERN =
Pattern.compile("<([a-zA-Z]+)[^>]*>");
// 匹配属性
private static final Pattern ATTRIBUTE_PATTERN =
Pattern.compile("(\\w+)=[\"']?([^\"'>]+)[\"']?");
// 匹配URL
private static final Pattern URL_PATTERN =
Pattern.compile("https?://[^\\s\"'<>]+");
public static void matchPatterns(String html) {
// 标签匹配
Matcher tagMatcher = TAG_PATTERN.matcher(html);
while (tagMatcher.find()) {
System.out.println("发现标签: " + tagMatcher.group(1));
}
// 属性匹配
Matcher attrMatcher = ATTRIBUTE_PATTERN.matcher(html);
while (attrMatcher.find()) {
System.out.println("属性: " + attrMatcher.group(1) +
" = " + attrMatcher.group(2));
}
}
}
自定义回调模式匹配
class CustomPatternMatcher extends HTMLEditorKit.ParserCallback {
// 模式匹配规则
private List<PatternRule> rules = new ArrayList<>();
public CustomPatternMatcher() {
// 定义匹配规则
rules.add(new PatternRule("标题", PatternType.TEXT_MATCH));
rules.add(new PatternRule("https?://", PatternType.URL_MATCH));
rules.add(new PatternRule("\\d{4}-\\d{2}-\\d{2}", PatternType.DATE_MATCH));
}
@Override
public void handleText(char[] data, int pos) {
String text = new String(data);
for (PatternRule rule : rules) {
if (rule.matches(text)) {
System.out.println("匹配规则 '" + rule.pattern + "': " + text);
}
}
}
@Override
public void handleStartTag(HTML.Tag tag, MutableAttributeSet attrs, int pos) {
if (tag == HTML.Tag.A) {
String href = (String) attrs.getAttribute(HTML.Attribute.HREF);
if (href != null && href.startsWith("http")) {
System.out.println("外部链接: " + href);
}
}
}
// 模式规则内部类
static class PatternRule {
String pattern;
PatternType type;
PatternRule(String pattern, PatternType type) {
this.pattern = pattern;
this.type = type;
}
boolean matches(String text) {
switch (type) {
case TEXT_MATCH:
return text.contains(pattern);
case URL_MATCH:
return text.matches(pattern + ".*");
case DATE_MATCH:
return text.matches(pattern);
default:
return false;
}
}
}
enum PatternType {
TEXT_MATCH,
URL_MATCH,
DATE_MATCH
}
}
使用模式匹配的实用函数
public class HTMLPatternUtils {
// 提取所有链接
public static List<String> extractLinks(String html) {
List<String> links = new ArrayList<>();
Pattern linkPattern = Pattern.compile(
"<a\\s+[^>]*href=[\"']([^\"']+)[\"'][^>]*>"
);
Matcher matcher = linkPattern.matcher(html);
while (matcher.find()) {
links.add(matcher.group(1));
}
return links;
}
// 提取所有图片
public static List<String> extractImages(String html) {
List<String> images = new ArrayList<>();
Pattern imgPattern = Pattern.compile(
"<img\\s+[^>]*src=[\"']([^\"']+)[\"'][^>]*>"
);
Matcher matcher = imgPattern.matcher(html);
while (matcher.find()) {
images.add(matcher.group(1));
}
return images;
}
// 清理HTML标签
public static String stripHTML(String html) {
return html.replaceAll("<[^>]*>", "")
.replaceAll("\\s+", " ")
.trim();
}
// 检查特定模式
public static boolean containsPattern(String html, String pattern) {
Pattern p = Pattern.compile(pattern, Pattern.CASE_INSENSITIVE);
Matcher m = p.matcher(html);
return m.find();
}
}
关键要点
-
解析器选择：
HTMLEditorKit.Parser- 用于Swing组件ParserDelegator- 更灵活的解析方式
-
模式匹配方法：
- 字符串匹配 (
contains,matches) - 正则表达式匹配
- 标签属性匹配
- 字符串匹配 (
-
回调处理：
handleText()- 处理文本内容handleStartTag()- 处理开始标签handleEndTag()- 处理结束标签handleSimpleTag()- 处理自闭合标签
这个框架提供了强大的HTML解析和模式匹配能力,可以根据需求实现复杂的HTML内容分析和处理。
