Java实现提取HTML文件中的文本内容

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>
<dependency>
    <groupId>e-iceblue</groupId>
    <artifactId>spire.doc.free</artifactId>
    <version>5.2.0</version>
</dependency>

import com.spire.doc.Document;
import com.spire.doc.FileFormat;
 
import java.io.FileWriter;
import java.io.IOException;
 
public class ExtractTextFromHTML {
    public static void main(String[] args) throws IOException {
 
        //创建Document对象
        Document doc = new Document();
 
        //加载一个HTML文件
        doc.loadFromFile("input.html", FileFormat.Html);
 
        //获取HTML文件中的文本
        String text = doc.getText();
 
        //将文本写入TXT文件
        FileWriter fileWriter = new FileWriter("提取HTML文本.txt");
        fileWriter.write(text);
        fileWriter.close();
    }
}

//核心代码
String unescapeString = StringEscapeUtils.unescapeHtml4(inputString);
String text = HTML2Text.convert(unescapeString);
 
 
 
 
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.Stack;
import java.util.logging.Logger;
 
public class HTML2Text extends HTMLEditorKit.ParserCallback {
    private static final Logger log = Logger
            .getLogger(Logger.GLOBAL_LOGGER_NAME);
 
    private StringBuffer stringBuffer;
 
    private Stack<IndexType> indentStack;
 
    public static class IndexType {
        public String type;
        public int counter; // used for ordered lists
 
        public IndexType(String type) {
            this.type = type;
            counter = 0;
        }
    }
 
    public HTML2Text() {
        stringBuffer = new StringBuffer();
        indentStack = new Stack<>();
    }
 
    public static String convert(String html) {
        HTML2Text parser = new HTML2Text();
        Reader in = new StringReader(html);
        try {
            // the HTML to convert
            parser.parse(in);
        } catch (Exception e) {
            log.severe(e.getMessage());
        } finally {
            try {
                in.close();
            } catch (IOException ioe) {
                // this should never happen
            }
        }
        return parser.getText();
    }
 
    public void parse(Reader in) throws IOException {
        ParserDelegator delegator = new ParserDelegator();
        // the third parameter is TRUE to ignore charset directive
        delegator.parse(in, this, Boolean.TRUE);
    }
 
    @Override
    public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        log.info("StartTag:" + t.toString());
        if (t.toString().equals("p")) {
            if (stringBuffer.length() > 0
                    && !stringBuffer.substring(stringBuffer.length() - 1)
                    .equals("\n")) {
                newLine();
            }
            newLine();
        } else if (t.toString().equals("ol")) {
            indentStack.push(new IndexType("ol"));
            newLine();
        } else if (t.toString().equals("ul")) {
            indentStack.push(new IndexType("ul"));
            newLine();
        } else if (t.toString().equals("li")) {
            IndexType parent = indentStack.peek();
            if (parent.type.equals("ol")) {
                String numberString = "" + (++parent.counter) + ".";
                stringBuffer.append(numberString);
                for (int i = 0; i < (4 - numberString.length()); i++) {
                    stringBuffer.append(" ");
                }
            } else {
                stringBuffer.append("*   ");
            }
            indentStack.push(new IndexType("li"));
        } else if (t.toString().equals("dl")) {
            newLine();
        } else if (t.toString().equals("dt")) {
            newLine();
        } else if (t.toString().equals("dd")) {
            indentStack.push(new IndexType("dd"));
            newLine();
        }
    }
 
    private void newLine() {
        stringBuffer.append("\n");
        for (int i = 0; i < indentStack.size(); i++) {
            stringBuffer.append("    ");
        }
    }
 
    @Override
    public void handleEndTag(HTML.Tag t, int pos) {
        log.info("EndTag:" + t.toString());
        if (t.toString().equals("p")) {
            newLine();
        } else if (t.toString().equals("ol")) {
            indentStack.pop();
            newLine();
        } else if (t.toString().equals("ul")) {
            indentStack.pop();
            newLine();
        } else if (t.toString().equals("li")) {
            indentStack.pop();
            newLine();
        } else if (t.toString().equals("dd")) {
            indentStack.pop();
        }
    }
 
    @Override
    public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        log.info("SimpleTag:" + t.toString());
        if (t.toString().equals("br")) {
            newLine();
        }
    }
 
    @Override
    public void handleText(char[] text, int pos) {
        log.info("Text:" + new String(text));
        stringBuffer.append(text);
    }
 
    public String getText() {
        return stringBuffer.toString();
    }
 }