<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.com/nexus/content/groups/public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.doc</artifactId>
        <version>14.3.1</version>
    </dependency>
</dependencies>

import com.spire.doc.Document;
import com.spire.doc.FileFormat;
import java.io.FileWriter;
import java.io.IOException;

public class HtmlTextExtractor {

    public static void main(String[] args) {
        // 1. 實(shí)例化 Document 對(duì)象
        Document document = new Document();

        // 2. 加載 HTML 文件（指定格式為 Html）
        document.loadFromFile("input.html", FileFormat.Html);

        // 3. 提取純文本內(nèi)容
        String extractedText = document.getText();

        // 4. 輸出或保存結(jié)果
        System.out.println("提取的文本內(nèi)容：\n" + extractedText);

        // 可選：保存到 txt 文件
        try (FileWriter writer = new FileWriter("output.txt")) {
            writer.write(extractedText);
            System.out.println("\n文本已成功保存到 output.txt");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

import com.spire.doc.Document;
import com.spire.doc.FileFormat;
import java.io.*;
import java.net.URL;
import java.net.URLConnection;

public class UrlTextExtractor {

    public static void main(String[] args) {
        String urlStr = "https://example.com";
        
        try {
            String htmlPath = fetchHtmlFromUrl(urlStr, "temp.html");
            Document doc = new Document();
            doc.loadFromFile(htmlPath, FileFormat.Html);
            String text = doc.getText();
            System.out.println(text);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    private static String fetchHtmlFromUrl(String urlString, String savePath) throws Exception {
        URL url = new URL(urlString);
        URLConnection conn = url.openConnection();
        conn.setConnectTimeout(5000);
        conn.setRequestProperty("User-Agent", "Mozilla/5.0");
        
        try (BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream(), "UTF-8"));
             FileWriter writer = new FileWriter(savePath)) {
            String line;
            while ((line = reader.readLine()) != null) {
                writer.write(line);
                writer.write("\n");
            }
        }
        return savePath;
    }
}

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.17.2</version>
</dependency>

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import java.io.File;

public class JsoupExtractor {

    public static void main(String[] args) throws Exception {
        // 加載 HTML 文件
        Document doc = Jsoup.parse(new File("input.html"), "UTF-8");
        
        // 提取純文本（自動(dòng)去除標(biāo)簽）
        String text = doc.text();
        
        System.out.println(text);
    }
}

Document doc = Jsoup.connect("https://example.com")
    .userAgent("Mozilla/5.0")
    .timeout(5000)
    .get();
String text = doc.text();