使用Java高效读取Word文档的实战指南

<repositories>
    <repository>
        <id>e-iceblue</id>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.doc</artifactId>
        <version>12.4.0</version> <!-- 请使用最新版本 -->
    </dependency>
</dependencies>

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

public class ExtractText {

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

        //创建一个Document类的对象
        Document document = new Document();

        //载入Word文档
        document.loadFromFile("示例.docx");

        //以字符串形式从文档中获取文本
        String text=document.getText();

        //将字符串写入文本文件中
        writeStringToTxt(text,"提取文本.txt");
    }
    public static void writeStringToTxt(String content, String txtFileName) throws IOException{
        FileWriter fWriter= new FileWriter(txtFileName,true);
        try {
            fWriter.write(content);
        }catch(IOException ex){
            ex.printStackTrace();
        }finally{
            try{
                fWriter.flush();
                fWriter.close();
            } catch (IOException ex) {
                ex.printStackTrace();
            }
        }
    }
}

import com.spire.doc.*;
import com.spire.doc.documents.*;
import com.spire.doc.fields.DocPicture;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

public class ExtractWordImages {
    public static void main(String[] args) {
        // 1. 创建Document对象并加载Word文档
        Document document = new Document();
        try {
            document.loadFromFile("data/DocumentWithImages.docx"); // 替换为包含图片的Word文档路径
            System.out.println("开始提取Word文档中的图片...");

            int imageCount = 0;
            // 2. 遍历文档中的所有节
            for (int i = 0; i < document.getSections().getCount(); i++) {
                Section section = document.getSections().get(i);

                // 3. 遍历节中的所有段落
                for (int j = 0; j < section.getParagraphs().getCount(); j++) {
                    Paragraph paragraph = section.getParagraphs().get(j);

                    // 4. 遍历段落中的所有子对象
                    for (int k = 0; k < paragraph.getChildObjects().getCount(); k++) {
                        DocumentObject docObject = paragraph.getChildObjects().get(k);

                        // 5. 判断子对象是否为DocPicture（图片）类型
                        if (docObject.getDocumentObjectType() == DocumentObjectType.Picture) {
                            DocPicture picture = (DocPicture) docObject;
                            BufferedImage image = picture.getImage(); // 获取图片对象

                            if (image != null) {
                                // 6. 将图片保存到本地文件
                                String outputPath = "output/Image_" + (++imageCount) + ".png"; // 指定输出路径和文件名
                                File outputDir = new File("output");
                                if (!outputDir.exists()) {
                                    outputDir.mkdirs(); // 创建输出目录
                                }
                                ImageIO.write(image, "PNG", new File(outputPath));
                                System.out.println("图片已保存至：" + outputPath);
                            }
                        }
                    }
                }
            }
            System.out.println("图片提取完成。共提取 " + imageCount + " 张图片。");

        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            // 释放文档资源
            if (document != null) {
                document.dispose();
            }
        }
    }
}