java有返回值将文档中的文字和图片解析的代码

以下是一个使用Java解析文档中文字和图片的示例代码：

import java.io.FileInputStream;
import java.io.IOException;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFPictureData;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.xmlbeans.XmlCursor;
import org.apache.xmlbeans.XmlObject;
import org.openxmlformats.schemas.drawingml.x2006.picture.CTPicture;

public class DocParser {
    public static String parseDocx(String filePath) throws IOException {
        FileInputStream fis = new FileInputStream(filePath);
        XWPFDocument doc = new XWPFDocument(fis);

        StringBuilder text = new StringBuilder();
        for (XWPFRun run : doc.getParagraphs().get(0).getRuns()) {
            text.append(run.getText(0));
        }

        StringBuilder images = new StringBuilder();
        for (XWPFPictureData picture : doc.getAllPictures()) {
            images.append("Image: ").append(picture.getFileName()).append("\n");
        }

        fis.close();
        return "Text: " + text.toString() + "\n" + images.toString();
    }

    public static String parseDoc(String filePath) throws IOException {
        FileInputStream fis = new FileInputStream(filePath);
        HWPFDocument doc = new HWPFDocument(fis);
        WordExtractor extractor = new WordExtractor(doc);

        StringBuilder text = new StringBuilder();
        for (String paragraph : extractor.getParagraphText()) {
            text.append(paragraph);
        }

        XmlCursor cursor = doc.getRange().newCursor();
        while (cursor.hasNextToken()) {
            cursor.toNextToken();
            XmlObject obj = cursor.getObject();
            if (obj instanceof CTPicture) {
                images.append("Image: ").append(((CTPicture) obj).getBlipFill().getBlip().getEmbed()).append("\n");
            }
        }

        fis.close();
        return "Text: " + text.toString() + "\n" + images.toString();
    }
}

这个示例代码使用了Apache POI库来解析Microsoft Word文档。`parseDocx()`方法用于解析.docx文件，`parseDoc()`方法用于解析.doc文件。这两个方法都返回一个字符串，其中包含文档中的文字和图片信息。