在Java中,你可以使用Apache POI库来读取Word文档并提取文本内容。你可以在 Maven 项目中添加以下依赖:
<!-- Apache POI for Word 2007+ (.docx) -->
<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>4.1.2</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>4.1.2</version>
</dependency><!-- Apache POI for Word 97-2003 (.doc) -->
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>4.1.2</version>
</dependency>
以下是一个简单的示例代码,展示如何使用Apache POI将Word文档转换为文本:
import lombok.extern.slf4j.Slf4j;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.springframework.web.multipart.MultipartFile;import java.io.IOException;@Slf4j
public class WordUtils {/*** Word转换为文本** @param file Word文件* @return 提取的文本*/public static String wordToTextConverter(MultipartFile file) {try {if (file.getOriginalFilename().endsWith(".doc")) {// 处理Word 97-2003文档return processOldWordDocument(file);} else if (file.getOriginalFilename().endsWith(".docx")) {// 处理Word 2007及以上文档return processNewWordDocument(file);} else {throw new RuntimeException("不支持的Word文档格式");}} catch (IOException e) {throw new RuntimeException("无法读取Word文档", e);}}private static String processOldWordDocument(MultipartFile file) throws IOException {try (HWPFDocument document = new HWPFDocument(file.getInputStream())) {WordExtractor extractor = new WordExtractor(document);String text = extractor.getText();log.info("Word文档内容: {}", text);return text;}}private static String processNewWordDocument(MultipartFile file) throws IOException {try (XWPFDocument document = new XWPFDocument(file.getInputStream())) {if (document.getParagraphs().isEmpty()) {throw new RuntimeException("Word文档为空");}XWPFWordExtractor extractor = new XWPFWordExtractor(document);String text = extractor.getText();log.info("Word文档内容: {}", text);return text;}}
}