第1个回答 2020-11-23
可以用free spire.doc for java来读取.docx文件中的内容,以下代码可供参考:
import com.spire.doc.Document;
import java.io.FileWriter;
import java.io.IOException;
public class ExtractText {
public static void main(String[] args) throws IOException {
//加载Word文档
Document document = new Document();
document.loadFromFile("C:\\Users\\Administrator\\Desktop\\sample.docx");
//获取文档中的文本保存为String
String text=document.getText();
//将String写入Txt文件
writeStringToTxt(text,"ExtractedText.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();
}
}
}
}