pageoffice java 读取word java读取word文件

Java读取word文档中的内容

一、效果：

1.1 doc文本

1.2 程序获取的内容

二、源码

2.1 pom文件

<!-- poi -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.16</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.16</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.16</version>
        </dependency>

2.2 Java代码

public class TestReadDoc {

    /**
     * 读取word文档中后缀为doc的文件
     * @param filePath
     * @return
     */
    public static String readWordDoc(String filePath){
        String content = null;
        InputStream input = null;
        try {
            input = new FileInputStream(new File(filePath));
            WordExtractor wex = new WordExtractor(input);
            content = wex.getText();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }
    
    /**
     * 读取word文档中后缀为docx的文件
     * @param filePath
     * @return
     */
    public static String readWordDocX(String filePath){
        String content = null;
        OPCPackage opcPackage = null;
        try {
            opcPackage = POIXMLDocument.openPackage(filePath);
            XWPFDocument xwpf = new XWPFDocument(opcPackage);
            POIXMLTextExtractor poiText = new XWPFWordExtractor(xwpf);
            content = poiText.getText();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }

    public static void main(String[] args) {
        System.out.println("****** 下面就是获取的内容 ******");
        
        String doc = "C:\\Users\\canwei\\Desktop\\test.doc";
        
        System.out.println(readWordDoc(doc));
    }
    
}