【用POI读取doc或者docx内容】

最新推荐文章于 2024-05-06 09:01:24 发布

想念是会呼吸的鱼

最新推荐文章于 2024-05-06 09:01:24 发布

阅读量636

点赞数 6

分类专栏： java 文章标签： java

本文链接：https://blog.csdn.net/weixin_45430750/article/details/136745695

版权

java 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

使用POI获取文档内容

1.添加依赖

        <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>

2.上代码

/**
     * 解析 docx
     *
     * @param docUrl 本地文档地址
     * @return 所读取的文档的对象
     */
    public static String parseDoc(String docUrl) {
        FileInputStream fis = null;
        XWPFDocument document = null;
        String content = null;
        try {
            fis = new FileInputStream(new File(docUrl));
            document = new XWPFDocument(fis);
            //XWPFWordExtractor
            XWPFWordExtractor extractor = new XWPFWordExtractor(document);
            content = extractor.getText();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return content;
    }


    /**
     * 从链接中解析 docx
     * @param docUrl doc访问链接
     * @return doc内容
     */
    public static String parseDocFromChain(String docUrl) {
        InputStream fis = null;
        XWPFDocument document = null;
        String content = null;
        try {
            fis =  new URL(docUrl).openStream();
            document = new XWPFDocument(fis);
            XWPFWordExtractor extractor = new XWPFWordExtractor(document);
            content = extractor.getText();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return content;
    }