zoukankan      html  css  js  c++  java
  • java提取docx文件中的图片

    使用的maven为:

    <dependency>
         <groupId>org.apache.poi</groupId>
         <artifactId>poi</artifactId>
         <version>3.17</version>
    </dependency>

    1. 获取docx文件中的所有图片

    //  获取word中的所有图片
      public static void readImageInParagraph() throws IOException {
    
        XWPFDocument document = new XWPFDocument(new FileInputStream("C:\Users\Administrator\Desktop\JP6-0-2006.docx"));
        // 用XWPFDocument的getAllPictures来获取所有的图片
        List<XWPFPictureData> picList = document.getAllPictures();
        for (XWPFPictureData pic : picList) {
          System.out.println(pic.getPictureType() +  pic.getFileName());
          byte[] bytev = pic.getData();
    //                System.out.println(bytev.length);
          // 大于1000bites的图片我们才弄下来,消除word中莫名的小图片的影响
          if (bytev.length > 300) {
            FileOutputStream fos = new FileOutputStream("C:\Users\Administrator\Desktop\cc\" + pic.getFileName());
            fos.write(bytev);
          }
        }
      }

    2. 根据docx的内容,获取每段内容对应的图片

     public static List<String> readImageInParagraphTest() throws IOException {  //XWPFParagraph paragraph
    InputStream is = new FileInputStream("C:\Users\Administrator\Desktop\JP6-0-2006.docx");
    XWPFDocument doc = new XWPFDocument(is);
    List<XWPFParagraph> paras = doc.getParagraphs(); //将得到包含段落列表
    List<String> picArr = new ArrayList<>();
    for (XWPFParagraph paragraph : paras) {
    List<XWPFRun> runs = paragraph.getRuns();
    for (XWPFRun run : runs) {
    List<XWPFPicture> pictures = run.getEmbeddedPictures();
    // System.out.println(pictures);
    if (!pictures.isEmpty()) {
    for (XWPFPicture picture : pictures) {
    // 将图片下载到本地,
    // XWPFPicture picture = pictures.get(0);
    XWPFPictureData pictureData = picture.getPictureData();
    // System.out.println(pictureData.getPictureType());
    byte[] bytev = pictureData.getData();

    // 大于1000bites的图片我们才弄下来,消除word中莫名的小图片的影响
    if (bytev.length > 20) {
    // String fileName = "../../../../resources/static/picture/" + pictureData.getFileName();
    String fileName = "D:\programming\fileex\src\main\resources\static\picture\" + pictureData.getFileName();
    FileOutputStream fos = new FileOutputStream(fileName);
    fos.write(bytev);
    String pic_string = "/picture/" + pictureData.getFileName();
    picArr.add(pic_string);
    System.out.println(pic_string); //获取指定大小的图片
    }
    }
    }
    }
    }
    return picArr;
    }
  • 相关阅读:
    [LUOGU] 1364 医院设置
    [POJ] 3278 Catch That Cow
    [OpenJudge] 2727 仙岛寻药
    [POJ] 2386 Lake Counting
    [POJ]1118 Lining up
    [LUOGU]1141 01迷宫
    [POJ]1111 Image Perimeters
    python之路——初识函数
    python----------文件操作
    Python中的split()函数的用法
  • 原文地址:https://www.cnblogs.com/lxz123/p/15136439.html
Copyright © 2011-2022 走看看