PDF解析返回一个对象

1.首先引入Maven jar包

<dependency>
    <groupId> e-iceblue </groupId>
    <artifactId>spire.pdf</artifactId>
    <version>2.2.0</version>
</dependency>

<repository>
    <id>com.e-iceblue</id>
    <name>e-iceblue</name>
    <url>http://repo.e-iceblue.com/nexus/content/groups/public/</url>
</repository>

2.直接在COontroller层里面开工
import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;

@PostMapping("/getPdf")
public StringBuilder getPdf() {
    StringBuilder stringBuilder = null;
//因为项目需要，所以先把文件上传到 fastdns服务器 服务器返回一个地址后端下载 然后拿着这个地址里面的文件进行解析 一般不需要
    ImportParams params = new ImportParams();
    params.setSaveUrl("/file");
    String filePath="http://dev.file.aq-100.com:80/group1/M00/00/04/wKgCt15fCcuAEXm9AABV0XpTz3g800.pdf";
    OkHttpUtil.download(filePath,"D://","test.pdf");
    /*InputStream in = new FileInputStream(new File("D://test.pdf"));*/
    try {
        PdfDocument doc = new PdfDocument();
        doc.loadFromFile("D://test.pdf");
        stringBuilder = new StringBuilder();
        PdfPageBase page;
        for (int i = 0; i < doc.getPages().getCount(); i++) {
            //获取每一行的page对象
            page = doc.getPages().get(i);
            stringBuilder.append(page.extractText(true));
            //这个if中是图片的解析输出
            if (page.extractImages() != null) {
                for (BufferedImage image : page.extractImages()) {
                    if (image != null) {
                        //指定输出图片名，指定图片格式,后缀自己换
                        File output = new File(String.valueOf("D://test.pdf"));
                        ImageIO.write(image, "PNG", output);
                    }
                }
            }
        }
        System.out.println(stringBuilder);
        doc.close();
    } catch (Exception e) {
        e.printStackTrace();
    }
    return stringBuilder;
}