PDF格式文件的读取

1、导入坐标

 <!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.21</version>
</dependency>

2、编写业务类

public class Test {
    public static String getTextFromPDF(String pdfFilePath) {
        String result = null;
        FileInputStream is = null;
        PDDocument document = null;
        try {
            is = new FileInputStream(pdfFilePath);
            PDFParser parser = new PDFParser(new RandomAccessBuffer(is));
            parser.parse();
            document = parser.getPDDocument();
            PDFTextStripper stripper = new PDFTextStripper();
            result = stripper.getText(document);
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (document != null) {
                try {
                    document.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return result;
    }

    public static void main(String[] args) {
        String str = Test.getTextFromPDF("D:\\Download\\Google\\123_20201106142215.pdf");
        System.out.println(str);

    }
}