Java读取PDF文件转为字符串

Java读取PDF文件中字符串

方法：PDFBox

1、加入依赖

<!-- https://mvnrepository.com/artifact/pdfbox/pdfbox -->
<dependency>
    <groupId>pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>0.7.3</version>
</dependency>
<!-- https://mvnrepository.com/artifact/FontBox/FontBox -->
<dependency>
    <groupId>FontBox</groupId>
    <artifactId>FontBox</artifactId>
    <version>0.1.0-dev</version>
</dependency>

2、测试代码

public static String getTextFromPDF(String pdfFilePath)
{
    String result = null;
    FileInputStream is = null;
    PDDocument document = null;
    try {
        is = new FileInputStream(pdfFilePath);
        PDFParser parser = new PDFParser(is);
        parser.parse();
        document = parser.getPDDocument();
        PDFTextStripper stripper = new PDFTextStripper();
        result = stripper.getText(document);
    } catch (FileNotFoundException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } finally {
        if (is != null) {
            try {
                is.close();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
        }
        if (document != null) {
            try {
                document.close();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
        }
    }
    return result;
}
public  static void main(String[] args)
{
    String str=getTextFromPDF("D:\\XXX.pdf");
    System.out.println(str);

}