java 获取pdf内容

1.pom文件

<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>pdfbox</artifactId>
			<version>2.0.12</version>
		</dependency>

2.代码

public static String pdfToString(File file) {

		String content = null;
		InputStream input = null;
		PDDocument document = null;
		try {
			input = new FileInputStream(file);
			boolean sort = false;
			// 开始提取页数
			int startPage = 1;
			// 结束提取页数
			int endPage = Integer.MAX_VALUE;
			document = PDDocument.load(input);
			PDFTextStripper pts = new PDFTextStripper();
			pts.setSortByPosition(sort);
			endPage = document.getNumberOfPages();
			//System.out.println("Total Page: " + endPage);
			pts.setStartPage(startPage);
			pts.setEndPage(endPage);
			content = pts.getText(document);
			return content;
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (InvalidPasswordException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

		return "";
	}