pdf读取

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.*;

/**
 * Created by xiaojun on 16/1/5
 */
public class PdfReader {

    private static final Logger logger = LoggerFactory.getLogger(PdfReader.class);


    public PdfReader() {
    }

    /**
     * @param file 文件
     * @return 读出的pdf的内容
     */
    public String getTextFromPdf(File file) {
        String result = null;
        PDDocument document = null;
        try {
            document = PDDocument.load(file);
            PDFTextStripper stripper = new PDFTextStripper();
            result = stripper.getText(document);
        } catch (IOException e) {
            logger.error("IOException",e);
        } finally {
            if (document != null) {
                try {
                    document.close();
                } catch (IOException e) {
                    logger.error("IOException",e);
                }
            }
        }
        return result;
    }

    public String getTextFromPdf(InputStream is) {
        String result = null;
        PDDocument document = null;
        try {
            document = PDDocument.load(is);
            PDFTextStripper stripper = new PDFTextStripper();
            result = stripper.getText(document);

        } catch (Exception ex) {
            logger.warn("获取文件内容，getTextFromPdf error",ex);
        } finally {
            if (document != null) {
                try {
                    document.close();
                } catch (IOException e) {
                    logger.warn("获取文件内容，getTextFromPdf error",e);
                }
            }
        }
        return result;
    }
}