WORD/PDF纯文本提取

/**
     * 提取WORD文档中的文本内容
     * @param path
     * @return
     */
    private static String getWordText(String path) {
        String resultText = null;
        if (path.endsWith(".doc")) {
            try (FileInputStream is = new FileInputStream(new File(path)); WordExtractor re = new WordExtractor(is);) {
                resultText = re.getText();
            } catch (IOException e) {
                e.printStackTrace();
            }
        } else if (path.endsWith(".docx")) {
            try {
                OPCPackage opcPackage = POIXMLDocument.openPackage(path);
                XWPFWordExtractor extractor = new XWPFWordExtractor(opcPackage);
                resultText = extractor.getText();
                extractor.close();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        return resultText;
    }
	
   /**
     * 提取PDF中的文本内容
     * @param file
     * @return
     */
    private static String getPdfText(File file) {
        String resultText = null;
        try {
            PDDocument pdDocument = PDDocument.load(file);
            PDFTextStripper stripper = new PDFTextStripper();
            resultText = stripper.getText(pdDocument);
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return resultText;
    }

本人osc:https://my.oschina.net/u/3269106/blog/4961298