JAVA读取PDF、WORD文档实例代码

读取PDF文件jar引用

  org.apache.pdfbox
  pdfbox
  1.8.13

读取WORD文件jar引用

  org.apache.poi
  poi-scratchpad
  3.16-beta1


  org.apache.poi
  poi
  3.16-beta1

读取WORD文件方法

  public static String getTextFromWord(String filePath) {
    String result = null;
    File file = new File(filePath);
    FileInputStream fis = null;
    try {
      fis = new FileInputStream(file);
      @SuppressWarnings("resource")
      WordExtractor wordExtractor = new WordExtractor(fis);
      result = wordExtractor.getText();
    } catch (FileNotFoundException e) {
      e.printStackTrace();
    } catch (IOException e) {
      e.printStackTrace();
    } finally {
      if (fis != null) {
 try {
   fis.close();
 } catch (IOException e) {
   e.printStackTrace();
 }
      }
    }
    return result;
  }

读取PDF文件方法

public static String getTextFromPdf(String filePath) {
  String result = null;
  FileInputStream is = null;
  PDdocument document = null;
  try {
    is = new FileInputStream(filePath);
    PDFParser parser = new PDFParser(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;
}

希望本篇实例代码可以帮到您