java读取pdf文件

方法很简单，利用著名的Runtime.getRuntime()即可，如下：

     /** */ /**
     * @param filePath  pdf文件路径
     * @return
     */
     public  String getPdfContent(String filePath) ... {
        String excute="pdftotext";

        String[] cmd=new String[]...{excute, "-enc", "UTF-8", "-q", filePath,"-"};
        Process p=null;
        try ...{
            p=Runtime.getRuntime().exec(cmd);
        } catch (IOException e) ...{
            e.printStackTrace();
        }

        BufferedInputStream bis=new BufferedInputStream(p.getInputStream());

        InputStreamReader reader=null;

        try ...{
            reader=new InputStreamReader(bis,"UTF-8");
        } catch (UnsupportedEncodingException e1) ...{
            e1.printStackTrace();
        }

        StringBuffer sb=new StringBuffer();

        try ...{
            BufferedReader br = new BufferedReader(reader);
            String line = br.readLine();            
            sb = new StringBuffer();
            while (line != null) ...{
                sb.append(line);
                sb.append(" ");
                line = br.readLine();
            }
        } catch (Exception e) ...{
            e.printStackTrace();
        }
        
        return sb.toString();
    }