java将pdf转为文本,使用xpdf将pdf文件转换为文本

// 读取PDF的内容

public String getPdfContent(String filePath) {

// 设置pdftotext所在的路径

String excute = "E:\\JAR\\xpdf\\xpdf-3.02pl4-win32\\pdftotext.exe";

//构造命令行里面的命令

String[] cmd = new String[] { excute, "-enc", "UTF-8", "-q", filePath,"-" };

Process p = null;

try {

// 调用本地命令,类似于在cmd里面敲上述命令

p = Runtime.getRuntime().exec(cmd);

} catch (IOException e) {

e.printStackTrace();

}

//封装成字符流

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();

BufferedReader br = new BufferedReader(reader);

String line;

try {

line = br.readLine();

sb = new StringBuffer();

while (line != null) {

sb.append(line);

sb.append(" ");

line = br.readLine();

}

} catch (IOException e) {

e.printStackTrace();

}

return sb.toString();

}