情参考:http://www-900.ibm.com/developerWorks/cn/java/l-java-tips/index.shtml抽取支持中文的pdf文件-xpdfimport java.io.*;
/**
* <p>Title: pdf extraction</p>
* <p>Description: email:[email protected]</p>
* <p>Copyright: Matrix Copyright (c) 2003</p>
* <p>Company: Matrix.org.cn</p>
* @author chris
* @version 1.0,who use this example pls remain the declare
*/
public class PdfWin {
public PdfWin() {
}
public static void main(String args[]) throws Exception
{
String PATH_TO_XPDF="C:\\Program Files\\xpdf\\pdftotext.exe";
String filename="c:\\a.pdf";
String[] cmd = new String[] { PATH_TO_XPDF, "-enc", "UTF-8", "-q", filename, "-"};
Process p = Runtime.getRuntime().exec(cmd);
BufferedInputStream bis = new BufferedInputStream(p.getInputStream());
InputStreamReader reader = new InputStreamReader(bis, "UTF-8");
StringWriter out = new StringWriter();
char [] buf = new char[10000];
int len;
while((len = reader.read(buf))>= 0) {
//out.write(buf, 0, len);
System.out.println("the length is"+len);
}
reader.close();
String ts=new String(buf);
System.out.println("the str is"+ts);
}
}
/**
* <p>Title: pdf extraction</p>
* <p>Description: email:[email protected]</p>
* <p>Copyright: Matrix Copyright (c) 2003</p>
* <p>Company: Matrix.org.cn</p>
* @author chris
* @version 1.0,who use this example pls remain the declare
*/
public class PdfWin {
public PdfWin() {
}
public static void main(String args[]) throws Exception
{
String PATH_TO_XPDF="C:\\Program Files\\xpdf\\pdftotext.exe";
String filename="c:\\a.pdf";
String[] cmd = new String[] { PATH_TO_XPDF, "-enc", "UTF-8", "-q", filename, "-"};
Process p = Runtime.getRuntime().exec(cmd);
BufferedInputStream bis = new BufferedInputStream(p.getInputStream());
InputStreamReader reader = new InputStreamReader(bis, "UTF-8");
StringWriter out = new StringWriter();
char [] buf = new char[10000];
int len;
while((len = reader.read(buf))>= 0) {
//out.write(buf, 0, len);
System.out.println("the length is"+len);
}
reader.close();
String ts=new String(buf);
System.out.println("the str is"+ts);
}
}
Process exec(String command)
Executes the specified string command in a separate process.
Process exec(String[] cmdarray)
Executes the specified command and arguments in a separate process.
Process exec(String[] cmdarray, String[] envp)
Executes the specified command and arguments in a separate process with the specified environment.
Process exec(String[] cmdarray, String[] envp, File dir)
Executes the specified command and arguments in a separate process with the specified environment and working directory.
Process exec(String cmd, String[] envp)
Executes the specified string command in a separate process with the specified environment.
Process exec(String command, String[] envp, File dir)
Executes the specified string command in a separate process with the specified environment and working directory.