pdfwin.java

pdf 文件解析器 xpdf-3.02pl2-win32.zip 带例子

package src;

import java.io.BufferedInputStream;
import java.io.InputStreamReader;
import java.io.StringWriter;

public class PdfWin {
	public PdfWin() {
		
	}
	public static void main(String args[]) throws Exception
	{
		//先指定需要的 pdf 解析器
		String PATH_TO_XPDF="C:\\Documents and Settings\\Administrator\\桌面\\xpdf-3.02pl2-win32\\xpdf-3.02pl2-win32\\pdftotext.exe";
		//指定需要转换的 pdf 文件
		String filename="c:\\Documents and Settings\\Administrator\\桌面\\新建 Microsoft Word 文档.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);
		}
	}