3、pdfbox-用来抽取pdf文件
但是pdfbox对中文支持还不好,先下载pdfbox:http://www.matrix.org.cn/down_view.asp?id=12
下面是一个如何使用pdfbox抽取pdf文件的例子:
import org.pdfbox.pdmodel.PDdocument. import org.pdfbox.pdfparser.PDFParser; import java.io.*; import org.pdfbox.util.PDFTextStripper; import java.util.Date; /** * <p>Title: pdf extraction</p> * <p>Description: email:chris@matrix.org.cn</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 PdfExtracter{
public PdfExtracter(){ } public String GetTextFromPdf(String filename) throws Exception { String temp=null; PDdocument.nbsppdfdocument.null; FileInputStream is=new FileInputStream(filename); PDFParser parser = new PDFParser( is ); parser.parse(); pdfdocument.nbsp= parser.getPDdocument.); ByteArrayOutputStream out = new ByteArrayOutputStream(); OutputStreamWriter writer = new OutputStreamWriter( out ); PDFTextStripper stripper = new PDFTextStripper(); stripper.writeText(pdfdocument.getdocument.), writer ); writer.close(); byte[] contents = out.toByteArray();
String ts=new String(contents); System.out.println("the string length is"+contents.length+"\n"); return ts; } public static void main(String args[]) { PdfExtracter pf=new PdfExtracter(); PDdocument.nbsppdfdocument.nbsp= null;
try{ String ts=pf.GetTextFromPdf("c:\\a.pdf"); System.out.println(ts); } catch(Exception e) { e.printStackTrace(); } }
} | 4、抽取支持中文的pdf文件-xpdf
xpdf是一个开源项目,我们可以调用他的本地方法来实现抽取中文pdf文件。
下载xpdf函数包:http://www.matrix.org.cn/down_view.asp?id=15
同时需要下载支持中文的补丁包:http://www.matrix.org.cn/down_view.asp?id=16
按照readme放好中文的patch,就可以开始写调用本地方法的java程序了
下面是一个如何调用的例子:
import java.io.*; /** * <p>Title: pdf extraction</p> * <p>Description: email:chris@matrix.org.cn</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); } } |
|
|