抽取word、pdf的几种方法。 1、用jacob. 其实jacob是一个bridage,连接java和com或者win32函数的一个中间件,jacob并不能直接抽取word,excel等文件,需要自己写dll哦,不过已经有为你写好的了,就是jacob的作者一并提供了。 jacob下载:http://www.matrix.org.cn/down_view.asp?id=13 下载了jacob并放到指定的路径之后(dll放到path,jar文件放到classpath),就可以写你自己的抽取程序了,下面是一个例子:import java.io.File; import com.jacob.com.*; import com.jacob.activeX.*; public class FileExtracter{public static void main(String[] args) {ActiveXComponent app = new ActiveXComponent("Word.Application"); String inFile = "c:\\test.doc"; String tpFile = "c:\\temp.htm"; String otFile = "c:\\temp.xml"; boolean flag = false; try { app.setProperty("Visible", new Variant(false)); Object docs = app.getProperty("document.").toDispatch(); Object doc = Dispatch.invoke(docs,"Open", Dispatch.Method, new Object[]{inFile,new Variant(false), new Variant(true)}, new int[1]).toDispatch(); Dispatch.invoke(doc,"SaveAs", Dispatch.Method, new Object[]{tpFile,new Variant(8)}, new int[1]); Variant f = new Variant(false); Dispatch.call(doc, "Close", f); flag = true; } catch (Exception e) { e.printStackTrace(); } finally { app.invoke("Quit", new Variant[] {}); }} } 2、用apache的poi来抽取word,excel poi是apache的一个项目,不过就算用poi你可能都觉得很烦,不过不要紧,这里提供了更加简单的一个接口给你: 下载经过封装后的poi包:http://www.matrix.org.cn/down_view.asp?id=14 下载之后,放到你的classpath就可以了,下面是如何使用它的一个例子:import java.io.*; import org.textmining.text.extraction.WordExtractor; /** * <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 PdfExtractor { public PdfExtractor() { } public static void main(String args[]) throws Exception { FileInputStream in = new FileInputStream ("c:\\a.doc"); WordExtractor extractor = new WordExtractor(); String str = extractor.extractText(in); System.out.println("the result length is"+str.length()); System.out.println("the result is"+str); } } 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:[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 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:[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); } }
不行啊,第一个例子import java.io.File; import com.jacob.com.*; import com.jacob.activeX.*; public class FileExtracter{public static void main(String[] args) {ActiveXComponent app = new ActiveXComponent("Word.Application"); String inFile = "c:\\test.doc"; String tpFile = "c:\\temp.htm"; String otFile = "c:\\temp.xml"; boolean flag = false; try { app.setProperty("Visible", new Variant(false)); Object docs = app.getProperty("document.").toDispatch(); Object doc = Dispatch.invoke(docs,"Open", Dispatch.Method, new Object[]{inFile,new Variant(false), new Variant(true)}, new int[1]).toDispatch(); Dispatch.invoke(doc,"SaveAs", Dispatch.Method, new Object[]{tpFile,new Variant(8)}, new int[1]); Variant f = new Variant(false); Dispatch.call(doc, "Close", f); flag = true; } catch (Exception e) { e.printStackTrace(); } finally { app.invoke("Quit", new Variant[] {}); }} } 能编译过去,但执行不了啊。下面是错误,大家快帮帮忙啊。 D:\hai\javawork\file\test>javac FileExtracter.javaD:\hai\javawork\file\test>java FileExtracter Exception in thread "main" java.lang.UnsatisfiedLinkError: no jacob in java.libr ary.path at java.lang.ClassLoader.loadLibrary(Unknown Source) at java.lang.Runtime.loadLibrary0(Unknown Source) at java.lang.System.loadLibrary(Unknown Source) at com.jacob.com.Dispatch.<clinit>(Dispatch.java) at FileExtracter.main(FileExtracter.java:8)
import com.jacob.com.*;
import com.jacob.activeX.*;
public class FileExtracter{public static void main(String[] args) {ActiveXComponent app = new ActiveXComponent("Word.Application");
String inFile = "c:\\test.doc";
String tpFile = "c:\\temp.htm";
String otFile = "c:\\temp.xml";
boolean flag = false;
try {
app.setProperty("Visible", new Variant(false));
Object docs = app.getProperty("document.").toDispatch();
Object doc = Dispatch.invoke(docs,"Open", Dispatch.Method, new Object[]{inFile,new Variant(false), new Variant(true)}, new int[1]).toDispatch();
Dispatch.invoke(doc,"SaveAs", Dispatch.Method, new Object[]{tpFile,new Variant(8)}, new int[1]);
Variant f = new Variant(false);
Dispatch.call(doc, "Close", f);
flag = true;
} catch (Exception e) {
e.printStackTrace();
} finally {
app.invoke("Quit", new Variant[] {});
}}
} 2、用apache的poi来抽取word,excel poi是apache的一个项目,不过就算用poi你可能都觉得很烦,不过不要紧,这里提供了更加简单的一个接口给你: 下载经过封装后的poi包:http://www.matrix.org.cn/down_view.asp?id=14 下载之后,放到你的classpath就可以了,下面是如何使用它的一个例子:import java.io.*;
import org.textmining.text.extraction.WordExtractor;
/**
* <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 PdfExtractor {
public PdfExtractor() {
}
public static void main(String args[]) throws Exception
{
FileInputStream in = new FileInputStream ("c:\\a.doc");
WordExtractor extractor = new WordExtractor();
String str = extractor.extractText(in);
System.out.println("the result length is"+str.length());
System.out.println("the result is"+str);
}
}
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:[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 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:[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);
}
}
import com.jacob.com.*;
import com.jacob.activeX.*;
public class FileExtracter{public static void main(String[] args) {ActiveXComponent app = new ActiveXComponent("Word.Application");
String inFile = "c:\\test.doc";
String tpFile = "c:\\temp.htm";
String otFile = "c:\\temp.xml";
boolean flag = false;
try {
app.setProperty("Visible", new Variant(false));
Object docs = app.getProperty("document.").toDispatch();
Object doc = Dispatch.invoke(docs,"Open", Dispatch.Method, new Object[]{inFile,new Variant(false), new Variant(true)}, new int[1]).toDispatch();
Dispatch.invoke(doc,"SaveAs", Dispatch.Method, new Object[]{tpFile,new Variant(8)}, new int[1]);
Variant f = new Variant(false);
Dispatch.call(doc, "Close", f);
flag = true;
} catch (Exception e) {
e.printStackTrace();
} finally {
app.invoke("Quit", new Variant[] {});
}}
}
能编译过去,但执行不了啊。下面是错误,大家快帮帮忙啊。
D:\hai\javawork\file\test>javac FileExtracter.javaD:\hai\javawork\file\test>java FileExtracter
Exception in thread "main" java.lang.UnsatisfiedLinkError: no jacob in java.libr
ary.path
at java.lang.ClassLoader.loadLibrary(Unknown Source)
at java.lang.Runtime.loadLibrary0(Unknown Source)
at java.lang.System.loadLibrary(Unknown Source)
at com.jacob.com.Dispatch.<clinit>(Dispatch.java)
at FileExtracter.main(FileExtracter.java:8)