展开全部
PDFBox是一个开源的对pdf文件进行操作的库。 PDFBox-0.7.3.jar加入classpath。同时FontBox1.0.jar加入classpath,否则报错62616964757a686964616fe4b893e5b19e31333339653637
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.util.PDFTextStripper;
public class PdfReader {
/**
* simply reader all the text from a pdf file.
* You have to deal with the format of the output text by yourself.
* 2008-2-25
* @param pdfFilePath file path
* @return all text in the pdf file
*/
public static String getTextFromPDF(String pdfFilePath)
{
String result = null;
FileInputStream is = null;
PDDocument document = null;
try {
is = new FileInputStream(pdfFilePath);
PDFParser parser = new PDFParser(is);
parser.parse();
document = parser.getPDDocument();
PDFTextStripper stripper = new PDFTextStripper();
result = stripper.getText(document);
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
if (is != null) {
try {
is.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
if (document != null) {
try {
document.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
return result;
}
public static void main(String[] args)
{
String str=PdfReader.getTextFromPDF("C:\\Read.pdf");
System.out.println(str);
}
}
代码2:import java.io.File;
import java.io.FileOutputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.net.MalformedURLException;
import java.net.URL;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.util.PDFTextStripper;
public class PDFReader {
public void readFdf(String file) throws Exception {
boolean sort = false;
String pdfFile = file;
String textFile = null;
String encoding = "UTF-8";
int startPage = 1;
int endPage = Integer.MAX_VALUE;
Writer output = null;
PDDocument document = null;
try {
try {
// 首先当作一个URL来装载文件,如果得到异常再从本地文件系统//去装载文件
URL url = new URL(pdfFile);
//注意参数已不是以前版本中的URL.而是File。
document = PDDocument.load(pdfFile);
// 获取PDF的文件名
String fileName = url.getFile();
// 以原来PDF的名称来命名新产生的txt文件
if (fileName.length() > 4) {
File outputFile = new File(fileName.substring(0, fileName
.length() - 4)
+ ".txt");
textFile = outputFile.getName();
}
} catch (MalformedURLException e) {
// 如果作为URL装载得到异常则从文件系统装载
//注意参数已不是以前版本中的URL.而是File。
document = PDDocument.load(pdfFile);
if (pdfFile.length() > 4) {
textFile = pdfFile.substring(0, pdfFile.length() - 4)
+ ".txt";
}
}
output = new OutputStreamWriter(new FileOutputStream(textFile),
encoding);
PDFTextStripper stripper = null;
stripper = new PDFTextStripper();
// 设置是否排序
stripper.setSortByPosition(sort);
// 设置起始页
stripper.setStartPage(startPage);
// 设置结束页
stripper.setEndPage(endPage);
// 调用PDFTextStripper的writeText提取并输出文本
stripper.writeText(document, output);
} finally {
if (output != null) {
// 关闭输出流
output.close();
}
if (document != null) {
// 关闭PDF Document
document.close();
}
}
}
/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
PDFReader pdfReader = new PDFReader();
try {
// 取得E盘下的SpringGuide.pdf的内容
pdfReader.readFdf("C:\\Read.pdf");
} catch (Exception e) {
e.printStackTrace();
}
}
}
2、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。
http://www.java-cn.com/technology/tech_downs/1880_004.zip
补丁包:
http://www.java-cn.com/technology/tech_downs/1880_005.zip
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.*;
/**
*
Title: pdf extraction
*
Description: email:chris@matrix.org.cn
*
Copyright: Matrix Copyright (c) 2003
*
Company: Matrix.org.cn
* @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 Filesxpdfpdftotext.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);
}
}