从PDF文件中提取文字

改写PDF在线浏览前，先将以往写的从提取PDF文件提取文本的代码留个爪，以便今后有用。

package com.eimone.institution.service.impl;

import java.io.BufferedInputStream;

import java.io.BufferedOutputStream;

import java.io.File;

import java.io.FileInputStream;

import java.io.FileNotFoundException;

import java.io.FileOutputStream;

import java.io.IOException;

import java.io.Writer;

import java.util.Date;

import java.util.List;

import javax.annotation.Resource;

import org.apache.pdfbox.pdfparser.PDFParser;

import org.apache.pdfbox.pdmodel.PDDocument;

import org.apache.pdfbox.util.PDFTextStripper;

import org.apache.struts2.ServletActionContext;

import org.hibernate.criterion.DetachedCriteria;

import org.springframework.stereotype.Component;

import com.eimone.institution.bean.Attachment;

import com.eimone.institution.dao.IInstitutionDao;

import com.eimone.institution.model.Institution;

import com.eimone.institution.service.IInstitutionService;

public class InstitutionServiceImpl {

private IInstitutionDao institutionDao;

public Institution saveInstitution(Institution institution,

Attachment attachment){

if (!(attachment == null || attachment.getFileFileName() == null || attachment

.getFileFileName().length == 0)) {

finishAttachment(attachment, institution);

}

Date now = new Date();

institution.setPublishTime(now);

return institutionDao.save(institution);

}

private String finishAttachment(Attachment attachment,

Institution institution){

String info = "";

File[] files = attachment.getFile();

String path = ServletActionContext.getServletContext().getRealPath(

"regulations");

File desc = new File(path);

if (!desc.exists()) {

desc.mkdir();

}

for (int i = 0; i < files.length; i++) {

File file = files[i];

long now = System.currentTimeMillis();

String fileName = attachment.getFileFileName()[i];

path += "\\" + now + "_" + fileName;

institution.setUrl(now + "_" + fileName);

saveFile(file, path);

institution.setContent(getTextFromPdf(path));

}

return info;

}

public void saveFile(File file, String path) {

BufferedOutputStream bof = null;

BufferedInputStream bis = null;

try {

FileOutputStream fos = new FileOutputStream(path);

bof = new BufferedOutputStream(fos);

bis = new BufferedInputStream(new FileInputStream(file));

byte[] buffer = new byte[1024];

try {

int len = bis.read(buffer);

while (len > 0) {

bof.write(buffer, 0, len);

len = bis.read(buffer);

}

} catch (IOException e) {

e.printStackTrace();

}

} catch (FileNotFoundException e) {

e.printStackTrace();

} finally {

try {

if (bof != null) {

bof.close();

}

if (bis != null) {

bis.close();

}

} catch (IOException e) {

e.printStackTrace();

}

/**

* @param filePath

* 文件路径

* @return 读出的pdf的内容

public String getTextFromPdf(String filePath) {

String result = null;

FileInputStream is = null;

PDDocument document = null;

try {

is = new FileInputStream(filePath);

PDFParser parser = new PDFParser(is);

parser.parse();

document = parser.getPDDocument();

PDFTextStripper stripper = new PDFTextStripper();

result = stripper.getText(document);

} catch (FileNotFoundException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

} catch(NoClassDefFoundError e) {

e.printStackTrace();

}

finally {

if (is != null) {

try {

is.close();

} catch (IOException e) {

e.printStackTrace();

}

if (document != null) {

try {

document.close();

} catch (IOException e) {

e.printStackTrace();

}

return result;

}

public static void main(String[] args) {

InstitutionServiceImpl impl = new InstitutionServiceImpl();

System.out.println(impl.getTextFromPdf("d:\\OUTLINE_DESIGN.pdf"));

}

posted on 2010-10-24 15:53 [ 王志伟 ] 阅读(831) 评论(0) 编辑收藏

常用链接

留言簿(1)

随笔档案(3)

文章档案(29)

搜索

最新评论

阅读排行榜

评论排行榜


只有注册用户登录后才能发表评论。




网站导航: 博客园 IT新闻 Chat2DB C++博客博问管理