Spire.pdf-使用学习记录

spire.pdf 使用学习记录

背景
简介
相似产品及特点
官网地址
功能实现
- 切割pdf
- - 按每页切割
  - 按指定页切割
- 将pdf转成txt
- 识别pdf中的篇章节生成对应文本
- 去除水印
- 获取书签
- 获取每页中图片
- 项目地址

背景

通过打印机将一本纸质书转为pdf的格式，以下所有操作都是在这个基础上操作，最终目的生成n篇txt文件，每个txt名字规则是:起始页_篇&章&节内容:是对应切割的内容；

简介

这是一款基于OCR框架的解析工具，拥有比价完整的Java 类库，及完善的API文档，不但具备pdf的读写，还支持文本和图片的提取，水印的添加，书签的增删改，表格的操作，同时还支持，将pdf转化成word、HTML、XPS、SVG、等多种方式；当然目前这类工具市面上有很多，不过通过比较最后选择了spire.pdf ;目前这款项目共有两个版本，一个是免费版本一个是付费版本，免费版本如果只是处理简单的pdf是没问题的，但是如果涉及到输出为pdf则会只显示前10页，第十一页则是预定的购买页介绍，不过介于spire.pdf的完善性我最后还是选择了他，至于10页的问题，后面会拿出我的处理办法,如果你是其他语言如.NET、Android、也可以使用这款产品;

相似产品及特点

PDFBox
itext
百度
Tesseract 只能用于识别图片，如果需要先将pdf转为图片

官网地址

https://www.e-iceblue.cn/Introduce/Free-Spire-PDF-JAVA.html

功能实现

前往官网下载jar包或者直接在maven上通过坐标也可实现，不过maven上的肯定没有网页下载的新；

<!-- 事先配置maven仓库路径-->
<repositories><repository><id>com.e-iceblue</id><url>http://repo.e-iceblue.cn/repository/maven-public/</url></repository></repositories><!--maven中 spire.pdf镜像依赖-->
<dependencies><dependency><groupId> e-iceblue </groupId><artifactId>spire.pdf.free</artifactId><version>3.11.6</version></dependency>
</dependencies>

切割pdf

按每页切割

    /***每一页生成一个pdf文档*/public static void splitPdfOneByOne(){PdfDocument pdf = new PdfDocument();int count = pdf.getPages().getCount();System.out.println(count);pdf.loadFromFile("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\book.pdf");pdf.split("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\output\\surgery_{0}.pdf",0);pdf.close();}

按指定页切割

package com.wangcc.wangccocrdemo001.ocr;import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;
import com.spire.pdf.graphics.PdfMargins;
import com.wangcc.wangccocrdemo001.util.FileUtil;import java.awt.geom.Point2D;
import java.io.File;/*** 拆分文档* 拆成每页一个* 拆成每九页一个(免费版最多只能处理九页)* @author wangcc* @createTime 2021年08月31日 23:25:00*/
public class SubPDF {/*** 每九页生成一个pdf**/public static void splitPdfMoreByOne(){String fileName = "C:\\Users\\wangchenchen\\Desktop\\boot-structure\\book.pdf";String outPath = "C:\\Users\\wangchenchen\\Desktop\\boot-structure\\outFile\\outPDFByMore";PdfDocument pdf = new PdfDocument();pdf.loadFromFile(fileName);int totalCount = pdf.getPages().getCount();PdfPageBase pageBase;PdfDocument document = new PdfDocument();int count = 1;for(int i = 41; i< 822;i++){System.out.println(i+"/"+822);pageBase = document.getPages().add(pdf.getPages().get(i).getSize(),new PdfMargins(0));pdf.getPages().get(i).createTemplate().draw(pageBase, new Point2D.Float(0,0));if(count % 9 == 0){String path = "\\splitPdf-"+i+".pdf";document.saveToFile(outPath+path);document = new PdfDocument();}count++;}if(document.getPages().getCount() >0){String path = "\\splitPdf-999999.pdf";document.saveToFile(outPath+path);}}/*** @Description //* @return void**/public static void splitPdfByNumber(Integer begin, Integer end,String filePath,String pdfOutPath){if(begin.equals("") || end.equals("") || filePath.equals("") || pdfOutPath.equals("")){System.out.println("传入参数有空.......");return;}if(begin >= end){System.out.println("截止页数不能小于或等于开始页数.......");return;}if(end-begin > 9){System.out.println("操作页数最多为9页");return;}File file = new File(pdfOutPath);if (file.exists()){FileUtil fileUtil = new FileUtil();fileUtil.DeleteFolder(pdfOutPath);}PdfDocument pdf = new PdfDocument();pdf.loadFromFile(filePath);int totalCount = pdf.getPages().getCount();PdfPageBase pageBase;PdfDocument document = new PdfDocument();for(int i = begin; i< end;i++){System.out.println(i+"/"+end);pageBase = document.getPages().add(pdf.getPages().get(i).getSize(),new PdfMargins(0));pdf.getPages().get(i).createTemplate().draw(pageBase, new Point2D.Float(0,0));String path = "\\surgery_"+i+".pdf";document.saveToFile(pdfOutPath+path);document = new PdfDocument();}}
}

将pdf转成txt

package com.wangcc.wangccocrdemo001.ocr;import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;import java.io.*;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;/*** 读取所有拆分文件生成txt文件* @author wangcc* @createTime 2021年08月31日 23:51:00*/
public class ReadAllSplitFile {public static String fileName = "C:\\Users\\wangchenchen\\Desktop\\boot-structure\\outFile\\outPDFByMore\\";public static String outPath = "C:\\Users\\wangchenchen\\Desktop\\boot-structure\\outFile\\readPdfFile.txt";public static void main(String[] args) {List<File> fileList = readAllFile();List<String> pdfFileNameList = new ArrayList<>();for (File file:fileList) {pdfFileNameList.add(file.getName());}Collections.sort(pdfFileNameList, new Comparator<String>() {@Overridepublic int compare(String o1, String o2) {int n1 = extractNumber(o1);int n2 = extractNumber(o2);return n1 - n2;}});File file = new File(outPath);if(file.exists()){file.delete();}for (String s:pdfFileNameList) {try {readFile(s);} catch (IOException e) {e.printStackTrace();}}}public static List<File> readAllFile(){String filePath = "C:\\Users\\wangchenchen\\Desktop\\boot-structure\\outFile\\outPDFByMore";ArrayList<File> fileList = new ArrayList<>();File file = new File(filePath);File[] files = file.listFiles();if(Objects.isNull(files)){return null;}for (File f:files) {if(f.isFile()){fileList.add(f);}}return fileList;}/*** @Param  orderStr 排序：asc,des,不区分大小写**/public static List<File> sortFileByName(List<File> fileList, final String orderStr){if(!orderStr.equalsIgnoreCase("asc") && !orderStr.equalsIgnoreCase("desc")){return fileList;}File[] files = fileList.toArray(new File[0]);Arrays.sort(files, new Comparator<File>() {@Overridepublic int compare(File o1, File o2) {int n1 = extractNumber(o1.getName());int n2 = extractNumber(o2.getName());if(orderStr == null || orderStr.length() < 1 || orderStr.equalsIgnoreCase("asc")){return n1 - n2;}else {//降序return n2 - n1;}}});return new ArrayList<File>(Arrays.asList(files));}public static int extractNumber(String name){int i;try {String s = name.replaceAll("[^\\d]", "");i = Integer.parseInt(s);}catch (Exception e){i = 0;}return i;}public static void readFile(String path) throws IOException {PdfDocument pdf = new PdfDocument();pdf.loadFromFile(fileName+path);PdfPageBase page;StringBuilder sb = new StringBuilder();Pattern pattern = Pattern.compile("(^(\\s*)第)(.{1,9})[章节卷集部篇回](\\s{1,10})(.{1,20})(\\s{1,10})");Pattern pattern1 = Pattern.compile("(\\s{0,10})([0-9][0-9]?[0-9]?[0-9]?)");//遍历PDF页面，获取每个页面的文本并添加到StringBuilder对象for(int i = 0;i < pdf.getPages().getCount();i++) {//System.out.println("循环遍历pdf页数：当前" + i + "页/" + pdf.getPages().getCount() + "页");page = pdf.getPages().get(i);int count = 0;String extractText = null;BufferedReader br = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(page.extractText(true).getBytes())));while ((extractText = br.readLine())!= null){Matcher matcher = pattern.matcher(extractText);Matcher matcher1 = pattern1.matcher(extractText);/*末尾包含数字的*/if (count != 0 || matcher.find()){//System.out.println(extractText);if(!extractText.equals("") && !matcher1.find()){String s = extractText.replaceAll("\\s{5,9}", " ");sb.append(s+"\n");}}count++;}br.close();}FileWriter writer;try {//将StringBuilder对象中的文本写入到文本文件writer = new FileWriter(outPath,true);System.out.println(sb.toString());writer.write(sb.toString());writer.flush();writer.close();sb.delete(0,sb.length());} catch (IOException e) {e.printStackTrace();}pdf.close();}
}

识别pdf中的篇章节生成对应文本

去除水印

package com.wangcc.wangccocrdemo001.ocr;import com.spire.pdf.PdfDocument;import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;/*** 去除水印（未必都有用，主要是看水印的类型）* 水印有两种*      1.文字，放在对应的位置*        2.大图片，png 背景透明* 一些特殊的水印原则上是去不掉的* @author wangcc* @createTime 2021年08月31日 23:46:00*/
public class ClearWaterMark {public static void main(String[] args) throws IOException {PdfDocument pdf = new PdfDocument();pdf.loadFromFile("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\out\\splitPdf-18.pdf");BufferedImage bufferedImage = null;for (int i = 0; i<pdf.getPages().getCount();i++){bufferedImage = pdf.saveAsImage(i);bufferedImage.getSubimage(bufferedImage.getMinX(),15,bufferedImage.getWidth(),bufferedImage.getHeight()-15);File saveFile = new File("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\outImg\\" + i + ".png");if(!saveFile.exists()){saveFile.mkdirs();}ImageIO.write(bufferedImage,"PNG",saveFile);bufferedImage.flush();}}
}

获取书签

package com.wangcc.wangccocrdemo001.ocr;import com.spire.pdf.PdfDocument;
import com.spire.pdf.bookmarks.PdfBookmark;
import com.spire.pdf.bookmarks.PdfBookmarkCollection;import java.io.FileWriter;
import java.io.IOException;/*** 获取书签* @author wangcc* @createTime 2021年08月31日 23:47:00*/
public class getBookMake {public static void main(String[] args) {PdfDocument pdf = new PdfDocument();pdf.loadFromFile("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\out\\splitPdf-18.pdf");PdfBookmarkCollection bookmarkCollection = pdf.getBookmarks();StringBuilder stringBuilder = new StringBuilder();/*获取书签*/GetBookMakeTitle(bookmarkCollection,stringBuilder);FileWriter writer;try {writer = new FileWriter("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\读取的书签.txt");writer.write(stringBuilder.toString());writer.flush();} catch (IOException e) {e.printStackTrace();}pdf.dispose();}public static void GetBookMakeTitle(PdfBookmarkCollection bookmarkCollection,StringBuilder stringBuilder){if(bookmarkCollection.getCount() > 0){for (int i = 0; i < bookmarkCollection.getCount(); i++){PdfBookmark bookmark = bookmarkCollection.get(i);stringBuilder.append(bookmark.getTitle());GetBookMakeTitle(bookmark,stringBuilder);}}}
}

获取每页中图片

package com.wangcc.wangccocrdemo001.ocr;import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.Objects;/*** 提取每页pdf中的图片* @author wangcc* @createTime 2021年08月31日 23:41:00*/
public class ExtractImg {public static void main(String[] args) throws Exception{//加载测试文档InputStream inputStream = new BufferedInputStream(new FileInputStream(new File("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\demo.pdf")));PdfDocument pdf = new PdfDocument();//pdf.loadFromFile("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\demo.pdf");pdf.loadFromStream(inputStream);//定义一个int型变量int index = 0;//遍历PDF每一页for (int i= 0;i< pdf.getPages().getCount(); i ++){System.out.println(i+"/"+pdf.getPages().getCount());//获取PDF页面PdfPageBase page = pdf.getPages().get(i);//使用extractImages方法获取页面上图片for (BufferedImage image : page.extractImages()) {if(Objects.nonNull(image)){//指定输出图片名称File output = new File( String.format("C:\\Users\\wangchenchen\\Desktop\\boot-structure\\Img\\Image_%d.pdf", index++));//将图片保存为PNG格式文件ImageIO.write(image, "PNG", output);}}}}
}

项目地址

spire.pdf 下载