所需依赖
<dependency>
<groupId>e-iceblue</groupId>
<artifactId>spire.doc.free</artifactId>
<version>3.9.0</version>
</dependency>
<!--操作pdf -->
<dependency>
<groupId>e-iceblue</groupId>
<artifactId>spire.pdf.free</artifactId>
<version>3.9.0</version>
</dependency>
<dependency>
<groupId>e-iceblue</groupId>
<artifactId>spire.pdf</artifactId>
<version>3.9.6</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>ooxml-schemas</artifactId>
<version>1.3</version>
</dependency>
<!--仓库地址-->
<repository>
<id>com.e-iceblue</id>
<url>https://repo.e-iceblue.cn/repository/maven-public/</url>
</repository>
PDF转word
去除首段水印
package com.example.daimademo.utils;
import com.spire.pdf.FileFormat;
import com.spire.pdf.PdfDocument;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.*;
public class PdfUtils {
public static void main(String[] args) throws Exception{
// pdf转换word
// pdf2Word("D:\\upload\\yy\\水土保持方案.pdf",
// "D:\\upload\\yy\\ssm3.docx");
//word截去第一段水印
RemoveTag("D:\\\\upload\\\\yy\\\\ssm3.docx","D:\\\\upload\\\\yy\\\\ssm31.docx");
}
/**
* pdf to word
* @param pdfPath
* @param wordPath
*/
public static void pdf2Word(String pdfPath,String wordPath){
PdfDocument pdf = new PdfDocument();
//Load a PDF file
pdf.loadFromFile(pdfPath);
//Save to .docx file
pdf.saveToFile(wordPath, FileFormat.DOCX);
pdf.close();
}
public static void RemoveTag(String wordPath,String wordPath2) throws Exception {
String type = wordPath;
InputStream inputStream=null;
if (type.endsWith(".doc")) {
inputStream = new FileInputStream(wordPath);
HWPFDocument hwpfDocument = new HWPFDocument(inputStream);
//以上Spire.Doc 生成的文件会自带警告信息，这里来删除Spire.Doc 的警告
//hwpfDocument.delete() 该方法去掉文档指定长度的内容
hwpfDocument.delete(0, 70);
//输出word内容文件流，新输出路径位置
OutputStream os = new FileOutputStream(wordPath2);
try {
hwpfDocument.write(os);
} catch (Exception e) {
e.printStackTrace();
} finally {
os.close();
inputStream.close();
}
} else if (type.endsWith(".docx")) {
inputStream = new FileInputStream(wordPath);
XWPFDocument old_document = new XWPFDocument(inputStream);
//以上Spire.Doc 生成的文件会自带警告信息，这里来删除Spire.Doc 的警告
old_document.removeBodyElement(0);
//输出word内容文件流，新输出路径位置
OutputStream os = new FileOutputStream(wordPath2);
try {
old_document.write(os);
} catch (Exception e) {
e.printStackTrace();
} finally {
os.close();
inputStream.close();
}
}
}
/**
* ConvertPdfToExcel
* @param pdfPath
* @param excelPath
*/
public void ConvertPdfToExcel (String pdfPath,String excelPath){
//Create a PdfDocument instance
PdfDocument pdf = new PdfDocument();
//Load a PDF file
pdf.loadFromFile(pdfPath);
//Save to .xlsx file
pdf.saveToFile(excelPath, FileFormat.XLSX);
pdf.close();
}
/**
* ConvertPdfToImage
* @param pdfPath
* @param pngPath
* @throws Exception
*/
public void ConvertPdfToImage (String pdfPath,String pngPath) throws Exception{
//Create a PdfDocument instance
PdfDocument pdf = new PdfDocument();
//Load a PDF file
pdf.loadFromFile(pdfPath);
//Declare a BufferedImage variable
BufferedImage image;
//Loop through the pages
for (int i = 0; i < pdf.getPages().getCount(); i++) {
//Save the specific page as image data
image = pdf.saveAsImage(i);
//Write image data to png file
File file = new File(String.format(pngPath, i));
ImageIO.write(image, "PNG", file);
}
pdf.close();
}
}
简单操作word
word转pdf
package com.iwhr.siyu.common.util.word;
import com.spire.doc.FileFormat;
import com.spire.doc.Document;
import com.spire.doc.documents.TextSelection;
import com.spire.doc.fields.DocPicture;
import com.spire.doc.fields.TextRange;
import lombok.SneakyThrows;
import org.apache.poi.xwpf.usermodel.*;
import org.junit.Test;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.*;
import java.util.regex.Pattern;
import static java.util.regex.Pattern.*;
/**
* word相关工具
* @author ssm
*/
public class WordUtils {
/**
* apache poi实现
*将word中某些标签替换成指定的值，并生成一个新的word文档。
* @param templateFilePath word模板文件路径
* @param outFilePath 填充后输出文件路径
* @param map key:word中的占位标签，value对应标签要替换的值。
* @throws IOException
*/
public static void insertAndOutFile(String templateFilePath, String outFilePath, Map<String,String> map) throws IOException {
//准备工作，生成docx对象
String templatePath=templateFilePath;
InputStream is=new FileInputStream(templatePath);
XWPFDocument docx=new XWPFDocument(is);
//获取该格子里所有的段
List<XWPFParagraph> paragraphs=docx.getParagraphs();
for(XWPFParagraph p:paragraphs) {
//遍历该格子里的段
List<XWPFRun> runs=p.getRuns();
for(XWPFRun run:runs) {
String text=run.getText(0);
Set<String> keySet = map.keySet();
for(String key:keySet){
if (text.indexOf(key) != -1) {
text = text.replace(key, map.get(key));
run.setText(text, 0);
}
}
}
}
OutputStream os=new FileOutputStream(outFilePath);
docx.write(os);
is.close();
os.close();
}
/**
* spire.doc.free 实现word转pdf
* @param wordPath
* @param pdfPath
*/
@SneakyThrows
public static void word2Pdf(String wordPath ,String pdfPath){
Document doc = new Document(wordPath);
doc.saveToFile(pdfPath, FileFormat.PDF);
}
/**
* 替换Word文件中 ${} 标识的特殊字符
* @param templateFilePath
* @param outFilePath
* @param map
*/
@SneakyThrows
public static void replaceSpecialWord(String templateFilePath,String outFilePath, Map<String, String> map) {
Document doc = new Document();
FileFormat type;
if("doc".equals(templateFilePath.substring(templateFilePath.length()-3))){
type = FileFormat.Doc;
}else{
type=FileFormat.Docx;
}
doc.loadFromFile(templateFilePath, type);
// 正则表达式，匹配所有的占位符 ${}
Pattern pattern = compile("\\$\\{.*?}");
// 根据正则表达式获取所有文本
TextSelection[] allPattern = doc.findAllPattern(pattern);
// 逐个替换占位符
for (TextSelection textSelection : allPattern) {
String tmp = map.get(textSelection.getSelectedText());
if(tmp!=null){
System.out.print(textSelection.getSelectedText());
int res = doc.replace(textSelection.getSelectedText(), tmp, true, true);
System.out.println(": " + res);
}
}
doc.saveToFile(outFilePath,type);
}
/**
* 读取本地文件
* 替换word中的图片类型的占位符
* @param templateFilePath
* @param outFilePath
* @param picMap
*/
public static void insertImages(String templateFilePath,String outFilePath, Map<String,String> picMap){
FileFormat type;
if("doc".equals(templateFilePath.substring(templateFilePath.length()-3))){
type = FileFormat.Doc;
}else{
type=FileFormat.Docx;
}
Document doc = new Document();
doc.loadFromFile(templateFilePath, type);
try {
Set<String> keySet = picMap.keySet();
for(String key:keySet){
File file = new File(picMap.get(key));
InputStream in = new FileInputStream(file);
replaceTextToImage(doc, key, in);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
}
doc.saveToFile(outFilePath,type);
}
/**
* 读取网络图片
*/
@SneakyThrows
public static void insertImages2(String templateFilePath, String outFilePath, Map<String,String> picMap){
FileFormat type;
if("doc".equals(templateFilePath.substring(templateFilePath.length()-3))){
type = FileFormat.Doc;
}else{
type=FileFormat.Docx;
}
Document doc = new Document();
doc.loadFromFile(templateFilePath, type);
URL url = null;
HttpURLConnection httpUrl = null;
BufferedInputStream bis=null;
try {
Set<String> keySet = picMap.keySet();
for(String key:keySet){
url = new URL(picMap.get(key));
httpUrl = (HttpURLConnection) url.openConnection();
httpUrl.connect();
bis = new BufferedInputStream(httpUrl.getInputStream());
replaceTextToImage(doc, key, bis);
}
} catch (Exception e) {
e.printStackTrace();
}finally {
bis.close();
}
doc.saveToFile(outFilePath,type);
}
/**
* 按照横纵比缩放图片
* @param pic: Spire 图片对象
* @param rate: 缩放比例 0.1<= rate <=10，
* @author He Peng
* @date 2021/10/23 9:28
*/
public static void zoomImage(DocPicture pic, float rate) {
if (rate < 0.1 || rate > 10) {
throw new IllegalArgumentException("缩放比例参数的数值范围为：0.1<= rate <=10，不能超过此范围");
}
float originalWidth = pic.getWidth();
float originalHeight = pic.getHeight();
pic.setWidth(originalWidth * rate);
pic.setHeight(originalHeight * rate);
}
/**
* 替换Word文档中的同一占位符，为多张不同的图片，每一个占位符对应一张图片，
* 如果占位符比图片数量多则该占位符会被写为空字符串
* @param doc: Spire Document
* @param matchString: 占位符
* @param picInput: 图片输入流
* @date 2021/10/22 20:09
*/
public static void replaceTextToImage(Document doc, String matchString, InputStream picInput) {
TextSelection[] selections = doc.findAllString(matchString, true, true);
for (TextSelection selection : selections) {
if (picInput != null) {
DocPicture pic = new DocPicture(doc);
pic.loadImage(picInput);
zoomImage(pic,0.8f);
TextRange range = selection.getAsOneRange();
int index = range.getOwnerParagraph().getChildObjects().indexOf(range);
range.getOwnerParagraph().getChildObjects().insert(index, pic);
range.getOwnerParagraph().getChildObjects().remove(range);
} else {
// 如果已近没有了图片则将所有占位符替换为空
doc.replace(selection.getSelectedText(), "", true, true);
break;
}
}
}
}