java处理docx文件
2024-05-08 09:12:39
文章目录
- 配置MAVEN
- 文本读
- 图片读
- 图片写
- 表格读
- 表格写
- 按格式写
- docx转pdf
使用工具包 Apache POI。
主要类：
- XWPFDocument整个文档对象
- XWPFParagraph段落
- XWPFRun一个片段(字体样式相同的一段)
- XWPFPicture图片
- XWPFTable表格
配置MAVEN
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd"><modelVersion>4.0.0</modelVersion><groupId>WEEK6_docx</groupId><artifactId>WEEK6_docx</artifactId><version>0.0.1-SNAPSHOT</version><properties><project.build.sourceEncoding>UTF-8</project.build.sourceEncoding><maven.compiler.source>1.8</maven.compiler.source><maven.compiler.target>1.8</maven.compiler.target></properties><repositories><repository><id>central</id><url>http://maven.aliyun.com/nexus/content/groups/public/</url></repository></repositories><pluginRepositories><pluginRepository><id>central</id><url>http://maven.aliyun.com/nexus/content/groups/public/</url></pluginRepository></pluginRepositories><dependencies><dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>3.14</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>ooxml-schemas</artifactId><version>1.3</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml-schemas</artifactId><version>3.14</version></dependency><dependency><groupId>org.apache.xmlbeans</groupId><artifactId>xmlbeans</artifactId><version>2.6.0</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-examples</artifactId><version>3.14</version></dependency><dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>org.apache.poi.xwpf.converter.pdf</artifactId><version>1.0.6</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox --><dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>2.0.13</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.pdfbox/xmpbox --><dependency><groupId>org.apache.pdfbox</groupId><artifactId>xmpbox</artifactId><version>2.0.13</version></dependency><!-- https://mvnrepository.com/artifact/com.itextpdf/itextpdf --><dependency><groupId>com.itextpdf</groupId><artifactId>itextpdf</artifactId><version>5.5.13</version></dependency></dependencies></project>
文本读
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.List;import javax.xml.namespace.QName;import org.apache.poi.POIXMLDocumentPart;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.util.IOUtils;
import org.apache.poi.xwpf.usermodel.BodyElementType;
import org.apache.poi.xwpf.usermodel.Document;
import org.apache.poi.xwpf.usermodel.IBodyElement;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFPicture;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.xmlbeans.XmlCursor;
import org.apache.xmlbeans.XmlObject;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTObject;public class TextRead {public static void main(String[] args) throws Exception {readDocx();}public static void readDocx() throws Exception {InputStream is;is = new FileInputStream("test.docx");//将test里的内容作为文件输入流XWPFDocument xwpf = new XWPFDocument(is);List<IBodyElement> ibs= xwpf.getBodyElements();//将文件输入流的元素分段for(IBodyElement ib:ibs){BodyElementType bet = ib.getElementType();if(bet== BodyElementType.TABLE){//表格System.out.println("table" + ib.getPart());}else{ //段落XWPFParagraph para = (XWPFParagraph) ib;System.out.println("It is a new paragraph....The indention is " + para.getFirstLineIndent() + "," + para.getIndentationFirstLine() );//System.out.println(para.getCTP().xmlText());List<XWPFRun> res = para.getRuns();//System.out.println("run");if(res.size()<=0){System.out.println("empty line");}for(XWPFRun re: res){ if(null == re.text()||re.text().length()<=0){if(re.getEmbeddedPictures().size()>0){System.out.println("image***" + re.getEmbeddedPictures().size()); } else{System.out.println("objects:" + re.getCTR().getObjectList().size());if(re.getCTR().xmlText().indexOf("instrText") > 0) {System.out.println("there is an equation field");}else{//System.out.println(re.getCTR().xmlText());} }}else{ System.out.println("=== "+ re.getCharacterSpacing() + re.text());}} }} is.close();}
}图片读
/*** 本类 完成docx的图片读取工作*/
import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.usermodel.*;import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Iterator;import javax.imageio.ImageIO;public class ImageRead {public static void imageRead() throws IOException, InvalidFormatException {File docFile = new File("simple.docx");XWPFDocument doc = new XWPFDocument(OPCPackage.openOrCreate(docFile));//打开文件int i = 0;//抽取图片for (XWPFParagraph p : doc.getParagraphs()) {for (XWPFRun run : p.getRuns()) {System.out.println("a new run");for (XWPFPicture pic : run.getEmbeddedPictures()) {System.out.println(pic.getCTPicture().xmlText());//image EMU(English Metric Unit)System.out.println(pic.getCTPicture().getSpPr().getXfrm().getExt().getCx());System.out.println(pic.getCTPicture().getSpPr().getXfrm().getExt().getCy());//image 显示大小 以厘米为单位System.out.println(pic.getCTPicture().getSpPr().getXfrm().getExt().getCx()/360000.0);System.out.println(pic.getCTPicture().getSpPr().getXfrm().getExt().getCy()/360000.0);int type = pic.getPictureData().getPictureType();byte [] img = pic.getPictureData().getData();BufferedImage bufferedImage= ImageRead.byteArrayToImage(img);System.out.println(bufferedImage.getWidth());System.out.println(bufferedImage.getHeight());String extension = "";switch(type){case Document.PICTURE_TYPE_EMF: extension = ".emf";break;case Document.PICTURE_TYPE_WMF: extension = ".wmf";break;case Document.PICTURE_TYPE_PICT: extension = ".pic";break;case Document.PICTURE_TYPE_PNG: extension = ".png";break;case Document.PICTURE_TYPE_DIB: extension = ".dib";break;default: extension = ".jpg";}//outputFile = new File ( );//BufferedImage image = ImageIO.read(new File(img));//ImageIO.write(image , "png", outputfile);FileOutputStream fos = new FileOutputStream("test" + i + extension);fos.write(img);fos.close();i++;}}}}public static BufferedImage byteArrayToImage(byte[] bytes){ BufferedImage bufferedImage=null;try {InputStream inputStream = new ByteArrayInputStream(bytes);bufferedImage = ImageIO.read(inputStream);} catch (IOException ex) {System.out.println(ex.getMessage());}return bufferedImage;
}public static void main(String[] args) throws Exception {imageRead();}
}
图片写
/*** 本类完成docx的图片保存工作*/
import org.apache.poi.util.Units;
import org.apache.poi.xwpf.usermodel.*;import java.io.FileInputStream;
import java.io.FileOutputStream;public class ImageWrite {public static void main(String[] args) throws Exception {XWPFDocument doc = new XWPFDocument();XWPFParagraph p = doc.createParagraph();XWPFRun r = p.createRun();String[] imgFiles = new String[2];imgFiles[0] = "c:/temp/ecnu.jpg";imgFiles[1] = "c:/temp/shida.jpg"; for(String imgFile : imgFiles) {int format;if(imgFile.endsWith(".emf")) format = XWPFDocument.PICTURE_TYPE_EMF;else if(imgFile.endsWith(".wmf")) format = XWPFDocument.PICTURE_TYPE_WMF;else if(imgFile.endsWith(".pict")) format = XWPFDocument.PICTURE_TYPE_PICT;else if(imgFile.endsWith(".jpeg") || imgFile.endsWith(".jpg")) format = XWPFDocument.PICTURE_TYPE_JPEG;else if(imgFile.endsWith(".png")) format = XWPFDocument.PICTURE_TYPE_PNG;else if(imgFile.endsWith(".dib")) format = XWPFDocument.PICTURE_TYPE_DIB;else if(imgFile.endsWith(".gif")) format = XWPFDocument.PICTURE_TYPE_GIF;else if(imgFile.endsWith(".tiff")) format = XWPFDocument.PICTURE_TYPE_TIFF;else if(imgFile.endsWith(".eps")) format = XWPFDocument.PICTURE_TYPE_EPS;else if(imgFile.endsWith(".bmp")) format = XWPFDocument.PICTURE_TYPE_BMP;else if(imgFile.endsWith(".wpg")) format = XWPFDocument.PICTURE_TYPE_WPG;else {System.err.println("Unsupported picture: " + imgFile +". Expected emf|wmf|pict|jpeg|png|dib|gif|tiff|eps|bmp|wpg");continue;}r.setText(imgFile);r.addBreak();r.addPicture(new FileInputStream(imgFile), format, imgFile, Units.toEMU(200), Units.toEMU(200)); // 200x200 pixelsr.addBreak(BreakType.PAGE);}FileOutputStream out = new FileOutputStream("images.docx");doc.write(out);out.close();}}
表格读
/*** 本类完成docx的表格内容读取*/
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.Iterator;
import java.util.List;import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.xwpf.usermodel.BodyElementType;
import org.apache.poi.xwpf.usermodel.IBodyElement;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.poi.xwpf.usermodel.XWPFTableCell;
import org.apache.poi.xwpf.usermodel.XWPFTableRow;public class TableRead {public static void main(String[] args) throws Exception {testTable();}public static void testTable() throws Exception {InputStream is = new FileInputStream("simple2.docx");XWPFDocument xwpf = new XWPFDocument(is);List<XWPFParagraph> paras = xwpf.getParagraphs();//List<POIXMLDocumentPart> pdps = xwpf.getRelations();List<IBodyElement> ibs= xwpf.getBodyElements();for(IBodyElement ib:ibs){BodyElementType bet = ib.getElementType();if(bet== BodyElementType.TABLE){//表格System.out.println("table" + ib.getPart());XWPFTable table = (XWPFTable) ib;List<XWPFTableRow> rows=table.getRows(); //读取每一行数据for (int i = 0; i < rows.size(); i++) {XWPFTableRow row = rows.get(i);//读取每一列数据List<XWPFTableCell> cells = row.getTableCells(); for (int j = 0; j < cells.size(); j++) {XWPFTableCell cell=cells.get(j);System.out.println(cell.getText());List<XWPFParagraph> cps = cell.getParagraphs();System.out.println(cps.size());}}}else{ //段落XWPFParagraph para = (XWPFParagraph) ib;System.out.println("It is a new paragraph....The indention is " + para.getFirstLineIndent() + "," + para.getIndentationFirstLine() + "," + para.getIndentationHanging()+"," + para.getIndentationLeft() + "," + para.getIndentationRight() + "," + para.getIndentFromLeft() + ","+ para.getIndentFromRight()+"," + para.getAlignment().getValue());//System.out.println(para.getAlignment());//System.out.println(para.getRuns().size());List<XWPFRun> res = para.getRuns();System.out.println("run");if(res.size()<=0){System.out.println("empty line");}for(XWPFRun re: res){ if(null == re.text()||re.text().length()<=0){if(re.getEmbeddedPictures().size()>0){System.out.println("image***" + re.getEmbeddedPictures().size());}else{System.out.println("objects:" + re.getCTR().getObjectList().size());System.out.println(re.getCTR().xmlText());}}else{System.out.println("===" + re.text());}}}} is.close();}
}
表格写
/** 本类测试写入表格*/import java.io.FileOutputStream;
import java.io.OutputStream;
import java.math.BigInteger;
import java.util.List;import org.apache.poi.xwpf.usermodel.*;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.*;public class TableWrite {public static void main(String[] args) throws Exception {try {createSimpleTable();}catch(Exception e) {System.out.println("Error trying to create simple table.");throw(e);} }public static void createSimpleTable() throws Exception {XWPFDocument doc = new XWPFDocument();try {XWPFTable table = doc.createTable(3, 3);table.getRow(1).getCell(1).setText("表格示例");XWPFParagraph p1 = table.getRow(0).getCell(0).getParagraphs().get(0);XWPFRun r1 = p1.createRun();r1.setBold(true);r1.setText("The quick brown fox");r1.setItalic(true);r1.setFontFamily("Courier");r1.setUnderline(UnderlinePatterns.DOT_DOT_DASH);r1.setTextPosition(100);table.getRow(2).getCell(2).setText("only text");OutputStream out = new FileOutputStream("simpleTable.docx");try {doc.write(out);} finally {out.close();}} finally {doc.close();}}
}
按格式写
假如有模板如下：
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.URL;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.util.Units;
import org.apache.poi.xwpf.usermodel.BodyElementType;
import org.apache.poi.xwpf.usermodel.Document;
import org.apache.poi.xwpf.usermodel.IBodyElement;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.poi.xwpf.usermodel.XWPFTableCell;
import org.apache.poi.xwpf.usermodel.XWPFTableRow;public class TemplateTest {public static void main(String[] args) throws Exception {XWPFDocument doc = openDocx("template.docx");//导入模板文件Map<String, Object> params = new HashMap<String, Object>();//文字类 key-valueparams.put("${name}", "Tom");params.put("${sex}", "男");Map<String,String> picParams = new HashMap<String,String>();//图片类 key-urlpicParams.put("${pic}", "c:/temp/ecnu.jpg");List<IBodyElement> ibes = doc.getBodyElements();for (IBodyElement ib : ibes) {if (ib.getElementType() == BodyElementType.TABLE) {replaceTable(ib, params, picParams, doc);}}writeDocx(doc, new FileOutputStream("template2.docx"));//输出}public static XWPFDocument openDocx(String url) {InputStream in = null;try {in = new FileInputStream(url);XWPFDocument doc = new XWPFDocument(in);return doc;} catch (FileNotFoundException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();} finally {if (in != null) {try {in.close();} catch (IOException e) {// TODO Auto-generated catch blocke.printStackTrace();}}}return null;}public static void writeDocx(XWPFDocument outDoc, OutputStream out) {try {outDoc.write(out);out.flush();if (out != null) {try {out.close();} catch (IOException e) {e.printStackTrace();}}} catch (IOException e) {e.printStackTrace();}}private static Matcher matcher(String str) {Pattern pattern = Pattern.compile("\\$\\{(.+?)\\}", Pattern.CASE_INSENSITIVE);Matcher matcher = pattern.matcher(str);return matcher;}/*** 写入image* @param run* @param imgFile* @param doc* @throws InvalidFormatException* @throws FileNotFoundException* @throws IOException*/public static void replacePic(XWPFRun run, String imgFile, XWPFDocument doc) throws Exception {int format;if (imgFile.endsWith(".emf"))format = Document.PICTURE_TYPE_EMF;else if (imgFile.endsWith(".wmf"))format = Document.PICTURE_TYPE_WMF;else if (imgFile.endsWith(".pict"))format = Document.PICTURE_TYPE_PICT;else if (imgFile.endsWith(".jpeg") || imgFile.endsWith(".jpg"))format = Document.PICTURE_TYPE_JPEG;else if (imgFile.endsWith(".png"))format = Document.PICTURE_TYPE_PNG;else if (imgFile.endsWith(".dib"))format = Document.PICTURE_TYPE_DIB;else if (imgFile.endsWith(".gif"))format = Document.PICTURE_TYPE_GIF;else if (imgFile.endsWith(".tiff"))format = Document.PICTURE_TYPE_TIFF;else if (imgFile.endsWith(".eps"))format = Document.PICTURE_TYPE_EPS;else if (imgFile.endsWith(".bmp"))format = Document.PICTURE_TYPE_BMP;else if (imgFile.endsWith(".wpg"))format = Document.PICTURE_TYPE_WPG;else {System.err.println("Unsupported picture: " + imgFile + ". Expected emf|wmf|pict|jpeg|png|dib|gif|tiff|eps|bmp|wpg");return;}if(imgFile.startsWith("http")||imgFile.startsWith("https")){run.addPicture(new URL(imgFile).openConnection().getInputStream(), format, "rpic",Units.toEMU(100),Units.toEMU(100));}else{run.addPicture(new FileInputStream(imgFile), format, "rpic",Units.toEMU(100),Units.toEMU(100));}}/*** 替换表格内占位符* @param para 表格对象* @param params 文字替换map* @param picParams 图片替换map* @param indoc* @throws Exception */public static void replaceTable(IBodyElement para ,Map<String, Object> params, Map<String, String> picParams, XWPFDocument indoc)throws Exception {Matcher matcher;XWPFTable table;List<XWPFTableRow> rows;List<XWPFTableCell> cells;table = (XWPFTable) para;rows = table.getRows();for (XWPFTableRow row : rows) {cells = row.getTableCells();int cellsize = cells.size();int cellcount = 0;for(cellcount = 0; cellcount<cellsize;cellcount++){XWPFTableCell cell = cells.get(cellcount);String runtext = "";List<XWPFParagraph> ps = cell.getParagraphs();for (XWPFParagraph p : ps) {for(XWPFRun run : p.getRuns()){runtext = run.text();matcher = matcher(runtext);if (matcher.find()) {if (picParams != null) {for (String pickey : picParams.keySet()) {if (matcher.group().equals(pickey)) {run.setText("",0);replacePic(run, picParams.get(pickey), indoc);}}}if (params != null) {for (String pickey : params.keySet()) {if (matcher.group().equals(pickey)) {run.setText(params.get(pickey)+"",0);}}}}}}}}}
}
docx转pdf
import java.awt.Color;
import java.io.FileInputStream;
import java.io.FileOutputStream;import org.apache.poi.xwpf.usermodel.XWPFDocument;import com.lowagie.text.Font;
import com.lowagie.text.pdf.BaseFont;import org.apache.poi.xwpf.converter.pdf.PdfConverter;
import org.apache.poi.xwpf.converter.pdf.PdfOptions;
import fr.opensagres.xdocreport.itext.extension.font.IFontProvider;
import fr.opensagres.xdocreport.itext.extension.font.ITextFontRegistry;/*** XDocReportTest 将docx文档转为pdf* @author Tom**/
public class XDocReportTest {public static void main(String[] args) throws Exception {XWPFDocument doc = new XWPFDocument(new FileInputStream("template.docx"));// docxPdfOptions options = PdfOptions.create();options.fontProvider(new IFontProvider() {// 设置中文字体public Font getFont(String familyName, String encoding, float size, int style, Color color) {try {BaseFont bfChinese = BaseFont.createFont("C:\\Program Files (x86)\\Microsoft Office\\root\\VFS\\Fonts\\private\\STSONG.TTF",BaseFont.IDENTITY_H, BaseFont.EMBEDDED);Font fontChinese = new Font(bfChinese, size, style, color);if (familyName != null)fontChinese.setFamily(familyName);return fontChinese;} catch (Throwable e) {e.printStackTrace();return ITextFontRegistry.getRegistry().getFont(familyName, encoding, size, style, color);}}});PdfConverter.getInstance().convert(doc, new FileOutputStream("template.pdf"), options);// pdf}
}
java处理docx文件相关推荐
- Java 读写docx文件后直接转成PDF文件方法
java将docx文件转成pdf文件的实现方法,需要的jar包下载地址:https://download.csdn.net/download/keke921231/10529672 1.读写docx文 ...
- Java替换.docx文件中标记地方的内容
docx格式的文件本质上是一个XML文件,只要用占位符在指定的地方标记,然后替换掉标记出的内容,就能达到我们的目的 我们把maven项目的resources目录下的test.docx文件像上图一样用{ ...
- java 实现docx文件指定位置插入图片
首先导入需要用到的jar: <dependencies><dependency><groupId>org.apache.poi</groupId>< ...
- Java将.docx文件转换为.pdf文件
一. 首先在pom.xml文件中加入以下依赖: <dependency><groupId>fr.opensagres.xdocreport</groupId>< ...
- java 下载 docx文件_Java文件下载的几种方式.docx
Java文件下载的几种方式文章分类:/blogs/category/javaJava编程 Java文件下载的几种方式Java代码 public?HttpServletResponse?download ...
- java生成docx文件
话不多说,直接上代码 service层代码. public String exportDoc(String text, String wordName) {String dateUrl = this. ...
- java处理docx文件中的图片
public static void main(String[] args) throws Exception {InputStream fileInputStream = null;FileOutp ...
- Java Docx文件简介和解析
Docx简介 以Microsoft Office的doc/docx 为主要处理对象 Word2003和之前都是doc,文档格式不公开 Word2007和之后都是docx,文档格式公开,遵循XML路线 ...
- Java poi api插入文字水印到docx文件
使用apache poi api实现wps插入水印效果. Office Open XML介绍 Microsoft Office从2007版开始使用xml格式存储.zip解压一个docx的word文档后 ...
最新文章
- 物联网与互联网的6大区别
- java 企业付款_java实现微信企业付款到个人功能
- JZOJ 5377. 【NOIP2017提高A组模拟9.19】开拓
- GNU make 与 override指令
- linux如何批量清理文件大小,Linux下自动清理超过指定大小文件的方法
- html+css面试题 行内元素padding和margin
- zookeeper配置文件说明
- 输入两个整数n和m，从数列1,2,3，……n中随意取几个数，使其和等于m 转载
- 腾讯PHP工程师面试题两份
- golang 数组组合成最小的整数_Redis之整数集合底层实现
- 线性代数矩阵思维导图_斌叔2021考研数学公式：几种特殊形式的矩阵
- python写字典_用python编写字典并将其写入HDF5-fi
- 2008年希赛软考学院招生
- Kotlin中文教程
- 【Photoshop】滤镜详解
- 百度AI身份验证（公安验证）接口开发
- ESP32 学习笔记（二十一）电源管理
- 图片底下配的文字叫什么_图片下面加文字 图片周边留白加文字，照片加边框并在照片下面加文字...
- HTML5后台管理模板
- IoT僵尸网络Miori通过ThinkPHP远程代码执行漏洞进行传播