如果有相关问题,可以一起研究下
引入依赖
e-iceblue
spire.doc.free
5.2.0
com.e-iceblue
e-iceblue
https://repo.e-iceblue.cn/repository/maven-public/
代码片段
import com.spire.doc.Document;
import com.spire.doc.FileFormat;
import com.spire.doc.documents.DocumentObjectType;
import com.spire.doc.fields.DocPicture;
import com.spire.doc.interfaces.ICompositeObject;
import com.spire.doc.interfaces.IDocumentObject;
import javax.imageio.ImageIO;
import java.awt.image.RenderedImage;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;
import java.util.Queue;
/**
* @Author: Climbing-pit
* @Date: 2022/4/15 21:25
* @Description: Doc工具类
*/
public class DocUtil {
/**
* 本地Doc文件提取Txt
* @param filePath 文件路径
* @param savePath 提取文件保存路径
* @param tempFileName 文件名
* @throws IOException
*/
public static void extractedText(String filePath, String savePath, long tempFileName) throws IOException {
//加载Word文档
Document doc = new Document();
doc.loadFromFile(filePath);
//获取文档中的文本保存为String
String text=doc.getText();
//将String写入Txt文件
writeStringToTxt(text,savePath+tempFileName+SystemConstant.DOC_TXT_SUFFIX);
}
/**
* 本地Doc文件转Html
* @param filePath 文件路径
* @param savePath 提取文件保存路径
* @param tempFileName 文件名
* @throws IOException
*/
public static void toHtml(String filePath, String savePath, long tempFileName) throws IOException {
//加载Word文档
Document doc = new Document();
doc.loadFromFile(filePath);
//保存为HTML格式
doc.saveToFile(savePath+tempFileName+ SystemConstant.DOC_HTML_SUFFIX,FileFormat.Html);
extractImages(filePath, savePath);
doc.dispose();
}
public static void writeStringToTxt(String content, String txtFileName) throws IOException {
FileWriter fWriter= new FileWriter(txtFileName,true);
try {
fWriter.write(content);
}catch(IOException ex){
ex.printStackTrace();
}finally{
try{
fWriter.flush();
fWriter.close();
} catch (IOException ex) {
ex.printStackTrace();
}
}
}
/**
* 本地Doc文件提取图片
* @param filePath 文件路径
* @param savePath 提取文件保存路径
* @throws IOException
*/
public static void extractImages(String filePath, String savePath) throws IOException {
//加载Word文档
Document document = new Document();
document.loadFromFile(filePath);
//创建Queue对象
Queue nodes = new LinkedList();
nodes.add(document);
//创建List对象
List images = new ArrayList();
//遍历文档中的子对象
while (nodes.size() > 0) {
ICompositeObject node = (ICompositeObject) nodes.poll();
for (int i = 0; i < node.getChildObjects().getCount(); i++) {
IDocumentObject child = node.getChildObjects().get(i);
if (child instanceof ICompositeObject) {
nodes.add(child);
//获取图片并添加到List
if (child.getDocumentObjectType() == DocumentObjectType.Picture) {
DocPicture picture = (DocPicture) child;
images.add(picture.getImage());
}
}
}
}
Integer size = images.size();
//将图片保存为PNG格式文件
for (int i = 0; i < size; i++) {
File file = new File(String.format(savePath+"图片-%d.png", i));
ImageIO.write((RenderedImage) images.get(i), "PNG", file);
}
}
public static void main(String[] args) {
long l = System.currentTimeMillis();
String filePath = "D:\\files\\practice\\明日提升练习.docx";
//创建保存路径
String parentFilePath = filePath.substring(0, filePath.lastIndexOf(File.separatorChar)+1);
String savePath = parentFilePath+SystemConstant.TEST_PAPER_SAVE_PATH+l+File.separator;
File parent = new File(savePath);
parent.mkdirs();
try {
DocUtil.extractedText(filePath, savePath, l);
DocUtil.toHtml(filePath, savePath, l);
} catch (IOException e) {
e.printStackTrace();
}
}
}
@Component
public class SystemConstant {
public static final String DOC_HTML_SUFFIX= ".html";
public static final String DOC_TXT_SUFFIX= "_ExtractedText.txt";
public static final String TEST_PAPER_SAVE_PATH= "testPaper"+ File.separator;
public static final String DOC_SAVE_PATH= "practice"+ File.separator;
}
其他接口请看官网:帮助文档 | 全面丰富的在线文档,助您快速了解如何使用产品
相关问题:
1、创建word只支持500行问题
用free spire.Doc for Java这个是免费版,有一定限制, 导出的时候可生成的段落不能超过固定的数量,超过数量之后会报错,错误信息如下:
com.spire.doc.packages.sprcdz: Spire.Doc free version is limited to 500 paragraphs. This limitation is enforced during reading or writing files.
Upgrade to Commercial Edition of Spire.Doc
at com.spire.doc.collections.DocumentObjectCollection.insert(Unknown Source)
at com.spire.doc.packages.sprfww.spr︻∯—(Unknown Source)
at com.spire.doc.packages.sprwcx.spr┰℠(Unknown Source)
at com.spire.doc.fields.TextRange.spr┐——(Unknown Source)
at com.spire.doc.DocumentObject.spr⌾——(Unknown Source)
at com.spire.doc.DocumentObject.spr┰——(Unknown Source)
at com.spire.doc.documents.Paragraph.spr┐——(Unknown Source)
at com.spire.doc.DocumentObject.spr⌾——(Unknown Source)
at com.spire.doc.DocumentObject.spr┰——(Unknown Source)
at com.spire.doc.Body.spr┐——(Unknown Source)
at com.spire.doc.packages.sprwcx.spr┄∯—(Unknown Source)
at com.spire.doc.packages.sprajx.spr▄۩—(Unknown Source)
at com.spire.doc.packages.sprajx.spr╽∮—(Unknown Source)
at com.spire.doc.packages.sprwcx.spr∫┃(Unknown Source)
at com.spire.doc.packages.spreyw.spr▄۩—(Unknown Source)
at com.spire.doc.packages.spreyw.spr◐…(Unknown Source)
at com.spire.doc.packages.spreyw.spr╻∮—(Unknown Source)
at com.spire.doc.packages.spreyw.spr⌨∯—(Unknown Source)
at com.spire.doc.Document.spr╼┈—(Unknown Source)
at com.spire.doc.Document.saveToFile(Unknown Source)
at com.cloud.common.util.DocUtil.writeStringToDoc(DocUtil.java:106)
at com.cloud.spider.service.impl.BiqvgeServiceImplTest.spidedrChapter(BiqvgeServiceImplTest.java:138)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.junit.platform.commons.util.ReflectionUtils.invokeMethod(ReflectionUtils.java:675)
at org.junit.jupiter.engine.execution.MethodInvocation.proceed(MethodInvocation.java:60)
at org.junit.jupiter.engine.execution.InvocationInterceptorChain$ValidatingInvocation.proceed(InvocationInterceptorChain.java:125)
at org.junit.jupiter.engine.extension.TimeoutExtension.intercept(TimeoutExtension.java:132)
at org.junit.jupiter.engine.extension.TimeoutExtension.interceptTestableMethod(TimeoutExtension.java:124)
at org.junit.jupiter.engine.extension.TimeoutExtension.interceptTestMethod(TimeoutExtension.java:74)
at org.junit.jupiter.engine.execution.ExecutableInvoker$ReflectiveInterceptorCall.lambda$ofVoidMethod$0(ExecutableInvoker.java:115)
at org.junit.jupiter.engine.execution.ExecutableInvoker.lambda$invoke$0(ExecutableInvoker.java:105)
at org.junit.jupiter.engine.execution.InvocationInterceptorChain$InterceptedInvocation.proceed(InvocationInterceptorChain.java:104)
at org.junit.jupiter.engine.execution.InvocationInterceptorChain.proceed(InvocationInterceptorChain.java:62)
at org.junit.jupiter.engine.execution.InvocationInterceptorChain.chainAndInvoke(InvocationInterceptorChain.java:43)
at org.junit.jupiter.engine.execution.InvocationInterceptorChain.invoke(InvocationInterceptorChain.java:35)
at org.junit.jupiter.engine.execution.ExecutableInvoker.invoke(ExecutableInvoker.java:104)
at org.junit.jupiter.engine.execution.ExecutableInvoker.invoke(ExecutableInvoker.java:98)
at org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.lambda$invokeTestMethod$6(TestMethodTestDescriptor.java:202)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.invokeTestMethod(TestMethodTestDescriptor.java:198)
at org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.execute(TestMethodTestDescriptor.java:135)
at org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.execute(TestMethodTestDescriptor.java:69)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:135)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:125)
at org.junit.platform.engine.support.hierarchical.Node.around(Node.java:135)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:123)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:122)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:80)
at java.util.ArrayList.forEach(ArrayList.java:1249)
at org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.invokeAll(SameThreadHierarchicalTestExecutorService.java:38)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:139)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:125)
at org.junit.platform.engine.support.hierarchical.Node.around(Node.java:135)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:123)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:122)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:80)
at java.util.ArrayList.forEach(ArrayList.java:1249)
at org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.invokeAll(SameThreadHierarchicalTestExecutorService.java:38)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:139)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:125)
at org.junit.platform.engine.support.hierarchical.Node.around(Node.java:135)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:123)
at org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:122)
at org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:80)
at org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.submit(SameThreadHierarchicalTestExecutorService.java:32)
at org.junit.platform.engine.support.hierarchical.HierarchicalTestExecutor.execute(HierarchicalTestExecutor.java:57)
at org.junit.platform.engine.support.hierarchical.HierarchicalTestEngine.execute(HierarchicalTestEngine.java:51)
at org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:229)
at org.junit.platform.launcher.core.DefaultLauncher.lambda$execute$6(DefaultLauncher.java:197)
at org.junit.platform.launcher.core.DefaultLauncher.withInterceptedStreams(DefaultLauncher.java:211)
at org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:191)
at org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:128)
at com.intellij.junit5.JUnit5IdeaTestRunner.startRunnerWithArgs(JUnit5IdeaTestRunner.java:69)
at com.intellij.rt.junit.IdeaTestRunner$Repeater.startRunnerWithArgs(IdeaTestRunner.java:33)
at com.intellij.rt.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:230)
at com.intellij.rt.junit.JUnitStarter.main(JUnitStarter.java:58)
目前我自己的解决方式是,分为多次写入,测试用例通过!