java POI doc docx 转 html

参考了很多大神的代码，在此感谢

有https://blog.csdn.net/qq_39197662/article/details/104977947

因为用的版本过高出现报错。现行版本4.12还是用3.14吧，会出现奇怪的报错

报错如下：

1.调了两个报错  包路径错误

POI word转html 异常 找不到org/apache/poi/POIXMLDocumentPart类

2.org.apache.poi.POIXMLDocumentPart.getPackageRelationship()Lorg/apache/poi/openxml4j/opc/PackageRelat

都是因为版本太高导致。

IDEA   jdk1.8以下是代码

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<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 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com</groupId>
    <artifactId>poi</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>org.apache.poi.xwpf.converter.core</artifactId>
            <version>1.0.6</version>
        </dependency>
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
            <version>1.0.6</version>
        </dependency>


        <!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/xdocreport -->
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>xdocreport</artifactId>
            <version>2.0.2</version>
        </dependency>


        <dependency>
            <groupId>org.apache.directory.studio</groupId>
            <artifactId>org.apache.commons.io</artifactId>
            <version>2.4</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.14</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-scratchpad -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.14</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml-schemas</artifactId>
            <version>3.14</version>
        </dependency>


        <!-- https://mvnrepository.com/artifact/org.apache.poi/ooxml-schemas -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>ooxml-schemas</artifactId>
            <version>1.3</version>
        </dependency>


    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

doc docx 转html代码，修改了大神的代码。亲测有效

package com;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.util.List;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.apache.commons.io.output.ByteArrayOutputStream;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;

import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.core.FileURIResolver;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;

public class Word2Html {
    private final static String tempPath = "";
    
    public static void main(String argv[]) {
        try {
            doc2Html("c:/bb.doc", "c:/bbb.html");
            //docx2Html("c:/dd.docx", "c:/ddd.html");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    
    /**
     * doc转换为html
     *
     * @param fileName
     * @param outPutFile
     * @throws TransformerException
     * @throws IOException
     * @throws ParserConfigurationException
     */
    public static void doc2Html(String fileName, String outPutFile) throws TransformerException, IOException, ParserConfigurationException {
        File file = new File(fileName);
        FileInputStream fileInputStream = new FileInputStream(file);
        // System.out.println(fileInputStream);
        HWPFDocument wordDocument = new HWPFDocument(fileInputStream);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        wordToHtmlConverter.setPicturesManager(new PicturesManager() {
            public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
                return "test/" + suggestedName;
            }
        });
        wordToHtmlConverter.processDocument(wordDocument);
        // 保存图片
        List<Picture> pics = wordDocument.getPicturesTable().getAllPictures();
        if (pics != null) {
            for (int i = 0; i < pics.size(); i++) {
                Picture pic = (Picture) pics.get(i);
                System.out.println();
                try {
                    pic.writeImageContent(new FileOutputStream(tempPath + pic.suggestFullFileName()));
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                }
            }
        }
        Document htmlDocument = wordToHtmlConverter.getDocument();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(out);
        TransformerFactory tf = TransformerFactory.newInstance();
        Transformer serializer = tf.newTransformer();
        serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
        serializer.setOutputProperty(OutputKeys.INDENT, "yes");
        serializer.setOutputProperty(OutputKeys.METHOD, "html");
        serializer.transform(domSource, streamResult);
        out.close();
        writeFile(new String(out.toByteArray()), outPutFile);
    }
    
    /**
     * 写文件
     *
     * @param content
     * @param path
     */
    public static void writeFile(String content, String path) {
        FileOutputStream fos = null;
        BufferedWriter bw = null;
        try {
            File file = new File(path);
            fos = new FileOutputStream(file);
            bw = new BufferedWriter(new OutputStreamWriter(fos, "utf-8"));
            bw.write(content);
        } catch (FileNotFoundException fnfe) {
            fnfe.printStackTrace();
        } catch (IOException ioe) {
            ioe.printStackTrace();
        } finally {
            try {
                if (bw != null)
                    bw.close();
                if (fos != null)
                    fos.close();
            } catch (IOException ie) {
            }
        }
    }
    
    /**
     * docx格式word转换为html
     *
     * @param fileName
     *            docx文件路径
     * @param outPutFile
     *            html输出文件路径
     * @throws TransformerException
     * @throws IOException
     * @throws ParserConfigurationException
     */
    public static void docx2Html(String fileName, String outPutFile) throws TransformerException, IOException, ParserConfigurationException {
        String fileOutName = outPutFile;
        XWPFDocument document = new XWPFDocument(new FileInputStream(fileName));
        XHTMLOptions options = XHTMLOptions.create().indent(4);
        // 导出图片
        File imageFolder = new File(tempPath);
        options.setExtractor(new FileImageExtractor(imageFolder));
        // URI resolver
        options.URIResolver(new FileURIResolver(imageFolder));
        File outFile = new File(fileOutName);
        outFile.getParentFile().mkdirs();
        OutputStream out = new FileOutputStream(outFile);
        XHTMLConverter.getInstance().convert(document, out, options);
    }
    
}