word转HTML && 读取word文件内容

word转HTML

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.springframework.web.multipart.MultipartFile;
import org.w3c.dom.Document;

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 java.io.*;

public class Word2HtmlUtil {

    /**
     * logger
     */
    private static final Logger logger = LogManager.getLogger(Word2HtmlUtil.class);

    public static String Word2007ToHtml(MultipartFile file) throws IOException {

//        String filepath = "C:/Users/YScredit/Desktop/";
//        String fileName = "test.docx";
//        String htmlName = "test.html";
//        final String localFile = filepath + fileName;
//        File f = new File(localFile);

        //if (!f.exists()) {
        if (file.isEmpty() || file.getSize() <= 0) {
            logger.error("Sorry File does not Exists!");
            return null;
        } else {
            //if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {
            if (file.getOriginalFilename().endsWith(".docx") || file.getOriginalFilename().endsWith(".DOCX")) {

                // 1) 加载word文档生成 XWPFDocument对象
                //InputStream in = new FileInputStream(f);
                InputStream in = file.getInputStream();
                XWPFDocument document = new XWPFDocument(in);

                // 也可以使用字符数组流获取解析的内容
                ByteArrayOutputStream baos = new ByteArrayOutputStream();
                XHTMLConverter.getInstance().convert(document, baos, null);
                String content = baos.toString();
                baos.close();
                return content;
            } else {
                logger.error("Enter only MS Office 2007+ files");
                return null;
            }
        }
    }

    public static String Word2003ToHtml(MultipartFile file)
            throws IOException, ParserConfigurationException, TransformerException {

        if (file.isEmpty() || file.getSize() <= 0) {
            logger.error("Sorry File does not Exists!");
            return null;
        } else {
            if (file.getOriginalFilename().endsWith(".doc") || file.getOriginalFilename().endsWith(".DOC")) {
                InputStream input = file.getInputStream();
                HWPFDocument wordDocument = new HWPFDocument(input);
                WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                        DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());

                // 解析word文档
                wordToHtmlConverter.processDocument(wordDocument);
                Document htmlDocument = wordToHtmlConverter.getDocument();

                // 也可以使用字符数组流获取解析的内容
                ByteArrayOutputStream baos = new ByteArrayOutputStream();
                DOMSource domSource = new DOMSource(htmlDocument);
                StreamResult streamResult = new StreamResult(baos);

                TransformerFactory factory = TransformerFactory.newInstance();
                Transformer serializer = factory.newTransformer();
                serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
                serializer.setOutputProperty(OutputKeys.INDENT, "yes");
                serializer.setOutputProperty(OutputKeys.METHOD, "html");
                serializer.transform(domSource, streamResult);

                // 也可以使用字符数组流获取解析的内容
                String content = new String(baos.toByteArray());
                baos.close();
                return content;
            } else {
                logger.error("Enter only MS Office 2003 files");
                return null;
            }
        }

    }
}

用到的依赖，在项目框架里用了 poi-ooxml 3.15的版本，导致版本冲突，不好用，遂改为3.13可行。

		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>3.13</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-scratchpad</artifactId>
			<version>3.15</version>
		</dependency>

读取word文件内容

import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

import java.io.*;

public class DocUtil {

    /**
     * 读取doc文件内容
     *
     * @param
     * @return 想要读取的文件对象 返回文件内容
     * @throws IOException
     */
    public static String doc2String(File file) throws IOException {
        String str = "";
        try {
            FileInputStream fis = new FileInputStream(file);
            WordExtractor re = new WordExtractor(fis);
            String doc1 = re.getText();
            System.out.println(doc1);
            str += doc1;
            fis.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return str;
    }


    /**
     * 读取docx文件内容
     *
     * @param
     * @return 想要读取的文件对象 返回文件内容
     * @throws IOException
     */
    public static String docx2String(File file)throws IOException {
        String str = "";
        try {
            FileInputStream fis = new FileInputStream(file);
            XWPFDocument xdoc = new XWPFDocument(fis);
            XWPFWordExtractor extractor = new XWPFWordExtractor(xdoc);
            String doc1 = extractor.getText();
            System.out.println(doc1);
            str += doc1;
            fis.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return str;
    }

}

用到的依赖

		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
			<version>1.0.6</version>
		</dependency>

		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>ooxml-schemas</artifactId>
			<version>1.4</version>
		</dependency>