Word 转成HTML

最新推荐文章于 2024-09-25 10:59:43 发布

weixin_33840661

最新推荐文章于 2024-09-25 10:59:43 发布

阅读量58

点赞数

文章标签： xhtml java python

原文链接：https://my.oschina.net/yangyan/blog/859438

版权

2019独角兽企业重金招聘Python工程师标准>>>

来自CSDN的代码：

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;

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.apache.poi.xwpf.usermodel.XWPFPictureData;
import org.junit.Assert;
import org.junit.Test;

public class word07toHtml {

	@Test
	public void canExtractImage() throws IOException {
		File f = new File("d:/test/test.docx");
		if (!f.exists()) {
			System.out.println("Sorry File does not Exists!");
		} else {
			if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {
				
				// 1) Load DOCX into XWPFDocument
				InputStream in = new FileInputStream(f);
				XWPFDocument document = new XWPFDocument(in);

				// 2) Prepare XHTML options (here we set the IURIResolver to
				// load images from a "word/media" folder)
				File imageFolderFile = new File("d:/test/media");
				XHTMLOptions options = XHTMLOptions.create().URIResolver(
						new FileURIResolver(imageFolderFile));
				options.setExtractor(new FileImageExtractor(imageFolderFile));

				// 3) Convert XWPFDocument to XHTML
				OutputStream out = new FileOutputStream(new File(
						"d:/test/test.htm"));
				XHTMLConverter.getInstance().convert(document, out, options);
			} else {
				System.out.println("Enter only MS Office 2007+ files");
			}
		}
	}
}

tips：

本文由wp2Blog导入，原文链接：http://devonios.com/word-convert-to-html.html

转载于:https://my.oschina.net/yangyan/blog/859438