org.apache.tika 解析word文档，跳过\删除页眉页脚

最新推荐文章于 2025-09-10 11:30:48 发布

原创最新推荐文章于 2025-09-10 11:30:48 发布 · 1k 阅读

10 ·

CC 4.0 BY-SA版权

文章标签：

#apache #word

随笔专栏收录该内容

9 篇文章

订阅专栏

示例代码

public void parseExample() {

ParseContext parseContext = new ParseContext();
AutoDetectParser parser = new AutoDetectParser();
BodyContentHandler handler = new BodyContentHandler();
Metadata metadata = new Metadata();

//跳过页眉页脚
OfficeParserConfig officeParserConfig = new OfficeParserConfig();
officeParserConfig.setIncludeHeadersAndFooters(false);
boolean hf= officeParserConfig.getIncludeHeadersAndFooters();
parseContext.set(OfficeParserConfig.class, officeParserConfig);

System.out.println("headfoot"+hf);
try(FileInputStream fin=new FileInputStream("D:\\docs\\Out22.docx")) {
	parser.parse(fin, handler, metadata, parseContext);
	String text = handler.toString();
	System.out.println("output :"+text);
} catch (IOException | SAXException | TikaException ex) {
	ex.printStackTrace();
 }
}