org.apache.tika 解析word文档，跳过\删除页眉页脚_apache tika 提取pdf文本过滤掉页脚

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();
 }
}
       
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23