备忘：ApacheTika内容分析与提取

• Z时代
• 2024-01-10
• 分类：综合

DEMO
import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
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.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.html.HtmlParser;
import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
import org.apache.tika.parser.pdf.PDFParser;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
public class TikaDemo {
// public static String PATH = "E:\test.docx";
// public static String PATH = "g:\丁聪生前访谈：画漫画有个屁用！_夏冬红_新浪博客.htm";
public static String PATH = "g:\你眷恋的 都已离去 歌词 - Google 搜索.htm";
// public static String PATH = "E:\summerbell的博客文章(32).pdf";
public static String OUTPATH = PATH + ".OUT";
/**
* @param args
* @throws TikaException
* @throws SAXException
* @throws IOException
*/
public static void main(String[] args) throws IOException, SAXException,
TikaException {
// Parser parser = new OOXMLParser();
// Parser parser = new PDFParser();
Parser parser = new HtmlParser();
/**
* */
// InputStream iStream = new BufferedInputStream(new FileInputStream(
// new File(PATH)));
// OutputStream oStream = new BufferedOutputStream(new FileOutputStream(
// new File(OUTPATH)));
// ContentHandler iHandler = new BodyContentHandler(oStream);
// parser.parse(iStream, iHandler, new Metadata(), new ParseContext());
/**
* 处理指定编码的html.
*/
InputStream iStream = new BufferedInputStream(new FileInputStream(
new File(PATH)));
OutputStream oStream = new BufferedOutputStream(new FileOutputStream(
new File(OUTPATH)));
ContentHandler iHandler = new BodyContentHandler(oStream);
Metadata meta = new Metadata();
meta.add(Metadata.CONTENT_ENCODING, "utf-8");
parser.parse(iStream, iHandler, meta, new ParseContext());
}
}

以上是 备忘：ApacheTika内容分析与提取 的全部内容， 来源链接： utcz.com/z/510550.html