利用poi解析word文件
package com.dreamers.read;
import java.io.File;
import java.io.FileInputStream;
import org.apache.poi.hwpf.extractor.WordExtractor;
public class WordReader {
public String readDoc(String doc) {
// 创建输入流读取DOC文件
//ArrayList<String> list = new ArrayList<String>();
try{ FileInputStream in = new FileInputStream(new File(doc));
WordExtractor extractor = null;
String text = null;
// 创建WordExtractor
extractor = new WordExtractor(in);
// 对DOC文件进行提取
text = extractor.getText();
return text;
}catch(Exception e){
System.out.println("未找到文件");
}
return null;
}
/*
public static void main(String[] args) {
// TODO Auto-generated method stub
WordReader re = new WordReader();
try {
ArrayList<String> list = new ArrayList<String>();
list = re.readDoc("d://《喂出来〉〉自学指导.doc");
System.out.println(list.get(0));
} catch (Exception e) {
e.printStackTrace();
}
}*/
}
