POI解析Doc
来源:互联网 发布:网络连接监控软件 编辑:程序博客网 时间:2024/05/20 15:37
- import java.io.File;
- import java.io.FileInputStream;
- import java.io.FileNotFoundException;
-
- import org.apache.poi.hwpf.HWPFDocument;
- import org.apache.poi.hwpf.usermodel.Paragraph;
- import org.apache.poi.hwpf.usermodel.Range;
- import org.apache.poi.hwpf.usermodel.Table;
- import org.apache.poi.hwpf.usermodel.TableCell;
- import org.apache.poi.hwpf.usermodel.TableIterator;
- import org.apache.poi.hwpf.usermodel.TableRow;
-
- import java.io.File;
- import java.io.FileInputStream;
- import java.io.InputStream;
-
- import org.apache.poi.POIXMLDocument;
- import org.apache.poi.POIXMLTextExtractor;
- import org.apache.poi.hwpf.extractor.WordExtractor;
- import org.apache.poi.openxml4j.opc.OPCPackage;
- import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
-
-
- import org.apache.poi.poifs.filesystem.POIFSFileSystem;
-
- public class ExportDocImpl
- {
- public void testWord(){
- try{
- FileInputStream in = new FileInputStream("D:\\sinye.doc");
- POIFSFileSystem pfs = new POIFSFileSystem(in);
- HWPFDocument hwpf = new HWPFDocument(pfs);
- Range range = hwpf.getRange();
- TableIterator it = new TableIterator(range);
-
- while (it.hasNext()) {
- Table tb = (Table) it.next();
-
- for (int i = 0; i < tb.numRows(); i++) {
- TableRow tr = tb.getRow(i);
-
- for (int j = 0; j < tr.numCells(); j++) {
- TableCell td = tr.getCell(j);
-
- for(int k=0;k<td.numParagraphs();k++){
- Paragraph para =td.getParagraph(k);
- String s = para.text();
- System.out.println(s);
- }
- }
- }
- }
- }catch(Exception e){
- e.printStackTrace();
- }
- }
-
-
- public void testWord1(){
- try {
-
- InputStream is = new FileInputStream(new File("D:\\sinye.doc"));
- WordExtractor ex = new WordExtractor(is);
- String text2003 = ex.getText();
- System.out.println(text2003);
-
- OPCPackage opcPackage = POIXMLDocument.openPackage("D:\\sinye.doc");
- POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
- String text2007 = extractor.getText();
- System.out.println(text2007);
-
- } catch (Exception e) {
- e.printStackTrace();
- }
- }
- }