java中word导入数据库

前言 >

word导入到数据库主要是对word的解析，word分为2003版、2007版以上，还有xml格式的，2003和2007以上的主要是对单元格内容进行判断，进行获取；而xml格式的主要是对标签进行解析，根据标签去内容，进行判断；还有htm格式的，就是对html内容读取，然后对标签进行获取内容；下面四种的解析方法都有：

1.直接附代码了

//导入word
    @RequestMapping("/wordImport")
    public String importTprkxx(@RequestParam("file")MultipartFile file, Model model) throws Exception {
        try {
            WordBean wordBean = new WordBean();
            InputStream inputStream = file.getInputStream();

            FileTypeUtils flt = new FileTypeUtils();
            String filetype = flt.getFileType(inputStream);//根据流获取文件的类型(解析文件头判断文件格式)
            InputStream is = file.getInputStream();

            if (is.available() != 0) { //判断输入流是否为空(文件是否为空)
                //根据不同的文件类型，进行不同的解析
                if ("doc".equals(filetype)) {
                    wordBean = WordLead.readWord2003(is);
                } else if ("docx".equals(filetype)) {
                    wordBean = WordLead.readWord2007(is);
                } else if ("xml".equals(filetype)) {
                    wordBean = WordLead.readXml(is);
                } else if ("htm".equals(filetype)) {
                    wordBean = WordLead.readHtm(is);
                }
            }
        }catch(IndexOutOfBoundsException e) {
            e.printStackTrace();
        }
        model.addAttribute("msg","导入成功！");
        return "views/success";
    }

2.两个工具类WordLead(解析word)和FileTypeUtils(获取文件类型)

import com.jdl.entity.WordBean;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.*;
import org.apache.poi.xwpf.usermodel.*;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTTblPr;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import javax.xml.parsers.*;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.*;
import org.xml.sax.SAXException;

public class WordLead {
    /**
     * word2007以上版本
     * @param is
     * @return
     * @throws IOException
     */
    public static WordBean readWord2007(InputStream is) throws IOException {
        WordBean wg = new WordBean();
        XWPFDocument doc = new XWPFDocument(is);
        List<XWPFParagraph> paras = doc.getParagraphs();
        List<XWPFRun> runs = paras.get(0).getRuns();
        for (int i = 0; i < runs.size(); i++) {
            runs.get(i);
        }
        for (XWPFRun run : runs) {
            String text = run.getText(0);
        }
        for (XWPFParagraph para : paras) {//当前段落的属性
            String text = para.getText();
        }
        List tables = doc.getTables();
        XWPFTable xwpf = (XWPFTable) tables.get(0);
        String text = xwpf.getText();
        CTTblPr pr = xwpf.getCTTbl().getTblPr();
        List<XWPFTableRow> rows = xwpf.getRows();
        for (XWPFTableRow row : rows) {
            List<XWPFTableCell> tableCells = row.getTableCells();
            for (int i = 0; i < tableCells.size(); i++) {
                if (tableCells.get(i).getText().equals("事件编号")) {
                    wg.setSj_bh(tableCells.get(++i).getText());
                } else if (tableCells.get(i).getText().equals("姓名")) {
                    wg.setRy_xm(tableCells.get(++i).getText());
                } else if (tableCells.get(i).getText().equals("地址")) {
                    wg.setRy_dz(tableCells.get(++i).getText());
                } else if (tableCells.get(i).getText().equals("事件类型")) {
                    wg.setSj_lx(tableCells.get(++i).getText());
                } else if (tableCells.get(i).getText().equals("事件地点")) {
                    wg.setSj_dd(tableCells.get(++i).getText());
                } else if (tableCells.get(i).getText().equals("事件内容")) {
                    wg.setSj_nr(tableCells.get(++i).getText());
                }
            }
        }
        return wg;
    }

    /**
     * word2003版
     * @param stream
     * @return
     * @throws IOException
     */
    public static WordBean readWord2003(InputStream stream) throws IOException {
        WordBean wg = new WordBean();
        HWPFDocument hwpf = new HWPFDocument(stream);
        Range range = hwpf.getRange();// 得到文档的读取范围
        TableIterator it = new TableIterator(range);// 迭代文档中的表格
        String info = "";
        String cellString = "";
        if (it.hasNext()) {
            TableRow tr = null;
            TableCell td = null;
            Paragraph para = null;
            Table tb = it.next();
            for (int i = 0; i < tb.numRows(); i++) {
                tr = tb.getRow(i);
                for (int j = 0; j < tr.numCells(); j++) {
                    td = tr.getCell(j);// 取得单元格
                    // 取得单元格的内容
                    para = td.getParagraph(0);
                    cellString = para.text();
                    boolean flag = true;
                    if (cellString != null && cellString.compareTo("") != 0 && flag == true) {
                        // 如果不trim，取出的内容后会有一个乱码字符
                        cellString = cellString.trim();
                    }
                    if (cellString.equals("事件编号")) {
                        wg.setSj_bh(tr.getCell(++j).getParagraph(0).text());
                    } else if (cellString.equals("姓名")) {
                        wg.setRy_xm(tr.getCell(++j).getParagraph(0).text());
                    } else if (cellString.equals("地址")) {
                        wg.setRy_dz(tr.getCell(++j).getParagraph(0).text());
                    } else if (cellString.equals("事件类型")) {
                        wg.setSj_lx(tr.getCell(++j).getParagraph(0).text());
                    } else if (cellString.equals("事件地点")) {
                        wg.setSj_dd(tr.getCell(++j).getParagraph(0).text());
                    } else if (cellString.equals("事件内容")) {
                        wg.setSj_nr(tr.getCell(++j).getParagraph(0).text());
                    }
                }
            }
        }
        return wg;
    }

    /**
     * xml格式word
     * @param stream
     * @return
     * @throws IOException
     * @throws ParserConfigurationException
     * @throws SAXException
     */
    public static WordBean readXml(InputStream stream) throws IOException, ParserConfigurationException, SAXException {
        WordBean wg = new WordBean();
        DocumentBuilderFactory bdf = DocumentBuilderFactory.newInstance();
        DocumentBuilder bd = bdf.newDocumentBuilder();
        Document doc = bd.parse(stream);
        doc.getDocumentElement().normalize();
        Element root = doc.getDocumentElement();
        String rootName = root.getNodeName();
        NodeList namesList = doc.getElementsByTagName("w:tc");
        int length = namesList.getLength();
        for (int i = 0; i < length; i++) {
            Node node = namesList.item(i);
            String content = node.getTextContent();
            if (content.equals("事件编号")) {
                wg.setSj_bh(namesList.item(++i).getTextContent());
            } else if (content.equals("姓名")) {
                wg.setRy_xm(namesList.item(++i).getTextContent());
            } else if (content.equals("地址")) {
                wg.setRy_dz(namesList.item(++i).getTextContent());
            } else if (content.equals("事件类型")) {
                wg.setSj_lx(namesList.item(++i).getTextContent());
            } else if (content.equals("事件地点")) {
                wg.setSj_dd(namesList.item(++i).getTextContent());
            } else if (content.equals("事件内容")) {
                wg.setSj_nr(namesList.item(++i).getTextContent());
            }
        }
        return wg;
    }
   /**
     * htm格式word(因为一个class里会有jar冲突，解析方法单独写了一个类)
     * @param stream
     * @return
     * @throws IOException
     * @throws ParserConfigurationException
     * @throws SAXException
     */
    public static WgglFb readHtm(InputStream stream) {
        HtmWordPro htmWord=new HtmWordPro();
        WgglFb fb = htmWord.readHmt(stream);
        return fb;
    }
}

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;

public class HtmWordPro {

    public WgglFb readHmt(InputStream stream) {
        WordBean wg = new WordBean();
        String html = getFileContent(stream);//获取html内容
        Document doc = Jsoup.parse(html);
        Elements rows = doc.select("table").get(0).select("tr");
        for(int i=0;i<rows.size();i++){
            Element row = rows.get(i);
            int tds = row.select("td").size();
            for(int j=0;j<tds;j++){
                String content = row.select("td").get(j).text().trim();
	            if (content.equals("事件编号")) {
	                wg.setSj_bh(row.select("td").get(++j).text().trim());
	            } else if (content.equals("姓名")) {
	                wg.setRy_xm(row.select("td").get(++j).text().trim());
	            } else if (content.equals("地址")) {
	                wg.setRy_dz(row.select("td").get(++j).text().trim());
	            } else if (content.equals("事件类型")) {
	                wg.setSj_lx(row.select("td").get(++j).text().trim());
	            } else if (content.equals("事件地点")) {
	                wg.setSj_dd(row.select("td").get(++j).text().trim());
	            } else if (content.equals("事件内容")) {
	                wg.setSj_nr(row.select("td").get(++j).text().trim());
	            }
            }
        }
        return wg;
    }

    /**
     * 获取html内容
     * @param stream
     * @return
     */
    public static String getFileContent(InputStream stream) {
        try {

            BufferedReader bis = new BufferedReader(new InputStreamReader(stream,"GBK"));//写上文件格式，要不然会乱码
            StringBuilder szContent = new StringBuilder();
            String szTemp;
            while ((szTemp = bis.readLine()) != null) {
                szContent.append(szTemp);
            }
            bis.close();
            return szContent.toString();
        } catch (Exception e) {
            return "";
        }
    }

}

import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;

public class FileTypeUtils {

    // 缓存文件头信息-文件头信息
    public static final HashMap<String, String> mFileTypes = new HashMap<String, String>();
    static {
        //文档
        mFileTypes.put("D0CF11E0", "doc");
        mFileTypes.put("504B0304", "docx");
        mFileTypes.put("3C3F786D", "xml");
        mFileTypes.put("3C68746D", "htm");
        mFileTypes.put("3C21444F", "html");
        
    }
    /**
     * 根据文件路径获取文件头信息
     * @param is
     * @return 文件头信息
     */
    public static String getFileType(InputStream is) {
        return mFileTypes.get(getFileHeader(is));
    }

    /**
     * 根据文件路径获取文件头信息
     * @param is 文件路径
     * @return 文件头信息
     */
    public static String getFileHeader(InputStream is) {
        String value = null;
        try {
            byte[] b = new byte[4];
            /*
             * int read() 从此输入流中读取一个数据字节。 int read(byte[] b) 从此输入流中将最多 b.length
             * 个字节的数据读入一个 byte 数组中。 int read(byte[] b, int off, int len)
             * 从此输入流中将最多 len 个字节的数据读入一个 byte 数组中。
             */
            is.read(b, 0, b.length);
            value = bytesToHexString(b);
        } catch (Exception e) {
        } finally {
            if (null != is) {
                try {
                    is.close();
                } catch (IOException e) {
                }
            }
        }
        return value;
    }
    /**
     * 将要读取文件头信息的文件的byte数组转换成string类型表示
     * @param src
     * 要读取文件头信息的文件的byte数组
     * @return 文件头信息
     */
    private static String bytesToHexString(byte[] src) {
        StringBuilder builder = new StringBuilder();
        if (src == null || src.length <= 0) {
            return null;
        }
        String hv;
        for (int i = 0; i < src.length; i++) {
            // 以十六进制（基数 16）无符号整数形式返回一个整数参数的字符串表示形式，并转换为大写
            hv = Integer.toHexString(src[i] & 0xFF).toUpperCase();
            if (hv.length() < 2) {
                builder.append(0);
            }
            builder.append(hv);
        }
        return builder.toString();
    }

}

3.WordBean

public class WordBean {
    private String sj_bh;//事件编号
    private String ry_xm;//人员姓名
    private String ry_dz;//人员地址
    private String sj_lx;//事件类型
    private String sj_dd;//事件地点
    private String sj_nr;//事件内容
    
    public String getSj_bh() {
        return sj_bh;
    }
    public void setSj_bh(String sj_bh) {
        this.sj_bh = sj_bh;
    }
    public String getRy_xm() {
        return ry_xm;
    }
    public void setRy_xm(String ry_xm) {
        this.ry_xm = ry_xm;
    }
    public String getRy_dz() {
        return ry_dz;
    }
    public void setRy_dz(String ry_dz) {
        this.ry_dz = ry_dz;
    }
    public String getSj_lx() {
        return sj_lx;
    }
    public void setSj_lx(String sj_lx) {
        this.sj_lx = sj_lx;
    }
    public String getSj_dd() {
        return sj_dd;
    }
    public void setSj_dd(String sj_dd) {
        this.sj_dd = sj_dd;
    }
    public String getSj_nr() {
        return sj_nr;
    }
    public void setSj_nr(String sj_nr) {
        this.sj_nr = sj_nr;
    }
}

4.结果