读取Excel工作表并将其插入数据库mysql

Question

I am new to java. I am using an apache poi to insert a data from excel sheet to the mysql. At the Backend I have created the table using mysql. I have imported all the jar files. The error which I am Facing is that: 1. The date value cannot be inserted. 2.When I remove the date column,it sends only the address of the data and not the value. 3.Sometimes it tells source not found. Please do help me with this issue.

  public static ArrayList readExcelFile(String fileName) throws SQLException
 {
/** --Define a ArrayList
    --Holds ArrayList Of Cells

 */

ArrayList cellArrayLisstHolder = new ArrayList();


enter code here
try{
/** Creating Input Stream**/
    FileInputStream myInput = new FileInputStream(fileName);

/** Create a POIFSFileSystem object**/
POIFSFileSystem myFileSystem = new POIFSFileSystem(myInput);

/** Create a workbook using the File System**/
 HSSFWorkbook myWorkBook = new HSSFWorkbook(myFileSystem);

 /** Get the first sheet from workbook**/
HSSFSheet mySheet = myWorkBook.getSheetAt(0);

/** We now need something to iterate through the cells.**/
  Iterator rowIter = mySheet.rowIterator();
  while(rowIter.hasNext()){
      HSSFRow myRow = (HSSFRow) rowIter.next();
      Iterator cellIter = myRow.cellIterator();
      ArrayList cellStoreArrayList=new ArrayList();
      while(cellIter.hasNext()){
          HSSFCell myCell = (HSSFCell) cellIter.next();
          HSSFCell cell = myRow.createCell((short) 0);
          cell.setCellType(HSSFCell.CELL_TYPE_NUMERIC);

          SimpleDateFormat datetemp = new SimpleDateFormat("mm-dd-yyyy");
          Date cellValue = datetemp.parse("1994-01-01");
          cell.setCellValue(cellValue);

          //binds the style you need to the cell.
          HSSFCellStyle dateCellStyle = myWorkBook.createCellStyle();
          short df = myWorkBook.createDataFormat().getFormat("dd-mmm");
          dateCellStyle.setDataFormat(df);
          cell.setCellStyle(dateCellStyle);
          cellStoreArrayList.add(myCell);

                    }
      cellArrayLisstHolder.add(cellStoreArrayList);
  }
}catch (Exception e){e.printStackTrace(); }
return cellArrayLisstHolder;
}%>
<%

 File f = new File("DeptHosp.xls");
 System.out.println(f.getAbsolutePath());

 File file = new File(".");
 for(String fileNames : file.list()) System.out.println(fileNames);
 String fileName="D://PROJECT//SOFTWARES//eclipse_Juno//eclipse//DeptHosp.xls";                    
 //Read an Excel File and Store in a ArrayList
 System.out.println(" path found");
 ArrayList dataHolder=readExcelFile(fileName);
 //Print the data read
 //printCellDataToConsole(dataHolder);
  con=connection.getConn();
  System.out.println("Inserting the details");
  String query=
  "insert into                       departmentmaster(Dept_id,Dept_Groupid,Dept_Kid,Dept_Groupkid,Dept_Group,Dept_Name,Dept_type     ,Dept_HospitalId,Dept_Datecreated,Dept_datelastrefreshed)values(?,?,?,?,?,?,?,?,?,?)";
  ps=con.prepareStatement(query);
 System.out.println("Database");
 int count=0;
 ArrayList cellStoreArrayList=null;
 Date datevalue=null;

  //For inserting into database
  for (int i=1;i < dataHolder.size(); i++) {
  cellStoreArrayList=(ArrayList)dataHolder.get(i);


   ps.setString(1,((HSSFCell)cellStoreArrayList.get(0)).getStringCellValue());
   ps.setString(2,((HSSFCell)cellStoreArrayList.get(1)).getStringCellValue());
   ps.setString(3,((HSSFCell)cellStoreArrayList.get(2)).getStringCellValue());
   ps.setString(4,((HSSFCell)cellStoreArrayList.get(3)).getStringCellValue());
   ps.setString(5,((HSSFCell)cellStoreArrayList.get(4)).getStringCellValue());
   ps.setString(6,((HSSFCell)cellStoreArrayList.get(5)).getStringCellValue());
   ps.setString(7,((HSSFCell)cellStoreArrayList.get(6)).getStringCellValue());
   ps.setString(8,((HSSFCell)cellStoreArrayList.get(7)).getStringCellValue());
   ps.setString(9,((HSSFCell)cellStoreArrayList.get(8)).getStringCellValue());
   ps.setString(10,((HSSFCell)cellStoreArrayList.get(9)).getStringCellValue());

   count= ps.executeUpdate();
   System.out.println(((HSSFCell)cellStoreArrayList.get(9)).getStringCellValue() +   "\t");
   }
  //For checking data is inserted or not?
  if(count>0)
   { %>

               <table>
                   <tr>
                       <th>Dept_Id</th>
                       <th>Dept_GroupId</th>
                       <th>Dept_KId</th>
                       <th>Dept_GroupKid</th>
                       <th>Dept_Group</th>
                       <th>Dept_Name</th>
                       <th>Dept_Type</th>
                       <th>Hospital_Id</th>
                       <th>Dept_datecreated</th>
                       <th>Dept_datelastrefreshed</th>


                   </tr>

   <% for (int i=1;i < dataHolder.size(); i++) {
cellStoreArrayList=(ArrayList)dataHolder.get(i);%>
<tr>
    <td><%=((HSSFCell)cellStoreArrayList.get(0)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(1)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(2)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(3)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(4)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(5)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(6)).getStringCellValue() %></td>
    <td><%=((HSSFCell)cellStoreArrayList.get(7)).getStringCellValue() %></td>
     <td><%=((HSSFCell)cellStoreArrayList.get(8)).getStringCellValue() %></td>
      <td><%=((HSSFCell)cellStoreArrayList.get(9)).getStringCellValue() %></td>




</tr>
   <%}
  }
else
{%>
<center> Details have not been inserted!!!!!!!!!</center>

<% }%>

The error which i am getting is: Jan 06, 2014 12:05:00 PM org.apache.catalina.core.StandardWrapperValve invoke SEVERE: Servlet.service() for servlet [jsp] in context with path [/Excel] threw exception [An exception occurred processing JSP page /Excel.jsp at line 139

136:        ps.setString(6,((HSSFCell)cellStoreArrayList.get(5)).getStringCellValue());
137:        ps.setString(7,((HSSFCell)cellStoreArrayList.get(6)).getStringCellValue());
138:        ps.setString(8,((HSSFCell)cellStoreArrayList.get(7)).getStringCellValue());
139:        ps.setString(9,((HSSFCell)cellStoreArrayList.get(8)).getStringCellValue());
140:        ps.setString(10,    ((HSSFCell)cellStoreArrayList.get(9)).getStringCellValue());
141:        
 142:        count= ps.executeUpdate();


     Stacktrace:] with root cause
    java.lang.IndexOutOfBoundsException: Index: 8, Size: 8
at java.util.ArrayList.rangeCheck(Unknown Source)
at java.util.ArrayList.get(Unknown Source)
at org.apache.jsp.Excel_jsp._jspService(Excel_jsp.java:234)
at org.apache.jasper.runtime.HttpJspBase.service(HttpJspBase.java:70)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:728)
at org.apache.jasper.servlet.JspServletWrapper.service(JspServletWrapper.java:432)
at org.apache.jasper.servlet.JspServlet.serviceJspFile(JspServlet.java:390)
at org.apache.jasper.servlet.JspServlet.service(JspServlet.java:334)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:728)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:305)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:210)
at org.apache.tomcat.websocket.server.WsFilter.doFilter(WsFilter.java:51)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:243)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:210)
at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:222)
at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:123)
at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:502)
at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:171)
at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:100)
at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:953)
at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:118)
at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:408)
at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:1041)
at org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:603)
at org.apache.tomcat.util.net.JIoEndpoint$SocketProcessor.run(JIoEndpoint.java:310)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)

Answer 1

I cant comment to your question, so i will try to answer based on my understanding that you have issues reading/writing the DATE fields in Excel.

I think you are missing a check on Date field, excel stores the dates as Numeric Contents internally and while displaying, It displays a formatted date. Also you need to ensure that the column is formatted as DATE column in the sheet you are reading.

You need to use below code fragment to read content as DATE.

if (cell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) {

// Excel stores the Date as a Numeric Contents. POI provides
// a Date utility to check
// if a particular cell is formatted as a date.
if (DateUtil.isCellDateFormatted(cell)) {
   Date date = DateUtil.getJavaDate((double) cell
         .getNumericCellValue());
   SimpleDateFormat df = new SimpleDateFormat("dd/MM/yyyy HH:mm z");
   System.out.println("The cell is a Date : " + df.format(date));
} else {
   // treat the cell as 'double' number
   System.out.println("The cell is a number : "
         + cell.getNumericCellValue());
}

}

For complete code snipper you can refer this link . Please note I have authored the link.

Answer 2

Can you use jython instead of POI? If so, the following code will spit out a CSV which can then be loaded into MySQL using the [bulk loader](http://dev.mysql.com/doc/refman/5.1/en/mysqlimport.html] by the command that follows the code:

#!/usr/bin/python
#
#   Copyright information
#
#   Copyright (C) 2013-2014 Hasan Diwan
#   This program is free software; you can redistribute it and/or modify
#   This program is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied warranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
__author__ = "Hasan Diwan <hasan.diwan@gmail.com>"
__license__ = "BSD"
__version__ = "0.1"

import csv, datetime, zipfile, string, sys, os, re
import xml.parsers.expat
from xml.dom import minidom
try:
    # python2.4
    from cStringIO import StringIO
except:
    pass
try:
    from argparse import ArgumentParser
except:
    # python2.4
    from optparse import OptionParser

# see also ruby-roo lib at: http://github.com/hmcgowan/roo
FORMATS = {
  'general' : 'float',
  '0' : 'float',
  '0.00' : 'float',
  '#,##0' : 'float',
  '#,##0.00' : 'float',
  '0%' : 'percentage',
  '0.00%' : 'percentage',
  '0.00e+00' : 'float',
  'mm-dd-yy' : 'date',
  'd-mmm-yy' : 'date',
  'd-mmm' : 'date',
  'mmm-yy' : 'date',
  'h:mm am/pm' : 'date',
  'h:mm:ss am/pm' : 'date',
  'h:mm' : 'time',
  'h:mm:ss' : 'time',
  'm/d/yy h:mm' : 'date',
  '#,##0 ;(#,##0)' : 'float',
  '#,##0 ;[red](#,##0)' : 'float',
  '#,##0.00;(#,##0.00)' : 'float',
  '#,##0.00;[red](#,##0.00)' : 'float',
  'mm:ss' : 'time',
  '[h]:mm:ss' : 'time',
  'mmss.0' : 'time',
  '##0.0e+0' : 'float',
  '@' : 'float',
  'yyyy\\-mm\\-dd' : 'date',
  'dd/mm/yy' : 'date',
  'hh:mm:ss' : 'time',
  "dd/mm/yy\\ hh:mm" : 'date',
  'dd/mm/yyyy hh:mm:ss' : 'date',
  'yy-mm-dd' : 'date',
  'd-mmm-yyyy' : 'date',
  'm/d/yy' : 'date',
  'm/d/yyyy' : 'date',
  'dd-mmm-yyyy' : 'date',
  'dd/mm/yyyy' : 'date',
  'mm/dd/yy hh:mm am/pm' : 'date',
  'mm/dd/yyyy hh:mm:ss' : 'date',
  'yyyy-mm-dd hh:mm:ss' : 'date',
}
STANDARD_FORMATS = {
  0 : 'general',
  1 : '0',
  2 : '0.00',
  3 : '#,##0',
  4 : '#,##0.00',
  9 : '0%',
  10 : '0.00%',
  11 : '0.00e+00',
  12 : '# ?/?',
  13 : '# ??/??',
  14 : 'mm-dd-yy',
  15 : 'd-mmm-yy',
  16 : 'd-mmm',
  17 : 'mmm-yy',
  18 : 'h:mm am/pm',
  19 : 'h:mm:ss am/pm',
  20 : 'h:mm',
  21 : 'h:mm:ss',
  22 : 'm/d/yy h:mm',
  37 : '#,##0 ;(#,##0)',
  38 : '#,##0 ;[red](#,##0)',
  39 : '#,##0.00;(#,##0.00)',
  40 : '#,##0.00;[red](#,##0.00)',
  45 : 'mm:ss',
  46 : '[h]:mm:ss',
  47 : 'mmss.0',
  48 : '##0.0e+0',
  49 : '@',
}

class XlsxException(Exception):
    pass

class InvalidXlsxFileException(XlsxException):
    pass

class SheetNotFoundException(XlsxException):
    pass

class OutFileAlreadyExistsException(XlsxException):
    pass

class Xlsx2csv:
    """
     Usage: Xlsx2csv("test.xslx", **params).convert("test.csv", sheetid=1)
     parameters:
       sheetid - sheet no to convert (0 for all sheets)
       dateformat - override date/time format
       delimiter - csv columns delimiter symbol
       sheet_delimiter - sheets delimiter used when processing all sheets
       skip_empty_lines - skip empty lines
    """

    def __init__(self, xlsxfile, dateformat=None, delimiter=",", sheetdelimiter="--------", skip_empty_lines=False, escape_strings=False, cmd=False):
        try:
            self.ziphandle = zipfile.ZipFile(xlsxfile)
        except (zipfile.BadZipfile, IOError):
            if cmd:
                sys.stderr.write("Invalid xlsx file: " + xlsxfile + os.linesep)
                sys.exit(1)
            raise InvalidXlsxFileException("Invalid xlsx file: " + xlsxfile)

        self.dateformat = dateformat
        self.delimiter = delimiter
        self.sheetdelimiter = sheetdelimiter
        self.skip_empty_lines = skip_empty_lines
        self.cmd = cmd
        self.py3 = sys.version_info[0] == 3

        self.shared_strings = self._parse(SharedStrings, "xl/sharedStrings.xml")
        self.styles = self._parse(Styles, "xl/styles.xml")
        self.workbook = self._parse(Workbook, "xl/workbook.xml")
        if escape_strings:
            self.shared_strings.escape_strings()

    def convert(self, outfile, sheetid=1):
        """outfile - path to file or filehandle"""
        if sheetid > 0:
            self._convert(sheetid, outfile)
        else:
            if isinstance(outfile, str):
                if not os.path.exists(outfile):
                    os.makedirs(outfile)
                elif os.path.isfile(outfile):
                    if cmd:
                        sys.stderr.write("File " + outfile + " already exists!" + os.linesep)
                        sys.exit(1)
                    raise OutFileAlreadyExistsException("File " + outfile + " already exists!")
            for s in self.workbook.sheets:
                sheetname = s['name']
                if not self.py3:
                    sheetname = sheetname.encode('utf-8')
                of = outfile
                if isinstance(outfile, str):
                    of = os.path.join(outfile, sheetname + '.csv')
                elif self.sheetdelimiter and len(self.sheetdelimiter):
                    of.write(self.sheetdelimiter + " " + str(s['id']) + " - " + sheetname + os.linesep)
                self._convert(s['id'], of)

    def _convert(self, sheetid, outfile):
        closefile = False
        if isinstance(outfile, str):
            outfile = open(outfile, 'w+')
            closefile = True
        try:
            writer = csv.writer(outfile, quoting=csv.QUOTE_ALL, delimiter=self.delimiter, lineterminator='\r\n')
            sheetfile = self._filehandle("xl/worksheets/sheet%i.xml" % sheetid)
            if not sheetfile:
                if self.cmd:
                    sys.stderr.write("Sheet %s not found!%s" %(sheetid, os.linesep))
                    sys.exit(1)
                raise SheetNotFoundException("Sheet %s not found" %sheetid)
            try:
                sheet = Sheet(self.workbook, self.shared_strings, self.styles, sheetfile)
                sheet.set_dateformat(self.dateformat)
                sheet.set_skip_empty_lines(self.skip_empty_lines)
                sheet.to_csv(writer)
            finally:
                sheetfile.close()
        finally:
            if closefile:
                outfile.close()

    def _filehandle(self, filename):
        for name in filter(lambda f: f.lower() == filename.lower(), self.ziphandle.namelist()):
            # python2.4 fix
            if not hasattr(self.ziphandle, "open"):
                return StringIO(self.ziphandle.read(name))
            return self.ziphandle.open(name, "r")
        return None

    def _parse(self, klass, filename):
        instance = klass()
        filehandle = self._filehandle(filename)
        if filehandle:
            instance.parse(filehandle)
            filehandle.close()
        return instance

class Workbook:
    def __init__(self):
        self.sheets = []
        self.date1904 = False

    def parse(self, filehandle):
        workbookDoc = minidom.parseString(filehandle.read())
        if len(workbookDoc.firstChild.getElementsByTagName("fileVersion")) == 0:
            self.appName = 'unknown'
        else:
            self.appName = workbookDoc.firstChild.getElementsByTagName("fileVersion")[0]._attrs['appName'].value
        try:
            self.date1904 = workbookDoc.firstChild.getElementsByTagName("workbookPr")[0]._attrs['date1904'].value.lower().strip() != "false"
        except:
            pass

        sheets = workbookDoc.firstChild.getElementsByTagName("sheets")[0]
        for sheetNode in sheets.getElementsByTagName("sheet"):
            attrs = sheetNode._attrs
            name = attrs["name"].value
            if self.appName == 'xl':
                if 'r:id' in attrs: id = int(attrs["r:id"].value[3:])
                else: id = int(attrs['sheetId'].value)
            else:
                if 'sheetId' in attrs: id = int(attrs["sheetId"].value)
                else: id = int(attrs['r:id'].value[3:])
            self.sheets.append({'name': name, 'id': id})

class Styles:
    def __init__(self):
        self.numFmts = {}
        self.cellXfs = []

    def parse(self, filehandle):
        styles = minidom.parseString(filehandle.read()).firstChild
        # numFmts
        numFmtsElement = styles.getElementsByTagName("numFmts")
        if len(numFmtsElement) == 1:
            for numFmt in numFmtsElement[0].childNodes:
                if numFmt.nodeType == minidom.Node.ELEMENT_NODE:
                    numFmtId = int(numFmt._attrs['numFmtId'].value)
                    formatCode = numFmt._attrs['formatCode'].value.lower().replace('\\', '')
                    self.numFmts[numFmtId] = formatCode
        # cellXfs
        cellXfsElement = styles.getElementsByTagName("cellXfs")
        if len(cellXfsElement) == 1:
            for cellXfs in cellXfsElement[0].childNodes:
                if cellXfs.nodeType != minidom.Node.ELEMENT_NODE or cellXfs.nodeName != "xf":
                    continue
                if 'numFmtId' in cellXfs._attrs:
                    numFmtId = int(cellXfs._attrs['numFmtId'].value)
                    self.cellXfs.append(numFmtId)
                else:
                    self.cellXfs.append(None)

class SharedStrings:
    def __init__(self):
        self.parser = None
        self.strings = []
        self.si = False
        self.t = False
        self.rPh = False
        self.value = ""

    def parse(self, filehandle):
        self.parser = xml.parsers.expat.ParserCreate()
        self.parser.CharacterDataHandler = self.handleCharData
        self.parser.StartElementHandler = self.handleStartElement
        self.parser.EndElementHandler = self.handleEndElement
        self.parser.ParseFile(filehandle)

    def escape_strings(self):
        for i in range(0, len(self.strings)):
            self.strings[i] = self.strings[i].replace("\r", "\\r").replace("\n", "\\n").replace("\t", "\\t")

    def handleCharData(self, data):
        if self.t:
            self.value+= data

    def handleStartElement(self, name, attrs):
        if name == 'si':
            self.si = True
            self.value = ""
        elif name == 't' and self.rPh:
            self.t = False
        elif name == 't' and self.si:
            self.t = True
        elif name == 'rPh':
            self.rPh = True

    def handleEndElement(self, name):
        if name == 'si':
            self.si = False
            self.strings.append(self.value)
        elif name == 't':
            self.t = False
        elif name == 'rPh':
            self.rPh = False

class Sheet:
    def __init__(self, workbook, sharedString, styles, filehandle):
        self.py3 = sys.version_info[0] == 3
        self.parser = None
        self.writer = None
        self.sharedString = None
        self.styles = None

        self.in_sheet = False
        self.in_row = False
        self.in_cell = False
        self.in_cell_value = False
        self.in_cell_formula = False

        self.columns = {}
        self.rowNum = None
        self.colType = None
        self.s_attr = None
        self.data = None

        self.dateformat = None
        self.skip_empty_lines = False

        self.filehandle = filehandle
        self.workbook = workbook
        self.sharedStrings = sharedString.strings
        self.styles = styles

    def set_dateformat(self, dateformat):
        self.dateformat = dateformat

    def set_skip_empty_lines(self, skip):
        self.skip_empty_lines = skip

    def to_csv(self, writer):
        self.writer = writer
        self.parser = xml.parsers.expat.ParserCreate()
        self.parser.CharacterDataHandler = self.handleCharData
        self.parser.StartElementHandler = self.handleStartElement
        self.parser.EndElementHandler = self.handleEndElement
        self.parser.ParseFile(self.filehandle)

    def handleCharData(self, data):
        if self.in_cell_value:
            self.collected_string+= data
            self.data = self.collected_string
            if self.colType == "s": # shared string
                self.data = self.sharedStrings[int(self.data)]
            elif self.colType == "b": # boolean
                self.data = (int(data) == 1 and "TRUE") or (int(data) == 0 and "FALSE") or data
            elif self.s_attr:
                s = int(self.s_attr)

                # get cell format
                format = None
                xfs_numfmt = self.styles.cellXfs[s]
                if xfs_numfmt in self.styles.numFmts:
                    format = self.styles.numFmts[xfs_numfmt]
                elif xfs_numfmt in STANDARD_FORMATS:
                    format = STANDARD_FORMATS[xfs_numfmt]
                # get format type
                if format and format in FORMATS:
                    format_type = FORMATS[format]
                    try:
                        if format_type == 'date': # date/time
                            if self.workbook.date1904:
                                date = datetime.datetime(1904, 1, 1) + datetime.timedelta(float(self.data))
                            else:
                                date = datetime.datetime(1899, 12, 30) + datetime.timedelta(float(self.data))
                            if self.dateformat:
                                # str(dateformat) - python2.5 bug, see: http://bugs.python.org/issue2782
                                self.data = date.strftime(str(self.dateformat))
                            else:
                                dateformat = format.replace("yyyy", "%Y").replace("yy", "%y"). \
                                  replace("hh:mm", "%H:%M").replace("h", "%H").replace("%H%H", "%H").replace("ss", "%S"). \
                                  replace("d", "%e").replace("%e%e", "%d"). \
                                  replace("mmmm", "%B").replace("mmm", "%b").replace(":mm", ":%M").replace("m", "%m").replace("%m%m", "%m"). \
                                  replace("am/pm", "%p")
                                self.data = date.strftime(str(dateformat)).strip()
                        elif format_type == 'time': # time
                            self.data = str(float(self.data) * 24*60*60)
                        elif format_type == 'float' and ('E' in self.data or 'e' in self.data):
                            self.data = ("%f" %(float(self.data))).rstrip('0').rstrip('.')
                    except (ValueError, OverflowError):
                        # invalid date format
                        pass
        # does not support it
        #elif self.in_cell_formula:
        #    self.formula = data

    def handleStartElement(self, name, attrs):
        if self.in_row and name == 'c':
            self.colType = attrs.get("t")
            self.s_attr = attrs.get("s")
            cellId = attrs.get("r")
            if cellId:
                self.colNum = cellId[:len(cellId)-len(self.rowNum)]
                self.colIndex = 0
            else:
                self.colIndex+= 1
            #self.formula = None
            self.data = ""
            self.in_cell = True
        elif self.in_cell and (name == 'v' or name == 'is'):
            self.in_cell_value = True
            self.collected_string = ""
        #elif self.in_cell and name == 'f':
        #    self.in_cell_formula = True
        elif self.in_sheet and name == 'row' and 'r' in attrs:
            self.rowNum = attrs['r']
            self.in_row = True
            self.columns = {}
            self.spans = None
            if 'spans' in attrs:
                self.spans = [int(i) for i in attrs['spans'].split(":")]
        elif name == 'sheetData':
            self.in_sheet = True

    def handleEndElement(self, name):
        if self.in_cell and name == 'v':
            self.in_cell_value = False
        #elif self.in_cell and name == 'f':
        #    self.in_cell_formula = False
        elif self.in_cell and name == 'c':
            t = 0
            for i in self.colNum: t = t*26 + ord(i) - 64
            self.columns[t - 1 + self.colIndex] = self.data
            self.in_cell = False
        if self.in_row and name == 'row':
            if len(self.columns.keys()) > 0:
                d = [""] * (max(self.columns.keys()) + 1)
                for k in self.columns.keys():
                    val = self.columns[k]
                    if not self.py3:
                        val = val.encode("utf-8")
                    d[k] = val
                if self.spans:
                    l = self.spans[0] + self.spans[1] - 1
                    if len(d) < l:
                        d+= (l - len(d)) * ['']
                # write line to csv
                if not self.skip_empty_lines or d.count('') != len(d):
                    self.writer.writerow(d)
            self.in_row = False
        elif self.in_sheet and name == 'sheetData':
            self.in_sheet = False

def convert_recursive(path, sheetid, kwargs):
    kwargs['cmd'] = False
    for name in os.listdir(path):
        fullpath = os.path.join(path, name)
        if os.path.isdir(fullpath):
            convert_recursive(fullpath, kwargs)
        else:
            if fullpath.lower().endswith(".xlsx"):
                outfilepath = fullpath[:-4] + 'csv'
                print("Converting %s to %s" %(fullpath, outfilepath))
                try:
                    Xlsx2csv(fullpath, **kwargs).convert(outfilepath, sheetid)
                except zipfile.BadZipfile:
                    print("File %s is not a zip file" %fullpath)

if __name__ == "__main__":
    if "ArgumentParser" in globals():
        parser = ArgumentParser(description = "xlsx to csv convertor")
        parser.add_argument('infile', metavar='xlsxfile', help="xlsx file path")
        parser.add_argument('outfile', metavar='outfile', nargs='?', help="output csv file path")
        parser.add_argument('-v', '--version', action='version', version='%(prog)s')
        argparser = True
    else:
        parser = OptionParser(usage = "%prog [options] infile [outfile]", version=__version__)
        parser.add_argument = parser.add_option
        argparser = False

    parser.add_argument("-a", "--all", dest="all", default=False, action="store_true",
      help="export all sheets")
    parser.add_argument("-d", "--delimiter", dest="delimiter", default=",",
      help="delimiter - csv columns delimiter, 'tab' or 'x09' for tab (comma is default)")
    parser.add_argument("-f", "--dateformat", dest="dateformat",
      help="override date/time format (ex. %%Y/%%m/%%d)")
    parser.add_argument("-i", "--ignoreempty", dest="skip_empty_lines", default=False, action="store_true",
      help="skip empty lines")
    parser.add_argument("-e", "--escape", dest='escape_strings', default=False, action="store_true",
      help="Escape \\r\\n\\t characters")
    parser.add_argument("-p", "--sheetdelimiter", dest="sheetdelimiter", default="--------",
      help="sheets delimiter used to separate sheets, pass '' if you don't want delimiters (default '--------')")
    parser.add_argument("-s", "--sheet", dest="sheetid", default=1, type=int,
      help="sheet no to convert (0 for all sheets)")

    if argparser:
        options = parser.parse_args()
    else:
        (options, args) = parser.parse_args()
        if len(args) < 1:
            parser.print_usage()
            sys.stderr.write("error: too few arguments" + os.linesep)
            sys.exit(1)
        options.infile = args[0]
        options.outfile = len(args) > 1 and args[1] or None

    if len(options.delimiter) == 1:
        delimiter = options.delimiter
    elif options.delimiter == 'tab':
        delimiter = '\t'
    elif options.delimiter == 'comma':
        delimiter = ','
    elif options.delimiter[0] == 'x':
        delimiter = chr(int(options.delimiter[1:]))
    else:
        raise XlsxException("Invalid delimiter")

    kwargs = {
      'delimiter' : delimiter,
      'sheetdelimiter' : options.sheetdelimiter,
      'dateformat' : options.dateformat,
      'skip_empty_lines' : options.skip_empty_lines,
      'escape_strings' : options.escape_strings,
      'cmd' : True
    }
    sheetid = options.sheetid
    if options.all:
        sheetid = 0

    if os.path.isdir(options.infile):mysq
        convert_recursive(options.infile, sheetid, kwargs)
    else:
        xlsx2csv = Xlsx2csv(options.infile, **kwargs)
        outfile = options.outfile or sys.stdout
        xlsx2csv.convert(outfile, sheetid)

To import this to mysql, use java -cp jython.jar org.python.util.jython xlsx2csv [xlsx-file] [csv-output-file]; mysqlimport --local db1 [csv-output-file] java -cp jython.jar org.python.util.jython xlsx2csv [xlsx-file] [csv-output-file]; mysqlimport --local db1 [csv-output-file] . I hope this helps...