gistfile1.txt

#!/usr/bin/python
import os, sys
import re
from stat import *
import xlrd, xlwt
from datetime import datetime
 
def walktree(top, callback):
   '''recursively descend the directory tree rooted at top,
      calling the callback function for each regular file'''
 
   for f in os.listdir(top):
       pathname = os.path.join(top, f)
       mode = os.stat(pathname)[ST_MODE]
       if S_ISDIR(mode):
           # It's a directory, recurse into it
           walktree(pathname, callback)
       elif S_ISREG(mode):
           # It's a file, call the callback function
           callback(pathname,f,top)
       else:
           # Unknown file type, print a message
           print 'Skipping %s' % pathname
 
def visitfile(fullname,file,path):
	global g_row
	if "xls".lower() in str(file).lower() and "~$" not in str(file).lower() and "anulada" not in str(file).lower():
   		# print 'visiting', file, 'in', path, "=", fullname
   		style0 = xlwt.easyxf('font: name Times New Roman, color-index red, bold on', num_format_str='#,##0.00')
   		style1 = xlwt.easyxf(num_format_str='D-MMM-YY')
   		try:
   			workbook = xlrd.open_workbook(fullname)
   			worksheet = workbook.sheet_by_index(0)
   			num_rows = worksheet.nrows
   			fecha = worksheet.cell_value(5, 2)
   			a1_tuple = xlrd.xldate_as_tuple(fecha, workbook.datemode) 
   			a1_datetime = datetime(*a1_tuple)

			for row in range(13, num_rows):
				articulo = worksheet.cell_value(row,3)
				cantidad = worksheet.cell_value(row,5)
				v_unit = worksheet.cell_value(row,6)
				v_total = worksheet.cell_value(row,7)
				
				if len(articulo)==0:
					break

				ws.write(g_row, 0, articulo, style0)
				ws.write(g_row, 1, cantidad, style0)
				ws.write(g_row, 2, v_unit, style0)
				ws.write(g_row, 3, v_total, style0)
				ws.write(g_row, 4, a1_datetime, style1)

				ws.write(g_row, 5, str(file.replace("ORDENES DE COMPRA", "").replace(".xlsx", "").replace(".xls", "").replace(str(re.sub(r'[^\d]', ' ', file.replace("ORDENES DE COMPRA", "").replace(".xlsx", "").replace(".xls", ""))).strip(), "")).strip(), style1)
				ws.write(g_row, 6, str(re.sub(r'[^\d]', ' ', file.replace("ORDENES DE COMPRA", "").replace(".xlsx", "").replace(".xls", ""))).strip(), style1)

				g_row+=1

			print file.replace("ORDENES DE COMPRA", "").replace(".xlsx", "").replace(".xls", "").replace(str(re.sub(r'[^\d]', ' ', file.replace("ORDENES DE COMPRA", "").replace(".xlsx", "").replace(".xls", ""))).strip(), "")
			print a1_datetime

		except Exception, e:
			print 'visiting', file, 'in', path, "=", fullname
			print e
 
if __name__ == '__main__':
	global g_row
	g_row = 1
	wb = xlwt.Workbook(encoding='latin-1')
	ws = wb.add_sheet('A Test Sheet')
   	walktree(sys.argv[1], visitfile)
   	wb.save('resultado-{0}.xls'.format(datetime.now()))