I am trying to write to excel files using openpyxl module. For some reason it only lets me write once. If I try to write again it raises:
PermissionError: [Errno 13] Permission denied: 'expenses.xlsx'
The excel file and python program are in the same folder on D drive. What's the problem?
from openpyxl import Workbook
from openpyxl import load_workbook
from datetime import datetime
import os
class ExpenseTracker:
def __init__(self, file_name = "expenses.xlsx"):
self.fname = file_name
self.load_wb()
def load_wb(self):
"""
if the excel file doesn't exists it creates a new one
with a sheet, and calls self.col_values() which
adds values for first two columns in row 1
"""
try:
wb = load_workbook(self.fname)
except Exception:
wb = Workbook()
wb.create_sheet("Expenses", 0)
self.col_values()
wb.save(self.fname)
finally:
self.wb = wb
self.ws = self.wb["Expenses"]
def col_values(self):
# adds values for first two columns in row 1
self.ws.cell(row = 1, column = 1).value = "Date"
self.ws.cell(row = 1, column = 2).value = "Spent"
def spend_income(self, amount):
date = datetime.now()
date_formatted = date.strftime("%d.%b %Y")
last_row = self.ws.max_row + 1
last_col = self.ws.max_column + 1
self.ws.cell(row = last_row, column = 1).value = date_formatted
self.ws.cell(row = last_row, column = 2).value = amount
# writes under the last input in cols 1 and 2
self.wb.save(self.fname)
wbook = ExpenseTracker()
wbook.spend_income(5)
Related
Hey I wanted to get quick Output for slicing my Source XLSX file for collect Data from Cell on index: 11, but my script seems to working very slow.
Expected output is Collected items from column index(11) Cell when on column index(16) Cell value = None. Script check from begin every row on column index(16) if value == None, but on my file i have thousands positions before script start collecting Data,
Can I speed up this process or find faster way?
XLUtils.py:
import openpyxl
def getRowCount(file,sheetName):
workbook = openpyxl.load_workbook(file)
sheet = workbook.get_sheet_by_name(sheetName)
return(sheet.max_row)
def getColumnCount(file,sheetName):
workbook = openpyxl.load_workbook(file)
sheet = workbook.get_sheet_by_name(sheetName)
return(sheet.max_column)
def readData(file,sheetName,rownum,columnno):
workbook = openpyxl.load_workbook(file)
sheet = workbook.get_sheet_by_name(sheetName)
return sheet.cell(row=rownum, column=columnno).value
def writeData(file,sheetName,rownum,columno,data):
workbook = openpyxl.load_workbook(file)
sheet = workbook.get_sheet_by_name(sheetName)
sheet.cell(row=rownum, column=columno).value = data
workbook.save(file)
My Script:
import pandas as pd
import XLUtils
from openpyxl import Workbook
from datetime import datetime
def LISTING_GENERATOR():
#This function Create product list file for current day
i = 1
i_range = 50
r = 1
x = 1
rows = 50
LISTED_DATE = XLUtils.readData(PRODUCT_RESEARCH,'Sheet1',r,16)
if LISTED_DATE == None:
ASIN = XLUtils.readData(PRODUCT_RESEARCH,'Sheet1',r,11)
print(ASIN)
wb.save('Product_'+TODAY_DATE + '.xlsx')
print('File has been created: ',FILE)
for r in range(2,rows+1):
CHECK_ASIN = XLUtils.readData(PRODUCT_RESEARCH,'Sheet1',r, 11)
if CHECK_ASIN == None:
print('No more ASIN avaiable')
break
FE = XLUtils.readData(PRODUCT_RESEARCH,'Sheet1',r, 16)
if FE != None:
print('Product last added: ',FE)
if FE == None:
ASIN = XLUtils.readData(PRODUCT_RESEARCH,'Sheet1',r,11)
print(f'ASIN nr. {i}: {ASIN}')
LIST.append(ASIN)
XLUtils.writeData(FILE,'Sheet',x,1,ASIN)
XLUtils.writeData(PRODUCT_RESEARCH,'Sheet1',r,16,TODAY_DATE_XLSX)
x+=1
i+=1
if i >= i_range:
print(f'List of {i_range} items, has been Created.')
break
else:
print('Error: product on the list')
XLUtils.writeData(FILE,'Sheet',x,1,' ')
print('Created list:\n',LIST)
print('__________________________________')
ALL_ITEMS = (TODAY_DATE + '.xlsx')
print('CSV file has been named: ', ALL_ITEMS)
DATA_XLS = pd.read_excel(FILE, 'Sheet', dtype=str, index_col=None)
DATA_XLS.to_csv(PRODUCT_NAME+'.csv', encoding='utf-8', index=False)
if __name__ == '__main__':
#---Product_list_generator ---# Variable --
wb = Workbook()
LIST = []
TODAY_DATE = datetime.today().strftime('%d_%m_%Y')
TODAY_DATE_XLSX = datetime.today().strftime('%d/%m/%Y')
PRODUCT_RESEARCH = ('Product_Research_copy2.xlsx') #<--- xlsx File
FILE = ('Product_'+TODAY_DATE + '.xlsx')
PRODUCT_NAME = ('Product_'+TODAY_DATE)
LISTING_GENERATOR()
I'm trying to automate pivot table creation using Python, but after runing my code I got an error: NameError: name 'run_excel' is not defined
I've wrote my script on the bassis of this article : https://towardsdatascience.com/automate-excel-with-python-pivot-table-899eab993966
Can someone explain to me how to solve this problem?
enter image description here
Here is my code:
import win32com.client as win32
import pandas as pd
import numpy as np
from pathlib import Path
import re
import sys
win32c = win32.constants
df = pd.read_csv("act 05.01.2022.csv", encoding = 'unicode_escape', engine ='python')
df = df.dropna()
df.to_excel(r"C:\Users\szczepan.czarniak\Desktop\Visual Studio\1\act 05.01.2022.xlsx", sheet_name = 'act 05.01.2022', index = False)
def pivot_table(wb: object, ws1: object, pt_ws: object, ws_name: str, pt_name: str, pt_rows: list, pt_filters: list, pt_fields: list):
"""
wb = workbook1 reference
ws1 = worksheet1 that contain the data
pt_ws = pivot table worksheet number
ws_name = pivot table worksheet name
pt_name = name given to pivot table
pt_rows, pt_cols, pt_filters, pt_fields: values selected for filling the pivot tables
"""
# pivot table location
pt_loc = len(pt_filters) + 2
# grab the pivot table source data
pc = wb.PivotCaches().Create(SourceType=win32c.xlDatabase, SourceData=ws1.UsedRange)
# create the pivot table object
pc.CreatePivotTable(TableDestination=f'{ws_name}!R{pt_loc}C1', TableName=pt_name)
# selecte the pivot table work sheet and location to create the pivot table
pt_ws.Select()
pt_ws.Cells(pt_loc, 1).Select()
# Sets the rows, columns and filters of the pivot table
for field_list, field_r in ((pt_filters, win32c.xlPageField),
(pt_rows, win32c.xlRowField)):
for i, value in enumerate(field_list):
pt_ws.PivotTables(pt_name).PivotFields(value).Orientation = field_r
pt_ws.PivotTables(pt_name).PivotFields(value).Position = i + 1
# Sets the Values of the pivot table
for field in pt_fields:
pt_ws.PivotTables(pt_name).AddDataField(pt_ws.PivotTables(pt_name).PivotFields(field[0]), field[1], field[2]).NumberFormat = field[3]
# Visiblity True or Valse
pt_ws.PivotTables(pt_name).ShowValuesRow = True
pt_ws.PivotTables(pt_name).ColumnGrand = True
def run_excel(f_path: Path, f_name: str, sheet_name: str):
filename = f_path / f_name
# create excel object
excel = win32.gencache.EnsureDispatch('Excel.Application')
# excel can be visible or not
excel.Visible = True # False
# try except for file / path
try:
wb = excel.Workbooks.Open(filename)
except com_error as e:
if e.excepinfo[5] == -2146827284:
print(f'Failed to open spreadsheet. Invalid filename or location: {filename}')
else:
raise e
sys.exit(1)
# set worksheet
ws1 = wb.Sheets('act 05.01.2022')
# Setup and call pivot_table
ws2_name = 'pivot_table'
wb.Sheets.Add().Name = ws2_name
ws2 = wb.Sheets(ws2_name)
# update the pt_name, pt_rows, pt_cols, pt_filters, pt_fields at your preference
pt_name = 'example' # pivot table name, must be a string
pt_rows = ['decision_date'] # rows of pivot table, must be a list
# pt_cols = [] # columns of pivot table, must be a list
pt_filters = ['open_loan_count_all', 'days_between_repayments'] # filter to be applied on pivot table, must be a list
# [0]: field name [1]: pivot table column name [3]: calulation method [4]: number format (explain the list item of pt_fields below)
pt_fields = [['id', 'Total id', win32c.xlCount, '0']]
# calculation method: xlAverage, xlSum, xlCount
pivot_table(wb, ws1, ws2, ws2_name, pt_name, pt_rows, pt_filters, pt_fields)
wb.Save() # save the pivot table created
# wb.Close(True)
# excel.Quit()
def main():
# sheet name for data
sheet_name = 'act 05.01.2022' # update with sheet name from your file
# file path
f_path = Path.cwd() # file in current working directory
# f_path = Path(r'c:\...\Documents') # file located somewhere else
# excel file
f_name = r"C:\Users\szczepan.czarniak\Desktop\Visual Studio\1\act 05.01.2022.xlsx" # change to your Excel file name
# function calls
run_excel(f_path, f_name, sheet_name)
main()
f_path = Path.cwd()
f_name = 'act 05.01.2022.xlsx'
filename = f_path / f_name
# create excel object
excel = win32.gencache.EnsureDispatch('Excel.Application')
# excel can be visible or not
excel.Visible = True # False
wb = excel.Workbooks.Open(filename)
pvtTable = wb.Sheets("pivot_table").Range("A3").PivotTable
page_range_item = []
for i in pvtTable.PageRange:
page_range_item.append(str(i))
print(page_range_item)
pvtTable.PivotFields('open_loan_count_all', 'days_between_repayments').ClearAllFilters()
Your run_excel function is defined inside the pivot_table function therefore it's not in the scope of you main() function. Did not test this code but fixed the formatting below.
import win32com.client as win32
import pandas as pd
import numpy as np
from pathlib import Path
import re
import sys
win32c = win32.constants
df = pd.read_csv("act 05.01.2022.csv", encoding = 'unicode_escape', engine ='python')
df = df.dropna()
df.to_excel(r"C:\Users\szczepan.czarniak\Desktop\Visual Studio\1\act 05.01.2022.xlsx", sheet_name = 'act 05.01.2022', index = False)
def pivot_table(wb: object, ws1: object, pt_ws: object, ws_name: str, pt_name: str, pt_rows: list, pt_filters: list, pt_fields: list):
"""
wb = workbook1 reference
ws1 = worksheet1 that contain the data
pt_ws = pivot table worksheet number
ws_name = pivot table worksheet name
pt_name = name given to pivot table
pt_rows, pt_cols, pt_filters, pt_fields: values selected for filling the pivot tables
"""
# pivot table location
pt_loc = len(pt_filters) + 2
# grab the pivot table source data
pc = wb.PivotCaches().Create(SourceType=win32c.xlDatabase, SourceData=ws1.UsedRange)
# create the pivot table object
pc.CreatePivotTable(TableDestination=f'{ws_name}!R{pt_loc}C1', TableName=pt_name)
# selecte the pivot table work sheet and location to create the pivot table
pt_ws.Select()
pt_ws.Cells(pt_loc, 1).Select()
# Sets the rows, columns and filters of the pivot table
for field_list, field_r in ((pt_filters, win32c.xlPageField),
(pt_rows, win32c.xlRowField)):
for i, value in enumerate(field_list):
pt_ws.PivotTables(pt_name).PivotFields(value).Orientation = field_r
pt_ws.PivotTables(pt_name).PivotFields(value).Position = i + 1
# Sets the Values of the pivot table
for field in pt_fields:
pt_ws.PivotTables(pt_name).AddDataField(pt_ws.PivotTables(pt_name).PivotFields(field[0]), field[1], field[2]).NumberFormat = field[3]
# Visiblity True or Valse
pt_ws.PivotTables(pt_name).ShowValuesRow = True
pt_ws.PivotTables(pt_name).ColumnGrand = True
def run_excel(f_path: Path, f_name: str, sheet_name: str):
filename = f_path / f_name
# create excel object
excel = win32.gencache.EnsureDispatch('Excel.Application')
# excel can be visible or not
excel.Visible = True # False
# try except for file / path
try:
wb = excel.Workbooks.Open(filename)
except com_error as e:
if e.excepinfo[5] == -2146827284:
print(f'Failed to open spreadsheet. Invalid filename or location: {filename}')
else:
raise e
sys.exit(1)
# set worksheet
ws1 = wb.Sheets('Sales')
# Setup and call pivot_table
ws2_name = 'pivot_table'
wb.Sheets.Add().Name = ws2_name
ws2 = wb.Sheets(ws2_name)
# update the pt_name, pt_rows, pt_cols, pt_filters, pt_fields at your preference
pt_name = 'example' # pivot table name, must be a string
pt_rows = ['Genre'] # rows of pivot table, must be a list
# pt_cols = [] # columns of pivot table, must be a list
pt_filters = ['Year'] # filter to be applied on pivot table, must be a list
# [0]: field name [1]: pivot table column name [3]: calulation method [4]: number format (explain the list item of pt_fields below)
pt_fields = [['North America', 'Total Sales in North America', win32c.xlSum, '0'], # must be a list of lists
['Europe', 'Total Sales in Europe', win32c.xlSum, '0'],
['Japan', 'Total Sales in Japan', win32c.xlSum, '0'],
['Rest of World', 'Total Sales in Rest of World', win32c.xlSum, '0'],
['Global', 'Total Global Sales', win32c.xlSum, '0']]
# calculation method: xlAverage, xlSum, xlCount
pivot_table(wb, ws1, ws2, ws2_name, pt_name, pt_rows, pt_filters, pt_fields)
wb.Save() # save the pivot table created
# wb.Close(True)
# excel.Quit()
def main():
# sheet name for data
sheet_name = 'act 05.01.2022' # update with sheet name from your file
# file path
f_path = Path.cwd() # file in current working directory
# f_path = Path(r'c:\...\Documents') # file located somewhere else
# excel file
f_name = r"C:\Users\szczepan.czarniak\Desktop\Visual Studio\1\act 05.01.2022.xlsx" # change to your Excel file name
# function calls
run_excel(f_path, f_name, sheet_name)
main()
f_path = Path.cwd()
f_name = 'act 05.01.2022.xlsx'
filename = f_path / f_name
# create excel object
excel = win32.gencache.EnsureDispatch('Excel.Application')
# excel can be visible or not
excel.Visible = True # False
wb = excel.Workbooks.Open(filename)
pvtTable = wb.Sheets("pivot_table").Range("A3").PivotTable
page_range_item = []
for i in pvtTable.PageRange:
page_range_item.append(str(i))
print(page_range_item)
pvtTable.PivotFields('open_loan_count_all', 'days_between_repayments').ClearAllFilters()
### Pivot the dataset
pivot_df = pd.pivot(df, index =['Date'], columns ='Country', values =['NewConfirmed'])
## renaming the columns
pivot_df.columns = df['Country'].sort_values().unique()
wrbk = xlrd.open_workbook("D:Book1.xlsx")
idx = 0
book_1 = xlrd.open_workbook("D:Book2.xlsx")
sh_1 = book_1.sheet_by_name('Sheet4')
i = 0
for x in range(sh_1.nrows):
i = i + 1
if i >= sh_1.nrows:
break
if sh_1.cell(i, 2).value:
concat = sh_1.cell(i, 2).value
for y in range(len(wrbk.sheets())):
sht = wrbk.sheet_by_index(y)
for j in range(sht.ncols):
for cell in range(sht.nrows):
list = str(sht.cell(cell, j).value)
if list.__contains__(concat):
print(sh_1.cell(i, 2).value)
Im using this code to find a value in a workbook and then search that value in another workbook.
I'm using xlrd, the output is fine so far but i can't read and write with xlrd.i need suggestions to change this code from xlrd to openpyxl.
This defines a function to do the search and uses a Regular Expression to do the 'contains' match. Change the print to suit.
from openpyxl import load_workbook
import re
# open workbook
excel_file1 = 'D:Book1.xlsx'
wb1 = load_workbook(excel_file1) # wrbk
ws1 = wb1["Sheet1"]
excel_file2 = 'D:Book2.xlsx'
wb2 = load_workbook(excel_file2) # book_1
ws2 = wb2["Sheet4"] # sh_1
# fn to search all sheets in workbook
def myfind(wb,s):
for ws in wb.worksheets:
for c in range(1,ws.max_column+1):
for r in range(1,ws.max_row+1):
txt = ws.cell(r,c).value
if txt is None:
pass
elif re.search(s,txt):
print("Found",s,txt,ws,r,c)
# scan col C
for r in range(1,ws2.max_row+1):
s = ws2.cell(r, 3).value
if s is None:
pass
else:
print(r,s)
myfind(wb1,s)
I'm working on a program to split excel files into sections of 1000. I can't seem to get it to create a second excel file, as xlsxwriter doesn't create the second file.
from os.path import join, dirname, abspath
from xlrd.sheet import ctype_text
import csv
import os
import sys
import xlrd
import xlsxwriter
import xlwt
file_paths = sys.argv[1:]
draganddrop = ''.join(file_paths)
beginGrab = 0
counting = 0
endGrab = 1000
thousands = 0
if draganddrop == "":
fileName = raw_input("\nInput the file with extension\n>")
else:
fileName = draganddrop
stopPoint = fileName.index('.')
prepRev = fileName[stopPoint:]
preName = fileName[:stopPoint]
if prepRev == ".csv":
excelFile = xlsxwriter.Workbook(preName + '.xlsx')
worksheet = excelFile.add_worksheet()
with open(fileName,'rb') as f:
content = csv.reader(f)
for index_col, data_in_col in enumerate(content):
for index_row, data_in_cell in enumerate(data_in_col):
worksheet.write(index_col,index_row,data_in_cell)
excelFile.close()
fileName = (preName + '.xlsx')
delMe = 1
print("Temporary Convert to xlsx done.\n")
stopPoint = fileName.index('.')
prepRev = fileName[0:stopPoint]
fname = join(dirname(abspath(__file__)), fileName)
xl_workbook = xlrd.open_workbook(fname)
sheet_names = xl_workbook.sheet_names()
xl_sheet = xl_workbook.sheet_by_name(sheet_names[0])
book = xlwt.Workbook(encoding="utf-8")
worksheet = book.add_sheet("Results", cell_overwrite_ok=True)
workbook = xlrd.open_workbook(fileName)
for sheet in workbook.sheets():
for row in range(sheet.nrows):
row = int(row)
if(int(row)>1000):
subDivide = int(row) / 1000
while(thousands != subDivide + 1):
thousands = thousands + 1
counting = 0
totalName = preName + "_" + str(thousands) + ".xlsx"
print(totalName)
excelFile = xlsxwriter.Workbook(str(totalName))
worksheet = excelFile.add_worksheet()
with open(totalName,'rb') as f:
col = xl_sheet.col_slice(0,1,10101010)
for idx, cell_obj in enumerate(col, start=beginGrab):
counting = counting + 1
if(counting == 1000):
break
cell_type_str = ctype_text.get(cell_obj.ctype, 'unknown type')
cell_obj_str = str(cell_obj)
telePhone = (cell_obj_str[7:19])
worksheet.write(idx+1, 0, "1" + telePhone)
worksheet.write(0,0, "Telephone Number")
beginGrab = thousands * 1000
endGrab = beginGrab + 1000
excelFile.close()
excelFile = None
else:
print("Mate, this is Tiny!")
print ("Ding! Job Done!")
I've been rubber ducking this and I can't find where I'm at fault.
EDIT:
SOLVED!!
By creating a sheet and then closing it, the program can then grasp it. I will probably make a git issue about this.
if prepRev == ".csv":
totalName = preName + '.xlsx'
excelFile = xlsxwriter.Workbook(totalName)
excelFile.close()
Closing it lets open see it while it still contains the same info.
excelFile = xlsxwriter.Workbook(totalName)
worksheet = excelFile.add_worksheet()
with open(fileName,'rb') as f:
Doesn't the save/close line need to be within the while loop? Otherwise it looks like it will only save either the first/last item:
while(thousands != subDivide + 1):
# write file
excelFile.close()
that line is probably the reason why you cannot read back your file and your script crashes:
fname = join(dirname(abspath('__file__')), '%s' % fileName)
'__file__' shouldn't have quotes. I'd do:
fname = join(dirname(abspath(__file__)), fileName)
I'm trying to read a string from a text file and write it into an excel sheet without overwriting. I found somewhere that to update excel sheets, openpyxl in used. But my script just overwrites the entire sheet. I want other data to be the same.
python script:
from openpyxl import Workbook
file_name="D:\\a.txt"
content={}
with open(file_name) as f:
for line in f:
(key,value)=line.split(":")
content[key]=value
wb=Workbook()
ws=wb.active
r = 2
for item in content:
ws.cell(row=r, column=3).value = item
ws.cell(row=r, column=4).value = content[item]
r += 1
wb.save("D:\\Reports.xlsx")
Excel sheet before script:
Excel sheet after script :
How do I write the data to excel with overwriting other things ? Help.
Overwriting is due to both saving the file with wb.save() and your hard coded starting row number r = 2.
1) If you don't care of overwriting the rows each time you execute your script you could use something like this:
from openpyxl import Workbook
from openpyxl import load_workbook
path = 'P:\Desktop\\'
file_name = "input.txt"
content= {}
with open(path + file_name) as f:
for line in f:
(key,value)=line.split(":")
content[key]=value
wb = load_workbook(path + 'Reports.xlsx')
ws = wb.active
r = 2
for item in content:
ws.cell(row=r, column=3).value = item
ws.cell(row=r, column=4).value = content[item]
r += 1
wb.save(path + "Reports.xlsx")
2) If you care about overwriting rows and the column numbers (3 & 4) you could try something like this:
from openpyxl import Workbook
from openpyxl import load_workbook
path = 'P:\Desktop\\'
file_name = "input.txt"
content= []
with open(path + file_name) as f:
for line in f:
key, value = line.split(":")
content.append(['','', key, value]) # adding empty cells in col 1 + 2
wb = load_workbook(path + 'Reports.xlsx')
ws = wb.active
for row in content:
ws.append(row)
wb.save(path + "Reports.xlsx")