I am trying to copy the data from multiple excel into one excel. I am novice to python and openpyxl. So i have opened each file and went row by row and copied them. I want to do this with multiple files. How do i loop through row and columns and copy the data consider the column in all the files are same order?
import openpyxl as xl
from openpyxl import workbook
incident_wb = xl.load_workbook('incident resolved yesterday.xlsx')
incident_sheet = incident_wb['Page 1']
combined_wb = xl.Workbook()
combined_sheet = combined_wb.active
combined_sheet.title = "combined_sheet"
combined_wb.save('combined_sheet.xlsx')
for row in range(1, incident_sheet.max_row+1):
incident_no = incident_sheet.cell(row,1)
opened_date = incident_sheet.cell(row,2)
shrt_desc = incident_sheet.cell(row,3)
requester = incident_sheet.cell(row,4)
incdnt_type = incident_sheet.cell(row,5)
priority = incident_sheet.cell(row,6)
assgn_grp = incident_sheet.cell(row,7)
assgn_to = incident_sheet.cell(row,8)
updated = incident_sheet.cell(row,9)
status = incident_sheet.cell(row,10)
sub_status = incident_sheet.cell(row,11)
##copy the data into the new sheet
incident_no_1 = combined_sheet.cell(row,1)
incident_no_1.value = incident_no.value
opened_date_1 = combined_sheet.cell(row,2)
opened_date_1.value = opened_date.value
shrt_desc_1 = combined_sheet.cell(row,3)
shrt_desc_1.value = shrt_desc.value
requester_1 = combined_sheet.cell(row,4)
requester_1.value = requester.value
incdnt_type_1 = combined_sheet.cell(row,5)
incdnt_type_1.value = incdnt_type.value
priority_1 = combined_sheet.cell(row,6)
priority_1.value = priority.value
assgn_grp_1 = combined_sheet.cell(row,7)
assgn_grp_1.value = assgn_grp.value
assgn_to_1 = combined_sheet.cell(row,8)
assgn_to_1.value = assgn_to.value
updated_1 = combined_sheet.cell(row,9)
updated_1.value = updated.value
status_1 = combined_sheet.cell(row,10)
status_1.value = status.value
sub_status_1 = combined_sheet.cell(row,11)
sub_status_1.value = sub_status.value
##print(f"The incident resolved yesterday {incident_no.value}")
combined_wb.save('combined_sheet.xlsx')
An alternative approach would be to build a list of date from multiple excel files and then write it to another file.
As a proof of concept:
import openpyxl as xl
from openpyxl import workbook
def provide_data(workbookName, sheetName):
wb = xl.load_workbook(workbookName)
sheet = wb[sheetName]
return [[y.value for y in x] for x in sheet.iter_rows()]
# This creates an array of rows, which contain an array of cell values.
# It will be much better to provide mapping for cells and return business object.
def save_data(list_of_sheets):
combined_wb = xl.Workbook()
combined_sheet = combined_wb.active
combined_sheet.title = "combined_sheet"
for sheet in list_of_sheets:
for row in sheet:
combined_sheet.append(row) # combining multiple rows.
combined_wb.save('combined_sheet.xlsx')
workSheetsToCopy = [['incident resolved yesterday.xlsx', 'Page 1'], ['other.xlsx', 'Page 1']]
workSheetsToCopy = [provide_data(x[0], x[1]) for x in workSheetsToCopy]
save_data(workSheetsToCopy)
Related
Background:I have a large 40MB XLSX file that contains client data which is Grouped over multiple levels, like so:
Expanded -
Not Expanded (sorry about the terrible dummy data!) -
Objective:I would like to split Client A, B C etc... and all their respective underlying data into separate sheets (named 'Client A' etc...) in a Workbook.
Question:Am I correct in assuming that there is no python library that would help with this (e.g., xlsxwriter) and that I will likely have to save into multiple pandas df before splitting and writing to the xlsx file?
Sample Data:Here is a link to some randomized sample data. In this file you will see only 1 client (the total row can be ignored) however imagine the normal file having 40 clients / groupings and sub levels.
Sample Code: this function takes the '.xlsxand writes each grouping to an appropriately named tab (e.g., 'Client A') to a separate Worksheet in a new.xlsx`. The issue with this code is that because I am basically going through and copying each cell individually, I didn't think to consider more holistically however to ensure the Groupings/Levels would be preserved. I think this code needs a complete re-write, and welcome feedback
import openpyxl
from copy import copy
from openpyxl import load_workbook
columns=['A','B','C','D','E','F','G','H','I','J','K','L']
def copy_cell(ws, row,ws_row,ws1):
for col in columns:
ws_cell=ws1[col+str(ws_row)]
new_cell = ws[col+str(row)]
if ws_cell.has_style:
new_cell.font = copy(ws_cell.font)
new_cell.border = copy(ws_cell.border)
new_cell.fill = copy(ws_cell.fill)
new_cell.number_format = copy(ws_cell.number_format)
new_cell.protection = copy(ws_cell.protection)
new_cell.alignment = copy(ws_cell.alignment)
wb1 = openpyxl.load_workbook('annonamized_test_data_to_be_split.xlsx')
ws1=wb1.active
indexs=[]
clients=[]
index=1
while ws1['A'+str(index)]:
if str(ws1['A'+str(index)].alignment.indent)=='0.0':
indexs.append(index)
clients.append(ws1['A'+str(index)].value)
if ws1['A'+str(index)].value is None:
indexs.append(index)
break
index+=1
wb1.close()
wb = openpyxl.Workbook()
ws=wb.active
start_index=1
headers=['Ownership Structure', 'Fee Schedule', 'Management Style', 'Advisory Firm', 'Inception Date', 'Days in Time Period', 'Adjusted Average Daily Balance (No Div, USD)', 'Assets Billed On (USD)',
'Effective Billing Rate', 'Billing Fees (USD)', 'Bill To Account', 'Model Type']
for y,index in enumerate(indexs):
try:
client=0
if len(clients[y])>=32:
client=clients[y][:31]
else:
client=clients[y]
wb.create_sheet(client)
ws=wb[client]
ws.column_dimensions['A'].width=35
ws.append(headers)
row_index=2
for i in range(start_index,indexs[y+1]):
ws.append([ws1[col+str(i)].value for col in columns])
copy_cell(ws,row_index,i,ws1)
row_index+=1
start_index=indexs[y+1]
except:
pass
wb.save('split_data.xlsx')
wb.close()
try:
wb1 = openpyxl.load_workbook('split_data.xlsx')
a=wb1['Sheet']
wb1.remove(a)
a=wb1['Sheet1']
wb1.remove(a)
wb1.save('split_data.xlsx')
wb1.close()
except:
pass
Please can someone point me in the right direction of a resource that might teach me how to achieve this?
from openpyxl import load_workbook
def get_client_rows(sheet):
"""Get client rows.
Skip header and then look for row dimensions without outline level
"""
return [row[0].row for row in sheet.iter_rows(2) if row[0].alignment.indent == 0.0]
return [
row_index
for row_index, row_dimension in sheet.row_dimensions.items()
if row_index > 1 and row_dimension.outline_level == 0
]
def delete_client_block(sheet, start, end):
"""
Delete rows starting from up to and including end.
"""
for row in range(start, end + 1):
sheet.row_dimensions.pop(row, None)
sheet.delete_rows(start, end - start + 1)
def split_workbook(input_file, output_file):
"""
Split workbook each main group into its own sheet.
Not too loose any formatting we copy the current sheet and remove all rows
which do not belong to extacted group.
"""
try:
workbook = load_workbook(input_file)
data_sheet = workbook.active
client_rows = get_client_rows(data_sheet)
for index, client_row in enumerate(client_rows):
# create new sheet for given client, shorten client as it might be too long
client_sheet = workbook.copy_worksheet(data_sheet)
client_sheet.title = data_sheet.cell(client_row, 1).value[:32]
# delete rows after current client if available
if index < len(client_rows) - 1:
row_after_client = client_rows[index + 1]
delete_client_block(
client_sheet, row_after_client, client_sheet.max_row
)
# delete rows before current client if available
if index > 0:
first_client_row = client_rows[0]
delete_client_block(
client_sheet, first_client_row, client_row - first_client_row + 1
)
# move left over dimensions to top of the sheet
for row_index in list(client_sheet.row_dimensions.keys()):
# skip header row dimension
if row_index > first_client_row - 1:
row_dimension = client_sheet.row_dimensions.pop(row_index)
new_index = row_index - client_row + first_client_row
row_dimension.index = new_index
client_sheet.row_dimensions[new_index] = row_dimension
del workbook[data_sheet.title]
workbook.save(output_file)
finally:
workbook.close()
if __name__ == "__main__":
# input_file = "annonamized_test_data_to_be_split.xlsx"
input_file = 'partial_Q1_Client_Billing_Data.xlsx'
# output_file = "split_data.xlsx"
output_file = "splitting_full_data.xlsx"
split_workbook(input_file, output_file)
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)
When I use gspread_dataframe and gspread to export data from a Jupyter Notebook to a Google Spreadsheet, rows are shuffled, which is not what I want. Can anyone help?
emp_uniq = gspread_df['E_code'].unique() dict_e_code = {} x_df = pd.DataFrame()
for emp in list(emp_uniq):
dict_e_code[emp] = gspread_df[gspread_df['E_code']==emp]
a = dict_e_code[emp][["Month","E_code","Allocation_ID","Project","Effective_days","Percentage_Util","Onsite/Offshore","Mapping","Payroll"]]
a_fin = a.groupby(['Month','E_code','Project','Allocation_ID','Percentage_Util','Onsite/Offshore']).sum()['Effective_days']
new_df = a_fin.to_frame().reset_index()
new_df['Percentage_Util'] = (new_df['Effective_days']/new_df['Effective_days'].sum())*100
x_df = x_df.append(new_df)
x_df.reset_index(inplace=True)
x_df.drop(['index'],axis=1,inplace=True)
sheet = client.open(input("Please Enter Main Spreadsheet as Output Data: ")) worksheet_new = sheet.worksheet(input("Please Enter Sheet Name as Output Data:"))
existing = get_as_dataframe(worksheet_new)
a = existing.append(x_df)
gsdf.set_with_dataframe(worksheet_new, a)
I have a series of CSV file like this one. I’m trying to convert and merge them into an xlsx file with python and openpyxl with this code:
import csv
import openpyxl
import glob
csvpath = 'C:/Users/Lorenzo/Downloads/CSV/'
csvfiles = glob.glob(csvpath + '*.csv')
data = input('Inserisci data Simulazione: ')
destinationfilepath = 'C:/Users/Lorenzo/Desktop/Simulazione_' + data + '.xlsx'
wb = openpyxl.Workbook()
for i in range(len(csvfiles)):
filename = csvfiles[i]
reader = csv.reader(open(filename), delimiter=',')
csvname = filename[len(csvpath):-4]
ws1 = wb.create_sheet(csvname)
k=0
for row in reader:
if k==0:
ws1.append(row)
else:
g=0
for cell in row:
c= ws1.cell(row=k, column=g)
c.value = float(cell)
g=g+1
k=k+1
ws1['A1'] = 'Iteration'
ws1['B1'] = 'CD'
ws1['C1'] = 'CL'
ws1['D1'] = 'CL_F'
ws1['E1'] = 'CL_R'
ws1['F1'] = 'CM'
sheet = wb['Sheet']
wb.remove(sheet)
wb.save(destinationfilepath)
The code runs but in most cells (and strangely enough not in all cells) I get the error “number stored as text” despite using the command float like suggested in this and similar topics.
What is that I'm doing wrong?
I am trying to use and Add-In for Excel that gets removed when I use win32com.client forcing me to restart my computer. I have found a work around using xlrd, openpyxl, and pandas but I have run into a completely new issue.
I first open Excel with the pandas and read through the file extracting the information that I require.
xl = pandas.ExcelFile(xlsx)
sheets = xl.sheet_names
df = xl.parse(sheets[2])
I then have to go into the same workbook and update the Meter Name and the date.
for i, value in enumerate(dataList):
wb = openpyxl.load_workbook(xlsx)
worksheets = wb.sheetnames
worksheet = wb.get_sheet_by_name(worksheets[0])
rowCoordinate = i
meterName = value[0]
creationDate = value[1]
units = value[2]
worksheet.cell(row=1, column=2).value = meterName
wb.save(copyXlsx)
dateList = []
for k, dateRange in enumerate(value[3]):
sDate = dateRange[0]
eDate = dateRange[1]
wb = openpyxl.load_workbook(copyXlsx)
worksheets = wb.sheetnames
worksheet = wb.get_sheet_by_name(worksheets[0])
worksheet.cell(row=2, column=2).value = sDate
worksheet.cell(row=3, column=2).value = eDate
wb.save(copyXlsx1)
print meterName, dateRange
xl1 = pandas.ExcelFile(copyXlsx1)
sheets = xl1.sheet_names
df = xl.parse(sheets[0])
print df
My issue is that the excel file opens and write the information perfectly. but pandas has all the header information updated but the numbers are the same from the original document. I have gone in and explored the Intermediate Excel Document and it doesn't match the number pandas shows