Facing the error "BadZipFile: File is not a zip file" when loading excel workbook using openpyxl load_workbook function. How do I solve this error?
workbook = r'C:\Desktop\Test.xlsx'
worksheet = 'Data'
# create a Pandas Excel writer using XlsxWriter as the engine.
writer = pd.ExcelWriter(workbook, engine='openpyxl')
wb = load_workbook(workbook)
writer.book = workbook
writer.sheets = {x.title: x for x in wb.worksheets}
ws = writer.sheets[worksheet]
for i in range(len(vehicle_sales)):
row = list(vehicle_sales.iloc[i])
for j in range(len(vehicle_sales.columns)):
value = row[j]
ws.cell(i+2, j+1, value)
xl.writer.excel.save_workbook(wb, workbook)
The excel files were in read-only mode. I saved the file as a new file and load_workbook worked.
Related
Here is a multi sheet excel file opened and operated on one sheet taken in a dataframe and then copied back. Now, a new sheet (sheet1) is being created while doing this. Objective however is to overwrite the old target sheet. When I am trying deleting the sheet before pasting data from dataframe, it says 'sheet' does not exist.
Here is the code:
import openpyxl as op
import pandas as pd
basePath = filePath
wbk = op.load_workbook(basePath + "file.xlsx")
writer = pd.ExcelWriter(basePath + "file.xlsx", engine = 'openpyxl', mode="a", if_sheet_exists="replace")
writer.book = wbk
df = pd.read_excel(basePath + "file.xlsx", sheet_name="sheet")
df.insert(0,"newCol2","")
#wbk.remove_sheet(wbk.get_sheet_by_name('sheet'))
df.to_excel(writer, sheet_name = 'sheet', index=False)
writer.save()
writer.close()
What am I doing wrong?
How can I append a row at the top of an excel sheet? Goal as follows:
The file itself is written by using pandas.df.to_excel as follows:
import pandas
with pandas.ExcelWriter(output_filename) as writer:
for file in files:
df = pandas.read_csv(file)
df.to_excel(writer, sheet_name=file.replace(".csv", "").replace("_", " ").title(), index=False)
Here is one way to do it using XlsxWriter as the Excel engine:
with pandas.ExcelWriter(output_filename, engine='xlsxwriter') as writer:
for file in files:
df = pandas.read_csv(file)
sheet_name = file.replace(".csv", "").replace("_", " ").title()
df.to_excel(writer, sheet_name=sheet_name, index=False, startrow=1)
worksheet = writer.sheets[sheet_name]
worksheet.write('A1', 'Here is some additional text')
You can use openpyxl to edit your Excel file afterwards:
import contextlib
import openpyxl
import pandas as pd
new_row = "THIS ROW IS APPENDED AFTER THE FILE IS WRITTEN BY PANDAS"
with contextlib.closing(openpyxl.open(output_filename)) as wb:
for file in files:
sheet_name = file.replace(".csv", "").replace("_", " ").title()
sheet = wb[sheet_name]
sheet.insert_rows(0)
sheet["A1"] = new_row
wb.save(output_filename)
my propose:
if excel file not exist, create it and copy data table to it;
if excel file exist, copy to data table to new sheet.
but following code running, only copy to data to new sheet, original sheet in excel file was removed.
import os
import pandas as pd
import openpyxl
f_name = "123.xlsx" #target excel file
if os.path.exists(f_name):
"""if excel file exist, added table to another sheet"""
wb = openpyxl.load_workbook(f_name) #load excel file
writer = pd.ExcelWriter(f_name, engine="openpyxl")
writer.wb = wb
df = pd.DataFrame(pd.read_excel("table_2.xlsx")) #get table to be added excel file
df.to_excel(writer, sheet_name="sheet2",index=False) #write to another sheet
writer.save()
writer.close()
else:
"""if excel file not exit, create it"""
df_1 = pd.DataFrame() # create excel file
df_1.to_excel(f_name)
writer = pd.ExcelWriter(f_name)
df_2 = pd.DataFrame(pd.read_excel("table_1.xlsx")) # get table_1
df_2.to_excel(writer, sheet_name="sheet1",index=False) # write table_1 into excel file
writer.save()
writer.close()
import os
import pandas as pd
import openpyxl
f_name = "123.xlsx" #target excel file
if os.path.exists(f_name):
"""if excel file exist, added table to another sheet"""
wb = openpyxl.load_workbook(f_name) #load excel file
writer = pd.ExcelWriter(f_name, engine="openpyxl") #assign engine
writer.book = wb #overwrite if no this
df = pd.DataFrame(pd.read_excel("table_2.xlsx")) #get table to be added excel file
df.to_excel(writer, sheet_name="table_2",index=False) #write to another sheet
writer.save()
writer.close()
else:
"""if excel file not exit, create it"""
df_1 = pd.DataFrame() # create excel file
df_1.to_excel(f_name)
writer = pd.ExcelWriter(f_name)
df_2 = pd.DataFrame(pd.read_excel("table_1.xlsx")) # get table_1
df_2.to_excel(writer, sheet_name="table_1",index=False) # write table_1 into excel file
writer.save()
writer.close()
Below creates a file and then fills in the excel. I would like to create an excel file with a condition based on a single column and redeposit the excel with a prefix of the column name.
So return only where columnX = i and create and save excel file i1_CCBHC_MONTHLY_CLAIMS.XLSX
i2_CCBHC_MONTHLY_CLAIMS.XLSX
I have the build of the large "parent" excel file.
filename = 'CCBHC_Monthly_Claims.xlsx'
if os.path.isfile(filename):
wb = xw.Book(filename)
ws = wb.sheets['CCBHC_DATA']
ws.range('A1').options(index=False).value = df_ora
wb = xw.Book(filename)
xw.apps[0].quit()
else:
writer = pd.ExcelWriter(filename, engine='xlsxwriter')
*df_ora.to_excel(writer, sheet_name='CCBHC_DATA',index=False)
wb = xw.Book(filename)
ws = wb.sheets['CCBHC_DATA']
ws.range('A1').options(in*dex=False).value = df_ora
wb = xw.Book(filename)
xw.apps[0].quit()
How to find total number of rows using XLWT or XLRD in Python? I have an excel file(accounts.xls) and would like to append rows in it.
I am getting an error here - AttributeError: 'Sheet' object has no attribute 'write'
from xlrd import open_workbook
from xlwt import Workbook
def saveWorkSpace(fields,r):
wb = open_workbook('accounts.xls')
ws = wb.sheet_by_index(0)
r = ws.nrows
r += 1
wb = Workbook()
ws.write(r,0,fields['name'])
ws.write(r,1,fields['phone'])
ws.write(r,2,fields['email'])
wb.save('accounts.xls')
print 'Wrote accounts.xls'
Here is the solution of the above question
import xlrd
import xlwt
from xlutils.copy import copy
def saveWorkSpace(fields):
rb = xlrd.open_workbook('accounts.xls',formatting_info=True)
r_sheet = rb.sheet_by_index(0)
r = r_sheet.nrows
wb = copy(rb)
sheet = wb.get_sheet(0)
sheet.write(r,0,fields['name'])
sheet.write(r,1,fields['phone'])
sheet.write(r,2,fields['email'])
wb.save('accounts.xls')
print 'Wrote accounts.xls'
Python Program to add Values to the last data row an Excel sheet.
from xlwt import Workbook
from xlrd import open_workbook
import openpyxl
# Function to get the last RowCount in the Excel sheet , change the index of the sheet accordingly to get desired sheet.
def getDataColumn():
#define the variables
rowCount=0
columnNumber=0
wb = open_workbook('C:\\Temp\\exp\\data.xlsx')
ws = wb.sheet_by_index(0)
rowCount = ws.nrows
rowCount+=1
columnNumber=1
print(rowCount)
writedata(rowCount,columnNumber)
#Data to specified cells.
def writedata(rowNumber,columnNumber):
book = openpyxl.load_workbook('C:\\Temp\\exp\\data.xlsx')
sheet = book.get_sheet_by_name('Sheet1')
sheet.cell(row=rowNumber, column=columnNumber).value = 'Appended Data'
book.save('C:\\Temp\\exp\\data.xlsx')
print('saved')
getDataColumn()
exit()