Write to excel files python

I need to write some data from my program to an Excel spreadsheet. I’ve searched online and there seem to be many packages available (xlwt, XlsXcessive, openpyxl). Others suggest writing to a .csv file (never used CSV and don’t really understand what it is).

The program is very simple. I have two lists (float) and three variables (strings). I don’t know the lengths of the two lists and they probably won’t be the same length.

I want the layout to be as in the picture below:

The pink column will have the values of the first list and the green column will have the values of the second list.

So what’s the best way to do this?

I am running Windows 7 but I won’t necessarily have Office installed on the computers running this program.

import xlwt

x=1
y=2
z=3

list1=[2.34,4.346,4.234]

book = xlwt.Workbook(encoding="utf-8")

sheet1 = book.add_sheet("Sheet 1")

sheet1.write(0, 0, "Display")
sheet1.write(1, 0, "Dominance")
sheet1.write(2, 0, "Test")

sheet1.write(0, 1, x)
sheet1.write(1, 1, y)
sheet1.write(2, 1, z)

sheet1.write(4, 0, "Stimulus Time")
sheet1.write(4, 1, "Reaction Time")

i=4

for n in list1:
    i = i+1
    sheet1.write(i, 0, n)

book.save("trial.xls")

I wrote this using all your suggestions. It gets the job done but it can be slightly improved.

How do I format the cells created in the for loop (list1 values) as scientific or number?

I do not want to truncate the values. The actual values used in the program would have around 10 digits after the decimal.

The following sections explain how to write various types of data to an Excel
worksheet using XlsxWriter.

import xlsxwriter

workbook = xlsxwriter.Workbook('write_data.xlsx')
worksheet = workbook.add_worksheet()

worksheet.write(0, 0, 1234)     # Writes an int
worksheet.write(1, 0, 1234.56)  # Writes a float
worksheet.write(2, 0, 'Hello')  # Writes a string
worksheet.write(3, 0, None)     # Writes None
worksheet.write(4, 0, True)     # Writes a bool

workbook.close()

import xlsxwriter

workbook = xlsxwriter.Workbook('write_list.xlsx')
worksheet = workbook.add_worksheet()

my_list = [1, 2, 3, 4, 5]

for row_num, data in enumerate(my_list):
    worksheet.write(row_num, 0, data)

workbook.close()

import xlsxwriter

workbook = xlsxwriter.Workbook('write_list.xlsx')
worksheet = workbook.add_worksheet()

my_list = [1, 2, 3, 4, 5]

for col_num, data in enumerate(my_list):
    worksheet.write(0, col_num, data)

workbook.close()

import xlsxwriter

workbook = xlsxwriter.Workbook('write_list.xlsx')
worksheet = workbook.add_worksheet()

my_list = [[1, 1, 1, 1, 1],
           [2, 2, 2, 2, 1],
           [3, 3, 3, 3, 1],
           [4, 4, 4, 4, 1],
           [5, 5, 5, 5, 1]]

for row_num, row_data in enumerate(my_list):
    for col_num, col_data in enumerate(row_data):
        worksheet.write(row_num, col_num, col_data)

workbook.close()

import xlsxwriter

workbook = xlsxwriter.Workbook('write_list.xlsx')
worksheet = workbook.add_worksheet()

my_list = [1, 2, 3, 4, 5]

worksheet.write_row(0, 1, my_list)
worksheet.write_column(1, 0, my_list)

workbook.close()

import xlsxwriter

workbook = xlsxwriter.Workbook('write_dict.xlsx')
worksheet = workbook.add_worksheet()

my_dict = {'Bob': [10, 11, 12],
           'Ann': [20, 21, 22],
           'May': [30, 31, 32]}

col_num = 0
for key, value in my_dict.items():
    worksheet.write(0, col_num, key)
    worksheet.write_column(1, col_num, value)
    col_num += 1

workbook.close()

import pandas as pd

# Create a Pandas dataframe from the data.
df = pd.DataFrame({'Data': [10, 20, 30, 20, 15, 30, 45]})

# Create a Pandas Excel writer using XlsxWriter as the engine.
writer = pd.ExcelWriter('pandas_simple.xlsx', engine='xlsxwriter')

# Convert the dataframe to an XlsxWriter Excel object.
df.to_excel(writer, sheet_name='Sheet1')

# Close the Pandas Excel writer and output the Excel file.
writer.close()

def write_uuid(worksheet, row, col, uuid, format=None):
    return worksheet.write_string(row, col, str(uuid), format)

#                           match,     action()
worksheet.add_write_handler(uuid.UUID, write_uuid)

my_uuid = uuid.uuid3(uuid.NAMESPACE_DNS, 'python.org')

# Write the UUID. This would raise a TypeError without the handler.
worksheet.write('A1', my_uuid)

worksheet.add_write_handler(int,   test_number_range)
worksheet.add_write_handler(float, test_number_range)

def write(self, row, col, *args):

    # The first arg should be the token for all write calls.
    token = args[0]

    # Get the token type.
    token_type = type(token)

    # Check for any user defined type handlers with callback functions.
    if token_type in self.write_handlers:
        write_handler = self.write_handlers[token_type]
        function_return = write_handler(self, row, col, *args)

        # If the return value is None then the callback has returned
        # control to this function and we should continue as
        # normal. Otherwise we return the value to the caller and exit.
        if function_return is None:
            pass
        else:
            return function_return

    # Check for standard Python types, if we haven't returned already.
    if token_type is bool:
        return self.write_boolean(row, col, *args)

    # Etc. ...

def my_function(worksheet, row, col, token, format=None):
    return worksheet.write_string(row, col, token, format)

def my_function(worksheet, row, col, token, *args):
    return worksheet.write_string(row, col, token, *args)

def hide_password(worksheet, row, col, string, format=None):
    if col == 1 and row > 0:
        return worksheet.write_string(row, col, '****', format)
    else:
        return worksheet.write_string(row, col, string, format)

def ignore_nan(worksheet, row, col, number, format=None):
    if math.isnan(number):
        return worksheet.write_blank(row, col, None, format)
    else:
        # Return control to the calling write() method.
        return None

def ignore_nan(worksheet, row, col, number, format=None):
    if math.isnan(number):
        return 0
    else:
        # Return control to the calling write() method.
        return None

Python Excel Writer: Create, Write(Text, Number, Formula), Modify, Save, Apply settings, Merge- unmerge cells and more

With
the help of openpyxl module we can also write to excel file in python.
The process is somewhat similar to reading an excel spreadsheet in
python. With python Excel writer, we will Create excel sheets, write text, numbers and formula in cells. After modifying we will save workbook. We will also add and delete sheets in a an excel workbook, apply setting, fonts and styles, set width and height of cells and areas, merge and unmerge cells. We can create any type of excel file, having hundreds
and thousands of columns and rows of data. Writing to excel files is a
necessity which no one can deny. There may be many cases for all
professionals from a computer operator to a data scientist that one has
to write to an excel spreadsheet in python. Here is the solution.

If you want to Read, Write and Manipulate(Copy, cut, paste, delete or search for an item or value etc) Excel files in Python with simple and practical examples I will suggest you to see this simple and to the point

Python Excel Openpyxl Course with examples about how to deal with MS Excel files in Python. This video course teaches efficiently how to manipulate excel files and automate tasks.

Everything you do in Microsoft Excel, can be automated with Python. So why not use the power of Python and make your life easy. You can make intelligent and thinking Excel sheets, bringing the power of logic and thinking of Python to Excel which is usually static, hence bringing flexibility in Excel and a number of opportunities.

Automate your Excel Tasks and save Time and Effort. You can save dozens or hundreds of hours by Python Excel Automation with just a single click get your tasks done with in seconds which used to take hours of Manual Excel and Data Entry Work.

Python Excel Create and Save files:

First we will learn how to create and save excel files with python.
First we will create an excel file.

First step will be to import openpyxl
module.

>>> import openpyxl

Next we will create an excel file or
technically a Workbook.

>>> mywb =
openpyxl.Workbook()

The above code will create a work book with one sheet in the beginning.
We can check the number of sheets with the following code, see which
sheet is active and what is the title of the active sheet. In this case
we have only one sheet, hence it will be the only answer.

>>>
mywb.get_sheet_names()

[‘Sheet’]

>>> sheet =
mywb.active

>>> sheet.title

‘Sheet’

We can also set the title of the
sheet, see the example given below.

>>>
sheet.title = ‘MyNewTitle’

>>>
wb.get_sheet_names()

[‘MyNewTitle’]

>>>mywb.save(‘NewExcelFile.xlsx’)

If you open your root folder or
current working directory, you will find a new excel file, with name
NewExcelFile, having one sheet with title MyNewTitle.

Loading an already existing excel file in Python and saving a
copy of it:

Whenever you load an already existing Excel file in memory, and modify
the contents, either sheets or cells, or creating whole sheets, or
deleting sheets, or any modification which could be done, you will have
to call save( ) method to save the file. If you don’t do so, any
modification will be lost. 

>>> import openpyxl

>>>
mywb = openpyxl.load_workbook(‘filetest.xlsx’)

>>>
sheet = mywb.active

>>>
sheet.title = ‘Working on Save as’

>>>
mywb.save(‘example_filetest.xlsx’)

In the code above you noticed that we
loaded already existing file, changed sheet title and saved its copy
with a different name. In this case original file plus this new file
will be in your working directory, which is usually your python root
folder. Open it and see the new copy. 

When you work on an excel spreadsheet
in python, its always better to save it with a different file name, so
that the original is always there, in case any mishap happens, for
example any bug in code, or mistake in saving, or writing.

Creating and Removing Sheets in Excel:

For creating new sheets in a
workbook, we use create_sheet( ) method. 

For deleting a sheet we use
remove_sheet( ) method.

>>>
import
openpyxl

>>> mywb =
openpyxl.Workbook()

>>> mywb.get_sheet_names()

[‘Sheet’]

>>>
mywb.create_sheet()

<Worksheet «Sheet1»>

>>> mywb.get_sheet_names()

[‘Sheet’, ‘Sheet1’]

>>>
wb.create_sheet(index=0, title=’1st
Sheet’)

<Worksheet «1st Sheet»>

>>>
mywb.get_sheet_names()

[‘1st Sheet’, ‘Sheet’, ‘Sheet1’]

>>>mywb.create_sheet(index=2,
title=’2nd
Sheet’)

<Worksheet «2nd Sheet»>

>>>mywb.get_sheet_names()

[‘1st Sheet’, ‘Sheet’, ‘2nd Sheet’,
‘Sheet1’]

Create sheet creates a new sheet,
which is by default the last sheet in the workbook. However, we can
specify the position of the new sheet with index number and we can also
pass a string as the title of new sheet. Keep in mind, the first sheet
will have index 0, second will have index 1 and so on.

Removing sheets from Excel Workbook:

When we want to remove any specific
sheet from an excel workbook, we will use method remove_sheet( )

>>>mywb.get_sheet_names()

[‘1st Sheet’, ‘Sheet’, ‘2nd Sheet’,
‘Sheet1’]

This is to see the number of sheets and their names, now working with
removing or deleting sheets.

>>>
mywb.remove_sheet(mywb.get_sheet_by_name(‘1st Sheet’))

>>>
mywb.remove_sheet(mywb.get_sheet_by_name(‘Sheet1’))

>>>
mywb.get_sheet_names()

[‘Sheet’, ‘2nd Sheet’]

It is very obvious that after
deleting the two sheets from four sheets, only two sheets are left.
remove_sheet method takes a worksheet object not name of the sheet,
instead of creating an object to that specific worksheet and then
removing it, we call get_sheet_by_name( ) and pass it the name of
sheet, the value it returns is the input argument of remove_sheet( )
method. In the end, use save( ) method to save the file after
modification. In this case removal of worksheets.

Python excel Writing Values in Cells:

Now we will see how to write values
to particular cells in an excel worksheet. Ofcourse we should know the
address of the cell where we want to write. 

>>> import openpyxl

>>> mywb =
openpyxl.Workbook()

>>> mysheet =
mywb.get_sheet_by_name(‘Sheet’)

>>> mysheet[‘F6’] =
‘Writing new Value!’

>>> mysheet[‘F6’].value  
 

‘Writing new Value’

Python Excel setting Fonts:

Applying different styles to your
sheet, emphasizes or stresses certain rows or columns. It is very
important to apply certain uniform styles to your excel sheets so that
it brings clarity in reading the data. If you have hundreds or
thousands of rows of data, styling can be a hectic job, however, with
our python code, you can write a few lines of code and apply on
millions of lines of data instantly. But take care, first styling
should be with absolute care, and second always save excel workbook
with a different name.

First we will import openpyxl, and then import Font and Style for use
in our code.

Here’s an example that creates a new
workbook and sets cell F6 to have a 32-point, italicized font. 

 >>>
import
openpyxl

>>>
from
openpyxl.styles import Font, Style

>>>
mywb
= openpyxl.Workbook()

>>>
mysheet
= mywb.get_sheet_by_name(‘Sheet’)

>>>
italic32Font = Font(size=32, italic=True)

>>>
sobj = Style(font=italic24Font)

>>>
mysheet[‘F6’].style = sobj

>>>
mysheet[‘F6’]
= ‘Applying Styles!’

>>>
mywb.save(‘Appliedstyle.xlsx’)

In openpyxl for excel worksheets each
cell has a style object which is in style attribute of the cell. We
create a style object and assign it to style attribute.

There are four arguments for Font objects

• Name: A string value is used, quoting the font name, like
  ‘Arial’.
• Size: An integer value, quoting the size.
• Bold: A boolean value, True for Bold font.
• Italic: Boolean value, True for Italic font.

In the example below we will call Font( ) method to create a Font
object and store it in a variable, next step will be to pass that as an
argument to Style( ) method. We will store the that object in another
variable and assign it to the specific cell object.

>>> import openpyxl

>>> from
openpyxl.styles import Font, Style

>>> mywb =
openpyxl.Workbook()

>>> mysheet =
mywb.get_sheet_by_name(‘Sheet’)

>>> firstFontObj =
Font(name=’Arial’,
bold=True)

>>> firstStyleObj =
Style(font=firstFontObj)

>>>
mysheet[‘F6’].style/firstStyleObj

>>> mysheet[‘F6’] =
‘Bold Arial’

>>> secondFontObj =
Font(size=32, italic=True)

>>> secondStyleObj =
Style(font=secondFontObj)

>>>
mysheet[‘D7’].style/secondStyleObj

>>> mysheet[‘D7′] =
’32 pt Italic’

>>>
mywb.save(‘ApplicationofStyles.xlsx’)

Python Excel
Writing Formulae:

Formulae in Excel are very important, infact the power of a spreadsheet
is in its formulae. Openpyxl provides the utility of writing formula in
any specific cell. Infact it is very much easy, instead of writing a
number or text, write an equal sign followed by the required formula.

>>>mysheet[‘F6’]
= ‘=Sum(D7:D20)’

This formula will sum up all values
from D7 to D20 and store in F6 cell.

Some more examples:

>>> import openpyxl

>>> mywb =
openpyxl.Workbook()

>>> mysheet =
mywb.active

>>> mysheet[‘F6’] =
500

>>> mysheet[‘F7’] =
800

>>> sheet[‘D3’] =
‘=SUM(F6:F7)’

>>>
mywb.save(‘Applyingformula.xlsx’)

In the above example we put 500 in
F6, and 800 in F7 cell. Cell D3 has a formula of adding up F6 and F7.
When you will open spreadsheet, it will show a value of 1300 in D3.

The cells in A1 and A2 are set to 200
and 300, respectively.
The value in cell A3 is set to a formula that sums the values in A1 and
A2.
When the spreadsheet is opened in Excel, A3 will display its value as
500.

Excel Adjusting Rows and Columns in a Sheet:

We can set Row heigh, column width in excel spreadsheet using openpyxl.
We can also freeze rows or columns so that they always appear. We can
also hide rows or columns.

>>> import openpyxl

>>> mywb =
openpyxl.Workbook()

>>> mysheet =
mywb.active

>>> mysheet[‘F6’] =
‘Tall row’

>>> mysheet[‘D7’] =
‘Wide column’

>>> mysheet.row_dimensions[3].height
= 65

>>>mysheet.column_dimensions[‘F’].width
= 25

>>>mywb.save(‘Heightandwidth.xlsx’)

The
default row height in excel spreadsheet is 12.75 points. Where one
point is equal to 1/72 of an inch. You can set a value between 0 to 409.

Column width can be set to a value from 0 to 255. It can be either an
integer or a floating value (decimal number). If you set 0 width for
column or 0  height for rows, it will be hidden. 

Excel Merging and unmerging

openpyxl allows us to merge and
unmerge cells in a workbook. 

>>> import openpyxl

>>>my wb =
openpyxl.Workbook()

>>> mysheet =
mywb.active

>>>
mysheet.merge_cells(‘B2:D3’)

>>> mysheet[‘A1’] =
‘cells merged
together.’

>>> mysheet.merge_cells(‘F6:F7’)

>>> mysheet[‘G5’] =
‘Two merged cells.’

>>> mywb.save(‘Mergingcells.xlsx’)

merge_cells method takes two cell
addresses as its arguments. First cell is the top left and second cell
is the right bottom of the rectangular area that is to be merged. If we
want to set value of that merged area, we use the address of top left
cell of the whole merged area.

If you want to unmerge cells, use the
idea below.

>>> import openpyxl

>>> mywb =
openpyxl.load_workbook(‘Mergingcells.xlsx’)

>>> mysheet =
mywb.active

>>>
mysheet.unmerge_cells(‘B2:D3’)

>>> mysheet.unmerge_cells(‘F6:F7’)

>>> mywb.save(‘unmerged.xlsx’)  
 

If you want to Read, Write and Manipulate(Copy, cut, paste, delete or search for an item or value etc) Excel files in Python with simple and practical examples I will suggest you to see this simple and to the point

Python Excel Openpyxl Course with examples about how to deal with MS Excel files in Python. This video course teaches efficiently how to manipulate excel files and automate tasks.

Everything you do in Microsoft Excel, can be automated with Python. So why not use the power of Python and make your life easy. You can make intelligent and thinking Excel sheets, bringing the power of logic and thinking of Python to Excel which is usually static, hence bringing flexibility in Excel and a number of opportunities.

Automate your Excel Tasks and save Time and Effort. You can save dozens or hundreds of hours by Python Excel Automation with just a single click get your tasks done with in seconds which used to take hours of Manual Excel and Data Entry Work.

Watch Now This tutorial has a related video course created by the Real Python team. Watch it together with the written tutorial to deepen your understanding: Editing Excel Spreadsheets in Python With openpyxl

Excel spreadsheets are one of those things you might have to deal with at some point. Either it’s because your boss loves them or because marketing needs them, you might have to learn how to work with spreadsheets, and that’s when knowing openpyxl comes in handy!

Spreadsheets are a very intuitive and user-friendly way to manipulate large datasets without any prior technical background. That’s why they’re still so commonly used today.

In this article, you’ll learn how to use openpyxl to:

• Manipulate Excel spreadsheets with confidence
• Extract information from spreadsheets
• Create simple or more complex spreadsheets, including adding styles, charts, and so on

This article is written for intermediate developers who have a pretty good knowledge of Python data structures, such as dicts and lists, but also feel comfortable around OOP and more intermediate level topics.

from openpyxl import Workbook

workbook = Workbook()
sheet = workbook.active

sheet["A1"] = "hello"
sheet["B1"] = "world!"

workbook.save(filename="hello_world.xlsx")

>>> from openpyxl import load_workbook
>>> workbook = load_workbook(filename="sample.xlsx")
>>> workbook.sheetnames
['Sheet 1']

>>> sheet = workbook.active
>>> sheet
<Worksheet "Sheet 1">

>>> sheet.title
'Sheet 1'

>>> sheet["A1"]
<Cell 'Sheet 1'.A1>

>>> sheet["A1"].value
'marketplace'

>>> sheet["F10"].value
"G-Shock Men's Grey Sport Watch"

>>> sheet.cell(row=10, column=6)
<Cell 'Sheet 1'.F10>

>>> sheet.cell(row=10, column=6).value
"G-Shock Men's Grey Sport Watch"

>>> sheet["A1:C2"]
((<Cell 'Sheet 1'.A1>, <Cell 'Sheet 1'.B1>, <Cell 'Sheet 1'.C1>),
 (<Cell 'Sheet 1'.A2>, <Cell 'Sheet 1'.B2>, <Cell 'Sheet 1'.C2>))

>>> # Get all cells from column A
>>> sheet["A"]
(<Cell 'Sheet 1'.A1>,
 <Cell 'Sheet 1'.A2>,
 ...
 <Cell 'Sheet 1'.A99>,
 <Cell 'Sheet 1'.A100>)

>>> # Get all cells for a range of columns
>>> sheet["A:B"]
((<Cell 'Sheet 1'.A1>,
  <Cell 'Sheet 1'.A2>,
  ...
  <Cell 'Sheet 1'.A99>,
  <Cell 'Sheet 1'.A100>),
 (<Cell 'Sheet 1'.B1>,
  <Cell 'Sheet 1'.B2>,
  ...
  <Cell 'Sheet 1'.B99>,
  <Cell 'Sheet 1'.B100>))

>>> # Get all cells from row 5
>>> sheet[5]
(<Cell 'Sheet 1'.A5>,
 <Cell 'Sheet 1'.B5>,
 ...
 <Cell 'Sheet 1'.N5>,
 <Cell 'Sheet 1'.O5>)

>>> # Get all cells for a range of rows
>>> sheet[5:6]
((<Cell 'Sheet 1'.A5>,
  <Cell 'Sheet 1'.B5>,
  ...
  <Cell 'Sheet 1'.N5>,
  <Cell 'Sheet 1'.O5>),
 (<Cell 'Sheet 1'.A6>,
  <Cell 'Sheet 1'.B6>,
  ...
  <Cell 'Sheet 1'.N6>,
  <Cell 'Sheet 1'.O6>))

>>> for row in sheet.iter_rows(min_row=1,
...                            max_row=2,
...                            min_col=1,
...                            max_col=3):
...     print(row)
(<Cell 'Sheet 1'.A1>, <Cell 'Sheet 1'.B1>, <Cell 'Sheet 1'.C1>)
(<Cell 'Sheet 1'.A2>, <Cell 'Sheet 1'.B2>, <Cell 'Sheet 1'.C2>)


>>> for column in sheet.iter_cols(min_row=1,
...                               max_row=2,
...                               min_col=1,
...                               max_col=3):
...     print(column)
(<Cell 'Sheet 1'.A1>, <Cell 'Sheet 1'.A2>)
(<Cell 'Sheet 1'.B1>, <Cell 'Sheet 1'.B2>)
(<Cell 'Sheet 1'.C1>, <Cell 'Sheet 1'.C2>)

>>> for value in sheet.iter_rows(min_row=1,
...                              max_row=2,
...                              min_col=1,
...                              max_col=3,
...                              values_only=True):
...     print(value)
('marketplace', 'customer_id', 'review_id')
('US', 3653882, 'R3O9SGZBVQBV76')

>>> for row in sheet.rows:
...     print(row)
(<Cell 'Sheet 1'.A1>, <Cell 'Sheet 1'.B1>, <Cell 'Sheet 1'.C1>
...
<Cell 'Sheet 1'.M100>, <Cell 'Sheet 1'.N100>, <Cell 'Sheet 1'.O100>)

>>> for value in sheet.iter_rows(min_row=1,
...                              max_row=1,
...                              values_only=True):
...     print(value)
('marketplace', 'customer_id', 'review_id', 'product_id', ...)

>>> for value in sheet.iter_rows(min_row=2,
...                              min_col=4,
...                              max_col=7,
...                              values_only=True):
...     print(value)
('B00FALQ1ZC', 937001370, 'Invicta Women's 15150 "Angel" 18k Yellow...)
('B00D3RGO20', 484010722, "Kenneth Cole New York Women's KC4944...)
...

import json
from openpyxl import load_workbook

workbook = load_workbook(filename="sample.xlsx")
sheet = workbook.active

products = {}

# Using the values_only because you want to return the cells' values
for row in sheet.iter_rows(min_row=2,
                           min_col=4,
                           max_col=7,
                           values_only=True):
    product_id = row[0]
    product = {
        "parent": row[1],
        "title": row[2],
        "category": row[3]
    }
    products[product_id] = product

# Using json here to be able to format the output for displaying later
print(json.dumps(products))

{
  "B00FALQ1ZC": {
    "parent": 937001370,
    "title": "Invicta Women's 15150 ...",
    "category": "Watches"
  },
  "B00D3RGO20": {
    "parent": 484010722,
    "title": "Kenneth Cole New York ...",
    "category": "Watches"
  }
}

import datetime
from dataclasses import dataclass

@dataclass
class Product:
    id: str
    parent: str
    title: str
    category: str

@dataclass
class Review:
    id: str
    customer_id: str
    stars: int
    headline: str
    body: str
    date: datetime.datetime

>>> for value in sheet.iter_rows(min_row=1,
...                              max_row=1,
...                              values_only=True):
...     print(value)
('marketplace', 'customer_id', 'review_id', 'product_id', ...)

>>> # Or an alternative
>>> for cell in sheet[1]:
...     print(cell.value)
marketplace
customer_id
review_id
product_id
product_parent
...

# Product fields
PRODUCT_ID = 3
PRODUCT_PARENT = 4
PRODUCT_TITLE = 5
PRODUCT_CATEGORY = 6

# Review fields
REVIEW_ID = 2
REVIEW_CUSTOMER = 1
REVIEW_STARS = 7
REVIEW_HEADLINE = 12
REVIEW_BODY = 13
REVIEW_DATE = 14

from datetime import datetime
from openpyxl import load_workbook
from classes import Product, Review
from mapping import PRODUCT_ID, PRODUCT_PARENT, PRODUCT_TITLE, 
    PRODUCT_CATEGORY, REVIEW_DATE, REVIEW_ID, REVIEW_CUSTOMER, 
    REVIEW_STARS, REVIEW_HEADLINE, REVIEW_BODY

# Using the read_only method since you're not gonna be editing the spreadsheet
workbook = load_workbook(filename="sample.xlsx", read_only=True)
sheet = workbook.active

products = []
reviews = []

# Using the values_only because you just want to return the cell value
for row in sheet.iter_rows(min_row=2, values_only=True):
    product = Product(id=row[PRODUCT_ID],
                      parent=row[PRODUCT_PARENT],
                      title=row[PRODUCT_TITLE],
                      category=row[PRODUCT_CATEGORY])
    products.append(product)

    # You need to parse the date from the spreadsheet into a datetime format
    spread_date = row[REVIEW_DATE]
    parsed_date = datetime.strptime(spread_date, "%Y-%m-%d")

    review = Review(id=row[REVIEW_ID],
                    customer_id=row[REVIEW_CUSTOMER],
                    stars=row[REVIEW_STARS],
                    headline=row[REVIEW_HEADLINE],
                    body=row[REVIEW_BODY],
                    date=parsed_date)
    reviews.append(review)

print(products[0])
print(reviews[0])

Product(id='B00FALQ1ZC', parent=937001370, ...)
Review(id='R3O9SGZBVQBV76', customer_id=3653882, ...)

from openpyxl import load_workbook

# Start by opening the spreadsheet and selecting the main sheet
workbook = load_workbook(filename="hello_world.xlsx")
sheet = workbook.active

# Write what you want into a specific cell
sheet["C1"] = "writing ;)"

# Save the spreadsheet
workbook.save(filename="hello_world_append.xlsx")

 1from openpyxl import Workbook
 2
 3filename = "hello_world.xlsx"
 4
 5workbook = Workbook()
 6sheet = workbook.active
 7
 8sheet["A1"] = "hello"
 9sheet["B1"] = "world!"
10
11workbook.save(filename=filename)

>>> def print_rows():
...     for row in sheet.iter_rows(values_only=True):
...         print(row)

>>> sheet["A1"] = "value"

>>> cell = sheet["A1"]
>>> cell
<Cell 'Sheet'.A1>

>>> cell.value
'hello'

>>> cell.value = "hey"
>>> cell.value
'hey'

>>> # Before, our spreadsheet has only 1 row
>>> print_rows()
('hello', 'world!')

>>> # Try adding a value to row 10
>>> sheet["B10"] = "test"
>>> print_rows()
('hello', 'world!')
(None, None)
(None, None)
(None, None)
(None, None)
(None, None)
(None, None)
(None, None)
(None, None)
(None, 'test')

>>> print_rows()
('hello', 'world!')

>>> # Insert a column before the existing column 1 ("A")
>>> sheet.insert_cols(idx=1)
>>> print_rows()
(None, 'hello', 'world!')

>>> # Insert 5 columns between column 2 ("B") and 3 ("C")
>>> sheet.insert_cols(idx=3, amount=5)
>>> print_rows()
(None, 'hello', None, None, None, None, None, 'world!')

>>> # Delete the created columns
>>> sheet.delete_cols(idx=3, amount=5)
>>> sheet.delete_cols(idx=1)
>>> print_rows()
('hello', 'world!')

>>> # Insert a new row in the beginning
>>> sheet.insert_rows(idx=1)
>>> print_rows()
(None, None)
('hello', 'world!')

>>> # Insert 3 new rows in the beginning
>>> sheet.insert_rows(idx=1, amount=3)
>>> print_rows()
(None, None)
(None, None)
(None, None)
(None, None)
('hello', 'world!')

>>> # Delete the first 4 rows
>>> sheet.delete_rows(idx=1, amount=4)
>>> print_rows()
('hello', 'world!')

>>> # Let's say you have two sheets: "Products" and "Company Sales"
>>> workbook.sheetnames
['Products', 'Company Sales']

>>> # You can select a sheet using its title
>>> products_sheet = workbook["Products"]
>>> sales_sheet = workbook["Company Sales"]

>>> workbook.sheetnames
['Products', 'Company Sales']

>>> products_sheet = workbook["Products"]
>>> products_sheet.title = "New Products"

>>> workbook.sheetnames
['New Products', 'Company Sales']

>>> workbook.sheetnames
['Products', 'Company Sales']

>>> operations_sheet = workbook.create_sheet("Operations")
>>> workbook.sheetnames
['Products', 'Company Sales', 'Operations']

>>> # You can also define the position to create the sheet at
>>> hr_sheet = workbook.create_sheet("HR", 0)
>>> workbook.sheetnames
['HR', 'Products', 'Company Sales', 'Operations']

>>> # To remove them, just pass the sheet as an argument to the .remove()
>>> workbook.remove(operations_sheet)
>>> workbook.sheetnames
['HR', 'Products', 'Company Sales']

>>> workbook.remove(hr_sheet)
>>> workbook.sheetnames
['Products', 'Company Sales']

>>> workbook.sheetnames
['Products', 'Company Sales']

>>> products_sheet = workbook["Products"]
>>> workbook.copy_worksheet(products_sheet)
<Worksheet "Products Copy">

>>> workbook.sheetnames
['Products', 'Company Sales', 'Products Copy']

>>> workbook = load_workbook(filename="sample.xlsx")
>>> sheet = workbook.active
>>> sheet.freeze_panes = "C2"
>>> workbook.save("sample_frozen.xlsx")

>>> # Check the used spreadsheet space using the attribute "dimensions"
>>> sheet.dimensions
'A1:O100'

>>> sheet.auto_filter.ref = "A1:O100"
>>> workbook.save(filename="sample_with_filters.xlsx")

>>> from openpyxl.utils import FORMULAE
>>> FORMULAE
frozenset({'ABS',
           'ACCRINT',
           'ACCRINTM',
           'ACOS',
           'ACOSH',
           'AMORDEGRC',
           'AMORLINC',
           'AND',
           ...
           'YEARFRAC',
           'YIELD',
           'YIELDDISC',
           'YIELDMAT',
           'ZTEST'})

>>> # Star rating is column "H"
>>> sheet["P2"] = "=AVERAGE(H2:H100)"
>>> workbook.save(filename="sample_formulas.xlsx")

>>> # The helpful votes are counted on column "I"
>>> sheet["P3"] = '=COUNTIF(I2:I100, ">0")'
>>> workbook.save(filename="sample_formulas.xlsx")

>>> # Import necessary style classes
>>> from openpyxl.styles import Font, Color, Alignment, Border, Side

>>> # Create a few styles
>>> bold_font = Font(bold=True)
>>> big_red_text = Font(color="00FF0000", size=20)
>>> center_aligned_text = Alignment(horizontal="center")
>>> double_border_side = Side(border_style="double")
>>> square_border = Border(top=double_border_side,
...                        right=double_border_side,
...                        bottom=double_border_side,
...                        left=double_border_side)

>>> # Style some cells!
>>> sheet["A2"].font = bold_font
>>> sheet["A3"].font = big_red_text
>>> sheet["A4"].alignment = center_aligned_text
>>> sheet["A5"].border = square_border
>>> workbook.save(filename="sample_styles.xlsx")

>>> # Reusing the same styles from the example above
>>> sheet["A6"].alignment = center_aligned_text
>>> sheet["A6"].font = big_red_text
>>> sheet["A6"].border = square_border
>>> workbook.save(filename="sample_styles.xlsx")

>>> from openpyxl.styles import NamedStyle

>>> # Let's create a style template for the header row
>>> header = NamedStyle(name="header")
>>> header.font = Font(bold=True)
>>> header.border = Border(bottom=Side(border_style="thin"))
>>> header.alignment = Alignment(horizontal="center", vertical="center")

>>> # Now let's apply this to all first row (header) cells
>>> header_row = sheet[1]
>>> for cell in header_row:
...     cell.style = header

>>> workbook.save(filename="sample_styles.xlsx")

>>> from openpyxl.styles import PatternFill
>>> from openpyxl.styles.differential import DifferentialStyle
>>> from openpyxl.formatting.rule import Rule

>>> red_background = PatternFill(fgColor="00FF0000")
>>> diff_style = DifferentialStyle(fill=red_background)
>>> rule = Rule(type="expression", dxf=diff_style)
>>> rule.formula = ["$H1<3"]
>>> sheet.conditional_formatting.add("A1:O100", rule)
>>> workbook.save("sample_conditional_formatting.xlsx")

>>> from openpyxl.formatting.rule import ColorScaleRule
>>> color_scale_rule = ColorScaleRule(start_type="min",
...                                   start_color="00FF0000",  # Red
...                                   end_type="max",
...                                   end_color="0000FF00")  # Green

>>> # Again, let's add this gradient to the star ratings, column "H"
>>> sheet.conditional_formatting.add("H2:H100", color_scale_rule)
>>> workbook.save(filename="sample_conditional_formatting_color_scale.xlsx")

>>> from openpyxl.formatting.rule import ColorScaleRule
>>> color_scale_rule = ColorScaleRule(start_type="num",
...                                   start_value=1,
...                                   start_color="00FF0000",  # Red
...                                   mid_type="num",
...                                   mid_value=3,
...                                   mid_color="00FFFF00",  # Yellow
...                                   end_type="num",
...                                   end_value=5,
...                                   end_color="0000FF00")  # Green

>>> # Again, let's add this gradient to the star ratings, column "H"
>>> sheet.conditional_formatting.add("H2:H100", color_scale_rule)
>>> workbook.save(filename="sample_conditional_formatting_color_scale_3.xlsx")

>>> from openpyxl.formatting.rule import IconSetRule

>>> icon_set_rule = IconSetRule("5Arrows", "num", [1, 2, 3, 4, 5])
>>> sheet.conditional_formatting.add("H2:H100", icon_set_rule)
>>> workbook.save("sample_conditional_formatting_icon_set.xlsx")

>>> from openpyxl.formatting.rule import DataBarRule

>>> data_bar_rule = DataBarRule(start_type="num",
...                             start_value=1,
...                             end_type="num",
...                             end_value="5",
...                             color="0000FF00")  # Green
>>> sheet.conditional_formatting.add("H2:H100", data_bar_rule)
>>> workbook.save("sample_conditional_formatting_data_bar.xlsx")

from openpyxl import load_workbook
from openpyxl.drawing.image import Image

# Let's use the hello_world spreadsheet since it has less data
workbook = load_workbook(filename="hello_world.xlsx")
sheet = workbook.active

logo = Image("logo.png")

# A bit of resizing to not fill the whole spreadsheet with the logo
logo.height = 150
logo.width = 150

sheet.add_image(logo, "A3")
workbook.save(filename="hello_world_logo.xlsx")

 1from openpyxl import Workbook
 2from openpyxl.chart import BarChart, Reference
 3
 4workbook = Workbook()
 5sheet = workbook.active
 6
 7# Let's create some sample sales data
 8rows = [
 9    ["Product", "Online", "Store"],
10    [1, 30, 45],
11    [2, 40, 30],
12    [3, 40, 25],
13    [4, 50, 30],
14    [5, 30, 25],
15    [6, 25, 35],
16    [7, 20, 40],
17]
18
19for row in rows:
20    sheet.append(row)

22chart = BarChart()
23data = Reference(worksheet=sheet,
24                 min_row=1,
25                 max_row=8,
26                 min_col=2,
27                 max_col=3)
28
29chart.add_data(data, titles_from_data=True)
30sheet.add_chart(chart, "E2")
31
32workbook.save("chart.xlsx")

 1import random
 2from openpyxl import Workbook
 3from openpyxl.chart import LineChart, Reference
 4
 5workbook = Workbook()
 6sheet = workbook.active
 7
 8# Let's create some sample sales data
 9rows = [
10    ["", "January", "February", "March", "April",
11    "May", "June", "July", "August", "September",
12     "October", "November", "December"],
13    [1, ],
14    [2, ],
15    [3, ],
16]
17
18for row in rows:
19    sheet.append(row)
20
21for row in sheet.iter_rows(min_row=2,
22                           max_row=4,
23                           min_col=2,
24                           max_col=13):
25    for cell in row:
26        cell.value = random.randrange(5, 100)

28chart = LineChart()
29data = Reference(worksheet=sheet,
30                 min_row=2,
31                 max_row=4,
32                 min_col=1,
33                 max_col=13)
34
35chart.add_data(data, from_rows=True, titles_from_data=True)
36sheet.add_chart(chart, "C6")
37
38workbook.save("line_chart.xlsx")

cats = Reference(worksheet=sheet,
                 min_row=1,
                 max_row=1,
                 min_col=2,
                 max_col=13)
chart.set_categories(cats)

chart.x_axis.title = "Months"
chart.y_axis.title = "Sales (per unit)"

# You can play with this by choosing any number between 1 and 48
chart.style = 24

import random
from openpyxl import Workbook
from openpyxl.chart import LineChart, Reference

workbook = Workbook()
sheet = workbook.active

# Let's create some sample sales data
rows = [
    ["", "January", "February", "March", "April",
    "May", "June", "July", "August", "September",
     "October", "November", "December"],
    [1, ],
    [2, ],
    [3, ],
]

for row in rows:
    sheet.append(row)

for row in sheet.iter_rows(min_row=2,
                           max_row=4,
                           min_col=2,
                           max_col=13):
    for cell in row:
        cell.value = random.randrange(5, 100)

# Create a LineChart and add the main data
chart = LineChart()
data = Reference(worksheet=sheet,
                           min_row=2,
                           max_row=4,
                           min_col=1,
                           max_col=13)
chart.add_data(data, titles_from_data=True, from_rows=True)

# Add categories to the chart
cats = Reference(worksheet=sheet,
                 min_row=1,
                 max_row=1,
                 min_col=2,
                 max_col=13)
chart.set_categories(cats)

# Rename the X and Y Axis
chart.x_axis.title = "Months"
chart.y_axis.title = "Sales (per unit)"

# Apply a specific Style
chart.style = 24

# Save!
sheet.add_chart(chart, "C6")
workbook.save("line_chart.xlsx")

from dataclasses import dataclass
from typing import List

@dataclass
class Sale:
    quantity: int

@dataclass
class Product:
    id: str
    name: str
    sales: List[Sale]

 1import random
 2
 3# Ignore these for now. You'll use them in a sec ;)
 4from openpyxl import Workbook
 5from openpyxl.chart import LineChart, Reference
 6
 7from db_classes import Product, Sale
 8
 9products = []
10
11# Let's create 5 products
12for idx in range(1, 6):
13    sales = []
14
15    # Create 5 months of sales
16    for _ in range(5):
17        sale = Sale(quantity=random.randrange(5, 100))
18        sales.append(sale)
19
20    product = Product(id=str(idx),
21                      name="Product %s" % idx,
22                      sales=sales)
23    products.append(product)

25workbook = Workbook()
26sheet = workbook.active
27
28# Append column names first
29sheet.append(["Product ID", "Product Name", "Month 1",
30              "Month 2", "Month 3", "Month 4", "Month 5"])
31
32# Append the data
33for product in products:
34    data = [product.id, product.name]
35    for sale in product.sales:
36        data.append(sale.quantity)
37    sheet.append(data)

38chart = LineChart()
39data = Reference(worksheet=sheet,
40                 min_row=2,
41                 max_row=6,
42                 min_col=2,
43                 max_col=7)
44
45chart.add_data(data, titles_from_data=True, from_rows=True)
46sheet.add_chart(chart, "B8")
47
48cats = Reference(worksheet=sheet,
49                 min_row=1,
50                 max_row=1,
51                 min_col=3,
52                 max_col=7)
53chart.set_categories(cats)
54
55chart.x_axis.title = "Months"
56chart.y_axis.title = "Sales (per unit)"
57
58workbook.save(filename="oop_sample.xlsx")

 1import pandas as pd
 2
 3data = {
 4    "Product Name": ["Product 1", "Product 2"],
 5    "Sales Month 1": [10, 20],
 6    "Sales Month 2": [5, 35],
 7}
 8df = pd.DataFrame(data)

10from openpyxl import Workbook
11from openpyxl.utils.dataframe import dataframe_to_rows
12
13workbook = Workbook()
14sheet = workbook.active
15
16for row in dataframe_to_rows(df, index=False, header=True):
17    sheet.append(row)
18
19workbook.save("pandas.xlsx")

import pandas as pd
from openpyxl import load_workbook

workbook = load_workbook(filename="sample.xlsx")
sheet = workbook.active

values = sheet.values
df = pd.DataFrame(values)

import pandas as pd
from openpyxl import load_workbook
from mapping import REVIEW_ID

workbook = load_workbook(filename="sample.xlsx")
sheet = workbook.active

data = sheet.values

# Set the first row as the columns for the DataFrame
cols = next(data)
data = list(data)

# Set the field "review_id" as the indexes for each row
idx = [row[REVIEW_ID] for row in data]

df = pd.DataFrame(data, index=idx, columns=cols)

>>> df.columns
Index(['marketplace', 'customer_id', 'review_id', 'product_id',
       'product_parent', 'product_title', 'product_category', 'star_rating',
       'helpful_votes', 'total_votes', 'vine', 'verified_purchase',
       'review_headline', 'review_body', 'review_date'],
      dtype='object')

>>> # Get first 10 reviews' star rating
>>> df["star_rating"][:10]
R3O9SGZBVQBV76    5
RKH8BNC3L5DLF     5
R2HLE8WKZSU3NL    2
R31U3UH5AZ42LL    5
R2SV659OUJ945Y    4
RA51CP8TR5A2L     5
RB2Q7DLDN6TH6     5
R2RHFJV0UYBK3Y    1
R2Z6JOQ94LFHEP    5
RX27XIIWY5JPB     4
Name: star_rating, dtype: int64

>>> # Grab review with id "R2EQL1V1L6E0C9", using the index
>>> df.loc["R2EQL1V1L6E0C9"]
marketplace               US
customer_id         15305006
review_id     R2EQL1V1L6E0C9
product_id        B004LURNO6
product_parent     892860326
review_headline   Five Stars
review_body          Love it
review_date       2015-08-31
Name: R2EQL1V1L6E0C9, dtype: object

Watch Now This tutorial has a related video course created by the Real Python team. Watch it together with the written tutorial to deepen your understanding: Editing Excel Spreadsheets in Python With openpyxl

1. Export Data to Excel With the DataFrame.to_excel() Function in Python
2. Export Data to Excel With the xlwt Library in Python
3. Export Data to Excel With the openpyxl Library in Python
4. Export Data to Excel With the XlsWriter Library in Python

This tutorial will demonstrate different methods to write tabular data to an excel file in Python.

Export Data to Excel With the DataFrame.to_excel() Function in Python

If we want to write tabular data to an Excel sheet in Python, we can use the to_excel() function in Pandas DataFrame.

A pandas DataFrame is a data structure that stores tabular data. The to_excel() function takes two input parameters: the file’s name and the sheet’s name. We must store our data inside a pandas DataFrame and then call the to_excel() function to export that data into an Excel file.

We need to have the pandas library already installed on our system for this method to work. The command to install the pandas library is given below.

A working demonstration of this approach is given below.

import pandas as pd
list1 = [10,20,30,40]
list2 = [40,30,20,10]
col1 = "X"
col2 = "Y"
data = pd.DataFrame({col1:list1,col2:list2})
data.to_excel('sample_data.xlsx', sheet_name='sheet1', index=False)

sample_data.xlsx file:

In the above code, we exported the data inside list1 and list2 as columns into the sample_data.xlsx Excel file with Python’s to_excel() function.

We first stored the data inside both lists into a pandas DataFrame. After that, we called the to_excel() function and passed the names of our output file and the sheet.

Keep in mind that this method will only work as long as the length of both lists is equal. If the lengths aren’t equal, we can compensate for the missing values by filling the shorter list with the None value.

This is the easiest method to write data to an Excel-compatible file in Python.

Export Data to Excel With the xlwt Library in Python

The xlwt library is used to write data into old spreadsheets compatible with Excel versions from 95 to 2003 in Python. It is the standard way for writing data to Excel files in Python.

It is also fairly simple and gives us more control over the Excel file than the previous method. We can create an object of the xlwt.Workbook class and call the .add_sheet() function to create a new sheet in our workbook.

We can then use the write() method to write our data. This write() function takes the row index (starting from 0), the column index (also starting from 0), and the data to be written as input parameters.

We need to install the xlwt library on our machine for this method to work. The command to install the library is given below.

A brief working example of this method is given below.

import xlwt
from xlwt import Workbook

wb = Workbook()

sheet1 = wb.add_sheet('Sheet 1')
#sheet1.write(row,col, data, style)
sheet1.write(1, 0, '1st Data')
sheet1.write(2, 0, '2nd Data')
sheet1.write(3, 0, '3rd Data')
sheet1.write(4, 0, '4th Data')

wb.save('sample_data2.xls')

sample_data2.xls file:

In Python, we wrote data to the sample_data2.xls file with the xlwt library.

We first created an object of the Workbook class. Using this object, we created a sheet with the add_sheet() method of the Workbook class.

We then wrote our data into the newly created sheet with the write() function. Lastly, when all the data has been properly written to its specified index, we saved the workbook into an Excel file with the save() function of the Workbook class.

This is a pretty straightforward approach, but the only drawback is that we have to remember the row and column index for each cell in our file. We can’t just use A1 and A2 indices. Another disadvantage of this approach is that we can only write files with the .xls extension.

Export Data to Excel With the openpyxl Library in Python

Another method that can be used to write data to an Excel-compatible file is the openpyxl library in Python.

This approach addresses all the drawbacks of the previous methods. We don’t need to remember the exact row and column indices for each data point. Simply specify our cells like A1 or A2 in the write() function.

Another cool advantage of this approach is that it can be used to write files with the new .xlsx file extensions, which wasn’t the case in the previous approach. This method works just like the previous one.

The only difference here is that we have to initialize each cell in addition to a sheet with the cell(row,col) method in the openpyxl library.

The openpyxl is also an external library. We need to install this library for this method to work properly. The command to install the openpyxl library on our machine is below.

A simple working demonstration of this approach is given below.

import openpyxl
my_wb = openpyxl.Workbook()
my_sheet = my_wb.active
c1 = my_sheet.cell(row = 1, column = 1)
c1.value = "Maisam"
c2 = my_sheet.cell(row= 1 , column = 2)
c2.value = "Abbas"
c3 = my_sheet['A2']
c3.value = "Excel"
# for B2: column = 2 & row = 2.
c4 = my_sheet['B2']
c4.value = "file"
my_wb.save("sample_data3.xlsx")

sample_data3.xlsx file:

In the above code, we wrote data to the sample_data3.xlsx Excel file with the openpyxl library in Python.

We first created an object of the Workbook class. We created a sheet with the Workbook.active using this object. We also created a cell object with my_sheet.cell(row = 1, column = 1).

Instead of writing the exact row and column number, we can also specify the cell name like A1. We can then assign our newly created cell value with c1.value = "Maisam".

Lastly, when all the data has been properly written to its specified index, we saved the workbook into an Excel file with the save() function of the Workbook class.

Export Data to Excel With the XlsWriter Library in Python

Another great and simple way to write data to an Excel-compatible file is the XlsWriter library in Python.

This library gives us much more control over our output file than any previous methods mentioned above. This library also supports the latest Excel compatible file extensions like xlsx.

To write data to an Excel file, we first have to create an object of the Workbook class by providing the constructor’s file name as an input parameter. We then have to create a sheet with the add_worksheet() function in the Workbook class.

After adding a sheet, we can write data with the sheet.write(cell, data) function. This sheet.write() function takes two parameters: the cell’s name and the data to be written.

After writing all the data to the sheet, we need to close our workbook with the close() method inside the Workbook class.

The XlsWriter is an external library and does not come pre-installed with Python. We first have to install the XlsWriter library on our machine for this method to work. The command to install the XlsWriter library is given below.

A working demonstration of this approach is shown below.

import xlsxwriter

workbook = xlsxwriter.Workbook('sample_data4.xlsx')
sheet = workbook.add_worksheet()

sheet.write('A1', 'Maisam')
sheet.write('A2', 'Abbas')

workbook.close()

sample_data4.xlsx file:

We wrote data to the sample_data4.xlsx Excel file with Python’s xlswriter library in the above code.

Microsoft Excel is probably one of the highly used data storage applications. A huge proportion of small to medium size businesses fulfill their analytics requirement using Excel.

However, analyzing huge amount of data in Excel can become highly tedious and time-consuming. You could build customized data processing and analytics application using Visual Basic(VBA), the language that powers the Excel sheets. However, learning VBA could be difficult and perhaps, not worth it.

However, if you have a little knowledge of Python, you could build highly professional Business Intelligence using Excel data, without the need of a database. Using Python with Excel could be a game changer for your business.

Sections Covered

1. Basic Information about Excel
2. What is Openpyxl and how to install it?
3. Reading data from Excel in Python
4. Reading multiple cells from Excel in Python
5. Find the max row and column number of an Excel sheet in Python
6. How to iterate over Excel rows and columns in Python?
7. Create a new Excel file with Python
8. Writing data to Excel in Python
9. Appending data to Excel in Python
10. Manipulating Excel Sheets in Python
11. Practical usage example of data analysis of Excel sheets in Python

Basic Information about Excel

Before beginning this Openpyxl tutorial, you need to keep the following details in mind.

1. Excel files are called Workbooks.
2. Each Workbook can contain multiple sheets.
3. Every sheet consists of rows starting from 1 and columns starting from A.
4. Rows and columns together make up a cell.
5. Any type of data can be stored.

What is Openpyxl and how to install it?

The Openpyxl module in Python is used to handle Excel files without involving third-party Microsoft application software. It is arguably, the best python excel library that allows you to perform various Excel operations and automate excel reports using Python. You can perform all kinds of tasks using Openpyxl like:-

1. Reading data
2. Writing data
3. Editing Excel files
4. Drawing graphs and charts
5. Working with multiple sheets
6. Sheet Styling etc.

You can install Openpyxl module by typing pip install openpyxl in your command line.

pip install openpyxl

Reading data from Excel in Python

To import an excel file in Python, use the load_workbook method from Openpyxl library.

Let’s import an Excel file named wb1.xlsx in Python using Openpyxl module. It has the following data as shown in the image below.

Step 1 — Import the load_workbook method from Openpyxl.

from openpyxl import load_workbook

Step 2 — Provide the file location for the Excel file you want to open in Python.

   wb = load_workbook('wb1.xlsx')

If your Excel file is present in the same directory as the python file, you don’t need to provide to entire file location.

Step 3 — Choose the first active sheet present in the workbook using wb.active attribute.

   sheet = wb.active

The above points are a standard way of accessing Excel sheets using Python. You will see them being used multiple times through out this article.

Let’s read all the data present in Row 1 (header row).

Method 1 — Reading data through Excel cell name in Python

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

print(sheet["A1"].value)
print(sheet["B1"].value)
print(sheet["C1"].value)
print(sheet["D1"].value)

Output

ProductId
ProductName
Cost per Unit
Quantity

Method 2 — Reading data from Excel using cell() method in Python

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

print(sheet.cell(row=1, column=1).value)
print(sheet.cell(row=1, column=2).value)
print(sheet.cell(row=1, column=3).value)
print(sheet.cell(row=1, column=4).value)

Output

ProductId
ProductName
Cost per Unit
Quantity

Reading Multiple Cells from Excel in Python

You can also read multiple cells from an Excel workbook. Let’s understand this through various examples. Refer to the image of the wb1.xlsx file above for clarity.

Method 1 — Reading a range of cells in Excel using cell names

To read the data from a specific range of cells in your Excel sheet, you need to slice your sheet object through both the cells.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells from A1 to D11
print(sheet["A1:D11"])

Output

((<Cell 'Sheet1'.A1>, <Cell 'Sheet1'.B1>, <Cell 'Sheet1'.C1>, <Cell 'Sheet1'.D1>), 
 (<Cell 'Sheet1'.A2>, <Cell 'Sheet1'.B2>, <Cell 'Sheet1'.C2>, <Cell 'Sheet1'.D2>), 
 (<Cell 'Sheet1'.A3>, <Cell 'Sheet1'.B3>, <Cell 'Sheet1'.C3>, <Cell 'Sheet1'.D3>), 
 (<Cell 'Sheet1'.A4>, <Cell 'Sheet1'.B4>, <Cell 'Sheet1'.C4>, <Cell 'Sheet1'.D4>), 
 (<Cell 'Sheet1'.A5>, <Cell 'Sheet1'.B5>, <Cell 'Sheet1'.C5>, <Cell 'Sheet1'.D5>), 
 (<Cell 'Sheet1'.A6>, <Cell 'Sheet1'.B6>, <Cell 'Sheet1'.C6>, <Cell 'Sheet1'.D6>), 
 (<Cell 'Sheet1'.A7>, <Cell 'Sheet1'.B7>, <Cell 'Sheet1'.C7>, <Cell 'Sheet1'.D7>), 
 (<Cell 'Sheet1'.A8>, <Cell 'Sheet1'.B8>, <Cell 'Sheet1'.C8>, <Cell 'Sheet1'.D8>), 
 (<Cell 'Sheet1'.A9>, <Cell 'Sheet1'.B9>, <Cell 'Sheet1'.C9>, <Cell 'Sheet1'.D9>), 
 (<Cell 'Sheet1'.A10>, <Cell 'Sheet1'.B10>, <Cell 'Sheet1'.C10>, <Cell 'Sheet1'.D10>), 
 (<Cell 'Sheet1'.A11>, <Cell 'Sheet1'.B11>, <Cell 'Sheet1'.C11>, <Cell 'Sheet1'.D11>))

You can see that by slicing the sheet data from A1:D11, it returned us tuples of row data inside a tuple. In order to read the values of every cell returned, you can iterate over each row and use .value.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells from A1 to D11
for row in sheet["A1:D11"]:
    print ([x.value for x in row])

Output

['ProductId', 'ProductName', 'Cost per Unit', 'Quantity']
[1, 'Pencil', '$0.5', 200]
[2, 'Pen', '$1', 500]
[3, 'Eraser', '$0.25', 100]
[4, 'Sharpner', '$0.75', 100]
[5, 'Files', '$3', 50]
[6, 'A4 Size Paper', '$9', 10]
[7, 'Pencil Box', '$12', 20]
[8, 'Pen Stand', '$5.5', 10]
[9, 'Notebook', '$2', 50]
[10, 'Marker', '$1', 75]

Method 2 — Reading a single row in Excel using cell name

To read a single row in your Excel sheet, just access the single row number from your sheet object.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells in row 1
for data in sheet["1"]:
    print(data.value)

Output

ProductId
ProductName
Cost per Unit
Quantity

Method 3 — Reading all rows in Excel using rows attribute

To read all the rows, use sheet.rows to iterate over rows with Openpyxl. You receive a tuple element per row by using the sheet.rows attribute.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells in row 1
for row in sheet.rows:
    print([data.value for data in row])

Output

['ProductId', 'ProductName', 'Cost per Unit', 'Quantity']
[1, 'Pencil', '$0.5', 200]
[2, 'Pen', '$1', 500]
[3, 'Eraser', '$0.25', 100]
[4, 'Sharpner', '$0.75', 100]
[5, 'Files', '$3', 50]
[6, 'A4 Size Paper', '$9', 10]
[7, 'Pencil Box', '$12', 20]
[8, 'Pen Stand', '$5.5', 10]
[9, 'Notebook', '$2', 50]
[10, 'Marker', '$1', 75]

Method 4 — Reading a single column in Excel using cell name

Similar to reading a single row, you can read the data in a single column of your Excel sheet by its alphabet.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells in column A
for data in sheet["A"]:
    print(data.value)

Output

ProductId
1
2
3
4
5
6
7
8
9
10

Method 5 — Reading all the columns in Excel using columns attribute

To read all the data as a tuple of the columns in your Excel sheet, use sheet.columns attribute to iterate over all columns with Openpyxl.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all columns
for col in sheet.columns:
    print([data.value for data in col])

Output

['ProductId', 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
['ProductName', 'Pencil', 'Pen', 'Eraser', 'Sharpner', 'Files', 'A4 Size Paper', 'Pencil Box', 'Pen Stand', 'Notebook', 'Marker']
['Cost per Unit', '$0.5', '$1', '$0.25', '$0.75', '$3', '$9', '$12', '$5.5', '$2', '$1']
['Quantity', 200, 500, 100, 100, 50, 10, 20, 10, 50, 75]

Method 6 — Reading all the data in Excel

To read all the data present in your Excel sheet, you don’t need to index the sheet object. You can just iterate over it.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells in Excel
for row in sheet:
    print([data.value for data in row])

Output

['ProductId', 'ProductName', 'Cost per Unit', 'Quantity']
[1, 'Pencil', '$0.5', 200]
[2, 'Pen', '$1', 500]
[3, 'Eraser', '$0.25', 100]
[4, 'Sharpner', '$0.75', 100]
[5, 'Files', '$3', 50]
[6, 'A4 Size Paper', '$9', 10]
[7, 'Pencil Box', '$12', 20]
[8, 'Pen Stand', '$5.5', 10]
[9, 'Notebook', '$2', 50]
[10, 'Marker', '$1', 75]

Find the max row and column number of an Excel Sheet in Python

To find the max row and column number from your Excel sheet in Python, use sheet.max_row and sheet.max_column attributes in Openpyxl.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

print(f"Max row in the active sheet is {sheet.max_row}")
print(f"Max column in the active sheet is {sheet.max_column}")

Output

Max row in the active sheet is 11
Max column in the active sheet is 4

Note — If you update a cell with a value, the sheet.max_row and sheet.max_column values also change, even though you haven’t saved your changes.

Code

from openpyxl import load_workbook

wb = load_workbook('pylenin.xlsx')

sheet = wb.active

sheet["A1"].value = "Lenin"
print(sheet.max_row)

sheet["A2"].value = "Mishra"
print(sheet.max_row)

# wb.save('pylenin.xlsx')

Output

1
2

How to iterate over Excel rows and columns in Python?

Openpyxl offers two commonly used methods called iter_rows and iter_cols to iterate over Excel rows and columns in Python.

1. iter_rows() — Returns one tuple element per row selected.
2. iter_cols() — Returns one tuple element per column selected.

Both the above mentioned methods can receive the following arguments for setting boundaries for iteration:

• min_row
• max_row
• min_col
• max_col

Example 1 — iter_rows()

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells from between 
# "Row 1 and Row 2" and "Column 1 and Column 3"
for row in sheet.iter_rows(min_row=1,
                           max_row=2,
                           min_col=1,
                           max_col=3):
    print([data.value for data in row])

Output

['ProductId', 'ProductName', 'Cost per Unit']
[1, 'Pencil', '$0.5']

As you can see, only the first 3 columns of the first 2 rows are returned. The tuples are row based.

You can also choose to not pass in some or any arguments in iter_rows method.

Code — Not passing min_col and max_col

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# min_col and max_col arguments are not provided
for row in sheet.iter_rows(min_row=1,
                           max_row=2):
    print([data.value for data in row])

Output

['ProductId', 'ProductName', 'Cost per Unit', 'Quantity']
[1, 'Pencil', '$0.5', 200]

All the columns from the first 2 rows are being printed.

Example 2 — iter_cols()

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Access all cells from A1 to D11
for row in sheet.iter_cols(min_row=1,
                           max_row=2,
                           min_col=1,
                           max_col=3):
    print([data.value for data in row])

Output

['ProductId', 1]
['ProductName', 'Pencil']
['Cost per Unit', '$0.5']

The tuples returned are column based on using iter_cols() method.

You can also choose to not pass in some or any arguments in iter_cols() method.

Code — Not passing any argument

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# min_col and max_col arguments are not provided
for row in sheet.iter_cols():
    print([data.value for data in row])

Output

['ProductId', 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
['ProductName', 'Pencil', 'Pen', 'Eraser', 'Sharpner', 'Files', 'A4 Size Paper', 'Pencil Box', 'Pen Stand', 'Notebook', 'Marker']
['Cost per Unit', '$0.5', '$1', '$0.25', '$0.75', '$3', '$9', '$12', '$5.5', '$2', '$1']
['Quantity', 200, 500, 100, 100, 50, 10, 20, 10, 50, 75]

Create a new Excel file with Python

To create a new Excel file in Python, you need to import the Workbook class from Openpyxl library.

Code

from openpyxl import Workbook

wb = Workbook()
sheet = wb.active

sheet['A1'] = "Pylenin"
sheet['B1'] = "loves"
sheet['C1'] = "Python"

wb.save("pylenin.xlsx")

This should create a new Excel workbook called pylenin.xlsx with the provided data.

Writing data to Excel in Python

There are multiple ways to write data to an Excel file in Python.

Method 1 — Writing data to Excel using cell names

Code

from openpyxl import Workbook

wb = Workbook()
sheet = wb.active

sheet['A1'] = "Pylenin"
sheet['B1'] = "loves"
sheet['C1'] = "Python"

wb.save("pylenin.xlsx")

Output

Method 2 — Writing data to Excel using the cell() method

Code

from openpyxl import Workbook

wb = Workbook()
sheet = wb.active

sheet.cell(row=1, column=1).value = "Pylenin"
sheet.cell(row=1, column=2).value = "loves"
sheet.cell(row=1, column=3).value = "Python"

wb.save("pylenin.xlsx")

Output

Method 3 — Writing data to Excel by iterating over rows

Code — Example 1

from openpyxl import Workbook

wb = Workbook()
sheet = wb.active

for row in sheet["A1:D3"]:
    row[0].value = "Pylenin"
    row[1].value = "loves"
    row[2].value = "Python"

wb.save("pylenin.xlsx")

Output

You can also use methods like iter_rows() and iter_cols() to write data to Excel.

Code — Example 2 — using iter_rows() method

from openpyxl import Workbook

wb = Workbook()
sheet = wb.active

for row in sheet.iter_rows(min_row=1,
                           max_row=3,
                           min_col=1,
                           max_col=3):
    row[0].value = "Pylenin"
    row[1].value = "loves"
    row[2].value = "Python"

wb.save("pylenin.xlsx")

Output

Code — Example 3 — using iter_cols() method

from openpyxl import Workbook

wb = Workbook()
sheet = wb.active

for col in sheet.iter_cols(min_row=1,
                           max_row=3,
                           min_col=1,
                           max_col=3):
    col[0].value = "Pylenin"
    col[1].value = "loves"
    col[2].value = "Python"

wb.save("pylenin.xlsx")

Output

Appending data to Excel in Python

Openpyxl provides an append() method, which is used to append values to an existing Excel sheet in Python.

Code

from openpyxl import load_workbook

wb = load_workbook('pylenin.xlsx')
sheet = wb.active

data = (
    ("Pylenin", "likes", "icecream"),
    ("Pylenin", "likes", "Cricket")
)

for row in data:
    sheet.append(row)
wb.save('pylenin.xlsx')

Output

Manipulating Excel Sheets in Python

Each Excel workbook can contain multiple sheets. To get a list of all the sheet names in an Excel workbook, you can use the wb.sheetnames.

Code

from openpyxl import load_workbook

wb = load_workbook('pylenin.xlsx')
print(wb.sheetnames)

Output

['Sheet']

As you can see, pylenin.xlsx has only one sheet.

To create a new sheet in Python, use the create_sheet() method from the Openpyxl library.

Code

from openpyxl import load_workbook

wb = load_workbook('pylenin.xlsx')
wb.create_sheet('Pylenin')

wb.save('pylenin.xlsx')

Output

You can also create sheets at different positions in the Excel Workbook.

Code

from openpyxl import load_workbook

wb = load_workbook('pylenin.xlsx')

# insert sheet at 2nd to last position
wb.create_sheet('Lenin Mishra', -1)

wb.save('pylenin.xlsx')

Output

If your Excel workbook contains multiple sheets and you want to work with a particular sheet, you can refer the title of that sheet in your workbook object.

Code

from openpyxl import load_workbook

wb = load_workbook('pylenin.xlsx')
ws = wb["Pylenin"]

ws["A1"].value = "Pylenin"
ws["A2"].value = "loves"
ws["A3"].value = "Python"

wb.save('pylenin.xlsx')

Output

Practical usage example of data analysis of Excel sheets in Python

Let’s perform some data analysis with wb1.xlsx file as shown in the first image.

Objective

1. Add a new column showing Total Price per Product.
2. Calculate the Total Cost of all the items bought.

The resulting Excel sheet should look like the below image.

Step 1 — Find the max row and max column of the Excel sheet

As mentioned before, you can use the sheet.max_row and sheet.max_column attributes to find the max row and max column for any Excel sheet with Openpyxl.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

print(f"Max row in the active sheet is {sheet.max_row}")
print(f"Max column in the active sheet is {sheet.max_column}")

Output

Max row in the active sheet is 11
Max column in the active sheet is 4

Step 2 — Add an extra column in Excel with Python

To add an extra column in the active Excel sheet, with calculations, you need to first create a new column header in the first empty cell and then iterate over all rows to multiply Quantity with Cost per Unit.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Add new column header

sheet.cell(row=1, column=sheet.max_column+1).value = "Total Price per Product"

wb.save("wb1.xlsx")

Output

Now that an extra column header has been created, the sheet.max_column value will change to 5.

Now you can calculate the Total Price per Product using iter_rows() method.

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

# Calculate Total Price per Product

for id, row in enumerate(sheet.iter_rows(min_row=2,
                                         max_row = sheet.max_row)):

    row_number = id + 2 # index for enumerate will start at 0
    product_name = row[1].value
    cost_per_unit = row[2].value
    quantity = row[3].value
    print(f"Total cost for {product_name} is {cost_per_unit*quantity}")

    # Update cell value in the last column
    current_cell = sheet.cell(row=row_number, column=sheet.max_column)
    current_cell.value = cost_per_unit*quantity

    # Format cell from number to $ currency
    current_cell.number_format = '$#,#0.0'

print("nSuccesfully updated Excel")
wb.save('wb1.xlsx')

Output

Total cost for Pencil is 100.0
Total cost for Pen is 500
Total cost for Eraser is 25.0
Total cost for Sharpner is 75.0
Total cost for Files is 150
Total cost for A4 Size Paper is 90
Total cost for Pencil Box is 240
Total cost for Pen Stand is 55.0
Total cost for Notebook is 100
Total cost for Marker is 75

Succesfully updated Excel

Step 3 — Calculate sum of a column in Excel with Python

The last step is to calculate the Total Cost of the last column in the Excel file.

Access the last column and add up all the cost.

You can read the last column by accessing the sheet.columns attribute. Since it returns a generator, you first convert it to a python list and access the last column.

last_column_data = list(sheet.columns)[-1]
# Ignore header cell 
total_cost = sum([x.value for x in last_column_data[1:]])

Create a new row 2 places down from the max_row and fill in Total Cost.

max_row = sheet.max_row
    
total_cost_descr_cell = sheet.cell(row = max_row +2, column = sheet.max_column -1)
total_cost_descr_cell.value = "Total Cost"
     
total_cost_cell =  sheet.cell(row = max_row +2, column = sheet.max_column)
total_cost_cell.value = total_cost

Import Font class from openpyxl.styles to make the last row Bold.

# Import the Font class from Openpyxl
from openpyxl.styles import Font
    
bold_font = Font(bold=True)
total_cost_descr_cell.font = bold_font
total_cost_cell.font = bold_font
    
total_cost_cell.number_format = "$#,#0.0"

Final Code

Code

from openpyxl import load_workbook

wb = load_workbook('wb1.xlsx')

sheet = wb.active

last_column_data = list(sheet.columns)[-1]
# Ignore header cell 
total_cost = sum([x.value for x in last_column_data[1:]])

max_row = sheet.max_row

total_cost_descr_cell = sheet.cell(row = max_row + 2, column = sheet.max_column -1)
total_cost_descr_cell.value = "Total Cost"

total_cost_cell =  sheet.cell(row = max_row + 2, column = sheet.max_column)
total_cost_cell.value = total_cost

# Import the Font class from Openpyxl
from openpyxl.styles import Font

bold_font = Font(bold=True)
total_cost_descr_cell.font = bold_font
total_cost_cell.font = bold_font

total_cost_cell.number_format = "$#,#0.0"

print("nSuccesfully updated Excel")
wb.save('wb1.xlsx')

When you run the above code, you should see all the relevant updates to your Excel sheet.