Creating excel file in python

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

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.