9.1 Introduction

Working with files is a fundamental skill in Python programming. Whether you’re reading data, saving results, or organizing files, understanding file operations is essential. In this tutorial, you’ll learn:

  • Reading and writing text files with open()
  • Working with JSON data
  • Finding and organizing files with glob

Prerequisites

Basic Python knowledge (variables, loops, functions) is recommended.


9.2 Reading and Writing Files with open()

9.3 Reading Files

The open() function is your gateway to reading files in Python. The most common way to read a file is using a context manager with the with statement.

Basic File Reading

# Read entire file at once
with open('data/sample.txt', 'r') as file:
    content = file.read()
    print(content)
Hello, World!
This is a sample text file.
It contains multiple lines.
Python makes file handling easy.
Learning Python is fun!

Key Points: - 'r' means “read mode” - with automatically closes the file when done - read() returns the entire file as a string

Reading Line by Line

# Method 1: Using readlines()
with open('data/sample.txt', 'r') as file:
    lines = file.readlines()
    print("Number of lines:", len(lines))
    print("First line:", lines[0])
Number of lines: 5
First line: Hello, World!
# Method 2: Iterating directly (memory efficient)
with open('data/sample.txt', 'r') as file:
    for line_num, line in enumerate(file, 1):
        print(f"Line {line_num}: {line.strip()}")
Line 1: Hello, World!
Line 2: This is a sample text file.
Line 3: It contains multiple lines.
Line 4: Python makes file handling easy.
Line 5: Learning Python is fun!

The .strip() method removes whitespace and newline characters from both ends of a string.

Reading Specific Lines

# Read only first 3 lines
with open('data/shopping_list.txt', 'r') as file:
    for i in range(3):
        line = file.readline()
        print(f"Item {i+1}: {line.strip()}")
Item 1: Apples
Item 2: Bananas
Item 3: Milk

9.4 Writing to Files

Writing New Content

# Write mode ('w') - overwrites existing content!
with open('data/output.txt', 'w') as file:
    file.write("This is the first line\n")
    file.write("This is the second line\n")

# Verify what we wrote
with open('data/output.txt', 'r') as file:
    print(file.read())
This is the first line
This is the second line

Appending to Files

# Append mode ('a') - adds to the end
with open('data/output.txt', 'a') as file:
    file.write("This line was appended\n")

# Check the updated content
with open('data/output.txt', 'r') as file:
    print(file.read())
This is the first line
This is the second line
This line was appended

Writing Multiple Lines

# Using writelines()
lines_to_write = ["Apple\n", "Banana\n", "Cherry\n"]

with open('data/fruits.txt', 'w') as file:
    file.writelines(lines_to_write)

# Read it back
with open('data/fruits.txt', 'r') as file:
    print(file.read())
Apple
Banana
Cherry

9.5 File Modes Summary

Mode Description Creates New? Truncates?
'r' Read only No No
'w' Write only Yes Yes
'a' Append only Yes No
'r+' Read and write No No
'w+' Read and write Yes Yes

9.6 Practical Example: Processing a Shopping List

# Read shopping list and count items
with open('data/shopping_list.txt', 'r') as file:
    items = [line.strip() for line in file if line.strip()]

print(f"You have {len(items)} items to buy:")
for idx, item in enumerate(items, 1):
    print(f"{idx}. {item}")

# Add more items
new_items = ["Pasta", "Olive Oil"]
with open('data/shopping_list.txt', 'a') as file:
    for item in new_items:
        file.write(f"{item}\n")

print("\nUpdated list:")
with open('data/shopping_list.txt', 'r') as file:
    print(file.read())
You have 15 items to buy:
1. Apples
2. Bananas
3. Milk
4. Bread
5. Eggs
6. Cheese
7. Orange Juice
8. Avocados
9. Almonds
10. Pasta
11. Olive Oil
12. Pasta
13. Olive Oil
14. Pasta
15. Olive Oil

Updated list:
Apples
Bananas
Milk
Bread
Eggs
Cheese
Orange Juice
Avocados
Almonds
Pasta
Olive Oil
Pasta
Olive Oil
Pasta
Olive Oil
Pasta
Olive Oil

9.7 Working with JSON Files

JSON (JavaScript Object Notation) is a popular format for storing and exchanging structured data. Python’s json module makes it easy to work with.

Loading JSON Data

import json

# Load JSON from a file
with open('data/students.json', 'r') as file:
    data = json.load(file)

print("Type:", type(data))
print("\nJSON Data:")
print(json.dumps(data, indent=2))
Type: <class 'dict'>

JSON Data:
{
  "students": [
    {
      "name": "Alice",
      "age": 20,
      "grade": 85,
      "courses": [
        "Math",
        "Physics"
      ]
    },
    {
      "name": "Bob",
      "age": 22,
      "grade": 92,
      "courses": [
        "Chemistry",
        "Biology"
      ]
    },
    {
      "name": "Charlie",
      "age": 21,
      "grade": 78,
      "courses": [
        "Math",
        "Computer Science"
      ]
    },
    {
      "name": "Diana",
      "age": 23,
      "grade": 95,
      "courses": [
        "Physics",
        "Engineering"
      ]
    },
    {
      "name": "Eve",
      "age": 20,
      "grade": 88,
      "courses": [
        "Biology",
        "Chemistry"
      ]
    }
  ],
  "school": "Data Science Academy",
  "year": 2024
}

9.8 Accessing JSON Data

# Access the students list
students = data['students']

print(f"Total students: {len(students)}\n")

# Loop through students
for student in students:
    print(f"{student['name']} - Grade: {student['grade']}, Courses: {student['courses']}")
Total students: 5

Alice - Grade: 85, Courses: ['Math', 'Physics']
Bob - Grade: 92, Courses: ['Chemistry', 'Biology']
Charlie - Grade: 78, Courses: ['Math', 'Computer Science']
Diana - Grade: 95, Courses: ['Physics', 'Engineering']
Eve - Grade: 88, Courses: ['Biology', 'Chemistry']

9.9 Modifying and Saving JSON

# Add a new student
new_student = {
    "name": "David Brown",
    "age": 22,
    "grade": 90,
    "courses": ["Engineering", "Math"]
}

data['students'].append(new_student)

# Save back to file
with open('data/students_updated.json', 'w') as file:
    json.dump(data, file, indent=2)

print("Updated data saved!")

# Verify
with open('data/students_updated.json', 'r') as file:
    updated_data = json.load(file)
    print(f"\nNow we have {len(updated_data['students'])} students")
Updated data saved!

Now we have 6 students

9.10 Working with Different JSON Structures

# Load inventory data
with open('data/inventory.json', 'r') as file:
    inventory = json.load(file)

print(f"Warehouse: {inventory['warehouse']}")
print(f"Last Updated: {inventory['last_updated']}\n")

print("Products:")
for product in inventory['products']:
    print(f"  {product['name']}: ${product['price']} (Qty: {product['quantity']})")
Warehouse: Main
Last Updated: 2024-01-15

Products:
  Laptop: $999.99 (Qty: 50)
  Mouse: $29.99 (Qty: 200)
  Keyboard: $79.99 (Qty: 150)
  Monitor: $399.99 (Qty: 75)
  Headphones: $149.99 (Qty: 100)

9.11 JSON Strings vs Files

# json.loads() - load from string
json_string = '{"name": "Eve", "age": 25, "city": "Boston"}'
person = json.loads(json_string)
print("From string:", person)

# json.dumps() - convert to string
person['occupation'] = 'Data Scientist'
json_output = json.dumps(person, indent=2)
print("\nTo string:")
print(json_output)
From string: {'name': 'Eve', 'age': 25, 'city': 'Boston'}

To string:
{
  "name": "Eve",
  "age": 25,
  "city": "Boston",
  "occupation": "Data Scientist"
}

Remember: - json.load() - read from file - json.loads() - read from string - json.dump() - write to file - json.dumps() - write to string


9.12 File Browsing with glob

The glob module helps you find files using pattern matching, similar to how you search in your file system.

9.13 Basic Glob Patterns

import glob

# Find all .txt files in data directory
txt_files = glob.glob('data/*.txt')
print("Text files found:")
for file in txt_files:
    print(f"  - {file}")
Text files found:
  - data/shopping_list.txt
  - data/config.txt
  - data/fruits.txt
  - data/employees.txt
  - data/output.txt
  - data/sample.txt

9.14 Common Glob Patterns

Pattern Matches
* Any characters
? Single character
[abc] Any of a, b, or c
[!abc] Not a, b, or c
** Any subdirectory (recursive)

9.15 Finding Specific File Types

# Find all JSON files
json_files = glob.glob('data/*.json')
print(f"Found {len(json_files)} JSON files:")
for file in json_files:
    print(f"  - {file}")
Found 4 JSON files:
  - data/students_updated.json
  - data/products.json
  - data/inventory.json
  - data/students.json

9.16 Pattern Matching Examples

# Find all log files
log_files = glob.glob('data/log_*.txt')
print("Log files:")
for file in sorted(log_files):
    print(f"  - {file}")
Log files:
# Find all report files
report_files = glob.glob('data/report_*.txt')
print("\nReport files:")
for file in sorted(report_files):
    print(f"  - {file}")

Report files:

9.18 Practical Use Case: Processing Multiple Files

import os

# Process all log files
log_files = glob.glob('data/log_*.txt')

print("Log File Analysis")
print("=" * 50)

for log_file in sorted(log_files):
    file_size = os.path.getsize(log_file)

    with open(log_file, 'r') as file:
        lines = file.readlines()

    print(f"\nFile: {os.path.basename(log_file)}")
    print(f"  Size: {file_size} bytes")
    print(f"  Lines: {len(lines)}")
    print(f"  First entry: {lines[0].strip()}")
Log File Analysis
==================================================

9.19 Combining Glob with JSON

# Process all JSON files
json_files = glob.glob('data/*.json')

for json_file in json_files:
    with open(json_file, 'r') as file:
        data = json.load(file)

    print(f"\n{os.path.basename(json_file)}:")
    print(f"  Top-level keys: {list(data.keys())}")

students_updated.json:
  Top-level keys: ['students', 'school', 'year']

products.json:
  Top-level keys: ['products']

inventory.json:
  Top-level keys: ['products', 'warehouse', 'last_updated']

students.json:
  Top-level keys: ['students', 'school', 'year']

9.20 Exercises

Now it’s time to practice! Try these exercises to reinforce your learning.

Exercise 1: Text File Processing

Task: Create a Python script that: 1. Reads data/shopping_list.txt 2. Counts how many items contain the letter ‘a’ 3. Writes those items to a new file exercises/items_with_a.txt

Hint Use a for loop to iterate through lines, and check if ‘a’ in item.lower()
# Your code here
# with open('data/shopping_list.txt', 'r') as file:
#     ...

Solution:

Click to show solution
# Solution
with open('data/shopping_list.txt', 'r') as file:
    items = [line.strip() for line in file if line.strip()]

items_with_a = [item for item in items if 'a' in item.lower()]

with open('exercises/items_with_a.txt', 'w') as file:
    for item in items_with_a:
        file.write(f"{item}\n")

print(f"Found {len(items_with_a)} items with 'a':")
for item in items_with_a:
    print(f"  - {item}")
Found 10 items with 'a':
  - Apples
  - Bananas
  - Bread
  - Orange Juice
  - Avocados
  - Almonds
  - Pasta
  - Pasta
  - Pasta
  - Pasta

Exercise 2: JSON Data Manipulation

Task: 1. Load data/students.json 2. Find students with GPA > 3.7 3. Save only those students to exercises/high_achievers.json

# Your code here

Solution:

Click to show solution
# Solution
import json

with open('data/students.json', 'r') as file:
    data = json.load(file)

high_achievers = [s for s in data['students'] if s['grade'] > 85]

output = {"high_achievers": high_achievers}

with open('exercises/high_achievers.json', 'w') as file:
    json.dump(output, file, indent=2)

print(f"Found {len(high_achievers)} high achievers:")
for student in high_achievers:
    print(f"  {student['name']}: {student['grade']}")
Found 3 high achievers:
  Bob: 92
  Diana: 95
  Eve: 88

Exercise 3: Glob Pattern Matching

Task: 1. Use glob to find all files starting with “log_” in the data directory 2. For each file, count the number of lines 3. Print a summary report

# Your code here

Solution:

Click to show solution
# Solution
import glob

log_files = glob.glob('data/log_*.txt')

print("Log File Summary")
print("-" * 40)

total_lines = 0
for log_file in sorted(log_files):
    with open(log_file, 'r') as file:
        line_count = len(file.readlines())

    total_lines += line_count
    print(f"{os.path.basename(log_file)}: {line_count} lines")

print("-" * 40)
print(f"Total lines across all log files: {total_lines}")
Log File Summary
----------------------------------------
----------------------------------------
Total lines across all log files: 0

Exercise 4: Combined Challenge

Task: Create a file inventory system that: 1. Uses glob to find all files in the data/ directory 2. Creates a JSON file with information about each file: - filename - extension - size in bytes - number of lines (for text files) 3. Saves this inventory to exercises/file_inventory.json

# Your code here

Solution:

Click to show solution
# Solution
import glob
import os
import json

files = glob.glob('data/*')
inventory = []

for filepath in files:
    if os.path.isfile(filepath):
        filename = os.path.basename(filepath)
        extension = os.path.splitext(filename)[1]
        size = os.path.getsize(filepath)

        file_info = {
            "filename": filename,
            "extension": extension,
            "size_bytes": size
        }

        # Count lines for text files
        if extension in ['.txt', '.json']:
            try:
                with open(filepath, 'r') as file:
                    line_count = len(file.readlines())
                file_info["lines"] = line_count
            except:
                file_info["lines"] = "N/A"

        inventory.append(file_info)

# Save inventory
output = {"inventory": inventory, "total_files": len(inventory)}

with open('exercises/file_inventory.json', 'w') as file:
    json.dump(output, file, indent=2)

print(f"Inventory created with {len(inventory)} files")
print(json.dumps(output, indent=2))
Inventory created with 12 files
{
  "inventory": [
    {
      "filename": "shopping_list.txt",
      "extension": ".txt",
      "size_bytes": 132,
      "lines": 17
    },
    {
      "filename": "config.txt",
      "extension": ".txt",
      "size_bytes": 99,
      "lines": 6
    },
    {
      "filename": "students_updated.json",
      "extension": ".json",
      "size_bytes": 906,
      "lines": 60
    },
    {
      "filename": "fruits.txt",
      "extension": ".txt",
      "size_bytes": 20,
      "lines": 3
    },
    {
      "filename": "sample_data.csv",
      "extension": ".csv",
      "size_bytes": 129
    },
    {
      "filename": "employees.txt",
      "extension": ".txt",
      "size_bytes": 128,
      "lines": 5
    },
    {
      "filename": "products.json",
      "extension": ".json",
      "size_bytes": 507,
      "lines": 9
    },
    {
      "filename": "inventory.json",
      "extension": ".json",
      "size_bytes": 443,
      "lines": 11
    },
    {
      "filename": "app.log",
      "extension": ".log",
      "size_bytes": 425
    },
    {
      "filename": "output.txt",
      "extension": ".txt",
      "size_bytes": 70,
      "lines": 3
    },
    {
      "filename": "students.json",
      "extension": ".json",
      "size_bytes": 522,
      "lines": 11
    },
    {
      "filename": "sample.txt",
      "extension": ".txt",
      "size_bytes": 127,
      "lines": 5
    }
  ],
  "total_files": 12
}

9.21 Best Practices

Always Use Context Managers

# GOOD - file closes automatically
with open('data/sample.txt', 'r') as file:
    content = file.read()

# AVOID - you must remember to close
# file = open('data/sample.txt', 'r')
# content = file.read()
# file.close()

Handle Exceptions

# Handle file not found errors
try:
    with open('data/nonexistent.txt', 'r') as file:
        content = file.read()
except FileNotFoundError:
    print("Error: File not found!")
except Exception as e:
    print(f"An error occurred: {e}")
Error: File not found!

Check if File Exists

import os

filename = 'data/sample.txt'

if os.path.exists(filename):
    print(f"{filename} exists!")
    print(f"Size: {os.path.getsize(filename)} bytes")
else:
    print(f"{filename} does not exist")
data/sample.txt exists!
Size: 127 bytes

9.22 Summary

Congratulations! You’ve learned:

  • File Operations: Reading and writing files with open(), using different modes
  • JSON Handling: Loading, modifying, and saving JSON data
  • File Discovery: Finding files with glob using pattern matching

Quick Reference

# Reading files
with open('file.txt', 'r') as f:
    content = f.read()           # entire file
    lines = f.readlines()        # list of lines
    for line in f:              # iterate line by line
        print(line)

# Writing files
with open('file.txt', 'w') as f:  # overwrites
    f.write("content")

with open('file.txt', 'a') as f:  # appends
    f.write("content")

# JSON
import json
with open('file.json', 'r') as f:
    data = json.load(f)

with open('file.json', 'w') as f:
    json.dump(data, f, indent=2)

# Glob
import glob
files = glob.glob('*.txt')        # all .txt files
files = glob.glob('data/*.json')  # all .json in data/

Next Steps

  • Explore the pathlib module for more powerful file operations
  • Learn about CSV files with the csv module
  • Practice with real-world datasets

Happy coding!