Learn Python Programming

Reading CSV Files in Python

Python's csv module provides two main approaches for reading CSV files: csv.reader (list-based) and csv.DictReader (dictionary-based). Both handle quoting, escaping, and delimiters automatically.

Basic Reading with csv.reader

import csv

# csv.reader returns each row as a list of strings
with open("employees.csv", "r") as f:
    reader = csv.reader(f)

    # First row is usually the header
    header = next(reader)
    print(header)  # ["name", "department", "salary"]

    # Iterate remaining rows
    for row in reader:
        name, department, salary = row
        print(f"{name} works in {department}, earns ${salary}")

# Output:
# Alice works in Engineering, earns $95000
# Bob works in Marketing, earns $72000

Reading with csv.DictReader

import csv

# DictReader uses the first row as keys automatically
with open("employees.csv", "r") as f:
    reader = csv.DictReader(f)

    # Access columns by header name — much more readable
    for row in reader:
        print(f"{row[\"name\"]}: {row[\"department\"]} - ${row[\"salary\"]}")

    # reader.fieldnames gives you the header list
    # print(reader.fieldnames)  # ["name", "department", "salary"]

# If CSV has no header, provide field names manually
with open("no_header.csv", "r") as f:
    reader = csv.DictReader(f, fieldnames=["id", "name", "email"])
    for row in reader:
        print(row["email"])

Reading with Different Delimiters

import csv

# Tab-separated values (TSV)
with open("data.tsv", "r") as f:
    reader = csv.reader(f, delimiter="\t")
    for row in reader:
        print(row)

# Semicolon-separated (common in European locales)
with open("data_eu.csv", "r") as f:
    reader = csv.reader(f, delimiter=";")
    for row in reader:
        print(row)

# Pipe-separated
with open("data.txt", "r") as f:
    reader = csv.reader(f, delimiter="|")
    for row in reader:
        print(row)

# Auto-detect delimiter with csv.Sniffer
with open("unknown.csv", "r") as f:
    sample = f.read(1024)
    dialect = csv.Sniffer().sniff(sample)
    f.seek(0)
    reader = csv.reader(f, dialect)
    for row in reader:
        print(row)

Loading CSV into Data Structures

import csv

# Load all rows into a list of dictionaries
def load_csv(filename):
    with open(filename, "r") as f:
        return list(csv.DictReader(f))

people = load_csv("employees.csv")
print(f"Total records: {len(people)}")
print(people[0])  # {"name": "Alice", "department": "Engineering", ...}

# Filter while reading
def load_filtered(filename, department):
    results = []
    with open(filename, "r") as f:
        for row in csv.DictReader(f):
            if row["department"] == department:
                results.append(row)
    return results

engineers = load_filtered("employees.csv", "Engineering")

# Convert types during reading (CSV values are always strings)
with open("sales.csv") as f:
    reader = csv.DictReader(f)
    total = 0
    for row in reader:
        amount = float(row["amount"])  # convert string to float
        quantity = int(row["quantity"])
        total += amount * quantity
    print(f"Total revenue: ${total:,.2f}")

Handling Encoding and Errors

import csv

# Handle UTF-8 BOM (common in Excel exports)
with open("excel_export.csv", "r", encoding="utf-8-sig") as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row)

# Handle encoding errors gracefully
with open("messy.csv", "r", encoding="utf-8", errors="replace") as f:
    reader = csv.reader(f)
    for row in reader:
        print(row)

# Skip malformed rows
with open("dirty.csv", "r") as f:
    reader = csv.reader(f)
    for i, row in enumerate(reader, 1):
        try:
            if len(row) < 3:  # expected 3 columns
                print(f"Skipping row {i}: too few columns")
                continue
            process(row)
        except Exception as e:
            print(f"Error on row {i}: {e}")

• Use csv.DictReader for readable, header-based column access.
• All CSV values are strings — cast to int/float as needed.
• Use encoding="utf-8-sig" for Excel-exported CSV files with BOM.
• Use csv.Sniffer to auto-detect delimiters in unknown files.
• Process row-by-row for large files to avoid loading everything into memory.