Чтение и запись файлов

Работа с файлами -- одна из базовых операций в любом языке программирования. Python предоставляет простой и мощный API для чтения, записи и обработки файлов через встроенную функцию open().

Функция open()

open() -- основной способ работы с файлами. Она возвращает файловый объект:

# Basic signature
# open(file, mode='r', encoding=None, errors=None, newline=None)

# Open a text file for reading (default mode)
file = open("data.txt")
content = file.read()
file.close()  # Don't forget to close!

Всегда используйте with

Контекстный менеджер гарантирует закрытие файла:

# CORRECT — file is always closed
with open("data.txt") as f:
    content = f.read()
# File is closed here, even if an exception occurred

# WRONG — file may not be closed on error
f = open("data.txt")
content = f.read()  # If this raises, file stays open
f.close()

Режимы открытия файлов

# Write mode — creates or overwrites
with open("output.txt", "w") as f:
    f.write("Hello, World!\n")

# Append mode — adds to the end
with open("log.txt", "a") as f:
    f.write("New log entry\n")

# Exclusive creation — fails if file exists
try:
    with open("new_file.txt", "x") as f:
        f.write("This file must not exist before")
except FileExistsError:
    print("File already exists!")

# Read and write
with open("data.txt", "r+") as f:
    content = f.read()
    f.write("\nAppended text")

Чтение файлов

read() -- все содержимое

with open("data.txt") as f:
    content = f.read()  # Entire file as a string
    print(len(content))

read(n) -- n символов

with open("data.txt") as f:
    chunk = f.read(100)  # First 100 characters
    print(chunk)

readline() -- одна строка

with open("data.txt") as f:
    first_line = f.readline()    # Includes '\n'
    second_line = f.readline()
    print(first_line.strip())    # Remove trailing newline

readlines() -- все строки в список

with open("data.txt") as f:
    lines = f.readlines()  # List of strings with '\n'
    print(f"Total lines: {len(lines)}")

# Strip newlines
with open("data.txt") as f:
    lines = [line.strip() for line in f.readlines()]

Итерация по строкам (рекомендуемый способ)

Самый эффективный способ для больших файлов -- итерация по файловому объекту:

# Memory-efficient — reads line by line
with open("large_file.txt") as f:
    for line_number, line in enumerate(f, start=1):
        if "ERROR" in line:
            print(f"Line {line_number}: {line.strip()}")

Запись файлов

write() -- запись строки

with open("output.txt", "w") as f:
    f.write("First line\n")
    f.write("Second line\n")
    # write() returns the number of characters written
    chars_written = f.write("Third line\n")
    print(f"Wrote {chars_written} characters")

writelines() -- запись списка строк

lines = ["Line 1\n", "Line 2\n", "Line 3\n"]

with open("output.txt", "w") as f:
    f.writelines(lines)  # Does NOT add newlines automatically!

# With generator expression
data = ["Alice", "Bob", "Charlie"]
with open("names.txt", "w") as f:
    f.writelines(f"{name}\n" for name in data)

print() в файл

with open("report.txt", "w") as f:
    print("Report Title", file=f)
    print("=" * 40, file=f)
    print(f"Total items: {42}", file=f)
    print("Item 1", "Item 2", sep=" | ", file=f)

Кодировки

Всегда указывайте кодировку явно, особенно для не-ASCII текста:

# UTF-8 — default on most systems, but be explicit
with open("data.txt", encoding="utf-8") as f:
    content = f.read()

# Write with encoding
with open("russian.txt", "w", encoding="utf-8") as f:
    f.write("Привет, мир!\n")

# Read Windows-encoded file
with open("legacy.txt", encoding="cp1251") as f:
    content = f.read()

# Handle encoding errors
with open("mixed.txt", encoding="utf-8", errors="replace") as f:
    content = f.read()  # Invalid bytes replaced with '?'

with open("mixed.txt", encoding="utf-8", errors="ignore") as f:
    content = f.read()  # Invalid bytes silently skipped

Python 3.14: UTF-8 по умолчанию

Начиная с Python 3.15, UTF-8 станет кодировкой по умолчанию. В Python 3.14 можно включить предупреждения:

import sys

# Check current default encoding
print(sys.getdefaultencoding())  # 'utf-8'

# Best practice: always specify encoding explicitly
with open("data.txt", encoding="utf-8") as f:
    content = f.read()

Бинарные файлы

Для работы с изображениями, аудио и другими бинарными данными используйте режим 'b':

# Read binary file
with open("image.png", "rb") as f:
    data = f.read()  # Returns bytes, not str
    print(type(data))   # <class 'bytes'>
    print(data[:8])     # First 8 bytes (PNG header)

# Write binary file
with open("copy.png", "wb") as f:
    f.write(data)

# Copy a file efficiently
def copy_file(src: str, dst: str, chunk_size: int = 8192) -> int:
    """Copy a file in chunks — memory efficient."""
    total_bytes = 0
    with open(src, "rb") as source, open(dst, "wb") as target:
        while chunk := source.read(chunk_size):
            target.write(chunk)
            total_bytes += len(chunk)
    return total_bytes

bytes_copied = copy_file("large_video.mp4", "backup.mp4")
print(f"Copied {bytes_copied:,} bytes")

Walrus-оператор для чтения чанками

# Read large file in chunks using walrus operator (:=)
with open("huge_file.bin", "rb") as f:
    while chunk := f.read(4096):
        process_chunk(chunk)

Позиция в файле

with open("data.txt", "r+") as f:
    # Read first 10 characters
    start = f.read(10)
    print(f"Position after read: {f.tell()}")  # 10

    # Move to beginning
    f.seek(0)
    print(f"Position after seek(0): {f.tell()}")  # 0

    # Move to position 5
    f.seek(5)
    rest = f.read()  # Read from position 5 to end

Временные файлы

Модуль tempfile создает временные файлы, которые автоматически удаляются:

import tempfile

# Temporary file — deleted when closed
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
    f.write("Temporary data\n")
    print(f"Temp file: {f.name}")

# Temporary directory
with tempfile.TemporaryDirectory() as tmpdir:
    filepath = f"{tmpdir}/data.txt"
    with open(filepath, "w") as f:
        f.write("Will be deleted with the directory")
# Directory and all contents are deleted here

Практический пример: обработка лог-файла

from collections import Counter
from datetime import datetime

def analyze_log(path: str) -> dict:
    """Analyze a log file and return statistics."""
    levels = Counter()
    errors: list[str] = []
    total_lines = 0

    with open(path, encoding="utf-8") as f:
        for line in f:
            total_lines += 1
            line = line.strip()

            # Count log levels
            for level in ("DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"):
                if level in line:
                    levels[level] += 1
                    break

            # Collect error messages
            if "ERROR" in line or "CRITICAL" in line:
                errors.append(line)

    return {
        "total_lines": total_lines,
        "levels": dict(levels),
        "errors": errors[:10],  # First 10 errors
        "error_rate": levels.get("ERROR", 0) / max(total_lines, 1),
    }

# Usage
stats = analyze_log("app.log")
print(f"Total lines: {stats['total_lines']}")
print(f"Error rate: {stats['error_rate']:.2%}")