Pythonのreadlinesを使ってファイルを1行ずつ処理する8つのテク

# サンプルファイル（sample.txt）の内容:
# Hello, World!
# Python is awesome.
# Let's learn readlines.

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

print(lines)

# readlines()を使用
with open('sample.txt', 'r') as file:
    lines = file.readlines()
    for line in lines:
        print(line.strip())

print("\n---\n")

# readline()を使用
with open('sample.txt', 'r') as file:
    while True:
        line = file.readline()
        if not line:
            break
        print(line.strip())

Hello, World!
Python is awesome.
Let's learn readlines.

---

Hello, World!
Python is awesome.
Let's learn readlines.

# メモリ効率の良いreadlines()の使用方法
def efficient_readlines(file_path):
    with open(file_path, 'r') as file:
        for line in file:
            yield line.strip()

# 使用例
for line in efficient_readlines('sample.txt'):
    print(line)

Hello, World!
Python is awesome.
Let's learn readlines.

def read_large_file(file_path):
    with open(file_path, 'r') as file:
        for line in file:
            yield line.strip()

# 使用例
for line in read_large_file('large_file.txt'):
    print(line)

# 方法1: strip()メソッドを使用
with open('sample.txt', 'r') as file:
    lines = [line.strip() for line in file.readlines()]

# 方法2: rstrip()メソッドを使用
with open('sample.txt', 'r') as file:
    lines = [line.rstrip('\n') for line in file.readlines()]

# 方法3: splitlines()メソッドを使用
with open('sample.txt', 'r') as file:
    content = file.read()
    lines = content.splitlines()

print(lines)

def extract_lines(file_path, line_numbers):
    with open(file_path, 'r') as file:
        return [line.strip() for i, line in enumerate(file, 1) if i in line_numbers]

# 使用例
result = extract_lines('sample.txt', [1, 3, 5])
print(result)

def csv_to_2d_array(file_path, delimiter=','):
    with open(file_path, 'r') as file:
        return [line.strip().split(delimiter) for line in file]

# 使用例
data = csv_to_2d_array('data.csv')
for row in data:
    print(row)

def process_numbers(file_path):
    with open(file_path, 'r') as file:
        numbers = [float(line.strip()) for line in file if line.strip().isdigit()]
    return sum(numbers), len(numbers), sum(numbers) / len(numbers) if numbers else 0

# 使用例
total, count, average = process_numbers('numbers.txt')
print(f"合計: {total}, 個数: {count}, 平均: {average}")

def read_with_encoding(file_path, encodings=['utf-8', 'shift_jis', 'euc-jp']):
    for encoding in encodings:
        try:
            with open(file_path, 'r', encoding=encoding) as file:
                return file.readlines()
        except UnicodeDecodeError:
            continue
    raise ValueError("適切なエンコーディングが見つかりませんでした。")

# 使用例
lines = read_with_encoding('unknown_encoding.txt')
print(lines)

def safe_file_operation(file_path):
    try:
        with open(file_path, 'r') as file:
            for line in file:
                # ファイル処理
                print(line.strip())
    except IOError as e:
        print(f"ファイル操作エラー: {e}")
    finally:
        print("ファイル操作が完了しました。")

# 使用例
safe_file_operation('sample.txt')

def memory_efficient_processing(file_path):
    def line_processor(line):
        # 行ごとの処理をここに記述
        return line.upper()

    with open(file_path, 'r') as file:
        for processed_line in map(line_processor, file):
            yield processed_line

# 使用例
for line in memory_efficient_processing('large_file.txt'):
    print(line)

try:
    with open('japanese_file.txt', 'r', encoding='utf-8') as file:
        lines = file.readlines()
except UnicodeDecodeError:
    with open('japanese_file.txt', 'r', encoding='shift_jis') as file:
        lines = file.readlines()

print(lines)

def process_large_file(file_path):
    with open(file_path, 'r') as file:
        while True:
            chunk = list(itertools.islice(file, 1000))
            if not chunk:
                break
            for line in chunk:
                # 各行の処理をここに書く
                print(line.strip())

# 使用例
process_large_file('large_file.txt')

1行目のデータ
2行目のデータ
...
1000行目のデータ
1001行目のデータ
...

import os

def safe_read_file(file_path):
    if not os.path.exists(file_path):
        print(f"ファイルが見つかりません: {file_path}")
        return None

    if not os.access(file_path, os.R_OK):
        print(f"ファイルの読み取り権限がありません: {file_path}")
        return None

    try:
        with open(file_path, 'r') as file:
            return file.readlines()
    except IOError as e:
        print(f"ファイルの読み込み中にエラーが発生しました: {e}")
        return None

# 使用例
lines = safe_read_file('example.txt')
if lines:
    for line in lines:
        print(line.strip())

1行目のテキスト
2行目のテキスト
3行目のテキスト

import csv
from collections import defaultdict

def process_large_csv(file_path):
    result = defaultdict(int)
    with open(file_path, 'r') as file:
        csv_reader = csv.reader(file)
        next(csv_reader)  # ヘッダーをスキップ
        for row in csv_reader:
            if len(row) >= 2:
                key = row[0]
                value = int(row[1])
                result[key] += value
    return dict(result)

# 使用例
file_path = 'large_data.csv'
processed_data = process_large_csv(file_path)
print(processed_data)

import re
from collections import Counter
import matplotlib.pyplot as plt

def analyze_log(file_path):
    ip_pattern = r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}'
    ip_addresses = []

    with open(file_path, 'r') as file:
        for line in file:
            match = re.search(ip_pattern, line)
            if match:
                ip_addresses.append(match.group())

    ip_counts = Counter(ip_addresses)
    return ip_counts

def visualize_ip_counts(ip_counts):
    top_10 = dict(ip_counts.most_common(10))
    plt.figure(figsize=(12, 6))
    plt.bar(top_10.keys(), top_10.values())
    plt.title('Top 10 IP Addresses')
    plt.xlabel('IP Address')
    plt.ylabel('Count')
    plt.xticks(rotation=45)
    plt.tight_layout()
    plt.show()

# 使用例
log_file = 'access.log'
ip_counts = analyze_log(log_file)
visualize_ip_counts(ip_counts)

def compare_files(file1_path, file2_path):
    with open(file1_path, 'r') as file1, open(file2_path, 'r') as file2:
        lines1 = file1.readlines()
        lines2 = file2.readlines()

    diff = []
    for i, (line1, line2) in enumerate(zip(lines1, lines2)):
        if line1 != line2:
            diff.append(f"Line {i+1}:")
            diff.append(f"< {line1.strip()}")
            diff.append(f"> {line2.strip()}")
            diff.append("")

    return "\n".join(diff)

# 使用例
file1_path = 'version1.txt'
file2_path = 'version2.txt'
differences = compare_files(file1_path, file2_path)
print(differences)

Line 3:
< This is the old version.
> This is the new version.

Line 5:
< Some content has been removed.
> Some content has been added.

import multiprocessing
import os

def process_chunk(chunk):
    # ここに各チャンクの処理ロジックを記述
    return sum(len(line.split()) for line in chunk)

def parallel_file_processing(file_path, num_processes=4):
    file_size = os.path.getsize(file_path)
    chunk_size = file_size // num_processes

    with open(file_path, 'r') as file:
        chunks = []
        for _ in range(num_processes):
            chunk = file.readlines(chunk_size)
            if chunk:
                chunks.append(chunk)

    with multiprocessing.Pool(processes=num_processes) as pool:
        results = pool.map(process_chunk, chunks)

    return sum(results)

# 使用例
file_path = 'very_large_file.txt'
total_words = parallel_file_processing(file_path)
print(f"Total words: {total_words}")