Python標準のzipfileとgzipで圧縮・解凍する方法をわかりやすく解説

# zipfile_basic_file.py
import zipfile

# 圧縮対象のファイルと、作成するZIPファイル名を指定します
src_file = "example.txt"
zip_name = "single_file.zip"

# with構文でクローズを自動化します
# compressionにZIP_DEFLATEDを指定すると一般的な圧縮が有効になります
with zipfile.ZipFile(zip_name, mode="w", compression=zipfile.ZIP_DEFLATED, compresslevel=6) as zf:
    # arcnameを指定すると、ZIP内の名前を任意に変えられます
    zf.write(src_file, arcname="docs/example.txt")

print(f"Created: {zip_name}")

# zipfile_zip_directory.py
import os
import zipfile

def zip_directory(src_dir: str, zip_name: str, compresslevel: int = 6) -> None:
    # src_dirの末尾スラッシュの有無に左右されないようにabs化
    src_dir_abs = os.path.abspath(src_dir)

    with zipfile.ZipFile(zip_name, mode="w", compression=zipfile.ZIP_DEFLATED, compresslevel=compresslevel) as zf:
        for root, _, files in os.walk(src_dir_abs):
            for file in files:
                full_path = os.path.join(root, file)
                # ZIP内に入れるときはsrc_dirからの相対パスを使うのが安全です
                arcname = os.path.relpath(full_path, start=src_dir_abs)
                zf.write(full_path, arcname=arcname)
        # 内容確認(学習用): 実運用では省略可
        print("Archive members:")
        for name in zf.namelist():
            print(" -", name)

if __name__ == "__main__":
    zip_directory("project_folder", "project_archive.zip", compresslevel=6)

# zipfile_extract_safe.py
import os
import zipfile

def safe_extractall(zip_path: str, dest_dir: str) -> None:
    # 出力先の絶対パス
    dest_abs = os.path.abspath(dest_dir)

    with zipfile.ZipFile(zip_path, "r") as zf:
        # 各メンバーの展開先パスを検証
        for info in zf.infolist():
            extracted_abs = os.path.abspath(os.path.join(dest_abs, info.filename))
            # commonpathで出力先ディレクトリ配下かを確認
            if os.path.commonpath([dest_abs, extracted_abs]) != dest_abs:
                raise ValueError(f"Unsafe path detected: {info.filename}")
        # 安全が確認できたらまとめて展開
        zf.extractall(dest_abs)

if __name__ == "__main__":
    os.makedirs("unpacked", exist_ok=True)
    safe_extractall("project_archive.zip", "unpacked")
    print("Extracted to 'unpacked'")

# zipfile_paths_and_levels.py
import zipfile

with zipfile.ZipFile("levels.zip", "w", compression=zipfile.ZIP_DEFLATED, compresslevel=9) as zf:
    # ZIP内は相対パスで揃える
    zf.write("large.txt", arcname="docs/large.txt")

# 日本語ファイル名を安全な英字名に差し替えて格納する例
import zipfile
with zipfile.ZipFile("safe_name.zip", "w", compression=zipfile.ZIP_DEFLATED) as zf:
    zf.write("レポート2025年3月版.txt", arcname="report_2025_03.txt")

# with構文の基本形
import zipfile

with zipfile.ZipFile("data.zip", "w", zipfile.ZIP_DEFLATED) as zf:
    zf.write("data.csv", arcname="data/data.csv")
# ここに来た時点で自動的にクローズされています

# gzip_text_write.py
import gzip

text = "こんにちは、Gzip圧縮の世界！\n圧縮するとサイズを節約できます。"

with gzip.open("hello.txt.gz", mode="wt", encoding="utf-8", compresslevel=9) as f:
    f.write(text)

print("Wrote hello.txt.gz")

# gzip_binary_file.py
import gzip

# ファイルから読み込んで.gzに書く(ストリーム)
with open("image.png", "rb") as src, gzip.open("image.png.gz", "wb", compresslevel=6) as dst:
    # 大きいファイルでもそのままコピー可能
    dst.write(src.read())

# メモリ上のbytesを圧縮する方法
data = b"A" * 1024  # 1KBのダミーデータ
compressed = gzip.compress(data, compresslevel=6)
decompressed = gzip.decompress(compressed)
assert decompressed == data

print("Binary gzip done")

# gzip_read.py
import gzip

# テキストとして読む
with gzip.open("hello.txt.gz", "rt", encoding="utf-8") as f:
    content = f.read()
print(content.splitlines()[0])  # 先頭行を確認

# バイナリとして読む
with gzip.open("image.png.gz", "rb") as f:
    data = f.read()
print(f"Read {len(data)} bytes")

# gzip_modes_and_levels.py
import gzip

# テキストを書き出す。再現性のためmtime=0を指定
with gzip.open("log.txt.gz", "wt", encoding="utf-8", compresslevel=6, mtime=0) as f:
    f.write("line1\nline2\n")

# gzip_extension.py
import os
import gzip

src = "app.log"
dst = src + ".gz"  # "app.log.gz"

with open(src, "rb") as fin, gzip.open(dst, "wb") as fout:
    fout.write(fin.read())

print(f"Compressed: {dst}")

# recipe_zip_for_distribution.py
import os
import zipfile

def zip_for_distribution(src_dir: str, zip_name: str) -> None:
    src_abs = os.path.abspath(src_dir)
    with zipfile.ZipFile(zip_name, "w", zipfile.ZIP_DEFLATED, compresslevel=6) as zf:
        for root, dirs, files in os.walk(src_abs):
            # .gitなどの隠しディレクトリを除外(必要に応じて拡張)
            dirs[:] = [d for d in dirs if not d.startswith(".")]
            for file in files:
                if file.startswith("."):
                    continue
                full_path = os.path.join(root, file)
                arcname = os.path.relpath(full_path, src_abs)
                zf.write(full_path, arcname=arcname)
    print(f"Packaged: {zip_name}")

if __name__ == "__main__":
    zip_for_distribution("my_project", "my_project.zip")

# recipe_gzip_daily_logs.py
import os
import gzip
from datetime import datetime

def gzip_today_log(prefix: str = "app"):
    today = datetime.now().strftime("%Y-%m-%d")
    src = f"{prefix}-{today}.log"
    dst = src + ".gz"
    if not os.path.exists(src):
        print(f"No log for today: {src}")
        return

    with open(src, "rb") as fin, gzip.open(dst, "wb", compresslevel=6, mtime=0) as fout:
        # mtime=0でビルドの再現性を高める
        fout.write(fin.read())
    print(f"Compressed: {dst}")

if __name__ == "__main__":
    gzip_today_log()

# recipe_zip_selected_ext.py
import os
import zipfile

def zip_selected_extensions(src_dir: str, zip_name: str, exts: tuple[str, ...]) -> None:
    src_abs = os.path.abspath(src_dir)
    with zipfile.ZipFile(zip_name, "w", zipfile.ZIP_DEFLATED, compresslevel=6) as zf:
        for root, _, files in os.walk(src_abs):
            for file in files:
                if file.lower().endswith(exts):
                    full_path = os.path.join(root, file)
                    arcname = os.path.relpath(full_path, src_abs)
                    zf.write(full_path, arcname=arcname)
    print(f"Created: {zip_name}")

if __name__ == "__main__":
    # .py と .md を含める
    zip_selected_extensions("my_project", "src_docs.zip", (".py", ".md"))

# recipe_error_handling.py
import os
import zipfile

def safe_zip_write(zip_name: str, file_to_add: str) -> None:
    if not os.path.exists(file_to_add):
        print(f"Not found: {file_to_add}")
        return

    try:
        with zipfile.ZipFile(zip_name, "a", zipfile.ZIP_DEFLATED, compresslevel=6) as zf:
            zf.write(file_to_add, arcname=os.path.basename(file_to_add))
        print(f"Added to {zip_name}: {file_to_add}")
    except PermissionError:
        print("Permission denied. Try running with proper permissions or change destination.")
    except OSError as e:
        print(f"OS error: {e}")

if __name__ == "__main__":
    safe_zip_write("assets.zip", "logo.png")

# recipe_extract_to_dir.py
import os
import zipfile

zip_path = "my_project.zip"
out_root = "dist"
subdir = "v1.0.0"

dest = os.path.join(out_root, subdir)  # dist/v1.0.0 (OSにより区切りが変化)
os.makedirs(dest, exist_ok=True)

with zipfile.ZipFile(zip_path, "r") as zf:
    zf.extractall(path=dest)

print(f"Extracted to: {dest}")