How to Compress and Decompress ZIP and TAR Files in Python

Compression and decompression are common tasks on both Windows (graphical) and Linux (command line), but implementing them programmatically can be less familiar; this article demonstrates how to perform these operations in Python.

1. ZIP file compression and decompression implementation

import os
import zipfile

# Compress a list of files and a list of directories into a zip archive
def my_zip_function(zip_file_name, zip_file_list=[], zip_dir_list=[]):
    # Use a context manager so the zip file is closed automatically
    with zipfile.ZipFile(zip_file_name, "w") as zip_obj:
        # Compress files
        for tmp_file in zip_file_list:
            zip_obj.write(tmp_file)
        # Compress directories (zipfile cannot add a directory directly, so walk it)
        for tmp_dir in zip_dir_list:
            for root, dirs, files in os.walk(tmp_dir):
                # Add the directory entry itself (comment out to skip empty dirs)
                zip_obj.write(root)
                for tmp_file in files:
                    # Build full file path; otherwise only the filename is used
                    tmp_file_path = os.path.join(root, tmp_file)
                    zip_obj.write(tmp_file_path)

# Traverse all entries in a zip archive
def my_traversal_zip_function(zip_file_name):
    with zipfile.ZipFile(zip_file_name, "r") as zip_obj:
        # Returns a list of ZipInfo objects
        all_file_list = zip_obj.infolist()
        for tmp_file in all_file_list:
            print(tmp_file.filename)
            # You can read file contents without extracting
            # if not tmp_file.is_dir():
            #     with zip_obj.open(tmp_file) as zip_fd:
            #         print(zip_fd.read())

# Extract a zip archive to a directory
def my_unzip_function(zip_file_name, path="."):
    with zipfile.ZipFile(zip_file_name, "r") as zip_obj:
        zip_obj.extractall(path=path)

if __name__ == "__main__":
    zip_file_name = "test_zip.zip"
    # Prepare test files and directories before running
    zip_file_list = ["test_tar_file1.txt", "test_tar_file2.txt"]
    zip_dir_list = ["test_tar_dir"]
    my_zip_function(zip_file_name, zip_file_list, zip_dir_list)
    my_traversal_zip_function(zip_file_name)
    # my_unzip_function(zip_file_name, path=".")

2. TAR file compression and decompression implementation

In addition to plain .tar files, formats such as .tar.gz, .tar.bz2, and .tar.xz are also supported.

import os
import tarfile

# Compress a list of files and directories into a tar archive
def my_tar_function(tar_file_name, tar_file_list=[], tar_dir_list=[], model="w"):
    # tarfile.open creates the archive; "w" creates a plain tar, other modes add compression
    with tarfile.open(tar_file_name, model) as tar_obj:
        # Add files
        for tmp_file in tar_file_list:
            tar_obj.add(tmp_file)
        # Add directories (tarfile can add a directory directly)
        for tmp_dir in tar_dir_list:
            tar_obj.add(tmp_dir)

# Traverse all entries in a tar archive
def my_traversal_tar_function(tar_file_name, model="r"):
    with tarfile.open(tar_file_name, model) as tar_obj:
        # Returns a list of TarInfo objects
        all_file_list = tar_obj.getmembers()
        for tmp_file in all_file_list:
            print(tmp_file.name)
            # You can read file contents without extracting
            # if not tmp_file.isdir():
            #     tar_fd = tar_obj.extractfile(tmp_file)
            #     print(tar_fd.read())

# Extract a tar archive to a directory
def my_untar_function(tar_file_name, path=".", model="r"):
    with tarfile.open(tar_file_name, model) as tar_obj:
        tar_obj.extractall(path=path)

if __name__ == "__main__":
    # Prepare test files and directories before running
    tar_file_list = ["test_tar_file1.txt", "test_tar_file2.txt"]
    tar_dir_list = ["test_tar_dir"]
    tar_file_name = "test_tar.tar"
    # tarfile also supports gz/bz2/xz compression by adding ":gz", ":bz2", etc. to the mode
    # For reading any format, use "r:*"
    open_model = "w"
    # open_model = "w:gz"
    my_tar_function(tar_file_name, tar_file_list, tar_dir_list, model=open_model)
    open_model = "r"
    # open_model = "r:*"
    my_traversal_tar_function(tar_file_name, model=open_model)
    # my_untar_function(tar_file_name, path=".", model=open_model)

Link: https://www.cnblogs.com/djdjdj123/p/18124124