Last active
April 19, 2024 09:01
-
-
Save rindeal/a6bbd5078f41b573e53f836c3e5da192 to your computer and use it in GitHub Desktop.
Python 3 function to extract/unpack TAR archive file directly from web URL in one continous stream.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# SPDX-FileCopyrightText: 2018 Jan Chren (rindeal) | |
# SPDX-License-Identifier: GPL-2.0-only OR GPL-3.0-only | |
import pathlib | |
import urllib | |
import shutil | |
import tarfile | |
def fetch_tar(url: str, dest_dir: pathlib.Path, clean_dest: bool = False, strip_components: int = 0): | |
if clean_dest and dest_dir.exists(): | |
shutil.rmtree(dest_dir) | |
if not dest_dir.exists(): | |
dest_dir.mkdir(parents=True, exist_ok=True) | |
with urllib.request.urlopen(url) as resp: | |
with tarfile.open(fileobj=resp, mode='r|*') as tar: | |
for tarinfo in tar.next(): | |
if strip_components: | |
tarinfo.name = pathlib.Path(*pathlib.Path(tarinfo.name).parts[strip_components:]) | |
tar.extract(tarinfo, path=dest_dir) | |
# clean member cache to save on memory usage and processing time wasted on managing this list | |
tar.members = [] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment