Python tarfile 进度输出?

21 投票
7 回答
13568 浏览
提问于 2025-04-16 03:51

我正在使用以下代码来解压一个tar文件:

import tarfile
tar = tarfile.open("sample.tar.gz")
tar.extractall()
tar.close()

不过,我想知道当前正在解压哪些文件,怎么才能做到这一点呢?

额外加分:有没有办法显示解压进度的百分比?我想用这个来更新tkinter中的进度条。谢谢!

7 个回答

7

你可以直接使用 tqdm() 这个工具,来显示正在提取的文件数量的进度:

import tarfile
from tqdm import tqdm

# open your tar.gz file
with tarfile.open(name=path) as tar:

    # Go over each member
    for member in tqdm(iterable=tar.getmembers(), total=len(tar.getmembers())):

        # Extract member
        tar.extract(member=member)
7

你可以在 extractall() 这个函数里指定 members 参数。

with tarfile.open(<path>, 'r') as tarball:
   tarball.extractall(path=<some path>, members = track_progress(tarball))

def track_progress(members):
   for member in members:
      # this will be the current file being extracted
      yield member

memberTarInfo 对象,想了解所有可用的功能和属性,可以在 这里查看。

13

文件进度和全局进度:

import io
import os
import tarfile

def get_file_progress_file_object_class(on_progress):
    class FileProgressFileObject(tarfile.ExFileObject):
        def read(self, size, *args):
            on_progress(self.name, self.position, self.size)
            return tarfile.ExFileObject.read(self, size, *args)
    return FileProgressFileObject

class TestFileProgressFileObject(tarfile.ExFileObject):
    def read(self, size, *args):
        on_progress(self.name, self.position, self.size)
        return tarfile.ExFileObject.read(self, size, *args)

class ProgressFileObject(io.FileIO):
    def __init__(self, path, *args, **kwargs):
        self._total_size = os.path.getsize(path)
        io.FileIO.__init__(self, path, *args, **kwargs)

    def read(self, size):
        print("Overall process: %d of %d" %(self.tell(), self._total_size))
        return io.FileIO.read(self, size)

def on_progress(filename, position, total_size):
    print("%s: %d of %s" %(filename, position, total_size))

tarfile.TarFile.fileobject = get_file_progress_file_object_class(on_progress)
tar = tarfile.open(fileobj=ProgressFileObject("a.tgz"))
tar.extractall()
tar.close()

撰写回答