Python3 tarfile extraction with a pprogress callback function

extract.py

#!/usr/bin/env python3

# A sample code to have a tarfile extraction handle a progress callback
# tarfile must handle gz, bz2 & xz files transparently
# Author: [email protected]
# Title: tar extraction with progress bar

import io
import os
import tarfile

class ProgressFileObject(io.FileIO):
    """Overide the fileio object to have a callback on progress"""

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

        # callback will be a function passed on progressfn
        if kwargs["progressfn"]:
            self.progfn = kwargs["progressfn"]           
            # must remove the progressfn if present from the kwargs to make fileio happy 
            kwargs.pop("progressfn")

        io.FileIO.__init__(self, path, *args, **kwargs)

    def read(self, size):
        """Each time a chunk in read call the progress function if there"""
        if self.progfn:    
            # must calc and call the progress callback function
            progress = self.tell() / self._total_size
            self.progfn(progress)

        return io.FileIO.read(self, size)


def prog(prog):
    print("Extraction progress is {:0.2%}".format(prog))


file = "./your_big_file.tar.gz"
tar = tarfile.open(fileobj=ProgressFileObject(file, progressfn=prog))
tar.extractall()
tar.close()