How do I create a zip file of a file path using Python, including empty directories?

Question

I've been trying to use the zipfile and shutil.make_archive modules to recursively create a zip file of a directory. Both modules work great--except empty directories do not get added to the archive. Empty directories containing other empty directories are also silently skipped.

I can use 7Zip to create an archive of the same path and empty directories are preserved. Therefore I know this is possible within the file format itself. I just don't know how to do it within Python. Any ideas? Thanks!

Answer 1

There is a example using zipfile:

import os, zipfile  
from os.path import join  
def zipfolder(foldername, filename, includeEmptyDIr=True):   
    empty_dirs = []  
    zip = zipfile.ZipFile(filename, 'w', zipfile.ZIP_DEFLATED)  
    for root, dirs, files in os.walk(foldername):  
        empty_dirs.extend([dir for dir in dirs if os.listdir(join(root, dir)) == []])  
        for name in files:  
            zip.write(join(root ,name))  
        if includeEmptyDIr:  
            for dir in empty_dirs:  
                zif = zipfile.ZipInfo(join(root, dir) + "/")  
                zip.writestr(zif, "")  
        empty_dirs = []  
    zip.close() 

if __name__ == "__main__":
    zipfolder('test1/noname/', 'zip.zip')

Answer 2

This is lifted from Adding folders to a zip file using python but is the only function I have tried that works. The one listed as the answer does not work under Python 2.7.3 (doesn't copy empty directories and is inefficient). The following is tried and tested:

#!/usr/bin/python
import os
import zipfile

def zipdir(dirPath=None, zipFilePath=None, includeDirInZip=True):

    if not zipFilePath:
        zipFilePath = dirPath + ".zip"
    if not os.path.isdir(dirPath):
        raise OSError("dirPath argument must point to a directory. "
        "'%s' does not." % dirPath)
    parentDir, dirToZip = os.path.split(dirPath)
    #Little nested function to prepare the proper archive path
    def trimPath(path):
        archivePath = path.replace(parentDir, "", 1)
        if parentDir:
            archivePath = archivePath.replace(os.path.sep, "", 1)
        if not includeDirInZip:
            archivePath = archivePath.replace(dirToZip + os.path.sep, "", 1)
        return os.path.normcase(archivePath)

    outFile = zipfile.ZipFile(zipFilePath, "w",
        compression=zipfile.ZIP_DEFLATED)
    for (archiveDirPath, dirNames, fileNames) in os.walk(dirPath):
        for fileName in fileNames:
            filePath = os.path.join(archiveDirPath, fileName)
            outFile.write(filePath, trimPath(filePath))
        #Make sure we get empty directories as well
        if not fileNames and not dirNames:
            zipInfo = zipfile.ZipInfo(trimPath(archiveDirPath) + "/")
            #some web sites suggest doing
            #zipInfo.external_attr = 16
            #or
            #zipInfo.external_attr = 48
            #Here to allow for inserting an empty directory.  Still TBD/TODO.
            outFile.writestr(zipInfo, "")
    outFile.close()

Answer 3

You'll need to register a new archive format to do that, since the default ZIP archiver does not support that. Take a look at the meat of the existing ZIP archiver. Make your own archiver that creates directories using that currently-unused dirpath variable. I looked for how to create an empty directory and found this:

zip.writestr(zipfile.ZipInfo('empty/'), '')

With that, you should be able to write the necessary code to make it archive empty directories.

Answer 4

def zip_dir(src_dir, dst_zip, *, skip_suffixes=None, dry=False):
    import logging
    from pathlib import Path
    from os import walk
    from tempfile import TemporaryDirectory
    from zipfile import ZipFile, ZipInfo

    _log = logging.getLogger(zip_dir.__name__)
    _log.addHandler(logging.NullHandler())
    _sep = 50 * "-"

    skip_suffixes = skip_suffixes or []
    src_dir, dst_zip = Path(src_dir), Path(dst_zip)
    _log.info("zipping dir: '%s' to: '%s", str(src_dir), str(dst_zip))

    if not src_dir.exists():
        raise FileNotFoundError(str(src_dir))
    if not src_dir.is_dir():
        raise NotADirectoryError(str(src_dir))
    if dst_zip.exists():
        raise FileExistsError(str(dst_zip))

    with TemporaryDirectory() as tmp_dir:
        tmp_zip_path = Path(tmp_dir).joinpath(dst_zip.name)

        with ZipFile(str(tmp_zip_path), mode="w") as zip_out:
            for root, dirs, files in walk(src_dir):
                root = Path(root)

                for folder in dirs:
                    folder = root.joinpath(folder)

                    # add empty folders to the zip
                    if not list(folder.iterdir()):
                        _log.debug(_sep)
                        folder_name = f"{str(folder.relative_to(src_dir))}/"
                        _log.debug("empty dir: '%s'", folder_name)

                        if dry:
                            continue

                        zip_out.writestr(ZipInfo(folder_name), "")

                for file in files:
                    file = root.joinpath(file)
                    _log.debug(_sep)
                    _log.debug("adding:  '%s'", str(file))

                    should_skip = None
                    for suffix in file.suffixes:
                        if suffix in skip_suffixes:
                            should_skip = suffix
                            break

                    if should_skip:
                        _log.debug("skipped [%s]: %s", should_skip, str(file))
                        continue

                    arcname = str(file.relative_to(src_dir))
                    _log.debug("arcname: '%s'", arcname)

                    if dry:
                        continue

                    zip_out.write(str(file), arcname=arcname)

        if not dry:
            dst_zip.write_bytes(tmp_zip_path.read_bytes())

        tmp_zip_path.unlink()

if __name__ == '__main__':
    import logging
    logging.basicConfig(level=logging.DEBUG, format="%(asctime)s | %(levelname)8s | %(module)25s:%(lineno)-5s | %(message)s")

    zip_dir("/tmp/opera_profile", "opera_profile.zip", skip_suffixes=[".log"], dry=True)