I have a Python script that zips a file (new.txt):
tofile = "/root/files/result/"+file
targetzipfile = new.zip # This is how I want my zip to look like
zf = zipfile.ZipFile(targetzipfile, mode='w')
try:
#adding to archive
zf.write(tofile)
finally:
zf.close()
When I do this I get the zip file. But when I try to unzip the file I get the text file inside of a series of directories corresponding to the path of the file i.e I see a folder called root in the result directory and more directories within it, i.e. I have
/root/files/result/new.zip
and when I unzip new.zip I have a directory structure that looks like
/root/files/result/root/files/result/new.txt
Is there a way I can zip such that when I unzip I only get new.txt?
In other words I have /root/files/result/new.zip and when I unzip new.zip, it should look like
/root/files/results/new.txt
The zipfile.write() method takes an optional arcname argument that specifies what the name of the file should be inside the zipfile
I think you need to do a modification for the destination, otherwise it will duplicate the directory. Use :arcname to avoid it. try like this:
import os
import zipfile
def zip(src, dst):
zf = zipfile.ZipFile("%s.zip" % (dst), "w", zipfile.ZIP_DEFLATED)
abs_src = os.path.abspath(src)
for dirname, subdirs, files in os.walk(src):
for filename in files:
absname = os.path.abspath(os.path.join(dirname, filename))
arcname = absname[len(abs_src) + 1:]
print 'zipping %s as %s' % (os.path.join(dirname, filename),
arcname)
zf.write(absname, arcname)
zf.close()
zip("src", "dst")
zf.write(tofile)
to change
zf.write(tofile, zipfile_dir)
for example
zf.write("/root/files/result/root/files/result/new.txt", "/root/files/results/new.txt")
To illustrate most clearly,
directory structure:
/Users
└── /user
. ├── /pixmaps
. │ ├── pixmap_00.raw
. │ ├── pixmap_01.raw
│ ├── /jpeg
│ │ ├── pixmap_00.jpg
│ │ └── pixmap_01.jpg
│ └── /png
│ ├── pixmap_00.png
│ └── pixmap_01.png
├── /docs
├── /programs
├── /misc
.
.
.
Directory of interest: /Users/user/pixmaps
First attemp
import os
import zipfile
TARGET_DIRECTORY = "/Users/user/pixmaps"
ZIPFILE_NAME = "CompressedDir.zip"
def zip_dir(directory, zipname):
"""
Compress a directory (ZIP file).
"""
if os.path.exists(directory):
outZipFile = zipfile.ZipFile(zipname, 'w', zipfile.ZIP_DEFLATED)
for dirpath, dirnames, filenames in os.walk(directory):
for filename in filenames:
filepath = os.path.join(dirpath, filename)
outZipFile.write(filepath)
outZipFile.close()
if __name__ == '__main__':
zip_dir(TARGET_DIRECTORY, ZIPFILE_NAME)
ZIP file structure:
CompressedDir.zip
.
└── /Users
└── /user
└── /pixmaps
├── pixmap_00.raw
├── pixmap_01.raw
├── /jpeg
│ ├── pixmap_00.jpg
│ └── pixmap_01.jpg
└── /png
├── pixmap_00.png
└── pixmap_01.png
Avoiding the full directory path
def zip_dir(directory, zipname):
"""
Compress a directory (ZIP file).
"""
if os.path.exists(directory):
outZipFile = zipfile.ZipFile(zipname, 'w', zipfile.ZIP_DEFLATED)
# The root directory within the ZIP file.
rootdir = os.path.basename(directory)
for dirpath, dirnames, filenames in os.walk(directory):
for filename in filenames:
# Write the file named filename to the archive,
# giving it the archive name 'arcname'.
filepath = os.path.join(dirpath, filename)
parentpath = os.path.relpath(filepath, directory)
arcname = os.path.join(rootdir, parentpath)
outZipFile.write(filepath, arcname)
outZipFile.close()
if __name__ == '__main__':
zip_dir(TARGET_DIRECTORY, ZIPFILE_NAME)
ZIP file structure:
CompressedDir.zip
.
└── /pixmaps
├── pixmap_00.raw
├── pixmap_01.raw
├── /jpeg
│ ├── pixmap_00.jpg
│ └── pixmap_01.jpg
└── /png
├── pixmap_00.png
└── pixmap_01.png
The arcname parameter in the write method specifies what will be the name of the file inside the zipfile:
import os
import zipfile
# 1. Create a zip file which we will write files to
zip_file = "/home/username/test.zip"
zipf = zipfile.ZipFile(zip_file, 'w', zipfile.ZIP_DEFLATED)
# 2. Write files found in "/home/username/files/" to the test.zip
files_to_zip = "/home/username/files/"
for file_to_zip in os.listdir(files_to_zip):
file_to_zip_full_path = os.path.join(files_to_zip, file_to_zip)
# arcname argument specifies what will be the name of the file inside the zipfile
zipf.write(filename=file_to_zip_full_path, arcname=file_to_zip)
zipf.close()
You can isolate just the file name of your sources files using:
name_file_only= name_full_path.split(os.sep)[-1]
For example, if name_full_path is /root/files/results/myfile.txt, then name_file_only will be myfile.txt. To zip myfile.txt to the root of the archive zf, you can then use:
zf.write(name_full_path, name_file_only)
Check out the documentation for Zipfile.write.
ZipFile.write(filename[, arcname[, compress_type]]) Write the file
named filename to the archive, giving it the archive name arcname (by
default, this will be the same as filename, but without a drive letter
and with leading path separators removed)
https://docs.python.org/2/library/zipfile.html#zipfile.ZipFile.write
Try the following:
import zipfile
import os
filename = 'foo.txt'
# Using os.path.join is better than using '/' it is OS agnostic
path = os.path.join(os.path.sep, 'tmp', 'bar', 'baz', filename)
zip_filename = os.path.splitext(filename)[0] + '.zip'
zip_path = os.path.join(os.path.dirname(path), zip_filename)
# If you need exception handling wrap this in a try/except block
with zipfile.ZipFile(zip_path, 'w') as zf:
zf.write(path, zip_filename)
The bottom line is that if you do not supply an archive name then the filename is used as the archive name and it will contain the full path to the file.
It is much simpler than expected, I configured the module using the parameter "arcname" as "file_to_be_zipped.txt", so the folders do not appear in my final zipped file:
mmpk_zip_file = zipfile.ZipFile("c:\\Destination_folder_name\newzippedfilename.zip", mode='w', compression=zipfile.ZIP_DEFLATED)
mmpk_zip_file.write("c:\\Source_folder_name\file_to_be_zipped.txt", "file_to_be_zipped.txt")
mmpk_zip_file.close()
We can use this
import os
# single File
os.system(f"cd {destinationFolder} && zip fname.zip fname")
# directory
os.system(f"cd {destinationFolder} && zip -r folder.zip folder")
For me, This is working.
Specify the arcname input of the write method as following:
tofile = "/root/files/result/"+file
NewRoot = "files/result/"
zf.write(tofile, arcname=tofile.split(NewRoot)[1])
More info:
ZipFile.write(filename, arcname=None, compress_type=None,
compresslevel=None)
https://docs.python.org/3/library/zipfile.html
I face the same problem and i solve it with writestr. You can use it like this:
zipObject.writestr(<filename> , <file data, bytes or string>)
If you want an elegant way to do it with pathlib you can use it this way:
from pathlib import Path
import zipfile
def zip_dir(path_to_zip: Path):
zip_file = Path(path_to_zip).with_suffix('.zip')
z = zipfile.ZipFile(zip_file, 'w', zipfile.ZIP_DEFLATED)
for f in list(path_to_zip.rglob('*.*')):
z.write(f, arcname=f.relative_to(path_to_zip))
To get rid of the absolute path, I came up with this:
def create_zip(root_path, file_name, ignored=[], storage_path=None):
"""Create a ZIP
This function creates a ZIP file of the provided root path.
Args:
root_path (str): Root path to start from when picking files and directories.
file_name (str): File name to save the created ZIP file as.
ignored (list): A list of files and/or directories that you want to ignore. This
selection is applied in root directory only.
storage_path: If provided, ZIP file will be placed in this location. If None, the
ZIP will be created in root_path
"""
if storage_path is not None:
zip_root = os.path.join(storage_path, file_name)
else:
zip_root = os.path.join(root_path, file_name)
zipf = zipfile.ZipFile(zip_root, 'w', zipfile.ZIP_DEFLATED)
def iter_subtree(path, layer=0):
# iter the directory
path = Path(path)
for p in path.iterdir():
if layer == 0 and p.name in ignored:
continue
zipf.write(p, str(p).replace(root_path, '').lstrip('/'))
if p.is_dir():
iter_subtree(p, layer=layer+1)
iter_subtree(root_path)
zipf.close()
Maybe it isn't the most elegant solution, but this works. If we just use p.name when providing the file name to write() method, then it doesn't create the proper directory structure.
Moreover, if it's needed to ignore the selected directories or files from the root path, this ignores those selections too.
This is an example I used. I have one excel file, Treport where I am using python + pandas in my dowork function to create pivot tables, etc. for each of the companies in CompanyNames. I create a zip file of the csv and a non-zip file so I can check as well.
The writer specifies the path where I want my .xlsx to go and for my zip files, I specify that in the zip.write(). I just specify the name of the xlsx file that was recently created, and that is what gets zipped up, not the whole directory. Beforehand I was just specifying 'writer' and would zip up the whole directory. This allows me to zip up just the recently created excel file.
Treport = 'TestReportData.csv'
CompanyNames = ['Company1','Company2','Company3']
for CompName in CompanyNames:
strcomp = str(CompName)
#Writer Creates pathway to output report to. Each company gets unique file.
writer = pd.ExcelWriter(f"C:\\Users\\MyUser\\Documents\\{strcomp}addReview.xlsx", engine='xlsxwriter')
DoWorkFunction(CompName, Treport, writer)
writer.save()
with ZipFile(f"C:\\Users\\MyUser\\Documents\\{strcomp}addR.zip", 'w') as zip:
zip.write(writer, f"{strcomp}addReview.xlsx")
Related
I'm working on a directory with 27 folders and various XML files inside each folder.
was able to:
parse one XML file and write to a CSV file
traverse one folder and read and parse all XML files in it
challenges:
having a problem trying to go through and parse all the XML files from the root folder to its subfolders
Send help and thank you. Code snippets below
# working in one folder only
import csv
import xml.etree.ElementTree as ET
import os
## directory
path = "/Users.../y"
filenames = []
## Count the number of xml files of each folder
files = os.listdir(path)
print("\n")
xml_data_to_csv = open('/Users.../xml_extract.csv', 'w')
list_head = []
csvwriter = csv.writer(xml_data_to_csv)
# Read XML files in a folder
for filename in os.listdir(path):
if not filename.endswith('.xml'):
continue
fullname = os.path.join(path,filename)
print("\n", fullname)
filenames.append(fullname)
# parse elements in each XML file
for filename in filenames:
tree = ET.parse(filename)
root = tree.getroot()
extract_xml=[]
## extract child elements per xml file
print("\n")
for x in root.iter('Info'):
for element in x:
print(element.tag,element.text)
extract_xml.append(element.text)
## Write list nodes to csv
csvwriter.writerow(extract_xml)
## Close CSV file
xml_data_to_csv.close()
You can get the list of all the XML files in a given path with
import os
path = "main/root"
filelist = []
for root, dirs, files in os.walk(path):
for file in files:
if not file.endswith('.xml'):
continue
filelist.append(os.path.join(root, file))
for file in filelist:
print(file)
# or in your case parse the XML 'file'
If for instance:
$ tree /main/root
/main/root
├── a
│ ├── a.xml
│ ├── b.xml
│ └── c.xml
├── b
│ ├── d.xml
│ ├── e.xml
│ └── x.txt
└── c
├── f.xml
└── g.xml
we get:
/main/root/c/g.xml
/main/root/c/f.xml
/main/root/b/e.xml
/main/root/b/d.xml
/main/root/a/c.xml
/main/root/a/b.xml
/main/root/a/a.xml
If you want to sort directories and files:
for root, dirs, files in os.walk(path):
dirs.sort()
for file in sorted(files):
if not file.endswith('.xml'):
continue
filelist.append(os.path.join(root, file))
You can use os.walk:
import os
for dir_name, dirs, files in os.walk('<root_dir>'):
# parse files
You can use the pathlib module to "glob" the XML files. It will search all subdirectories for the pattern you supply and return Path objects that already include the path to the file. Cleaning up your script a bit, you would have
import csv
import xml.etree.ElementTree as ET
from pathlib import Path
## directory
path = Path("/Users.../y")
with open('/Users.../xml_extract.csv', 'w') as xml_data_to_csv:
csvwriter = csv.writer(xml_data_to_csv)
# Read XML files in a folder
for filepath in path.glob("**/*.xml"):
tree = ET.parse(filename)
root = tree.getroot()
extract_xml=[]
## extract child elements per xml file
print("\n")
for x in root.iter('Info'):
for element in x:
print(element.tag,element.text)
extract_xml.append(element.text)
## Write list nodes to csv
csvwriter.writerow(extract_xml)
This thread here advises to use shutilto zip files:
import shutil
shutil.make_archive(output_filename, 'zip', dir_name)
This zips everything in dir_name and maintains the folder structure in it. Is it possible to use this same library to remove all sub-folders and just zip all files in dir_name into the same level? Or must I introduce a separate code chunk to first consolidate the files? For eg., this is a hypothetical folder structure:
\dir_name
\dir1
\cat1
file1.txt
file2.txt
\cat2
file3.txt
\dir2
\cat3
file4.txt
Output zip should just contain:
file1.txt
file2.txt
file3.txt
file4.txt
shutil.make_archive does not have a way to do what you want without copying files to another directory, which is inefficient. Instead you can use a compression library directly similar to the linked answer you provided. Note this doesn't handle name collisions!
import zipfile
import os
with zipfile.ZipFile('output.zip','w',zipfile.ZIP_DEFLATED,compresslevel=9) as z:
for path,dirs,files in os.walk('dir_name'):
for file in files:
full = os.path.join(path,file)
z.write(full,file) # write the file, but with just the file's name not full path
# print the files in the zipfile
with zipfile.ZipFile('output.zip') as z:
for name in z.namelist():
print(name)
Given:
dir_name
├───dir1
│ ├───cat1
│ │ file1.txt
│ │ file2.txt
│ │
│ └───cat2
│ file3.txt
│
└───dir2
└───cat3
file4.txt
Output:
file1.txt
file2.txt
file3.txt
file4.txt
# The root directory to search for
path = r'dir_name/'
import os
import glob
# List all *.txt files in the root directory
file_paths = [file_path
for root_path, _, _ in os.walk(path)
for file_path in glob.glob(os.path.join(root_path, '*.txt'))]
import tempfile
# Create a temporary directory to copy your files into
with tempfile.TemporaryDirectory() as tmp:
import shutil
for file_path in file_paths:
# Get the basename of the file
basename = os.path.basename(file_path)
# Copy the file to the temporary directory
shutil.copyfile(file_path, os.path.join(tmp, basename))
# Zip the temporary directory to the working directory
shutil.make_archive('output', 'zip', tmp)
This will create a output.zip file in the current working directory. The temporary directory will be deleted when the end of the context manager is reached.
How can I create a zip archive of a directory structure in Python?
The easiest way is to use shutil.make_archive. It supports both zip and tar formats.
import shutil
shutil.make_archive(output_filename, 'zip', dir_name)
If you need to do something more complicated than zipping the whole directory (such as skipping certain files), then you'll need to dig into the zipfile module as others have suggested.
As others have pointed out, you should use zipfile. The documentation tells you what functions are available, but doesn't really explain how you can use them to zip an entire directory. I think it's easiest to explain with some example code:
import os
import zipfile
def zipdir(path, ziph):
# ziph is zipfile handle
for root, dirs, files in os.walk(path):
for file in files:
ziph.write(os.path.join(root, file),
os.path.relpath(os.path.join(root, file),
os.path.join(path, '..')))
with zipfile.ZipFile('Python.zip', 'w', zipfile.ZIP_DEFLATED) as zipf:
zipdir('tmp/', zipf)
To add the contents of mydirectory to a new zip file, including all files and subdirectories:
import os
import zipfile
zf = zipfile.ZipFile("myzipfile.zip", "w")
for dirname, subdirs, files in os.walk("mydirectory"):
zf.write(dirname)
for filename in files:
zf.write(os.path.join(dirname, filename))
zf.close()
How can I create a zip archive of a directory structure in Python?
In a Python script
In Python 2.7+, shutil has a make_archive function.
from shutil import make_archive
make_archive(
'zipfile_name',
'zip', # the archive format - or tar, bztar, gztar
root_dir=None, # root for archive - current working dir if None
base_dir=None) # start archiving from here - cwd if None too
Here the zipped archive will be named zipfile_name.zip. If base_dir is farther down from root_dir it will exclude files not in the base_dir, but still archive the files in the parent dirs up to the root_dir.
I did have an issue testing this on Cygwin with 2.7 - it wants a root_dir argument, for cwd:
make_archive('zipfile_name', 'zip', root_dir='.')
Using Python from the shell
You can do this with Python from the shell also using the zipfile module:
$ python -m zipfile -c zipname sourcedir
Where zipname is the name of the destination file you want (add .zip if you want it, it won't do it automatically) and sourcedir is the path to the directory.
Zipping up Python (or just don't want parent dir):
If you're trying to zip up a python package with a __init__.py and __main__.py, and you don't want the parent dir, it's
$ python -m zipfile -c zipname sourcedir/*
And
$ python zipname
would run the package. (Note that you can't run subpackages as the entry point from a zipped archive.)
Zipping a Python app:
If you have python3.5+, and specifically want to zip up a Python package, use zipapp:
$ python -m zipapp myapp
$ python myapp.pyz
This function will recursively zip up a directory tree, compressing the files, and recording the correct relative filenames in the archive. The archive entries are the same as those generated by zip -r output.zip source_dir.
import os
import zipfile
def make_zipfile(output_filename, source_dir):
relroot = os.path.abspath(os.path.join(source_dir, os.pardir))
with zipfile.ZipFile(output_filename, "w", zipfile.ZIP_DEFLATED) as zip:
for root, dirs, files in os.walk(source_dir):
# add directory (needed for empty dirs)
zip.write(root, os.path.relpath(root, relroot))
for file in files:
filename = os.path.join(root, file)
if os.path.isfile(filename): # regular files only
arcname = os.path.join(os.path.relpath(root, relroot), file)
zip.write(filename, arcname)
Use shutil, which is part of python standard library set.
Using shutil is so simple(see code below):
1st arg: Filename of resultant zip/tar file,
2nd arg: zip/tar,
3rd arg: dir_name
Code:
import shutil
shutil.make_archive('/home/user/Desktop/Filename','zip','/home/username/Desktop/Directory')
Modern Python (3.6+) using the pathlib module for concise OOP-like handling of paths, and pathlib.Path.rglob() for recursive globbing. As far as I can tell, this is equivalent to George V. Reilly's answer: zips with compression, the topmost element is a directory, keeps empty dirs, uses relative paths.
from pathlib import Path
from zipfile import ZIP_DEFLATED, ZipFile
from os import PathLike
from typing import Union
def zip_dir(zip_name: str, source_dir: Union[str, PathLike]):
src_path = Path(source_dir).expanduser().resolve(strict=True)
with ZipFile(zip_name, 'w', ZIP_DEFLATED) as zf:
for file in src_path.rglob('*'):
zf.write(file, file.relative_to(src_path.parent))
Note: as optional type hints indicate, zip_name can't be a Path object (would be fixed in 3.6.2+).
With python 3.9, pathlib & zipfile module you can create a zip files from anywhere in the system.
def zip_dir(dir: Union[Path, str], filename: Union[Path, str]):
"""Zip the provided directory without navigating to that directory using `pathlib` module"""
# Convert to Path object
dir = Path(dir)
with zipfile.ZipFile(filename, "w", zipfile.ZIP_DEFLATED) as zip_file:
for entry in dir.rglob("*"):
zip_file.write(entry, entry.relative_to(dir))
It is neat, typed, and has less code.
For adding compression to the resulting zip file, check out this link.
You need to change:
zip = zipfile.ZipFile('Python.zip', 'w')
to
zip = zipfile.ZipFile('Python.zip', 'w', zipfile.ZIP_DEFLATED)
I've made some changes to code given by Mark Byers. Below function will also adds empty directories if you have them. Examples should make it more clear what is the path added to the zip.
#!/usr/bin/env python
import os
import zipfile
def addDirToZip(zipHandle, path, basePath=""):
"""
Adding directory given by \a path to opened zip file \a zipHandle
#param basePath path that will be removed from \a path when adding to archive
Examples:
# add whole "dir" to "test.zip" (when you open "test.zip" you will see only "dir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir')
zipHandle.close()
# add contents of "dir" to "test.zip" (when you open "test.zip" you will see only it's contents)
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir', 'dir')
zipHandle.close()
# add contents of "dir/subdir" to "test.zip" (when you open "test.zip" you will see only contents of "subdir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir/subdir', 'dir/subdir')
zipHandle.close()
# add whole "dir/subdir" to "test.zip" (when you open "test.zip" you will see only "subdir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir/subdir', 'dir')
zipHandle.close()
# add whole "dir/subdir" with full path to "test.zip" (when you open "test.zip" you will see only "dir" and inside it only "subdir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir/subdir')
zipHandle.close()
# add whole "dir" and "otherDir" (with full path) to "test.zip" (when you open "test.zip" you will see only "dir" and "otherDir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir')
addDirToZip(zipHandle, 'otherDir')
zipHandle.close()
"""
basePath = basePath.rstrip("\\/") + ""
basePath = basePath.rstrip("\\/")
for root, dirs, files in os.walk(path):
# add dir itself (needed for empty dirs
zipHandle.write(os.path.join(root, "."))
# add files
for file in files:
filePath = os.path.join(root, file)
inZipPath = filePath.replace(basePath, "", 1).lstrip("\\/")
#print filePath + " , " + inZipPath
zipHandle.write(filePath, inZipPath)
Above is a simple function that should work for simple cases. You can find more elegant class in my Gist:
https://gist.github.com/Eccenux/17526123107ca0ac28e6
I have another code example that may help, using python3, pathlib and zipfile.
It should work in any OS.
from pathlib import Path
import zipfile
from datetime import datetime
DATE_FORMAT = '%y%m%d'
def date_str():
"""returns the today string year, month, day"""
return '{}'.format(datetime.now().strftime(DATE_FORMAT))
def zip_name(path):
"""returns the zip filename as string"""
cur_dir = Path(path).resolve()
parent_dir = cur_dir.parents[0]
zip_filename = '{}/{}_{}.zip'.format(parent_dir, cur_dir.name, date_str())
p_zip = Path(zip_filename)
n = 1
while p_zip.exists():
zip_filename = ('{}/{}_{}_{}.zip'.format(parent_dir, cur_dir.name,
date_str(), n))
p_zip = Path(zip_filename)
n += 1
return zip_filename
def all_files(path):
"""iterator returns all files and folders from path as absolute path string
"""
for child in Path(path).iterdir():
yield str(child)
if child.is_dir():
for grand_child in all_files(str(child)):
yield str(Path(grand_child))
def zip_dir(path):
"""generate a zip"""
zip_filename = zip_name(path)
zip_file = zipfile.ZipFile(zip_filename, 'w')
print('create:', zip_filename)
for file in all_files(path):
print('adding... ', file)
zip_file.write(file)
zip_file.close()
if __name__ == '__main__':
zip_dir('.')
print('end!')
To retain the folder hierarchy under the parent directory to be archived:
import glob
import os
import zipfile
with zipfile.ZipFile(fp_zip, "w", zipfile.ZIP_DEFLATED) as zipf:
for fp in glob(os.path.join(parent, "**/*")):
base = os.path.commonpath([parent, fp])
zipf.write(fp, arcname=fp.replace(base, ""))
If you want, you could change this to use pathlib for file globbing.
If you want a functionality like the compress folder of any common graphical file manager you can use the following code, it uses the zipfile module. Using this code you will have the zip file with the path as its root folder.
import os
import zipfile
def zipdir(path, ziph):
# Iterate all the directories and files
for root, dirs, files in os.walk(path):
# Create a prefix variable with the folder structure inside the path folder.
# So if a file is at the path directory will be at the root directory of the zip file
# so the prefix will be empty. If the file belongs to a containing folder of path folder
# then the prefix will be that folder.
if root.replace(path,'') == '':
prefix = ''
else:
# Keep the folder structure after the path folder, append a '/' at the end
# and remome the first character, if it is a '/' in order to have a path like
# folder1/folder2/file.txt
prefix = root.replace(path, '') + '/'
if (prefix[0] == '/'):
prefix = prefix[1:]
for filename in files:
actual_file_path = root + '/' + filename
zipped_file_path = prefix + filename
zipf.write( actual_file_path, zipped_file_path)
zipf = zipfile.ZipFile('Python.zip', 'w', zipfile.ZIP_DEFLATED)
zipdir('/tmp/justtest/', zipf)
zipf.close()
So many answers here, and I hope I might contribute with my own version, which is based on the original answer (by the way), but with a more graphical perspective, also using context for each zipfile setup and sorting os.walk(), in order to have a ordered output.
Having these folders and them files (among other folders), I wanted to create a .zip for each cap_ folder:
$ tree -d
.
├── cap_01
| ├── 0101000001.json
| ├── 0101000002.json
| ├── 0101000003.json
|
├── cap_02
| ├── 0201000001.json
| ├── 0201000002.json
| ├── 0201001003.json
|
├── cap_03
| ├── 0301000001.json
| ├── 0301000002.json
| ├── 0301000003.json
|
├── docs
| ├── map.txt
| ├── main_data.xml
|
├── core_files
├── core_master
├── core_slave
Here's what I applied, with comments for better understanding of the process.
$ cat zip_cap_dirs.py
""" Zip 'cap_*' directories. """
import os
import zipfile as zf
for root, dirs, files in sorted(os.walk('.')):
if 'cap_' in root:
print(f"Compressing: {root}")
# Defining .zip name, according to Capítulo.
cap_dir_zip = '{}.zip'.format(root)
# Opening zipfile context for current root dir.
with zf.ZipFile(cap_dir_zip, 'w', zf.ZIP_DEFLATED) as new_zip:
# Iterating over os.walk list of files for the current root dir.
for f in files:
# Defining relative path to files from current root dir.
f_path = os.path.join(root, f)
# Writing the file on the .zip file of the context
new_zip.write(f_path)
Basically, for each iteration over os.walk(path), I'm opening a context for zipfile setup and afterwards, iterating iterating over files, which is a list of files from root directory, forming the relative path for each file based on the current root directory, appending to the zipfile context which is running.
And the output is presented like this:
$ python3 zip_cap_dirs.py
Compressing: ./cap_01
Compressing: ./cap_02
Compressing: ./cap_03
To see the contents of each .zip directory, you can use less command:
$ less cap_01.zip
Archive: cap_01.zip
Length Method Size Cmpr Date Time CRC-32 Name
-------- ------ ------- ---- ---------- ----- -------- ----
22017 Defl:N 2471 89% 2019-09-05 08:05 7a3b5ec6 cap_01/0101000001.json
21998 Defl:N 2471 89% 2019-09-05 08:05 155bece7 cap_01/0101000002.json
23236 Defl:N 2573 89% 2019-09-05 08:05 55fced20 cap_01/0101000003.json
-------- ------- --- -------
67251 7515 89% 3 files
You probably want to look at the zipfile module; there's documentation at http://docs.python.org/library/zipfile.html.
You may also want os.walk() to index the directory structure.
To give more flexibility, e.g. select directory/file by name use:
import os
import zipfile
def zipall(ob, path, rel=""):
basename = os.path.basename(path)
if os.path.isdir(path):
if rel == "":
rel = basename
ob.write(path, os.path.join(rel))
for root, dirs, files in os.walk(path):
for d in dirs:
zipall(ob, os.path.join(root, d), os.path.join(rel, d))
for f in files:
ob.write(os.path.join(root, f), os.path.join(rel, f))
break
elif os.path.isfile(path):
ob.write(path, os.path.join(rel, basename))
else:
pass
For a file tree:
.
├── dir
│ ├── dir2
│ │ └── file2.txt
│ ├── dir3
│ │ └── file3.txt
│ └── file.txt
├── dir4
│ ├── dir5
│ └── file4.txt
├── listdir.zip
├── main.py
├── root.txt
└── selective.zip
You can e.g. select only dir4 and root.txt:
cwd = os.getcwd()
files = [os.path.join(cwd, f) for f in ['dir4', 'root.txt']]
with zipfile.ZipFile("selective.zip", "w" ) as myzip:
for f in files:
zipall(myzip, f)
Or just listdir in script invocation directory and add everything from there:
with zipfile.ZipFile("listdir.zip", "w" ) as myzip:
for f in os.listdir():
if f == "listdir.zip":
# Creating a listdir.zip in the same directory
# will include listdir.zip inside itself, beware of this
continue
zipall(myzip, f)
Here is a variation on the answer given by Nux that works for me:
def WriteDirectoryToZipFile( zipHandle, srcPath, zipLocalPath = "", zipOperation = zipfile.ZIP_DEFLATED ):
basePath = os.path.split( srcPath )[ 0 ]
for root, dirs, files in os.walk( srcPath ):
p = os.path.join( zipLocalPath, root [ ( len( basePath ) + 1 ) : ] )
# add dir
zipHandle.write( root, p, zipOperation )
# add files
for f in files:
filePath = os.path.join( root, f )
fileInZipPath = os.path.join( p, f )
zipHandle.write( filePath, fileInZipPath, zipOperation )
Try the below one .it worked for me.
import zipfile, os
zipf = "compress.zip"
def main():
directory = r"Filepath"
toZip(directory)
def toZip(directory):
zippedHelp = zipfile.ZipFile(zipf, "w", compression=zipfile.ZIP_DEFLATED )
list = os.listdir(directory)
for file_list in list:
file_name = os.path.join(directory,file_list)
if os.path.isfile(file_name):
print file_name
zippedHelp.write(file_name)
else:
addFolderToZip(zippedHelp,file_list,directory)
print "---------------Directory Found-----------------------"
zippedHelp.close()
def addFolderToZip(zippedHelp,folder,directory):
path=os.path.join(directory,folder)
print path
file_list=os.listdir(path)
for file_name in file_list:
file_path=os.path.join(path,file_name)
if os.path.isfile(file_path):
zippedHelp.write(file_path)
elif os.path.isdir(file_name):
print "------------------sub directory found--------------------"
addFolderToZip(zippedHelp,file_name,path)
if __name__=="__main__":
main()
Say you want to Zip all the folders(sub directories) in the current directory.
for root, dirs, files in os.walk("."):
for sub_dir in dirs:
zip_you_want = sub_dir+".zip"
zip_process = zipfile.ZipFile(zip_you_want, "w", zipfile.ZIP_DEFLATED)
zip_process.write(file_you_want_to_include)
zip_process.close()
print("Successfully zipped directory: {sub_dir}".format(sub_dir=sub_dir))
Zip a file or a tree (a directory and its sub-directories).
from pathlib import Path
from zipfile import ZipFile, ZIP_DEFLATED
def make_zip(tree_path, zip_path, mode='w', skip_empty_dir=False):
with ZipFile(zip_path, mode=mode, compression=ZIP_DEFLATED) as zf:
paths = [Path(tree_path)]
while paths:
p = paths.pop()
if p.is_dir():
paths.extend(p.iterdir())
if skip_empty_dir:
continue
zf.write(p)
To append to an existing archive, pass mode='a', to create a fresh archive mode='w' (the default in the above). So let's say you want to bundle 3 different directory trees under the same archive.
make_zip(path_to_tree1, path_to_arch, mode='w')
make_zip(path_to_tree2, path_to_arch, mode='a')
make_zip(path_to_file3, path_to_arch, mode='a')
A solution using pathlib.Path, which is independent of the OS used:
import zipfile
from pathlib import Path
def zip_dir(path: Path, zip_file_path: Path):
"""Zip all contents of path to zip_file"""
files_to_zip = [
file for file in path.glob('*') if file.is_file()]
with zipfile.ZipFile(
zip_file_path, 'w', zipfile.ZIP_DEFLATED) as zip_f:
for file in files_to_zip:
print(file.name)
zip_f.write(file, file.name)
current_dir = Path.cwd()
zip_dir = current_dir / "test"
tools.zip_dir(
zip_dir, current_dir / 'Zipped_dir.zip')
The obvious way to go would be to go with shutil, Like the second top answer says so, But if you still wish to go with ZipFile for some reason, And if you are getting some trouble doing that (Like ERR 13 in Windows etc), You can use this fix:
import os
import zipfile
def retrieve_file_paths(dirName):
filePaths = []
for root, directories, files in os.walk(dirName):
for filename in files:
filePath = os.path.join(root, filename)
filePaths.append(filePath)
return filePaths
def main(dir_name, output_filename):
filePaths = retrieve_file_paths(dir_name)
zip_file = zipfile.ZipFile(output_filename+'.zip', 'w')
with zip_file:
for file in filePaths:
zip_file.write(file)
main("my_dir", "my_dir_archived")
This one recursively iterates through every sub-folder/file in your given folder, And writes them to a zip file instead of attempting to directly zip a folder.
Here's a modern approach, using pathlib, and a context manager. Puts the files directly in the zip, rather than in a subfolder.
def zip_dir(filename: str, dir_to_zip: pathlib.Path):
with zipfile.ZipFile(filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
# Use glob instead of iterdir(), to cover all subdirectories.
for directory in dir_to_zip.glob('**'):
for file in directory.iterdir():
if not file.is_file():
continue
# Strip the first component, so we don't create an uneeded subdirectory
# containing everything.
zip_path = pathlib.Path(*file.parts[1:])
# Use a string, since zipfile doesn't support pathlib directly.
zipf.write(str(file), str(zip_path))
I prepared a function by consolidating Mark Byers' solution with Reimund and Morten Zilmer's comments (relative path and including empty directories). As a best practice, with is used in ZipFile's file construction.
The function also prepares a default zip file name with the zipped directory name and '.zip' extension. Therefore, it works with only one argument: the source directory to be zipped.
import os
import zipfile
def zip_dir(path_dir, path_file_zip=''):
if not path_file_zip:
path_file_zip = os.path.join(
os.path.dirname(path_dir), os.path.basename(path_dir)+'.zip')
with zipfile.ZipFile(path_file_zip, 'wb', zipfile.ZIP_DEFLATED) as zip_file:
for root, dirs, files in os.walk(path_dir):
for file_or_dir in files + dirs:
zip_file.write(
os.path.join(root, file_or_dir),
os.path.relpath(os.path.join(root, file_or_dir),
os.path.join(path_dir, os.path.pardir)))
# import required python modules
# You have to install zipfile package using pip install
import os,zipfile
# Change the directory where you want your new zip file to be
os.chdir('Type your destination')
# Create a new zipfile ( I called it myfile )
zf = zipfile.ZipFile('myfile.zip','w')
# os.walk gives a directory tree. Access the files using a for loop
for dirnames,folders,files in os.walk('Type your directory'):
zf.write('Type your Directory')
for file in files:
zf.write(os.path.join('Type your directory',file))
Well, after reading the suggestions I came up with a very similar way that works with 2.7.x without creating "funny" directory names (absolute-like names), and will only create the specified folder inside the zip.
Or just in case you needed your zip to contain a folder inside with the contents of the selected directory.
def zipDir( path, ziph ) :
"""
Inserts directory (path) into zipfile instance (ziph)
"""
for root, dirs, files in os.walk( path ) :
for file in files :
ziph.write( os.path.join( root, file ) , os.path.basename( os.path.normpath( path ) ) + "\\" + file )
def makeZip( pathToFolder ) :
"""
Creates a zip file with the specified folder
"""
zipf = zipfile.ZipFile( pathToFolder + 'file.zip', 'w', zipfile.ZIP_DEFLATED )
zipDir( pathToFolder, zipf )
zipf.close()
print( "Zip file saved to: " + pathToFolder)
makeZip( "c:\\path\\to\\folder\\to\\insert\\into\\zipfile" )
Function to create zip file.
def CREATEZIPFILE(zipname, path):
#function to create a zip file
#Parameters: zipname - name of the zip file; path - name of folder/file to be put in zip file
zipf = zipfile.ZipFile(zipname, 'w', zipfile.ZIP_DEFLATED)
zipf.setpassword(b"password") #if you want to set password to zipfile
#checks if the path is file or directory
if os.path.isdir(path):
for files in os.listdir(path):
zipf.write(os.path.join(path, files), files)
elif os.path.isfile(path):
zipf.write(os.path.join(path), path)
zipf.close()
One thing completely missed by previous answers is the fact that using os.path.join() can easily return POSIX-incompatible paths when you run the code on Windows. The resulting archive will contain files with literal backslashes in their names when processing it with any common archive software on Linux, which is not what you want. Use path.as_posix() for the arcname parameter instead!
import zipfile
from pathlib import Path
with zipfile.ZipFile("archive.zip", "w", zipfile.ZIP_DEFLATED) as zf:
for path in Path("include_all_of_this_folder").rglob("*"):
zf.write(path, path.as_posix())
I am trying to create a backup script in Python 3.5 that will zip all the contents of a specified folder. Here is what I am doing now:
import shutil
import datetime
import os
import os.path
import dropbox
INPUT_FOLDER = '~/Documents/db-backup-test/'
ARCHIVE_PATH = '~/Documents/tmp/'
ARCHIVE_FILE_NAME = "db-backup_iOS__"
def compress_folder(origem, destino):
try:
arq = shutil.make_archive(destino, 'zip', root_dir=origem, base_dir=origem)
except Exception as e:
print('\n\nAn error was found during compression:')
print(e)
timestamp = str(datetime.datetime.now())
input_path = os.path.expanduser(INPUT_FOLDER)
archive_path = os.path.expanduser(ARCHIVE_PATH + ARCHIVE_FILE_NAME + timestamp)
compress_folder(input_path, archive_path)
I goes well, except for one thing: the resulting zip archive extracts its contents with a reproduction of the full original path. What I would like is to get is a simple copy of the folder, with its original name and its contents with relative paths, when extracting the archive.
I was looking into a simple and short solution that would not require to iterate through the folder contents.
Is this possible with shutil.make_archive(), or will I need to dig into other modules, like zipfile?
Use the arcname parameter to control the name/path in the zip file.
#!/usr/bin/env python2.7
import os
import zipfile
def zip(src, dst):
zf = zipfile.ZipFile("%s.zip" % (dst), "w", zipfile.ZIP_DEFLATED)
abs_src = os.path.abspath(src)
for dirname, subdirs, files in os.walk(src):
for filename in files:
absname = os.path.abspath(os.path.join(dirname, filename))
arcname = absname[len(abs_src) + 1:]
print 'zipping %s as %s' % (os.path.join(dirname, filename), arcname)
zf.write(absname, arcname)
zf.close()
zip("src", "dst")
With a directory structure like this:
src
└── a
├── b
│ └── bar
└── foo
How can I create a zip archive of a directory structure in Python?
The easiest way is to use shutil.make_archive. It supports both zip and tar formats.
import shutil
shutil.make_archive(output_filename, 'zip', dir_name)
If you need to do something more complicated than zipping the whole directory (such as skipping certain files), then you'll need to dig into the zipfile module as others have suggested.
As others have pointed out, you should use zipfile. The documentation tells you what functions are available, but doesn't really explain how you can use them to zip an entire directory. I think it's easiest to explain with some example code:
import os
import zipfile
def zipdir(path, ziph):
# ziph is zipfile handle
for root, dirs, files in os.walk(path):
for file in files:
ziph.write(os.path.join(root, file),
os.path.relpath(os.path.join(root, file),
os.path.join(path, '..')))
with zipfile.ZipFile('Python.zip', 'w', zipfile.ZIP_DEFLATED) as zipf:
zipdir('tmp/', zipf)
To add the contents of mydirectory to a new zip file, including all files and subdirectories:
import os
import zipfile
zf = zipfile.ZipFile("myzipfile.zip", "w")
for dirname, subdirs, files in os.walk("mydirectory"):
zf.write(dirname)
for filename in files:
zf.write(os.path.join(dirname, filename))
zf.close()
How can I create a zip archive of a directory structure in Python?
In a Python script
In Python 2.7+, shutil has a make_archive function.
from shutil import make_archive
make_archive(
'zipfile_name',
'zip', # the archive format - or tar, bztar, gztar
root_dir=None, # root for archive - current working dir if None
base_dir=None) # start archiving from here - cwd if None too
Here the zipped archive will be named zipfile_name.zip. If base_dir is farther down from root_dir it will exclude files not in the base_dir, but still archive the files in the parent dirs up to the root_dir.
I did have an issue testing this on Cygwin with 2.7 - it wants a root_dir argument, for cwd:
make_archive('zipfile_name', 'zip', root_dir='.')
Using Python from the shell
You can do this with Python from the shell also using the zipfile module:
$ python -m zipfile -c zipname sourcedir
Where zipname is the name of the destination file you want (add .zip if you want it, it won't do it automatically) and sourcedir is the path to the directory.
Zipping up Python (or just don't want parent dir):
If you're trying to zip up a python package with a __init__.py and __main__.py, and you don't want the parent dir, it's
$ python -m zipfile -c zipname sourcedir/*
And
$ python zipname
would run the package. (Note that you can't run subpackages as the entry point from a zipped archive.)
Zipping a Python app:
If you have python3.5+, and specifically want to zip up a Python package, use zipapp:
$ python -m zipapp myapp
$ python myapp.pyz
This function will recursively zip up a directory tree, compressing the files, and recording the correct relative filenames in the archive. The archive entries are the same as those generated by zip -r output.zip source_dir.
import os
import zipfile
def make_zipfile(output_filename, source_dir):
relroot = os.path.abspath(os.path.join(source_dir, os.pardir))
with zipfile.ZipFile(output_filename, "w", zipfile.ZIP_DEFLATED) as zip:
for root, dirs, files in os.walk(source_dir):
# add directory (needed for empty dirs)
zip.write(root, os.path.relpath(root, relroot))
for file in files:
filename = os.path.join(root, file)
if os.path.isfile(filename): # regular files only
arcname = os.path.join(os.path.relpath(root, relroot), file)
zip.write(filename, arcname)
Use shutil, which is part of python standard library set.
Using shutil is so simple(see code below):
1st arg: Filename of resultant zip/tar file,
2nd arg: zip/tar,
3rd arg: dir_name
Code:
import shutil
shutil.make_archive('/home/user/Desktop/Filename','zip','/home/username/Desktop/Directory')
Modern Python (3.6+) using the pathlib module for concise OOP-like handling of paths, and pathlib.Path.rglob() for recursive globbing. As far as I can tell, this is equivalent to George V. Reilly's answer: zips with compression, the topmost element is a directory, keeps empty dirs, uses relative paths.
from pathlib import Path
from zipfile import ZIP_DEFLATED, ZipFile
from os import PathLike
from typing import Union
def zip_dir(zip_name: str, source_dir: Union[str, PathLike]):
src_path = Path(source_dir).expanduser().resolve(strict=True)
with ZipFile(zip_name, 'w', ZIP_DEFLATED) as zf:
for file in src_path.rglob('*'):
zf.write(file, file.relative_to(src_path.parent))
Note: as optional type hints indicate, zip_name can't be a Path object (would be fixed in 3.6.2+).
With python 3.9, pathlib & zipfile module you can create a zip files from anywhere in the system.
def zip_dir(dir: Union[Path, str], filename: Union[Path, str]):
"""Zip the provided directory without navigating to that directory using `pathlib` module"""
# Convert to Path object
dir = Path(dir)
with zipfile.ZipFile(filename, "w", zipfile.ZIP_DEFLATED) as zip_file:
for entry in dir.rglob("*"):
zip_file.write(entry, entry.relative_to(dir))
It is neat, typed, and has less code.
For adding compression to the resulting zip file, check out this link.
You need to change:
zip = zipfile.ZipFile('Python.zip', 'w')
to
zip = zipfile.ZipFile('Python.zip', 'w', zipfile.ZIP_DEFLATED)
I've made some changes to code given by Mark Byers. Below function will also adds empty directories if you have them. Examples should make it more clear what is the path added to the zip.
#!/usr/bin/env python
import os
import zipfile
def addDirToZip(zipHandle, path, basePath=""):
"""
Adding directory given by \a path to opened zip file \a zipHandle
#param basePath path that will be removed from \a path when adding to archive
Examples:
# add whole "dir" to "test.zip" (when you open "test.zip" you will see only "dir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir')
zipHandle.close()
# add contents of "dir" to "test.zip" (when you open "test.zip" you will see only it's contents)
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir', 'dir')
zipHandle.close()
# add contents of "dir/subdir" to "test.zip" (when you open "test.zip" you will see only contents of "subdir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir/subdir', 'dir/subdir')
zipHandle.close()
# add whole "dir/subdir" to "test.zip" (when you open "test.zip" you will see only "subdir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir/subdir', 'dir')
zipHandle.close()
# add whole "dir/subdir" with full path to "test.zip" (when you open "test.zip" you will see only "dir" and inside it only "subdir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir/subdir')
zipHandle.close()
# add whole "dir" and "otherDir" (with full path) to "test.zip" (when you open "test.zip" you will see only "dir" and "otherDir")
zipHandle = zipfile.ZipFile('test.zip', 'w')
addDirToZip(zipHandle, 'dir')
addDirToZip(zipHandle, 'otherDir')
zipHandle.close()
"""
basePath = basePath.rstrip("\\/") + ""
basePath = basePath.rstrip("\\/")
for root, dirs, files in os.walk(path):
# add dir itself (needed for empty dirs
zipHandle.write(os.path.join(root, "."))
# add files
for file in files:
filePath = os.path.join(root, file)
inZipPath = filePath.replace(basePath, "", 1).lstrip("\\/")
#print filePath + " , " + inZipPath
zipHandle.write(filePath, inZipPath)
Above is a simple function that should work for simple cases. You can find more elegant class in my Gist:
https://gist.github.com/Eccenux/17526123107ca0ac28e6
I have another code example that may help, using python3, pathlib and zipfile.
It should work in any OS.
from pathlib import Path
import zipfile
from datetime import datetime
DATE_FORMAT = '%y%m%d'
def date_str():
"""returns the today string year, month, day"""
return '{}'.format(datetime.now().strftime(DATE_FORMAT))
def zip_name(path):
"""returns the zip filename as string"""
cur_dir = Path(path).resolve()
parent_dir = cur_dir.parents[0]
zip_filename = '{}/{}_{}.zip'.format(parent_dir, cur_dir.name, date_str())
p_zip = Path(zip_filename)
n = 1
while p_zip.exists():
zip_filename = ('{}/{}_{}_{}.zip'.format(parent_dir, cur_dir.name,
date_str(), n))
p_zip = Path(zip_filename)
n += 1
return zip_filename
def all_files(path):
"""iterator returns all files and folders from path as absolute path string
"""
for child in Path(path).iterdir():
yield str(child)
if child.is_dir():
for grand_child in all_files(str(child)):
yield str(Path(grand_child))
def zip_dir(path):
"""generate a zip"""
zip_filename = zip_name(path)
zip_file = zipfile.ZipFile(zip_filename, 'w')
print('create:', zip_filename)
for file in all_files(path):
print('adding... ', file)
zip_file.write(file)
zip_file.close()
if __name__ == '__main__':
zip_dir('.')
print('end!')
To retain the folder hierarchy under the parent directory to be archived:
import glob
import os
import zipfile
with zipfile.ZipFile(fp_zip, "w", zipfile.ZIP_DEFLATED) as zipf:
for fp in glob(os.path.join(parent, "**/*")):
base = os.path.commonpath([parent, fp])
zipf.write(fp, arcname=fp.replace(base, ""))
If you want, you could change this to use pathlib for file globbing.
If you want a functionality like the compress folder of any common graphical file manager you can use the following code, it uses the zipfile module. Using this code you will have the zip file with the path as its root folder.
import os
import zipfile
def zipdir(path, ziph):
# Iterate all the directories and files
for root, dirs, files in os.walk(path):
# Create a prefix variable with the folder structure inside the path folder.
# So if a file is at the path directory will be at the root directory of the zip file
# so the prefix will be empty. If the file belongs to a containing folder of path folder
# then the prefix will be that folder.
if root.replace(path,'') == '':
prefix = ''
else:
# Keep the folder structure after the path folder, append a '/' at the end
# and remome the first character, if it is a '/' in order to have a path like
# folder1/folder2/file.txt
prefix = root.replace(path, '') + '/'
if (prefix[0] == '/'):
prefix = prefix[1:]
for filename in files:
actual_file_path = root + '/' + filename
zipped_file_path = prefix + filename
zipf.write( actual_file_path, zipped_file_path)
zipf = zipfile.ZipFile('Python.zip', 'w', zipfile.ZIP_DEFLATED)
zipdir('/tmp/justtest/', zipf)
zipf.close()
So many answers here, and I hope I might contribute with my own version, which is based on the original answer (by the way), but with a more graphical perspective, also using context for each zipfile setup and sorting os.walk(), in order to have a ordered output.
Having these folders and them files (among other folders), I wanted to create a .zip for each cap_ folder:
$ tree -d
.
├── cap_01
| ├── 0101000001.json
| ├── 0101000002.json
| ├── 0101000003.json
|
├── cap_02
| ├── 0201000001.json
| ├── 0201000002.json
| ├── 0201001003.json
|
├── cap_03
| ├── 0301000001.json
| ├── 0301000002.json
| ├── 0301000003.json
|
├── docs
| ├── map.txt
| ├── main_data.xml
|
├── core_files
├── core_master
├── core_slave
Here's what I applied, with comments for better understanding of the process.
$ cat zip_cap_dirs.py
""" Zip 'cap_*' directories. """
import os
import zipfile as zf
for root, dirs, files in sorted(os.walk('.')):
if 'cap_' in root:
print(f"Compressing: {root}")
# Defining .zip name, according to Capítulo.
cap_dir_zip = '{}.zip'.format(root)
# Opening zipfile context for current root dir.
with zf.ZipFile(cap_dir_zip, 'w', zf.ZIP_DEFLATED) as new_zip:
# Iterating over os.walk list of files for the current root dir.
for f in files:
# Defining relative path to files from current root dir.
f_path = os.path.join(root, f)
# Writing the file on the .zip file of the context
new_zip.write(f_path)
Basically, for each iteration over os.walk(path), I'm opening a context for zipfile setup and afterwards, iterating iterating over files, which is a list of files from root directory, forming the relative path for each file based on the current root directory, appending to the zipfile context which is running.
And the output is presented like this:
$ python3 zip_cap_dirs.py
Compressing: ./cap_01
Compressing: ./cap_02
Compressing: ./cap_03
To see the contents of each .zip directory, you can use less command:
$ less cap_01.zip
Archive: cap_01.zip
Length Method Size Cmpr Date Time CRC-32 Name
-------- ------ ------- ---- ---------- ----- -------- ----
22017 Defl:N 2471 89% 2019-09-05 08:05 7a3b5ec6 cap_01/0101000001.json
21998 Defl:N 2471 89% 2019-09-05 08:05 155bece7 cap_01/0101000002.json
23236 Defl:N 2573 89% 2019-09-05 08:05 55fced20 cap_01/0101000003.json
-------- ------- --- -------
67251 7515 89% 3 files
You probably want to look at the zipfile module; there's documentation at http://docs.python.org/library/zipfile.html.
You may also want os.walk() to index the directory structure.
To give more flexibility, e.g. select directory/file by name use:
import os
import zipfile
def zipall(ob, path, rel=""):
basename = os.path.basename(path)
if os.path.isdir(path):
if rel == "":
rel = basename
ob.write(path, os.path.join(rel))
for root, dirs, files in os.walk(path):
for d in dirs:
zipall(ob, os.path.join(root, d), os.path.join(rel, d))
for f in files:
ob.write(os.path.join(root, f), os.path.join(rel, f))
break
elif os.path.isfile(path):
ob.write(path, os.path.join(rel, basename))
else:
pass
For a file tree:
.
├── dir
│ ├── dir2
│ │ └── file2.txt
│ ├── dir3
│ │ └── file3.txt
│ └── file.txt
├── dir4
│ ├── dir5
│ └── file4.txt
├── listdir.zip
├── main.py
├── root.txt
└── selective.zip
You can e.g. select only dir4 and root.txt:
cwd = os.getcwd()
files = [os.path.join(cwd, f) for f in ['dir4', 'root.txt']]
with zipfile.ZipFile("selective.zip", "w" ) as myzip:
for f in files:
zipall(myzip, f)
Or just listdir in script invocation directory and add everything from there:
with zipfile.ZipFile("listdir.zip", "w" ) as myzip:
for f in os.listdir():
if f == "listdir.zip":
# Creating a listdir.zip in the same directory
# will include listdir.zip inside itself, beware of this
continue
zipall(myzip, f)
Here is a variation on the answer given by Nux that works for me:
def WriteDirectoryToZipFile( zipHandle, srcPath, zipLocalPath = "", zipOperation = zipfile.ZIP_DEFLATED ):
basePath = os.path.split( srcPath )[ 0 ]
for root, dirs, files in os.walk( srcPath ):
p = os.path.join( zipLocalPath, root [ ( len( basePath ) + 1 ) : ] )
# add dir
zipHandle.write( root, p, zipOperation )
# add files
for f in files:
filePath = os.path.join( root, f )
fileInZipPath = os.path.join( p, f )
zipHandle.write( filePath, fileInZipPath, zipOperation )
Try the below one .it worked for me.
import zipfile, os
zipf = "compress.zip"
def main():
directory = r"Filepath"
toZip(directory)
def toZip(directory):
zippedHelp = zipfile.ZipFile(zipf, "w", compression=zipfile.ZIP_DEFLATED )
list = os.listdir(directory)
for file_list in list:
file_name = os.path.join(directory,file_list)
if os.path.isfile(file_name):
print file_name
zippedHelp.write(file_name)
else:
addFolderToZip(zippedHelp,file_list,directory)
print "---------------Directory Found-----------------------"
zippedHelp.close()
def addFolderToZip(zippedHelp,folder,directory):
path=os.path.join(directory,folder)
print path
file_list=os.listdir(path)
for file_name in file_list:
file_path=os.path.join(path,file_name)
if os.path.isfile(file_path):
zippedHelp.write(file_path)
elif os.path.isdir(file_name):
print "------------------sub directory found--------------------"
addFolderToZip(zippedHelp,file_name,path)
if __name__=="__main__":
main()
Say you want to Zip all the folders(sub directories) in the current directory.
for root, dirs, files in os.walk("."):
for sub_dir in dirs:
zip_you_want = sub_dir+".zip"
zip_process = zipfile.ZipFile(zip_you_want, "w", zipfile.ZIP_DEFLATED)
zip_process.write(file_you_want_to_include)
zip_process.close()
print("Successfully zipped directory: {sub_dir}".format(sub_dir=sub_dir))
Zip a file or a tree (a directory and its sub-directories).
from pathlib import Path
from zipfile import ZipFile, ZIP_DEFLATED
def make_zip(tree_path, zip_path, mode='w', skip_empty_dir=False):
with ZipFile(zip_path, mode=mode, compression=ZIP_DEFLATED) as zf:
paths = [Path(tree_path)]
while paths:
p = paths.pop()
if p.is_dir():
paths.extend(p.iterdir())
if skip_empty_dir:
continue
zf.write(p)
To append to an existing archive, pass mode='a', to create a fresh archive mode='w' (the default in the above). So let's say you want to bundle 3 different directory trees under the same archive.
make_zip(path_to_tree1, path_to_arch, mode='w')
make_zip(path_to_tree2, path_to_arch, mode='a')
make_zip(path_to_file3, path_to_arch, mode='a')
A solution using pathlib.Path, which is independent of the OS used:
import zipfile
from pathlib import Path
def zip_dir(path: Path, zip_file_path: Path):
"""Zip all contents of path to zip_file"""
files_to_zip = [
file for file in path.glob('*') if file.is_file()]
with zipfile.ZipFile(
zip_file_path, 'w', zipfile.ZIP_DEFLATED) as zip_f:
for file in files_to_zip:
print(file.name)
zip_f.write(file, file.name)
current_dir = Path.cwd()
zip_dir = current_dir / "test"
tools.zip_dir(
zip_dir, current_dir / 'Zipped_dir.zip')
The obvious way to go would be to go with shutil, Like the second top answer says so, But if you still wish to go with ZipFile for some reason, And if you are getting some trouble doing that (Like ERR 13 in Windows etc), You can use this fix:
import os
import zipfile
def retrieve_file_paths(dirName):
filePaths = []
for root, directories, files in os.walk(dirName):
for filename in files:
filePath = os.path.join(root, filename)
filePaths.append(filePath)
return filePaths
def main(dir_name, output_filename):
filePaths = retrieve_file_paths(dir_name)
zip_file = zipfile.ZipFile(output_filename+'.zip', 'w')
with zip_file:
for file in filePaths:
zip_file.write(file)
main("my_dir", "my_dir_archived")
This one recursively iterates through every sub-folder/file in your given folder, And writes them to a zip file instead of attempting to directly zip a folder.
Here's a modern approach, using pathlib, and a context manager. Puts the files directly in the zip, rather than in a subfolder.
def zip_dir(filename: str, dir_to_zip: pathlib.Path):
with zipfile.ZipFile(filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
# Use glob instead of iterdir(), to cover all subdirectories.
for directory in dir_to_zip.glob('**'):
for file in directory.iterdir():
if not file.is_file():
continue
# Strip the first component, so we don't create an uneeded subdirectory
# containing everything.
zip_path = pathlib.Path(*file.parts[1:])
# Use a string, since zipfile doesn't support pathlib directly.
zipf.write(str(file), str(zip_path))
I prepared a function by consolidating Mark Byers' solution with Reimund and Morten Zilmer's comments (relative path and including empty directories). As a best practice, with is used in ZipFile's file construction.
The function also prepares a default zip file name with the zipped directory name and '.zip' extension. Therefore, it works with only one argument: the source directory to be zipped.
import os
import zipfile
def zip_dir(path_dir, path_file_zip=''):
if not path_file_zip:
path_file_zip = os.path.join(
os.path.dirname(path_dir), os.path.basename(path_dir)+'.zip')
with zipfile.ZipFile(path_file_zip, 'wb', zipfile.ZIP_DEFLATED) as zip_file:
for root, dirs, files in os.walk(path_dir):
for file_or_dir in files + dirs:
zip_file.write(
os.path.join(root, file_or_dir),
os.path.relpath(os.path.join(root, file_or_dir),
os.path.join(path_dir, os.path.pardir)))
# import required python modules
# You have to install zipfile package using pip install
import os,zipfile
# Change the directory where you want your new zip file to be
os.chdir('Type your destination')
# Create a new zipfile ( I called it myfile )
zf = zipfile.ZipFile('myfile.zip','w')
# os.walk gives a directory tree. Access the files using a for loop
for dirnames,folders,files in os.walk('Type your directory'):
zf.write('Type your Directory')
for file in files:
zf.write(os.path.join('Type your directory',file))
Well, after reading the suggestions I came up with a very similar way that works with 2.7.x without creating "funny" directory names (absolute-like names), and will only create the specified folder inside the zip.
Or just in case you needed your zip to contain a folder inside with the contents of the selected directory.
def zipDir( path, ziph ) :
"""
Inserts directory (path) into zipfile instance (ziph)
"""
for root, dirs, files in os.walk( path ) :
for file in files :
ziph.write( os.path.join( root, file ) , os.path.basename( os.path.normpath( path ) ) + "\\" + file )
def makeZip( pathToFolder ) :
"""
Creates a zip file with the specified folder
"""
zipf = zipfile.ZipFile( pathToFolder + 'file.zip', 'w', zipfile.ZIP_DEFLATED )
zipDir( pathToFolder, zipf )
zipf.close()
print( "Zip file saved to: " + pathToFolder)
makeZip( "c:\\path\\to\\folder\\to\\insert\\into\\zipfile" )
Function to create zip file.
def CREATEZIPFILE(zipname, path):
#function to create a zip file
#Parameters: zipname - name of the zip file; path - name of folder/file to be put in zip file
zipf = zipfile.ZipFile(zipname, 'w', zipfile.ZIP_DEFLATED)
zipf.setpassword(b"password") #if you want to set password to zipfile
#checks if the path is file or directory
if os.path.isdir(path):
for files in os.listdir(path):
zipf.write(os.path.join(path, files), files)
elif os.path.isfile(path):
zipf.write(os.path.join(path), path)
zipf.close()
One thing completely missed by previous answers is the fact that using os.path.join() can easily return POSIX-incompatible paths when you run the code on Windows. The resulting archive will contain files with literal backslashes in their names when processing it with any common archive software on Linux, which is not what you want. Use path.as_posix() for the arcname parameter instead!
import zipfile
from pathlib import Path
with zipfile.ZipFile("archive.zip", "w", zipfile.ZIP_DEFLATED) as zf:
for path in Path("include_all_of_this_folder").rglob("*"):
zf.write(path, path.as_posix())