Create zipfile at local and write files from s3 - python

I am creating a zipfile on my local machine and would like to write files from s3. So far I'm unable to do it. Here's what I have in the mean time.
import os
import zipfile
from fs import open_fs
fs = open_fs(os.getenv('s3_sample_folder'))
file_names = file_names() #list of file names
with zipfile.ZipFile('zipfile.zip', mode='w') as zf:
for file in file_names:
with fs.open('/'+file, 'rb') as remote_file:
content = remote_file.read()
zf.write(content, basename(content))

The ZipFile.write method accepts a file name, not file content. You should use the ZipFile.writestr method instead to write file content to the zip file:
zf.writestr(file, content)

Since you are using PyFilesystem, you can open a S3 filesystem and a Zip filesystem, then use copy_file to copy between them.
Something like the following should work:
import os
from fs import open_fs
from fs.copy import copy_file
with open_fs(os.getenv('s3_sample_folder')) as s3_fs:
with open_fs('zip://zipfile.zip', create=True) as zip_fs:
for filename in file_names():
copy_file(s3_fs, filename, zip_fs, filename)

Related

Extracting zip with password to another dir without foldername

I have this password protected zip folder:
folder_1\1.zip
When I extract this it gives me
1\image.png
How can I extract this to another folder without its folder name? Just the contents of it: image.png
So far I have done all stackoverflows solutions and took me 11 hrs straight just to solve this.
import zipfile
zip = zipfile.ZipFile('C:\\Users\\Desktop\\folder_1\\1.zip', 'r')
zip.setpassword(b"virus")
zip.extractall('C:\\Users\\Desktop') <--target dir to extract all contents
zip.close()
EDIT:
This code worked for me: (Now I want many paths to be extracted at once, any ideas?
import os
import shutil
import zipfile
my_dir = r"C:\\Users\\Desktop"
my_zip = r"C:\\Users\\Desktop\\test\\folder_1\\1.zip"
with zipfile.ZipFile(my_zip) as zip_file:
zip_file.setpassword(b"virus")
for member in zip_file.namelist():
filename = os.path.basename(member)
# skip directories
if not filename:
continue
# copy file (taken from zipfile's extract)
source = zip_file.open(member)
target = file(os.path.join(my_dir, filename), "wb")
with source, target:
shutil.copyfileobj(source, target)
You can use the ZipFile.read() method to read the specific file in the archive, open your target file for writing by joining the target directory with the base name of the source file, and then write what you read to it:
import zipfile
import os
zip = zipfile.ZipFile('C:\\Users\\Desktop\\folder_1\\1.zip', 'r')
zip.setpassword(b"virus")
for name in zip.namelist():
if not name.endswith(('/', '\\')):
with open(os.path.join('C:\\Users\\Desktop', os.path.basename(name)), 'wb') as f:
f.write(zip.read(name))
zip.close()
And if you have several paths containing 1.zip for extraction:
import zipfile
import os
for path in 'C:\\Users\\Desktop\\folder_1', 'C:\\Users\\Desktop\\folder_2', 'C:\\Users\\Desktop\\folder_3':
zip = zipfile.ZipFile(os.path.join(path, '1.zip'), 'r')
zip.setpassword(b"virus")
for name in zip.namelist():
if not name.endswith(('/', '\\')):
with open(os.path.join('C:\\Users\\Desktop', os.path.basename(name)), 'wb') as f:
f.write(zip.read(name))
zip.close()

reading zip files within tar file

I am trying to extract some xml files within zipped files, from a tar file. Actually, there is a large tar file, in which there are multiple "zip" files. Each zipfile contains another zipfile with the xml file.
import tarfile, os
import sys
from zipfile import ZipFile
os.chdir("C://.../temp/foo")
tar = tarfile.open("C://....")
for member in tar.getmembers():
if member.name.endswith(".zip"):
f=tar.extractfile(member)
content=ZipFile(f, 'r')
content = content.extract(content)
tar.close()
The script above the not extract the good file
You have to do a bit of manipulation to get the second ZipFile into a ZipFile rather than a ZipExtFile, as you would have noticed.
The key thing is that the second-level ZipFile has to be instantiated out of a bytestream object, and then it will behave properly. I created a test file with your spec and it works fine (tar - zip - zip - textfile) and if you have deeper levels of zipfile nesting you can just generalise the code some more.
import tarfile
from zipfile import ZipFile
import io
mytar = tarfile.open('mytar.tar')
print('Opening tar file, members:')
for member in mytar.getnames():
print('>%s'%member)
if member.endswith('zip'):
# get the tarfile object
tf = mytar.extractfile(member)
# this is what the first-lelvel ZipFile will be
with ZipFile(tf) as myzip1:
print(myzip1.namelist())
# now let's get at those second-level ZipFiles, which currently exist as ZipExtFile
for zipfile2name in myzip1.namelist():
# read the file into bytes
zipfile2bytes = myzip1.read(zipfile2name)
# get a bytestream
f = io.BytesIO(zipfile2bytes)
# now instantiate a ZipFile Object
zipfile2 = ZipFile(f)
# now we can use it like a proper ZipFile
print(zipfile2.namelist())
for textfile in zipfile2.namelist():
with zipfile2.open(textfile) as myfile:
print(myfile.read())
print('--finished--')
mytar.close()

Unable to remove zipped file after unzipping

I'm attempting to remove a zipped file after unzipping the contents on windows. The contents can be stored in a folder structure in the zip. I'm using the with statement and thought this would close the file-like object (source var) and zip file. I've removed lines of code relating to saving the source file.
import zipfile
import os
zipped_file = r'D:\test.zip'
with zipfile.ZipFile(zipped_file) as zip_file:
for member in zip_file.namelist():
filename = os.path.basename(member)
if not filename:
continue
source = zip_file.open(member)
os.remove(zipped_file)
The error returned is:
WindowsError: [Error 32] The process cannot access the file because it is being used by another process: 'D:\\test.zip'
I've tried:
looping over the os.remove line in case it's a slight timing issue
Using close explicitly instead of the with statment
Attempted on local C drive and mapped D Drive
instead of passing in a string to the ZipFile constructor, you can pass it a file like object:
import zipfile
import os
zipped_file = r'D:\test.zip'
with open(zipped_file, mode="r") as file:
zip_file = zipfile.ZipFile(file)
for member in zip_file.namelist():
filename = os.path.basename(member)
if not filename:
continue
source = zip_file.open(member)
os.remove(zipped_file)
You are opening files inside the zip... which create a file lock on the whole zip file. close the inner file open first... via source.close() at the end of your loop
import zipfile
import os
zipped_file = r'D:\test.zip'
with zipfile.ZipFile(zipped_file) as zip_file:
for member in zip_file.namelist():
filename = os.path.basename(member)
if not filename:
continue
source = zip_file.open(member)
source.close()
os.remove(zipped_file)
Try to close the zipfile before removing.
you can do also like this, which works pretty good:
import os, shutil, zipfile
fpath= 'C:/Users/dest_folder'
path = os.getcwd()
for file in os.listdir(path):
if file.endswith(".zip"):
dirs = os.path.join(path, file)
if os.path.exists(fpath):
shutil.rmtree(fpath)
_ = os.mkdir(fpath)
with open(dirs, 'rb') as fileobj:
z = zipfile.ZipFile(fileobj)
z.extractall(fpath)
z.close()
os.remove(dirs)

Extract All Zipped Files to Same Directory Using Python

I have a large amount of zipped files in a single directory that I would like to decompress and save them to the same directory and with the same name as the zipped file.
Start with something like:
import glob
import os
import zipfile
zip_files = glob.glob('*.zip')
for zip_filename in zip_files:
dir_name = os.path.splitext(zip_filename)[0]
os.mkdir(dir_name)
zip_handler = zipfile.ZipFile(zip_filename, "r")
zip_handler.extractall(dir_name)
Sorry, I don't have time to test this code; any bug is left as an exercise for you.
[Updated with eumiro's suggestion]

Extract files from zip without keeping the structure using python ZipFile?

I try to extract all files from .zip containing subfolders in one folder. I want all the files from subfolders extract in only one folder without keeping the original structure. At the moment, I extract all, move the files to a folder, then remove previous subfolders. The files with same names are overwrited.
Is it possible to do it before writing files?
Here is a structure for example:
my_zip/file1.txt
my_zip/dir1/file2.txt
my_zip/dir1/dir2/file3.txt
my_zip/dir3/file4.txt
At the end I whish this:
my_dir/file1.txt
my_dir/file2.txt
my_dir/file3.txt
my_dir/file4.txt
What can I add to this code ?
import zipfile
my_dir = "D:\\Download\\"
my_zip = "D:\\Download\\my_file.zip"
zip_file = zipfile.ZipFile(my_zip, 'r')
for files in zip_file.namelist():
zip_file.extract(files, my_dir)
zip_file.close()
if I rename files path from zip_file.namelist(), I have this error:
KeyError: "There is no item named 'file2.txt' in the archive"
This opens file handles of members of the zip archive, extracts the filename and copies it to a target file (that's how ZipFile.extract works, without taking care of subdirectories).
import os
import shutil
import zipfile
my_dir = r"D:\Download"
my_zip = r"D:\Download\my_file.zip"
with zipfile.ZipFile(my_zip) as zip_file:
for member in zip_file.namelist():
filename = os.path.basename(member)
# skip directories
if not filename:
continue
# copy file (taken from zipfile's extract)
source = zip_file.open(member)
target = open(os.path.join(my_dir, filename), "wb")
with source, target:
shutil.copyfileobj(source, target)
It is possible to iterate over the ZipFile.infolist(). On the returned ZipInfo objects you can then manipulate the filename to remove the directory part and finally extract it to a specified directory.
import zipfile
import os
my_dir = "D:\\Download\\"
my_zip = "D:\\Download\\my_file.zip"
with zipfile.ZipFile(my_zip) as zip:
for zip_info in zip.infolist():
if zip_info.filename[-1] == '/':
continue
zip_info.filename = os.path.basename(zip_info.filename)
zip.extract(zip_info, my_dir)
Just extract to bytes in memory,compute the filename, and write it there yourself,
instead of letting the library do it - -mostly, just use the "read()" instead of "extract()" method:
Python 3.6+ update(2020) - the same code from the original answer, but using pathlib.Path, which ease file-path manipulation and other operations (like "write_bytes")
from pathlib import Path
import zipfile
import os
my_dir = Path("D:\\Download\\")
my_zip = my_dir / "my_file.zip"
zip_file = zipfile.ZipFile(my_zip, 'r')
for files in zip_file.namelist():
data = zip_file.read(files, my_dir)
myfile_path = my_dir / Path(files.filename).name
myfile_path.write_bytes(data)
zip_file.close()
Original code in answer without pathlib:
import zipfile
import os
my_dir = "D:\\Download\\"
my_zip = "D:\\Download\\my_file.zip"
zip_file = zipfile.ZipFile(my_zip, 'r')
for files in zip_file.namelist():
data = zip_file.read(files, my_dir)
# I am almost shure zip represents directory separator
# char as "/" regardless of OS, but I don't have DOS or Windos here to test it
myfile_path = os.path.join(my_dir, files.split("/")[-1])
myfile = open(myfile_path, "wb")
myfile.write(data)
myfile.close()
zip_file.close()
A similar concept to the solution of Gerhard Götz, but adapted for extracting single files instead of the entire zip:
with ZipFile(zipPath, 'r') as zipObj:
zipInfo = zipObj.getinfo(path_in_zip))
zipInfo.filename = os.path.basename(destination)
zipObj.extract(zipInfo, os.path.dirname(os.path.realpath(destination)))
In case you are getting badZipFile error. you can unzip the archive using 7zip sub process. assuming you have installed the 7zip then use the following code.
import subprocess
my_dir = destFolder #destination folder
my_zip = destFolder + "/" + filename.zip #file you want to extract
ziploc = "C:/Program Files/7-Zip/7z.exe" #location where 7zip is installed
cmd = [ziploc, 'e',my_zip ,'-o'+ my_dir ,'*.txt' ,'-r' ]
#extracting only txt files and from all subdirectories
sp = subprocess.Popen(cmd, stderr=subprocess.STDOUT, stdout=subprocess.PIPE)

Categories