(Feb-08-2020, 11:28 AM)jim2007 Wrote: It is almost certainly an issue with passing the correct file name to the function. Try hard coding one of the file names into the my_zip variable and see if it runs without error.

import glob
import zipfile
import shutil
import os

my_dir = "/Users/myusernamehere/Documents/My_Dataset/new"
my_zip = r"/Users/myusernamehere/Documents/My_Dataset/something.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)

(Feb-09-2020, 04:53 AM)jim2007 Wrote: Have a read of this, it should get you off the starting block in finding a list of files: https://realpython.com/working-with-files-in-python/

import os
 
'''
    For the given path, get the List of all files in the directory tree 
'''
def getListOfFiles(dirName):
    # create a list of file and sub directories 
    # names in the given directory 
    listOfFile = os.listdir(dirName)
    allFiles = list()
    # Iterate over all the entries
    for entry in listOfFile:
        # Create full path
        fullPath = os.path.join(dirName, entry)
        # If entry is a directory then get the list of files in this directory 
        if os.path.isdir(fullPath):
            allFiles = allFiles + getListOfFiles(fullPath)
        else:
            allFiles.append(fullPath)
                
    return allFiles        
 
 
def main():
    
    dirName = '/home/varun/Downloads';
    
    # Get the list of all files in directory tree at given path
    listOfFiles = getListOfFiles(dirName)
    
    # Print the files
    for elem in listOfFiles:
        print(elem)
 
    print ("****************")
    
    # Get the list of all files in directory tree at given path
    listOfFiles = list()
    for (dirpath, dirnames, filenames) in os.walk(dirName):
        listOfFiles += [os.path.join(dirpath, file) for file in filenames]
        
        
    # Print the files    
    for elem in listOfFiles:
        print(elem)    
        
        
        
        
if __name__ == '__main__':
    main()

import os
from typing import List

FileList = List[str]

def get_list_of_files(base_folder: str, files: FileList) -> None:
    with os.scandir(base_folder) as entries:
        for entry in entries:
            # Skip all hidden files and folders
            if entry.name.startswith('.'):
                continue

            qualified_name = os.path.join(base_folder, entry)

            # If it's a file we'll added it to the collection
            if entry.is_file():
                files.append(qualified_name)
            elif entry.is_dir():
                # If it's a folder then we'll process that as well
                get_list_of_files(os.path.join(base_folder, entry), files)

files = []
base_folder = '/Users/<user>/Development'

get_list_of_files(base_folder, files)

for file in files:
    print(file)

(Feb-10-2020, 04:51 PM)jim2007 Wrote: So I did the same, but it is a function that returns a list of files"

import os, zipfile, shutil
from typing import List

FileList = List[str]


def get_list_of_files(base_folder: str, files: FileList) -> None:
    with os.scandir(base_folder) as entries:
        for entry in entries:
            # Skip all hidden files and folders
            if entry.name.startswith('.'):
                continue

            qualified_name = os.path.join(base_folder, entry)

            # If it's a file we'll added it to the collection
            if entry.is_file():
                files.append(qualified_name)
            elif entry.is_dir():
                # If it's a folder then we'll process that as well
                get_list_of_files(os.path.join(base_folder, entry), files)


files = []
base_folder = r"C:\Users\username\My_Dataset"

get_list_of_files(base_folder, files)

for file in files:
    print(file)
    my_zipfile = zipfile.ZipFile(file)
    my_zipfile.extractall(r'C:\Users\username\My_Dataset\new')

# Generate the file paths to traverse, or a single path if a file name was given
def getfiles(path):
    if os.path.isdir(path):
        for root, dirs, files in os.walk(path):
            for name in files:
                yield os.path.join(root, name)
    else:
        yield path


destination = r"C:\Users\Documents\flatten"
fromdir = r"C:\Users\username\My_Dataset\new"
for f in getfiles(fromdir):
    filename = str.split(f, '/')[-1]
    if os.path.isfile(destination + filename):
        filename = f.replace(fromdir, "", 1).replace("/", "_")
    # os.rename(f, destination+filename)
    shutil.copy2(f, r"C:\Users\username\Documents\flatten")

if filetype is = shp, shx, cpg, prj, dbf
    continue 

from pathlib import Path
from typing import Generator


FileList = Generator[Path, None, None]


def get_list_of_files(base_folder: Path) -> FileList:
    for entry in base_folder.rglob('*'):
        # Skip all hidden files and folders
        if entry.name.startswith('.'):
            continue
            
        if entry.is_file():
            yield entry


base_folder = Path.home() / 'Development'
files = list(get_list_of_files(base_folder))

for file in files:
    print(file)

from pathlib import Path

my_extensions = ['.txt', '.odt', '.csv']
my_path = Path('/A/directory/somewhere/that/does/not.exist/file.txt')
print('The suffix is:', my_path.suffix)

if my_path.suffix not in my_extensions:
    print(my_path, 'has not the allowed file extension')

 
for file in get_list_of_files(base_folder):
    print(file)
    my_zipfile = zipfile.ZipFile(file)
    my_zipfile.extractall(r'C:\Users\username\My_Dataset\new')

(Feb-10-2020, 07:45 PM)puredata Wrote: Would you have any input about this? Thanks a lot again in advance!

(Feb-06-2020, 09:58 PM)puredata Wrote: Hello, I'm trying to use Python to automate unzipping of multiple files in a folder. I already have a script that works and unzips my files. But it won't copy contents of the zip files which has subfolders. In order to be able to extract everything into one main folder (disregarding original subfolder structure) I have found this code chunk on stackexchange. A moderator reported that the code is working for him therefore I should be investigating something else, not the code itself.

import os
import shutil
import zipfile

my_dir = r"C:\Users\username\My_Dataset\new"
my_zip = r"C:\Users\username\My_Dataset"

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)

Here is the Traceback I get:

Error:
Traceback (most recent call last):
  File "C:/Users/username/PycharmProjects/GeoPandas/mergeAnswer.py", line 8, in <module>
    with zipfile.ZipFile(my_zip) as zip_file:
  File "C:\Users\username\Anaconda3\envs\playground\lib\zipfile.py", line 1207, in __init__
    self.fp = io.open(file, filemode)
PermissionError: [Errno 13] Permission denied: 'C:\\Users\\username\\My_Dataset

The only thing that looks suspicious to me is the direction of the slashes on Traceback. Some of them are forwards slashes while some of them are backwards. Could it be related to that? I'm running this code in Windows and haven't tried on a mac or linux.

Would it be possible to get some suggestions in order to make this script work? I don't need to use this specific script, I'm just trying to unzip a lot of files (some are under subfolders some are not) into one main folder.

Thanks in advance!