I have a script that copies files from a folder to another folder, but I want it to ignore the txt files. I have this code that works, but it does not ignore the txt files. It just copies everything without any warning.
What am I doing wrong?
import sys, os, shutil
script, filetobackup = sys.argv
backupdir = r'*path to backupdir*'
def copytree(filetobackup, backupdir, symlinks=False):
if not os.path.exists(backupdir):
os.makedirs(backupdir)
for item in os.listdir(filetobackup):
s = os.path.join(filetobackup, item)
d = os.path.join(backupdir, item)
if os.path.isdir(s):
shutil.copytree(s, d, symlinks, ignore=ignore_patterns('*.txt'))
else:
if not os.path.exists(d) or os.stat(s).st_mtime - os.stat(d).st_mtime > 1:
shutil.copy2(s, d)
copytree(filetobackup, backupdir)
Edit: Hmm, no one knows?
Related
The below works as expected:
import shutil
source = "c:\\mydir\myfile.txt"
dest_dir = "c:\\newdir"
shutil.move(source,dest_dir)
However, this also succeeds. I would want this to fail.
import shutil
source = "c:\\mydir"
dest_dir = "c:\\newdir"
shutil.move(source,dest_dir)
Any way to ensure that only a file is moved. Both Windows and Unix would be great. If not, Unix at least.
You could use pathlib's purepath.suffix to determine if a path points to a file or a directory, like so:
import pathlib
def points_to_file(path) -> bool:
if pathlib.PurePath(path).suffix:
return True
else:
return False
pathtodir = r'C:\Users\username'
pathtofile = r'C:\Users\username\filename.extension'
print (f'Does "{pathtodir}" point to a file? {points_to_file(pathtodir)}')
# Result -> Does "C:\Users\username" point to a file? False
print (f'Does "{pathtofile}" point to a file? {points_to_file(pathtofile)}')
# Result -> Does "C:\Users\username\filename.extension" point to a file? True
You can define a custom function to ensure that source is a file (with os.path.isfile function):
from os import path
def move_file(src, dst):
if not path.isfile(src):
raise IsADirectoryError('Source is not a file')
shutil.move(src, dst)
I recently started getting into Python and I am having a hard time searching through directories and matching files based on a regex that I have created.
Basically I want it to scan through all the directories in another directory and find all the files that ends with .zip or .rar or .r01 and then run various commands based on what file it is.
import os, re
rootdir = "/mnt/externa/Torrents/completed"
for subdir, dirs, files in os.walk(rootdir):
if re.search('(w?.zip)|(w?.rar)|(w?.r01)', files):
print "match: " . files
import os
import re
rootdir = "/mnt/externa/Torrents/completed"
regex = re.compile('(.*zip$)|(.*rar$)|(.*r01$)')
for root, dirs, files in os.walk(rootdir):
for file in files:
if regex.match(file):
print(file)
CODE BELLOW ANSWERS QUESTION IN FOLLOWING COMMENT
That worked really well, is there a way to do this if match is found on regex group 1 and do this if match is found on regex group 2 etc ? – nillenilsson
import os
import re
regex = re.compile('(.*zip$)|(.*rar$)|(.*r01$)')
rx = '(.*zip$)|(.*rar$)|(.*r01$)'
for root, dirs, files in os.walk("../Documents"):
for file in files:
res = re.match(rx, file)
if res:
if res.group(1):
print("ZIP",file)
if res.group(2):
print("RAR",file)
if res.group(3):
print("R01",file)
It might be possible to do this in a nicer way, but this works.
Given that you are a beginner, I would recommend using glob in place of a quickly written file-walking-regex matcher.
Snippets of functions using glob and a file-walking-regex matcher
The below snippet contains two file-regex searching functions (one using glob and the other using a custom file-walking-regex matcher). The snippet also contains a "stopwatch" function to time the two functions.
import os
import sys
from datetime import timedelta
from timeit import time
import os
import re
import glob
def stopwatch(method):
def timed(*args, **kw):
ts = time.perf_counter()
result = method(*args, **kw)
te = time.perf_counter()
duration = timedelta(seconds=te - ts)
print(f"{method.__name__}: {duration}")
return result
return timed
#stopwatch
def get_filepaths_with_oswalk(root_path: str, file_regex: str):
files_paths = []
pattern = re.compile(file_regex)
for root, directories, files in os.walk(root_path):
for file in files:
if pattern.match(file):
files_paths.append(os.path.join(root, file))
return files_paths
#stopwatch
def get_filepaths_with_glob(root_path: str, file_regex: str):
return glob.glob(os.path.join(root_path, file_regex))
Comparing runtimes of the above functions
On using the above two functions to find 5076 files matching the regex filename_*.csv in a dir called root_path (containing 66,948 files):
>>> glob_files = get_filepaths_with_glob(root_path, 'filename_*.csv')
get_filepaths_with_glob: 0:00:00.176400
>>> oswalk_files = get_filepaths_with_oswalk(root_path,'filename_(.*).csv')
get_filepaths_with_oswalk: 0:03:29.385379
The glob method is much faster and the code for it is shorter.
For your case
For your case, you can probably use something like the following to get your *.zip,*.rar and *.r01 files:
files = []
for ext in ['*.zip', '*.rar', '*.r01']:
files += get_filepaths_with_glob(root_path, ext)
Here's an alternative using glob.
from pathlib import Path
rootdir = "/mnt/externa/Torrents/completed"
for extension in 'zip rar r01'.split():
for path in Path(rootdir).glob('*.' + extension):
print("match: " + path)
I would do it this way:
import re
from pathlib import Path
def glob_re(path, regex="", glob_mask="**/*", inverse=False):
p = Path(path)
if inverse:
res = [str(f) for f in p.glob(glob_mask) if not re.search(regex, str(f))]
else:
res = [str(f) for f in p.glob(glob_mask) if re.search(regex, str(f))]
return res
NOTE: per default it will recursively scan all subdirectories. If you want to scan only the current directory then you should explicitly specify glob_mask="*"
How to make this code works?
There is a zip file with folders and .png files in it. Folder ".\icons_by_year" is empty. I need to get every file one by one without unzipping it and copy to the root of the selected folder (so no extra folders made).
class ArrangerOutZip(Arranger):
def __init__(self):
self.base_source_folder = '\\icons.zip'
self.base_output_folder = ".\\icons_by_year"
def proceed(self):
self.create_and_copy()
def create_and_copy(self):
reg_pattern = re.compile('.+\.\w{1,4}$')
f = open(self.base_source_folder, 'rb')
zfile = zipfile.ZipFile(f)
for cont in zfile.namelist():
if reg_pattern.match(cont):
with zfile.open(cont) as file:
shutil.copyfileobj(file, self.base_output_folder)
zfile.close()
f.close()
arranger = ArrangerOutZip()
arranger.proceed()
shutil.copyfileobj uses file objects for source and destination files. To open the destination you need to construct a file path for it. pathlib is a part of the standard python library and is a nice way to handle file paths. And ZipFile.extract does some of the work of creating intermediate output directories for you (plus sets file metadata) and can be used instead of copyfileobj.
One risk of unzipping files is that they can contain absolute or relative paths outside of the target directory you intend (e.g., "../../badvirus.exe"). extract is a bit too lax about that - putting those files in the root of the target directory - so I wrote a little something to reject the whole zip if you are being messed with.
With a few tweeks to make this a testable program,
from pathlib import Path
import re
import zipfile
#import shutil
#class ArrangerOutZip(Arranger):
class ArrangerOutZip:
def __init__(self, base_source_folder, base_output_folder):
self.base_source_folder = Path(base_source_folder).resolve(strict=True)
self.base_output_folder = Path(base_output_folder).resolve()
def proceed(self):
self.create_and_copy()
def create_and_copy(self):
"""Unzip files matching pattern to base_output_folder, raising
ValueError if any resulting paths are outside of that folder.
Output folder created if it does not exist."""
reg_pattern = re.compile('.+\.\w{1,4}$')
with open(self.base_source_folder, 'rb') as f:
with zipfile.ZipFile(f) as zfile:
wanted_files = [cont for cont in zfile.namelist()
if reg_pattern.match(cont)]
rebased_files = self._rebase_paths(wanted_files,
self.base_output_folder)
for cont, rebased in zip(wanted_files, rebased_files):
print(cont, rebased, rebased.parent)
# option 1: use shutil
#rebased.parent.mkdir(parents=True, exist_ok=True)
#with zfile.open(cont) as file, open(rebased, 'wb') as outfile:
# shutil.copyfileobj(file, outfile)
# option 2: zipfile does the work for you
zfile.extract(cont, self.base_output_folder)
#staticmethod
def _rebase_paths(pathlist, target_dir):
"""Rebase relative file paths to target directory, raising
ValueError if any resulting paths are not within target_dir"""
target = Path(target_dir).resolve()
newpaths = []
for path in pathlist:
newpath = target.joinpath(path).resolve()
newpath.relative_to(target) # raises ValueError if not subpath
newpaths.append(newpath)
return newpaths
#arranger = ArrangerOutZip('\\icons.zip', '.\\icons_by_year')
import sys
try:
arranger = ArrangerOutZip(sys.argv[1], sys.argv[2])
arranger.proceed()
except IndexError:
print("usage: test.py zipfile targetdir")
I'd take a look at the zipfile libraries' getinfo() and also ZipFile.Path() for construction since the constructor class can also use paths that way if you intend to do any creation.
Specifically PathObjects. This is able to do is to construct an object with a path in it, and it appears to be based on pathlib. Assuming you don't need to create zipfiles, you can ignore this ZipFile.Path()
However, that's not exactly what I wanted to point out. Rather consider the following:
zipfile.getinfo()
There is a person who I think is getting at this exact situation here:
https://www.programcreek.com/python/example/104991/zipfile.getinfo
This person seems to be getting a path using getinfo(). It's also clear that NOT every zipfile has the info.
I wrote a function that is supposed to look for all the file with the extension chosen, in the selected directory. Actually, it runs but it doesn't return anything.
I am trying to keep things simple/stupid, since I am just at the beginning of my journey in Python
Below, I reported the code.
Thanks for your help!
THIS ONE RUNS, BUT RETURNS AN EMPTY LIST
import fnmatch
import glob
def lookfor(dir, ext):
direct = glob.glob(dir)
files = []
for file in direct:
if fnmatch.fnmatch(file, ext):
files.append(file)
return files
print(lookfor('C:/Users/nameuser/where/folder/', '*.docx'))
THIS ONE WORKS PROPERLY, BUT ONLY FOR .docx FILE, AS WRITTEN INSIDE THE FUNCT
import fnmatch
import glob
def lookfor(dir):
direct = glob.glob(dir)
files = []
for file in direct:
if fnmatch.fnmatch(file, '*.docx'):
files.append(file)
return files
print(lookfor('C:/Users/nameuser/where/folder/*.docx'))
I'm having trouble making a subfolder for files to be stored into after choosing the Parent Folder or directory.
This is my current script:
import os, sys, subprocess, shutil, glob, os.path, csv
#User Chooses Folder or File Path Directory
path_new = filedialog.askdirectory()
def saveData():
serial_number = input('Scan Barcode: ')
folder_name = print('Folder Name:', serial_number)
os.chdir(path_new) #Not sure if this is necessary
if not os.path.exists(path_new):
os.makedirs(path_new)
print ('The data has been stored in the following directory:', path_new)
shutil.move('file_directory/TOTAL.csv', 'chosen_directory/%s'% (serial_number))
shutil.move('file_directory/enviro.csv', 'chosen_directory/%s' % (serial_number))
The script runs, but just not how I would like it to. Does anyone have any recommendations or an alternate solution to creating a folder and selecting it as the directory to have subfolders created and have files transferred into them?
I resolved my issue. If anyone else knows of a "cleaner" way of writing this out please update with a better answer. As of now this does exactly what I want.
Code:
import os, sys, shutil. os.path
path = filedialog.askdirectory()
def saveData():
serial_number = input('Scan Barcode: ')
folder_name = print('Folder Name:', serial_number)
path_new = os.path.join(path, '%s' % (serial_number))
if not os.path.exists(path_new):
os.makedirs(path_new)
shutil.move('C:/files/TOTAL.csv', path_new)
shutil.move('C:/files/enviro.csv', path_new)
print('The data has been stored in the following directory:', path_new)