I work as an IT help desk associate and have to constantly clear out disk space for VDIs. I want to write a code that can clear out specific folders all at once to save time. I wrote a code, but only have it to run one folder at a time. Is there a way for me to make it a function and just make variables for each path and have them all cleared at once. Sample:
import os
#path to delete
path = r"C:\Users\jwals\test test"
#will check if the path is a dir or not
if os.path.exists(path):
#iterating through subfolders
for root_folder, folders, files in os.walk(path):
#checking for files
for file in files:
#file path
file_path = os.path.join(root_folder, file)
#delete the files in that path
if not os.remove(file_path):
#will print if successful
print(f"{file_path} deleted successfully")
#unsuccessful message (if this prints something went wrong)
else:
print(f"Unable to delete the {file_path}")
IIUIC, you can simply do this:
import os
#paths to delete
paths = [r"C:\Users\jwals\test test", r"C:\Users\jwals\another test"]
def delete_files(path):
#will check if the path is a dir or not
if os.path.exists(path):
#iterating through subfolders
for root_folder, folders, files in os.walk(path):
#checking for files
for file in files:
#file path
file_path = os.path.join(root_folder, file)
...
for path in paths:
delete_files(path)
Related
Usually I navigate to the folder I am extracting data from and copy the file name directly:
df2=pd.read_csv('10_90_bnOH-MEA.csv',usecols=[1])
If I have multiple files and want to do the same for all the files, how do I specify the folder to open and get all the files inside?
I want to run the above code without specifying the file's full path
(C:\Users\X\Desktop\Y\Z\10_90_bnOH-MEA.csv)
You want listdir from the os module.
import os
path = "C:\\Users\\X\\Desktop\\Y\\Z\\"
files = os.listdir(path)
print(files)
dataframe_list = []
for filename in files:
dataframe_list.append(pd.read_csv(os.path.join(path,filename)))
You should open the desired directory and loop through all the files then do something to them.
# import required module
import os
# assign directory
directory = 'files'
# iterate over files in
def goThroughDirectory(directory):
for filename in os.listdir(directory):
f = os.path.join(directory, filename)
# checking if it is a file
if os.path.isfile(f):
# do something
If you also want to loop through all the files in a directory you should add a check for if os.path.isdir(f) like this
...
def goThroughDirectory(directory):
for filename in os.listdir(directory):
f = os.path.join(directory, filename)
# checking if it is a file
if os.path.isfile(f):
# do something
elif os.path.isdir(f):
# its not a file but a directory then loop through that directory aswell
goThroughDirectory(directory + "\" + f)
for more information you should check geeksforgeeks
I have problems solving a task. Below you can see my code. I want to work with sub-sub-folders too but my code only moves the sub-folders. How can I do this recursively that it moves all folders in main folder?
path = (r"C:\Users\Desktop\testfolder")
os.chdir(path)
all_files = list(os.listdir())
outputs = os.getcwd()
for files in all_files:
try:
inputs = glob.glob(files + "\\*")
for a in inputs:
shutil.move(a, outputs)
except:
pass
for files in os.listdir("."):
dir_folder = files[:32]
if not os.path.isdir(dir_folder):
try:
os.mkdir(dir_folder)
except:
pass
Here is the new code, that will maintain the folder structure in the output folder as it was in the input folder
from pathlib import Path
import shutil
import os
for path, dir_folder, files in os.walk('./test_folder'):
for file in files:
full_path = os.path.join(path,file)
## Create the path to the subfolder
sub_folder_path = '/'.join(path.split('/')[2:])
# Create output path by joining subfolder path and output directory
output_path = os.path.join(outputs, sub_folder_path)
# Create the output path directory structure if it does not exists, ignore if it does
Path(output_path).mkdir(parents=True, exist_ok=True)
# Move file
shutil.move(full_path, output_path)
You can use os.walk to recursively visit each folder and sub folder and then move all the files in that folder.
import shutil
import os
for path, dir_folder, files in os.walk(input_folder):
for file in files:
full_path = os.path.join(path,file)
move_path = os.path.join(output_path,file)
print(move_path)
shutil.move(full_path, move_path)
print(file)
Where output_path is the path to the folder you move to move the files to.
This will not create the same folder structure in output folder, just move all the files there, do you also want to maintain structure in output folder? If so, I can edit my answer to reflect that
I have ~1000 directories, containing various .csv files within them. I am trying to check if a specific type of csv file, containing a filename that begins with PTSD_OCOTBER, exists in each directory.
If this file does not exist in the directory, I want to print out that directory into a .txt file.
Here is what I have so far.
import os,sys,time,shutil
import subprocess
#determine filetype to look for.
file_type = ".csv"
print("Running file counter for" + repr(file_type))
#for each folder in the root directory
for subdir, dirs, files in os.walk(rootdir):
if("GeneSet" in subdir):
folder_name = subdir.rsplit('/', 1)[-1] #get the folder name.
for f in files:
#unclear how to write this part.
#how to tell if no files exist in directory?
This successfully finds the .csv files of interest, but how do achieve the above?
So files is the list of files in that directory that you are currently walking. You want to know if there are no files that start with PTSD_OCOTBER (PTSD_OCTOBER ?):
for subdir, dirs, files in os.walk(rootdir):
if("GeneSet" in subdir):
folder_name = subdir.rsplit('/', 1)[-1] #get the folder name.
dir_of_interest = not any(f.startswith('PTSD_OCOTBER') for f in files)
if dir_of_interest:
# do stuff with folder_name
Now you want to save the results into a text file? If you have a Unix-style computer, then you can use output redirection on your terminal, such as
python3 fileanalysis.py > result.txt
after writing print(folder_name) instead of # do stuff with folder_name.
Or you can use Python itself to write the file, such as:
found_dirs = []
for subdir, dirs, files in os.walk(rootdir):
...
if dir_of_interest:
found_dirs.append(folder_name)
with open('result.txt', 'w') as f:
f.write('\n'.join(found_dirs))
I have the following directory structure:
-mailDir
-folderA
-sub1
-sub2
-inbox
-1.txt
-2.txt
-89.txt
-subInbox
-subInbox2
-folderB
-sub1
-sub2
-inbox
-1.txt
-2.txt
-200.txt
-577.txt
The aim is to copy all the txt files under inbox folder into another folder.
For this I tried the below code
import os
from os import path
import shutil
rootDir = "mailDir"
destDir = "destFolder"
eachInboxFolderPath = []
for root, dirs, files in os.walk(rootDir):
for dirName in dirs:
if(dirName=="inbox"):
eachInboxFolderPath.append(root+"\\"+dirName)
for ii in eachInboxFolderPath:
for i in os.listdir(ii):
shutil.copy(path.join(ii,i),destDir)
If the inbox directory only has .txt files then the above code works fine. Since the inbox folder under folderA directory has other sub directory along with .txt files, the code returns permission denied error. What I understood is shutil.copy won't allow to copy the folders.
The aim is to copy only the txt files in every inbox folder to some other location. If the file names are same in different inbox folder I have to keep both file names. How we can improve the code in this case ? Please note other than .txt all others are folders only.
One simple solution is to filter for any i that does not have the .txt extension by using the string endswith() method.
import os
from os import path
import shutil
rootDir = "mailDir"
destDir = "destFolder"
eachInboxFolderPath = []
for root, dirs, files in os.walk(rootDir):
for dirName in dirs:
if(dirName=="inbox"):
eachInboxFolderPath.append(root+"\\"+dirName)
for ii in eachInboxFolderPath:
for i in os.listdir(ii):
if i.endswith('.txt'):
shutil.copy(path.join(ii,i),destDir)
This should ignore any folders and non-txt files that are found with os.listdir(ii). I believe that is what you are looking for.
Just remembered that I once wrote several files to solve this exact problem before. You can find the source code here on my Github.
In short, there are two functions of interest here:
list_files(loc, return_dirs=False, return_files=True, recursive=False, valid_exts=None)
copy_files(loc, dest, rename=False)
For your case, you could copy and paste these functions into your project and modify copy_files like this:
def copy_files(loc, dest, rename=False):
# get files with full path
files = list_files(loc, return_dirs=False, return_files=True, recursive=True, valid_exts=('.txt',))
# copy files in list to dest
for i, this_file in enumerate(files):
# change name if renaming
if rename:
# replace slashes with hyphens to preserve unique name
out_file = sub(r'^./', '', this_file)
out_file = sub(r'\\|/', '-', out_file)
out_file = join(dest, out_file)
copy(this_file, out_file)
files[i] = out_file
else:
copy(this_file, dest)
return files
Then just call it like so:
copy_files('mailDir', 'destFolder', rename=True)
The renaming scheme might not be exactly what you want, but it will at least not override your files. I believe this should solve all your problems.
Here you go:
import os
from os import path
import shutil
destDir = '<absolute-path>'
for root, dirs, files in os.walk(os.getcwd()):
# Filter out only '.txt' files.
files = [f for f in files if f.endswith('.txt')]
# Filter out only 'inbox' directory.
dirs[:] = [d for d in dirs if d == 'inbox']
for f in files:
p = path.join(root, f)
# print p
shutil.copy(p, destDir)
Quick and simple.
sorry, I forgot the part where, you also need unique file names as well. The above solution only works for distinct file names in a single inbox folder.
For copying files from multiple inboxes and having a unique name in the destination folder, you can try this:
import os
from os import path
import shutil
sourceDir = os.getcwd()
fixedLength = len(sourceDir)
destDir = '<absolute-path>'
filteredFiles = []
for root, dirs, files in os.walk(sourceDir):
# Filter out only '.txt' files in all the inbox directories.
if root.endswith('inbox'):
# here I am joining the file name to the full path while filtering txt files
files = [path.join(root, f) for f in files if f.endswith('.txt')]
# add the filtered files to the main list
filteredFiles.extend(files)
# making a tuple of file path and file name
filteredFiles = [(f, f[fixedLength+1:].replace('/', '-')) for f in filteredFiles]
for (f, n) in filteredFiles:
print 'copying file...', f
# copying from the path to the dest directory with specific name
shutil.copy(f, path.join(destDir, n))
print 'copied', str(len(filteredFiles)), 'files to', destDir
If you need to copy all files instead of just txt files, then just change the condition f.endswith('.txt') to os.path.isfile(f) while filtering out the files.
One main folder that has one folder named old and another called new
The old has some folders. The new has a few of these folders with same names and nothing more.
I want to delete the folders of the old that are not present in the new first and then: make a loop that will take each file -same name -pair, and put it in the
the following line:
arcpy.Append_management(["shpfromonefolder.shp", "shpfromsecondfolder.shp"],"NO_TEST")
for example: land.shp from one folder with land.shp from the other folder so it will be:
arcpy.Append_management(["land.shp", "land.shp"],"NO_TEST")
This will delete folders in old_path if they exist do not in new_path:
import os
import shutil
old_path = r"old file path"
new_path = r"old file path"
for folder in os.listdir(old_path):
if folder not in os.listdir(new_path):
shutil.rmtree(os.path.join(old_path, folder))
This will find the matching shape files and pass them to arcpy.Append_management():
import os
import arcpy
for dir_path, dir_names, file_names in arcpy.da.Walk(workspace=new_path, datatype="FeatureClass"):
for filename in file_names:
new_file_path = os.path.join(dir_path, filename)
folder = os.path.basename(os.path.dirname(new_file_path))
old_file_path = os.path.join(old_path, folder, filename)
if os.path.exists(old_file_path):
arcpy.Append_management(inputs=[new_file_path], target=old_file_path, schema_type="NO_TEST")