I am trying to change file names like below:
the 000000 are the same number.
000000_ABC.png --->000000+1_ABC.png
000000_DEF.png --->000000+2_DEF.png
000000_GHI.png --->000000+3_GHI.png
000000_JKL.png --->000000+4_JKL.png
In order to do so, I wrote code like below.
img_files = os.listdir(PATH_TO_PNG_FILES)
for img_file, i in zip(img_files, range(len(img_files))):
new_img_file = img_file.replace("_", "+"+str(i)+"_")
os.rename(path + img_file, path + new_img_file)
There are more than just four files and more of similar lines.
The problem is that immediately after running pycharm, it successfully produces the desired results, but after I run another page related to the result directories, the results continue to be changed like below even after the process finished. I do not understand why.
000000+1+1_ABC.png
000000+2+2_DEF.png
000000+3+3_GHI.png
000000+4+4_JKL.png
or
otherwise "+unexpected number"
This is because the other directory may already contain file in the format of "000000+1_ABC.png" and your script is changing _ to "+1_" resulting in "000000+1+1_ABC.png". To solve this you can add a if statement to check it should not contain "+" symbol.
img_files = os.listdir(path inside of which the png files are saved)
for img_file, i in zip(img_files, range(len(img_files))):
if not ("+" in img_file):
new_img_file = img_file.replace("_", "+"+str(i)+"_")
os.rename(path + img_file, path + new_img_file)
A simple and naive way would be to add a verification to check whether there is a '+' in the filename. If you have other files which may contain a +, you may have to check for a stricter pattern.
I made a YouTube video https://youtu.be/K9jhAPZLZLc on how to rename multiple files like the one you have assuming all your files are in the same directory.
To answer your question. assuming all image files are in the same folder.
path = 'C:\\Users\\USER\\Desktop\\rename_images\\images\\' # path to your images
files = os.listdir(path)
for count, filename in enumerate(files):
# Get the file extension
file, file_extension = os.path.splitext(filename)
# check if the current file is a folder or not
full_path = f'{path}{filename}'
if os.path.isdir(full_path):
print('This is a directory')
elif os.path.isfile(full_path):
print('This is a normal file')
# Rename
if not '+' in file:
try:
file_split = file.split('_')
zeros = file_split[0]
alpha = file_split[-1]
current_file_name = os.path.join(path, filename)
new_file_name = os.path.join(path, ''.join([f'{zeros}+{count}_{alpha}', file_extension]))
os.rename(current_file_name, new_file_name)
except:
pass
else:
pass
else:
print('This is a special file')
I would imagine that the problem comes from modifying the name insted of overwriting.
import os
DIR_PATH = 'files'
def rename_files(dir_name):
img_files = os.listdir(dir_name)
for i in range(len(img_files)):
file_name = img_files[i].split('_')[-1]
file_name = '000000+{0}_{1}'.format(i, file_name)
os.rename(
os.path.join(dir_name, img_files[i]),
os.path.join(dir_name, file_name)
)
if __name__ == '__main__':
rename_files(DIR_PATH)
Related
I have this error when I'm trying to run this code, maybe anyone can help me and give me directions.
After that problem will be solved, I need to create a loop that searching in all the xml files and finding a string, if that sting is in the file than it will move the file to the directory, anyone have an idea how can I do it?
import os
import glob
import shutil
def remove_ext(list_of_pathnames):
"""
removes the extension from each filename
"""
return [os.path.splitext(filename)[0] for filename in list_of_pathnames]
path = os.getcwd()
os.chdir("D:\\TomProject\\Images\\")
os.mkdir("Done\\") # create a new folder
newpath = os.path.join("D:\\TomProject\\","image_with_xml") # made it os independent...
list_of_jpgs = glob.glob(path+"*.jpg")
list_of_xmls = glob.glob(path+"*.xml")
list_of_txts = glob.glob(path+"*.txt")
print(list_of_jpgs, "\n\n", list_of_xmls, "\n\n", list_of_txts) #remove
jpgs_without_extension = remove_ext(list_of_jpgs)
xmls_without_extension = remove_ext(list_of_xmls)
txts_without_extension = remove_ext(list_of_txts)
for filename in jpgs_without_extension:
if filename in xmls_without_extension:
if filename in txts_without_extension:
print("moving", filename) #remove
shutil.move(filename + '*.jpg', newpath) # move image to new path.
shutil.move(filename + '*.xml', newpath)
shutil.move(filename + '*.txt', newpath)
make sure all jpg, xml, txt are in the current working directory. you may add one line to check current directory with
print(path)
please change the lines
list_of_jpgs = glob.glob(path+"*.jpg")
list_of_xmls = glob.glob(path+"*.xml")
list_of_txts = glob.glob(path+"*.txt")
to
list_of_jpgs = glob.glob(os.path.join(path,"*.jpg"))
list_of_xmls = glob.glob(os.path.join(path,"*.xml"))
list_of_txts = glob.glob(os.path.join(path,"*.txt"))
last three lines should be indented. and * should be removed.
for filename in jpgs_without_extension:
if filename in xmls_without_extension:
if filename in txts_without_extension:
print("moving", filename) #remove
shutil.move(filename + '.jpg', newpath) # move image to new path.
shutil.move(filename + '.xml', newpath)
shutil.move(filename + '.txt', newpath)
A script was supplied to me in order to upload files to a cloud bucket. You input the dir where the files you want to upload are and bingo bango, done.
What needs to happen is that there are additional sub dirs with their own files in them that I would like to transfer as well based on the input of the root dir. They would need to retain their tree structure relative to the root dir input.
Using the current code I get a write error/access denied fail. I know this is because the for loop is using os.listdir which can't parse the extra sub dirs and files but I'm not sure how to modify.
I attempted to get all the information I needed using os.walk and parsing that out. I verified with some print tests that it was looking in the right place for everything. However I hit a wall when I got this error when running the script:
folder\folder\lib\ntpath.py", line 76, in join
path = os.fspath(path)
TypeError: expected str, bytes or os.PathLike object, not list
I understand that something is being generated as a list when it shouldn't be but I'm not sure how to go about this...
This is the original script provided to me below. I have added the variable at the top just to be a little less abstract.
local_directory_path = 'C:\folder\folder\sync\FROM_LOCAL_UPLOAD'
def upload_folder_to_cloud(self, mount_id, local_directory_path):
''' This method will list every file at the local_directory_path and then for each,
it will call the api method athera.sync.upload_file for every file in your local directory
'''
_, destination_folder = os.path.split(local_directory_path)
if not destination_folder:
self.logger.error("Make sure the provided 'local_directory_path' does not end with a '/' or a '\\'")
sys.exit(2)
destination_folder = destination_folder + "/"
self.logger.info("Folder = {}".format(destination_folder))
for filename in os.listdir(local_directory_path):
destination_path = destination_folder + filename
filepath = os.path.join(local_directory_path, filename)
with open(filepath, "rb") as f:
_, err = self.client.upload_file(self.group_id, mount_id, f, destination_path=destination_path,)
if err != None:
self.logger.error(err)
sys.exit(4)
return destination_folder
This is what I modified it to as a test:
for root, dirs, files in os.walk(local_directory_path):
srcFile = (os.path.join(files))
srcRoot = (os.path.join(root))
rootSplit = os.path.normpath(srcRoot).split(os.path.sep)
srcDirs = '/'.join(rootSplit[4:])
src = str('fixLocalFolder') + '/' + str(srcDirs) +'/'+ (files)
dst = str(srcDirs) + '/' + (files)
destination_folder = str(srcRoot) + "/"
destination_path = str(destination_folder) + str(srcFile)
filepath = os.path.join((str(srcDirs), str(srcFile)))
with open(filepath, "rb") as f:
_, err = self.client.upload_file(
self.group_id,
mount_id,
f,
destination_path=destination_path,
)
if err != None:
self.logger.error(err)
sys.exit(4)
return destination_folder
I do not code for a living so I am sure I am not going about this the right way. I apologize for any code atrocities in advance. Thank you!
I do see some issues in that code, even without testing it. Something like the following might work for that loop. (Note! Untested!).
for root, dirs, files in os.walk(local_directory_path):
# Iterate through files in the currently processed directory
for current_file in files:
# Full path to file
src_file = os.path.join(root, current_file)
# Get the sub-path relative the original root.
sub_path = os.path.relpath(root, start=destination_folder)
# Get the destination path
destination_path = os.path.join(sub_path, current_file)
with open(src_file, "rb") as f:
_, err = self.client.upload_file(
self.group_id,
mount_id,
f,
destination_path=destination_path,
)
if err != None:
self.logger.error(err)
sys.exit(4)
I believe your central problem was misunderstanding what os.walk gives you. It gives you listing of each directory (and subdirectory), one after another.
Thus the values of one iterations might look like (when listing /mydir):
# First iteration:
root = "/mydir"
dirs = ["subdir", ...]
files = ["something.doc", "something else.txt"]
# Second iteration:
root = "/mydir/subdir"
dirs = ["sub-sub-dir1", ...]
files = ["file1.txt", "file2.txt", ...]
I am trying to sort a large number of files based off of their file extension. A lot of the files are .doc, .docx, .xls, etc.
This is what I was thinking in my head, but if there is a simpler way to do things, let me know! I do have multiple files with the same extension, so I don't want it to create a new folder for that extension every time and overwrite the previous file. I also have a much larger list, but for this example I don't believe all of them are needed. The OS is MacOS.
import os, shutil
extList = ['.doc', '.docx', '.xls']
for ext in extList:
os.mkdir(path + '/' + ext +'_folder')
for file in os.listdir(filepath):
if file.endswith(ext): #missing an indent
print(file)
shutil.copyfile(file + '/' + ext +'_folder' + file)
Also, if I run into a file that I do not have on my list, I would like it to go into a folder named 'noextlist'.
Here is what I was able to create quickly
import os, re, shutil
DocFolder = r'...'#Your doc folder path
DocxFolder = r'...'#Your docx folder path
XlsFolder = r'...'#Your xls folder path
MiscFolder = r'...'#Your misc folder path
for root, dirs, files in os.walk(r'...'): #Your folder path you want to sort
for file in files:
if file.endswith(".doc"):
sourceFolder = os.path.join(root,file)
print sourceFolder
shutil.copy2(sourceFolder,DocFolder)
elif file.endswith(".docx"):
sourceFolder = os.path.join(root,file)
print sourceFolder
shutil.copy2(sourceFolder,DocxFolder)
elif file.endswith(".xls"):
sourceFolder = os.path.join(root,file)
print sourceFolder
shutil.copy2(sourceFolder,XlsFolder)
else:
sourceFolder = os.path.join(root,file)
print sourceFolder
shutil.copy2(sourceFolder,MiscFolder)
Edit:The main function here is the for root,dirs,files in os.walk This allows the program to transverse through the provided path to search all files including the ones in the sub folder and sort it out accordingly.
import errno
import shutil
from os import listdir, mkdir
from os.path import splitext, join
# set for fast lookup
extList = set(['.doc', '.docx', '.xls'])
# source path
filepath = ...
# dest path
path = ...
for f in listdir(filepath):
# extract extension from file name
ext = splitext(f)[1]
if ext in extList:
dir_ = join(path, "{}_folder".format(ext))
try:
mkdir(dir_)
except OSError as e:
if ex.errno != errno.EEXIST:
raise # raise if any other error than "already exists"
dest = join(dir_, f)
else:
dest = join(path, "noextlist_folder", f)
shutil.copy2(join(filepath, f), dest)
If I understand correctly, you like your solution but you need a way to rename files with duplicate names so that the extras don't disappear. You can check if the destination file already exists and construct a variant name by adding _1, _2, etc. to the filename until you find something unused.
newpathname = path + '/' + ext +'_folder' + "/" + file
n = 0
while os.path.exists(newpathname):
n += 1
base, ext = os.path.splitext(newpathname)
newpathname = "%s_%d%s" % (base, n, ext)
shutil.copyfile(filepath+"/"+file, newpathname)
But your code has some other glitches, so here's a rewritten scanner. It uses os.walk() to descend into several levels of subdirectories (you don't say if that's needed or not), and it collects files of all extensions in one pass. And it constructs variant names as before.
import os, shutil
extList = ['.doc', '.docx', '.xls']
from os.path import join as joinpath
# Make sure the destination directories exist
for ext in extList:
extdir = joinpath(path, ext[1:]+"_folder")
if not os.path.exists(extdir):
os.mkdir(extdir)
for dirname, _dirs, files in os.walk(filepath):
for file in files:
base, ext = os.path.splitext(file)
if ext not in extList:
continue
destpath = joinpath(path, ext[1:]+"_folder")
n = 0
newpathname = joinpath(destpath, file)
# If the new name is in use, find an unused variant
while os.path.exists(newpathname):
n += 1
newfile = "%s_%d%s" % (base, n, ext)
newpathname = joinpath(path, newfile)
sh.copy(joinpath(dirname, file), newpathname) # or other copy method
So I'm trying to iterate through a list of files that are within a subfolder named eachjpgfile and change the file from doc to the subfolder eachjpgfile mantaining the file's name but when I do this it adds the file to directory before eachjpgfile rather than keeping it in it. Looking at the code below, can you see why is it doing this and how can I keep it in the eachjpgfile directory?
Here is the code:
for eachjpgfile in filelist:
os.chdir(eachjpgfile)
newdirectorypath = os.curdir
list_of_files = os.listdir(newdirectorypath)
for eachfile in list_of_files:
onlyfilename = os.path.splitext(eachfile)[0]
if onlyfilename == 'doc':
newjpgfilename = eachfile.replace(onlyfilename,eachjpgfile)
os.rename(eachfile, newjpgfilename)
There is a lot of weird stuff going on in here, but I think the one that's causing your particular issue is using 'eachjpgfile' in 'eachfile.replace'.
From what I can tell, the 'eachjpgfile' you're passing in is a full-path, so you're replacing 'doc' in the filename with '/full/path/to/eachjpgfile', which puts it parallel to the 'eachjpgfile' directory regardless of your current working directory.
You could add a line to split the path/file names prior to the replace:
for eachjpgfile in filelist:
os.chdir(eachjpgfile)
newdirectorypath = os.curdir
list_of_files = os.listdir(newdirectorypath)
for eachfile in list_of_files:
onlyfilename = os.path.splitext(eachfile)[0]
if onlyfilename == 'doc':
root, pathName= os.path.split(eachjpgfile) #split out dir name
newjpgfilename = eachfile.replace(onlyfilename,pathName)
os.rename(eachfile, newjpgfilename)
which is a very dirty fix for a very dirty script. :)
try this:
import os
path = '.'
recursive = False # do not descent into subdirs
for root,dirs,files in os.walk( path ) :
for name in files :
new_name = name.replace( 'aaa', 'bbb' )
if name != new_name :
print name, "->", new_name
os.rename( os.path.join( root, name),
os.path.join( root, new_name ) )
if not recursive :
break
I am writing a Python function to change the extension of a list of files into another extension, like txt into rar, that's just an idle example. But I'm getting an error. The code is:
import os
def dTask():
#Get a file name list
file_list = os.listdir('C:\Users\B\Desktop\sil\sil2')
#Change the extensions
for file_name in file_list:
entry_pos = 0;
#Filter the file name first for '.'
for position in range(0, len(file_name)):
if file_name[position] == '.':
break
new_file_name = file_name[0:position]
#Filtering done !
#Using the name filtered, add extension to that name
new_file_name = new_file_name + '.rar'
#rename the entry in the file list, using new file name
print 'Expected change from: ', file_list[entry_pos]
print 'into File name: ', new_file_name
os.rename(file_list[entry_pos], new_file_name)
++entry_pos
Error:
>>> dTask()
Expected change from: New Text Document (2).txt
into File name: New Text Document (2).rar
Traceback (most recent call last):
File "<pyshell#10>", line 1, in <module>
dTask()
File "C:\Users\B\Desktop\dTask.py", line 19, in dTask
os.rename(file_list[entry_pos], new_file_name)
WindowsError: [Error 2] The system cannot find the file specified
I can succeed in getting the file name with another extension in variable level as you can see in the print-out, but not in reality because I can not end this process in OS level. The error is coming from os.rename(...). Any idea how to fix this ?
As the others have already stated, you either need to provide the path to those files or switch the current working directory so the os can find the files.
++entry_pos doesn't do anything. There is no increment operator in Python. Prefix + is just there fore symmetry with prefix -. Prefixing something with two + is just two no-ops. So you're not actually doing anything (and after you change it to entry_pos += 1, you're still resetting it to zero in each iteration.
Also, your code is very inelegant - for example, you are using a separate index to file_list and fail to keep that in synch with the iteration variable file_name, even though you could just use that one! To show how this can be done better.
-
def rename_by_ext(to_ext, path):
if to_ext[0] != '.':
to_ext = '.'+to_ext
print "Renaming files in", path
for file_name in os.listdir(path):
root, ext = os.path.splitext(file_name)
print "Renaming", file_name, "to", root+ext
os.rename(os.path.join(path, file_name), os.path.join(path, root+to_ext))
rename_by_ext('.rar', '...')
os.rename really doesn't like variables. Use shutil. Example taken from How to copy and move files with Shutil.
import shutil
import os
source = os.listdir("/tmp/")
destination = "/tmp/newfolder/"
for files in source:
if files.endswith(".txt"):
shutil.move(files,destination)
In your case:
import shutil
shutil.move(file_list[entry_pos], new_file_name)
You also want to double backslashes to escape them in Python strings, so instead of
file_list = os.listdir('C:\Users\B\Desktop\sil\sil2')
you want
file_list = os.listdir('C:\\Users\\B\\Desktop\\sil\\sil2')
Or use forward slashes - Python magically treats them as path separators on Windows.
You must use the full path for the rename.
import os
def dTask():
#Get a file name list
dir = 'C:\Users\B\Desktop\sil\sil2'
file_list = os.listdir(dir)
#Change the extensions
for file_name in file_list:
entry_pos = 0;
#Filter the file name first for '.'
for position in range(0, len(file_name)):
if file_name[position] == '.':
break
new_file_name = file_name[0:position]
#Filtering done !
#Using the name filtered, add extension to that name
new_file_name = new_file_name + '.rar'
#rename the entry in the file list, using new file name
print 'Expected change from: ', file_list[entry_pos]
print 'into File name: ', new_file_name
os.rename( os.path.join(dir, file_list[entry_pos]), os.path.join(dir,new_file_name))
++entry_pos
If you aren't in the directory C:\Users\B\Desktop\sil\sil2, then Python certainly won't be able to find those files.
import os
def extChange(path,newExt,oldExt=""):
if path.endswith != "\\" and path.endswith != "/":
myPath = path + "\\"
directory = os.listdir(myPath)
for i in directory:
x = myPath + i[:-4] + "." + newExt
y = myPath + i
if oldExt == "":
os.rename(y,x)
else:
if i[-4:] == "." + oldExt:
os.rename(y,x)
now call it:
extChange("C:/testfolder/","txt","lua") #this will change all .txt files in C:/testfolder to .lua files
extChange("C:/testfolder/","txt") #leaving the last parameter out will change all files in C:/testfolder to .txt