How to rename files after being copied based on creation time? - python

After copying files from a user provided source and destination, the files need to be renamed based on the creation time. The files have multiple extension types that need to be preserved while being renamed and a record original filenames. The issue arises when attempting to rename the file after it has been copied to the destination. All attempted solutions creates an exception in callback. What's the best approach here?
def filter_copy(self):
current_dir = self.Source.get()
destination_dir = self.Destination.get()
extensions = (['.avi', '.mpg'])
os.chdir(current_dir)
for root, dir, files in os.walk('.'):
for file in files:
if os.path.splitext(file)[1] in extensions:
src = os.path.join(root, file)
time.sleep(0.1)
logging.info("Copying the file %s..." % file)
print("Copying the file %s..." % file)
try:
with open('OriginalFilesReceipt.txt', 'w') as f:
f.write(file)
except FileNotFoundError:
logging.info("The directory does not exist to create to generate a receipt")
shutil.copy(src, destination_dir)
for names in os.listdir('.'):
t = os.path.getmtime(names)
v = datetime.datetime.fromtimestamp(t)
x = v.strftime('%Y%m%d-%H%M%S')
os.rename(names, x)

Found a solution based on the work from yzhong52 here: https://gist.github.com/tvdsluijs/1640613a32416b1197fc36b45e7b4999
The main error that was being received should have been obvious. The working directory wasn't the destination directory. The solution for the original question:
os.chdir(destination_dir)
for names in os.listdir('.'):
#split into filename and extension
filename, extension = os.path.splitext(names)
if (extension in extensions):
create_time = os.path.getctime(names)
format_time = datetime.datetime.fromtimestamp(create_time)
format_time_string = format_time.strftime("%Y-%m-%d %H.%M.%S")
newfile = format_time_string + extension
#if other file with same timestamp
if(newfile in newfilesDictionary.keys()):
index = newfilesDictionary[newfile] + 1
newfilesDictionary[newfile] = index
newfile = format_time_string + '-' + str(index) + extension
else:
newfilesDictionary[newfile] = 0
os.rename(names, newfile)
num_files = num_files + 1
print(names.rjust(35) + ' => ' + newfile.ljust(35))

Related

Losing absolute paths after returning them from function

I have this function here that renames (if necessary) all files in a given folder and returns all filenames as absolute paths:
I forgot to mention: filepath is always an absolute path.
import re
import os
# This function renames all files in a given
# folder and return them as absolute paths
def rename_get_Files(filepath):
files = os.listdir(filepath)
files_list = []
counter = 1
files_renamed = 0
for filename in files:
# If the file does not start with 'Offer_Pic_' > rename it and add to the files_list
if not re.search('Offer_Pic_.+', filename):
file_name, file_extension = os.path.splitext(filepath+filename)
print(file_extension)
new_filename = "Offer_Pic_" + str(counter) + file_extension
old_filename = filepath + filename
new_filename = filepath + new_filename
# rename() function will
# rename all the files
os.rename(old_filename, new_filename)
counter += 1
print(f'This is the new filename: ' + new_filename)
files_list.append(new_filename)
files_renamed += 1
else:
# Append the absolute paths of all already correctly named files to the files_list
files_list.append(os.path.abspath(filename))
print(files_list)
print(f'We have renamed ' + str(files_renamed) + ' files.')
return files_list
However, when I call the function from another one to use these absolute paths:
pictures = rename_get_Files(filepath)
print(pictures)
... it returns the paths being inside the script's working directory.
Because of that, the next function of my script crashes because it assumes that the files are in the working directory of the script - which they are not as they were not moved from their initial location (filepath).
Please help me to keep the absolute file paths.
I tried to regain the absolute path of the pictures, but the wrong one (inside script dir keeps being returned)
for pic in pictures:
abs_path_pic = os.path.abspath(pic)
print(pic)
print(abs_path_pic)
pictureBox.send_keys(abs_path_pic)
I found the error: initially no absolute path was returned by os.
I added to the end of the function:
path = os.path.abspath(filepath)
files_list = [entry.path for entry in os.scandir(path) if entry.is_file()]
The whole function now looks like this:
# This function renames all files in a given folder and return them as absolute paths
def rename_get_files(filepath):
print(f'this is the given filepath: {filepath}')
files = os.listdir(filepath)
files_list = []
print(f'these are our initial files: {files}')
counter = 1
files_renamed = 0
for filename in files:
# If the file does not start with 'Offer_Pic_' > rename it and add to the files_list
if not re.search('Offer_Pic_.+', filename):
file_name, file_extension = os.path.splitext(filepath+filename)
print(file_extension)
new_filename = "Offer_Pic_" + str(counter) + file_extension
old_filename = filepath + "/" + filename
print(old_filename)
new_filename = filepath + "/" + new_filename
print(new_filename)
# rename() function will
# rename all the files
os.rename(old_filename, new_filename)
counter += 1
print(f'This is the new filename: ' + new_filename)
files_list.append(os.path.abspath(new_filename))
files_renamed += 1
else:
# Append the absolute paths of all already correctly named files to the files_list
files_list.append(os.path.abspath(filename))
print(f'We have renamed ' + str(files_renamed) + ' files.')
path = os.path.abspath(filepath)
files_list = [entry.path for entry in os.scandir(path) if entry.is_file()]
print(f'this is our files_list, no files were renamed: {files_list}')
return files_list
Now it works perfectly! Thank you all for your help!

Patch Movement: File Backup and Replace

I'm getting an error while trying to copy files from a single source directory which contains bug fixes: /home/saurabh/testbed/patch_dir/ to multiple destination directories: app_dir_1 and app_dir_2.
Both these directories are exact replicas of each other.
The script does the following:-
Read lines from a text file into a list. Each line contains the name of one component. In this case: ['file1.class', file2.html]
Search value at each index recursively, starting from a particular directory:
/home/saurabh/testbed/dest_dir/
Take a backup of these files wherever they are found by appending ddMonyyyy to their extension.
Copy files from directory which contains patched components: /home/saurabh/testbed/patch_dir/
to the directory where backup was taken earlier
Directory Overview:-
/home/saurabh/testbed/dest_dir/
|--app_dir_1
|--file1.class
|--file2.html
|--file3.jsp
|--file4.xml
|--sub_dir
|--app_dir_2
|--file1.class
|--file2.html
|--file3.jsp
|--file4.xml
|--sub_dir
|--other_directories
/home/saurabh/testbed/patch_dir/
|--file1.class
|--file2.html
Below is my code:
#!/usr/bin/env python
import os
import fnmatch
import datetime
import shutil
with open('filenames.txt') as f:
content = f.readlines()
content = [x.strip() for x in content]
print('File contents:')
print(content)
suffix = datetime.datetime.now().strftime("_%d%b%Y")
approot = '/home/saurabh/testbed/dest_dir/'
source_dir = '/home/saurabh/testbed/patch_dir/'
dir_list = []
print('\n' + 'Renaming files present at:')
for root, dirs, files in os.walk(approot):
for file_list in content:
for filename in fnmatch.filter(files, file_list):
print(os.path.join(root, filename))
dir_list.append(root)
current_file = os.path.join(root, filename)
backup_file = os.path.join(root, filename + suffix)
os.rename(current_file, backup_file)
print("\n" + "Backup of all files complete!")
print('Backup of ' + str(len(dir_list)) + ' files taken recursively')
print('Number of files mentioned in text file: ' + str(len(content)) + '\n')
# 2 instances in UAT
# 12 instances in PROD
if (2*len(content)) == len(dir_list):
print("Retrofitted components will be copied to their respective directories")
for dst_ind in range(0, len(dir_list)):
if filename in fnmatch.filter(files, file_list):
print(source_dir + content[dst_ind] + "\t" + dir_list[dst_ind])
#shutil.copy2(source_dir+content[dst_ind], dir_list[dst_ind])
I'm getting the below error while copying the files (4.)
File contents:
['file1.class', 'file2.html']
Renaming files present at:
/home/saurabh/testbed/dest_dir/app_dir_1/file1.class
/home/saurabh/testbed/dest_dir/app_dir_1/file2.html
/home/saurabh/testbed/dest_dir/app_dir_2/file1.class
/home/saurabh/testbed/dest_dir/app_dir_2/file2.html
Backup of all files complete!
Backup of 4 files taken recursively
Number of files mentioned in text file: 2
Retrofitted components will be copied to their respective directories
/home/saurabh/testbed/patch_dir/file1.class /home/saurabh/testbed/dest_dir/app_dir_1
/home/saurabh/testbed/patch_dir/file2.html /home/saurabh/testbed/dest_dir/app_dir_1
Traceback (most recent call last):
File "./prod_movement.py", line 56, in <module>
print(source_dir + content[dst_ind] + "\t" + dir_list[dst_ind])
IndexError: list index out of range
Expected Output:
File contents:
['file1.class', 'file2.html']
Renaming files present at:
/home/saurabh/testbed/dest_dir/app_dir_1/file1.class
/home/saurabh/testbed/dest_dir/app_dir_1/file2.html
/home/saurabh/testbed/dest_dir/app_dir_2/file1.class
/home/saurabh/testbed/dest_dir/app_dir_2/file2.html
Backup of all files complete!
Backup of 4 files taken recursively
Number of files mentioned in text file: 2
Retrofitted components will be copied to their respective directories
/home/saurabh/testbed/patch_dir/file1.class /home/saurabh/testbed/dest_dir/app_dir_1
/home/saurabh/testbed/patch_dir/file2.html /home/saurabh/testbed/dest_dir/app_dir_1
/home/saurabh/testbed/patch_dir/file1.class /home/saurabh/testbed/dest_dir/app_dir_2
/home/saurabh/testbed/patch_dir/file2.html /home/saurabh/testbed/dest_dir/app_dir_2
Appreciate any help to fix the code.
Figured it out !!
#!/usr/bin/env python
import os
import fnmatch
import datetime
import shutil
with open('filenames.txt') as f:
content = f.readlines()
content = [x.strip() for x in content]
print('File contents:')
print(content)
suffix = datetime.datetime.now().strftime("_%d%b%Y")
approot = '/Users/saurabhm/Desktop/Python/testbed/dest_dir/'
source_dir = '/Users/saurabhm/Desktop/Python/testbed/patch_dir/'
dir_list = []
print('\n' + 'Renaming files present at:')
for root, dirs, files in os.walk(approot):
for file_list in content:
for filename in fnmatch.filter(files, file_list):
print(os.path.join(root, filename))
dir_list.append(root)
current_file = os.path.join(root, filename)
backup_file = os.path.join(root, filename + suffix)
#print(current_file, backup_file)
os.rename(current_file, backup_file)
#print(source_dir + filename + "\t" + root)
shutil.copy2(source_dir + filename, root)
os.chmod(root + '/' + filename, 0o750)
print("\n" + "Backup of all files complete!")
print('Backup of ' + str(len(dir_list)) + ' files taken recursively')
print('Number of files mentioned in text file: ' + str(len(content)) + '\n')
Once patched components are received over email, they are copied to a directory in the respective server. All these files are consolidated in a single directory (patch_dir)
Backup of existing files (having the same name and are present in "dest_dir") are taken wherever they are found, following which each file is copied from "patch_dir" to the directories inside "dest_dir", where their backup was taken.

os.rename deleting files python 3

Python novice, my simple script gets a given directory and renames all files sequentially, however it is deleting the files but the print is showing the files names getting renamed, not sure where its going wrong here.
Also, in what order does it retrieve these files?
import os
path = os.path.abspath("D:\Desktop\gp")
i = 0
for file_name in os.listdir(path):
try:
print (file_name + " - " + str(i))
os.rename(os.path.join(path,file_name), str(i))
except WindowsError:
os.remove(str(i))
os.rename(os.path.join(path,file_name), str(i))
i += 1
print(str(i) + " files.")
Edit
Below is the solution with working code, retrieves all files in a dir by creation date and assigns them a iterated number while retaining file extension.
import os
def sorted_dir(folder):
def getctime(name):
path = os.path.join(folder, name)
return os.path.getctime(path)
return sorted(os.listdir(path), key=getctime)
path = os.path.abspath("D:\Path\Here")
i = 0
for file_name in sorted_dir(path):
_, ext = os.path.splitext(file_name)
print (file_name + " - " + str(i)+ext)
os.rename(os.path.join(path,file_name), os.path.join(path, str(i) + ext))
i += 1
print(str(i-1) + " files.")
The problem is that you're using an absolute path for the source, but a relative path for the destination. So the files aren't getting deleted, they're just getting moved into the current working directory.
To fix it so they get renamed into the same directory they were already in, you can do the same thing on the destination you do on the source:
os.rename(os.path.join(path,file_name), os.path.join(path, str(i)))
From a comment, it sounds like you may want to preserve the extensions on these files. To do that:
_, ext = os.path.splitext(file_name)
os.rename(os.path.join(path,file_name), os.path.join(path, str(i) + ext))

How to create an extension for a file without extension in Python

I have a folder with a list of files without extensions, I need to rename or create an extension to each file ".text"
This is my code, but there is a small bug, the second time I run the code the files renamed again with a long name ,, for example
The file name : XXA
after first run : XXA.text
second : XXAXXA.text.text
import os
def renamefiles():
filelist = os.listdir(r"D:\")
print(filelist)
os.chdir(r"D:\")
path = os.getcwd()
for filename in filelist:
print("Old Name - "+filename)
(prefix, sep, sffix) = filename.rpartition(".")
newfile = prefix + filename + '.text'
os.rename(filename, newfile)
print("New Name - "+newfile)
os.chdir(path)
rename_files()
Where you have
newfile = prefix + '.text'
You can have
if not file_name.contains(".text"):
newfile = prefix + file_name + '.text'
Note where you have newfile = prefix + file_name + '.text', I changed it to newfile = prefix + '.text'. If you think about it, you don't need filename when you have already extracted the actual file name into prefix.
for file in os.listdir(os.curdir):
name, ext = os.path.splitext(file)
os.rename(file, name + ".text")
Don't do the partitioning that way, use os.path.splitext:
file_name, extension = os.path.splitext(filename)
if not extension:
newfile = file_name + '.text'
os.rename(filename, newfile)
If the file has no extension splitext returns '' which is Falsy. The file extension can then be changed.
import os
def renamefiles():
filelist = os.listdir(r"D:\")
print(filelist)
os.chdir(r"D:\")
path = os.getcwd()
for filename in filelist:
print("Old Name - "+filename)
(prefix, sep, sffix) = filename.rpartition(".")
newfile = prefix + filename + '.text'
if not filename.endswith(".text"):
os.rename(filename, newfile)
print("New Name - "+newfile)
os.chdir(path)
renamefiles()
You need to check if the filename ends with .text, and skip those

Organizing data by filetype

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

Categories

Resources