Python: Check if files exist and copy only the missing files - python

I'm a begynder in python and trying to make a script that does the following:
Check number of files, if they exist in the destFile
If they all exist, exit the script (don't do anything)
If some files are missing, copy only the missing files from the srcFile to the destFile
The script that I have made is working, but the issue that I would like your help with is to make my script only copies the file/files missing and not as my script is doing now, which copies from file 1 (test1.txt) to the file missing. Example if test4.txt & test5.txt files are missing in destFile, my script will copy from test1.txt to test5.txt, in stead of only copying the two missing files test4.txt & test5.txt.
import os, shutil
from datetime import datetime
count = 0
error = "ERROR! file is missing! (files have been copied)"
sttime = datetime.now().strftime('%d/%m/%Y - %H:%M:%S - ')
os.chdir("C:\log")
log = "log.txt"
srcFile = [r"C:\srcFile\test1.txt",
r"C:\srcFile\test2.txt",
r"C:\srcFile\test3.txt",
r"C:\srcFile\test4.txt",
r"C:\srcFile\test5.txt"]
destFile = [r"C:\destFile\test1.txt",
r"C:\destFile\test2.txt",
r"C:\destFile\test3.txt",
r"C:\destFile\test4.txt",
r"C:\destFile\test5.txt"]
for file in destFile:
if not os.path.exists(file):
for file_sr in srcFile:
if not os.path.exists(file):
shutil.copy(file_sr, 'C:\destFile')
count +=1
with open(log, 'a') as logfile:
logfile.write(sttime + error + " " + str(count) + " => " + file + '\n')


The problem is that you're iterating over all of the source files whenever you detect a missing destination file: for file_sr in srcFile:. Instead, you can copy just the missing file by keeping track of the position (in the array) of the missing destination file:
for position, file in enumerate(destFile):
if not os.path.exists(file):
file_sr = srcFile[position]
if not os.path.exists(file):
shutil.copy(file_sr, 'C:\destFile')


Using your code, you can do:
import os, shutil
from datetime import datetime
count = 0
error = "ERROR! file is missing! (files have been copied)"
sttime = datetime.now().strftime('%d/%m/%Y - %H:%M:%S - ')
os.chdir("C:\log")
log = "log.txt"
srcFile = [r"C:\srcFile\test1.txt",
r"C:\srcFile\test2.txt",
r"C:\srcFile\test3.txt",
r"C:\srcFile\test4.txt",
r"C:\srcFile\test5.txt"]
destFile = [r"C:\destFile\test1.txt",
r"C:\destFile\test2.txt",
r"C:\destFile\test3.txt",
r"C:\destFile\test4.txt",
r"C:\destFile\test5.txt"]
for file in destFile:
if not os.path.exists(file):
src_file = destFile.replace("destFile","srcFile")
shutil.copy(src_file, file)
count +=1
with open(log, 'a') as logfile:
logfile.write(sttime + error + " " + str(count) + " => " + file + '\n')


Thank you for your help guys. Exactly my problem was that I was iterating over all of the source files whenever I detected a missing destination file. The following logic from mackorone is doing what I was looking for.
for position, file in enumerate(destFile):
if not os.path.exists(file):
file_sr = srcFile[position]
shutil.copy(file_sr, 'C:\destFile')


I have updated the script, so now this script compares two folders, source folder and destination folder. If destination folder is missing files from the source folder, it will be copied. The script is working fine.
import os
import shutil
from datetime import datetime
sttime = datetime.now().strftime('%d/%m/%Y - %H:%M:%S - ')
error = "ERROR! file is missing! (files have been copied)"
des_path = 'C:\des_folder'
sr_path = 'C:\sr_folder'
des_folder = os.listdir(des_path)
sr_folder = os.listdir(sr_path)
count = 0
os.chdir("C:\log")
log = "log.txt"
def compare_folder(folder1,folder2):
files_in_sr_folder = set(sr_folder) - set(des_folder)
return files_in_sr_folder
files_missing = compare_folder(sr_folder,des_folder)
if len(files_missing) != 0:
for file in files_missing:
full_path_files = os.path.join(sr_path,file)
shutil.copy(full_path_files,des_path)
count +=1
with open(log, 'a') as logfile:
logfile.write(sttime + error + " " + str(count) + " => " + file + '\n')
else:
exit

Related

Generating instances of duplicate files

I'm trying to edit a script I've previously written to generate .lab files (or basically txt files with a .lab extension) as part of a project I'm currently working on. Specifically, what I'm currently working on is to edit the script such that it will be able to handle duplicate filenames. Example: if a file named filename already exists, instead of appending or overwriting the existing file, it would instead create a new file named filename_1.
The script is written as shown below:
for line in reader:
utterance = line[4]
path = line[1].split("/")
folder_name = path[len(path) - 2]
file_name = path[len(path) - 1].split(".")[0]
duplicate_num = 0
# Generate the .lab file
try:
if os.path.isfile(truncated_audio_dir + "/" + folder_name + "/" + file_name + "_cut.lab"):
new_file_name = file_name + "_" + str(duplicate_num)
while os.path.isfile(truncated_audio_dir + "/" + folder_name + "/" + new_file_name + "_cut.lab"):
duplicate_num += 1
new_file_name = file_name + "_" + str(duplicate_num)
print("New File Name: ", new_file_name)
outfile = open(truncated_audio_dir + "/" + folder_name + "/" + file_name + "_cut.lab", "a")
outfile.write(utterance)
outfile.close()
elif not os.path.isfile(truncated_audio_dir + "/" + folder_name + "/" + file_name + "_cut.lab"):
print("Is File")
outfile = open(truncated_audio_dir + "/" + folder_name + "/" + file_name + "_cut.lab", "a")
outfile.write(utterance)
outfile.close()
except FileNotFoundError:
print(truncated_audio_dir + "/" + folder_name + "/" + file_name + "_cut.lab" + " not found")
continue
The issue is that when I try and run the script, the issues I'd been experiencing beforehand still seem to persist. Particularly, the case I'd written to handle duplicates does not seem to trigger at all, instead the program keeps throwing FileNotFoundError exceptions (which I'd originally written to handle the case if there was a directory that didn't exist). I'm suspecting that the FileNotFoundError exception handling I'd originally written is causing the issue, but maybe there may be something else that I may not be aware of. Any help would be gladly appreciated.
(the above code is a majority of the script, but not the complete script; I imported sys, csv, and os and reader refers to a csv that I am reading from)

Python convert files in directory one by one

How do I convert all files in directory one by one with the code below?
This code takes all the files in a folder and converts them together, but uses up too much memory. I need to do it in the loop for each file separately.
i.e. Find file. Convert. Move. Repeat.
import os
import shutil
import glob
command = ('convert -compress LZW -alpha off -density 320 -depth 4 -
contrast-stretch 700x0 -gamma .45455 *.pdf -set filename:base "%
[basename]" +adjoin "%[filename:base].tiff"')
newpath = r'...'
new_dir = 'tiff'
if not os.path.exists(newpath):
try:
os.mkdir(new_dir)
os.system(command)
except:
print "The folder is already exist"
for file in glob.glob("*.tiff"):
try:
print('"' + file + '"' + ' has just moved to ' + '"' + new_dir + '"' + ' folder')
shutil.move(file, new_dir);
except:
print "Error"

using rename?
import os
os.mkdir("new_folder")
for file in ['file1.txt', 'file2.txt']:
os.rename(file,f'new_folder/{file}')

How am I getting this error when looping through files in a directory? "OSError: [Errno 2] No such file or directory"

I have thousands of files I need to delete in a directory. I want to keep the first ten (alphabetically/numerically) that match the conditions. For example, I want to keep 'part-of-file-name-abc00000.filetype' but not 'part-of-file-name-abc42422.filetype'. Below is the code I'm using to do so:
import os
i = 0
for f in os.listdir('/dir/dir'):
if 'part-of-file-name' in f:
i = i + 1
if i > 10:
os.remove(f)
else:
os.remove(f)
print("Files found: " + str(i))
print("Files removed: " + str(i - 10))
This is the error I'm getting:
File "delete_data_files.py", line 11, in <module>
os.remove(f)
OSError: [Errno 2] No such file or directory: 'part-of-file-name-i-want-then-other-parts.filetype'
This makes no sense to me. The file obviously exists; otherwise, I would not be reading the entire file name in the error.

import os
i = 0
path = './dir/dir'
for f in os.listdir(path):
print "file path", f
f = path + "/" + f;
if 'part-of-file-name' in f:
i = i + 1
if i > 10:
os.remove(f)
else:
os.remove(f)
print("Files found: " + str(i))
print("Files removed: " + str(i - 10))
Output:
file path part-of-file-name.txt
Files found: 1
Files removed: -9
You are providing file name only. You need to provide full path for removing the files.

check out for your path directory
os.listdir('./dir/dir')
if the directories are in the script file you run. You can check our wether the path exists by
import os
path = './dir/dir'
print(os.path.exists(path))
# True
# Means the path exists if its false means you are directing the path to a false location

I am simply trying to write a python script that will change the filename in a directory of files

I am trying to create a script in python 2.7 that will rename all the files in a directory. Below is the code I have so far. The first function removes any numbers in the file name. The second function is supposed to rename the new file name. I get the following error when the second function runs:
[Error 183] Cannot create a file when that file already exists
I know this is because I am not looping through the files and adding an incrementing number to the new filename, so the script changes the name of the first file, and then tries to change the name of the second file to the same name as the first, producing the error.
Can someone help me create a loop that adds an incrementing number to each filename in the directory?
I tried adding:
if file_name == filename:
file_name = file_name + 1
in the while loop, but that obviously doesn't work because I cant concatenate an integer with a string.
import os
def replace_num():
file_list = os.listdir(r"C:\Users\Admin\Desktop\Python Pics")
print(file_list)
saved_path = os.getcwd()
print("Current Working Directory is " + saved_path)
os.chdir(r"C:\Users\Admin\Desktop\Python Pics")
for file_name in file_list:
print("Old Name - " + file_name)
os.rename(file_name, file_name.translate(None, "0123456789"))
os.chdir(saved_path)
replace_num()
def rename_files():
file_list = os.listdir(r"C:\Users\Admin\Desktop\Python Pics")
print(file_list)
saved_path = os.getcwd()
print("Current Working Directory is " + saved_path)
os.chdir(r"C:\Users\Admin\Desktop\Python Pics")
for new_name in file_list:
print("New Name - " + new_name)
try:
os.rename(new_name, "iPhone")
except Exception, e:
print e
rename_files()

instead of doing:
if file_name == filename:
file_name = file_name + 1
do something like this:
counter = 0
for file_name in file_container:
if file_name == file_name: # this will always be True - so it's unnecessary
file_name = "{0}_{1}".format(file_name, counter)
counter += 1

Python copy files to a new directory and rename if file name already exists

I've already read this thread but when I implement it into my code it only works for a few iterations.
I'm using python to iterate through a directory (lets call it move directory) to copy mainly pdf files (matching a unique ID) to another directory (base directory) to the matching folder (with the corresponding unique ID). I started using shutil.copy but if there are duplicates it overwrites the existing file.
I'd like to be able to search the corresponding folder to see if the file already exists, and iteratively name it if more than one occurs.
e.g.
copy file 1234.pdf to folder in base directory 1234.
if 1234.pdf exists to name it 1234_1.pdf,
if another pdf is copied as 1234.pdf then it would be 1234_2.pdf.
Here is my code:
import arcpy
import os
import re
import sys
import traceback
import collections
import shutil
movdir = r"C:\Scans"
basedir = r"C:\Links"
try:
#Walk through all files in the directory that contains the files to copy
for root, dirs, files in os.walk(movdir):
for filename in files:
#find the name location and name of files
path = os.path.join(root, filename)
print path
#file name and extension
ARN, extension = os.path.splitext(filename)
print ARN
#Location of the corresponding folder in the new directory
link = os.path.join(basedir,ARN)
# if the folder already exists in new directory
if os.path.exists(link):
#this is the file location in the new directory
file = os.path.join(basedir, ARN, ARN)
linkfn = os.path.join(basedir, ARN, filename)
if os.path.exists(linkfn):
i = 0
#if this file already exists in the folder
print "Path exists already"
while os.path.exists(file + "_" + str(i) + extension):
i+=1
print "Already 2x exists..."
print "Renaming"
shutil.copy(path, file + "_" + str(i) + extension)
else:
shutil.copy(path, link)
print ARN + " " + "Copied"
else:
print ARN + " " + "Not Found"

Sometimes it is just easier to start over... I apologize if there is any typo, I haven't had the time to test it thoroughly.
movdir = r"C:\Scans"
basedir = r"C:\Links"
# Walk through all files in the directory that contains the files to copy
for root, dirs, files in os.walk(movdir):
for filename in files:
# I use absolute path, case you want to move several dirs.
old_name = os.path.join( os.path.abspath(root), filename )
# Separate base from extension
base, extension = os.path.splitext(filename)
# Initial new name
new_name = os.path.join(basedir, base, filename)
# If folder basedir/base does not exist... You don't want to create it?
if not os.path.exists(os.path.join(basedir, base)):
print os.path.join(basedir,base), "not found"
continue # Next filename
elif not os.path.exists(new_name): # folder exists, file does not
shutil.copy(old_name, new_name)
else: # folder exists, file exists as well
ii = 1
while True:
new_name = os.path.join(basedir,base, base + "_" + str(ii) + extension)
if not os.path.exists(new_name):
shutil.copy(old_name, new_name)
print "Copied", old_name, "as", new_name
break
ii += 1

I always use the time-stamp - so its not possible, that the file exists already:
import os
import shutil
import datetime
now = str(datetime.datetime.now())[:19]
now = now.replace(":","_")
src_dir="C:\\Users\\Asus\\Desktop\\Versand Verwaltung\\Versand.xlsx"
dst_dir="C:\\Users\\Asus\\Desktop\\Versand Verwaltung\\Versand_"+str(now)+".xlsx"
shutil.copy(src_dir,dst_dir)

For me shutil.copy is the best:
import shutil
#make a copy of the invoice to work with
src="invoice.pdf"
dst="copied_invoice.pdf"
shutil.copy(src,dst)
You can change the path of the files as you want.

I would say you have an indentation problem, at least as you wrote it here:
while not os.path.exists(file + "_" + str(i) + extension):
i+=1
print "Already 2x exists..."
print "Renaming"
shutil.copy(path, file + "_" + str(i) + extension)
should be:
while os.path.exists(file + "_" + str(i) + extension):
i+=1
print "Already 2x exists..."
print "Renaming"
shutil.copy(path, file + "_" + str(i) + extension)
Check this out, please!

import os
import shutil
import glob
src = r"C:\Source"
dest = r"C:\Destination"
par = "*"
i=1
d = []
for file in glob.glob(os.path.join(src,par)):
f = str(file).split('\\')[-1]
for n in glob.glob(os.path.join(dest,par)):
d.append(str(n).split('\\')[-1])
if f not in d:
print("copied",f," to ",dest)
shutil.copy(file,dest)
else:
f1 = str(f).split(".")
f1 = f1[0]+"_"+str(i)+"."+f1[1]
while f1 in d:
f1 = str(f).split(".")
f1 = f1[0]+"_"+str(i)+"."+f1[1]
print("{} already exists in {}".format(f1,dest))
i =i + 1
shutil.copy(file,os.path.join(dest,f1))
print("renamed and copied ",f1 ,"to",dest)
i = 1

Categories