Develop Reference

How to get Python to ask for directory, read each filename in the dir and place that filename(without .csv) in the same file respectively?

I'm very new to Python, I have several hundred folders with many thousands of files each containing times series data. Each file has an anonymized unique filename followed by an underscore and file number for each file (0 thru however many files are in the folder) "18667_0.csv, 18667_1.csv, 18667_3.csv" associated with it. I need to run a for loop that will take this unique filename "18667" and place it in whatever cell(Im using excel to read the csv) I choose for the same csv file. So if I have 300 files in the folder all will have the unique "18667" and I just want that number to be placed in the file. I have part of the code for the dir request but I've not been successful in combining the right read/write statements to implement this task. Here's what I have
import tkinter as tk
import pandas as pd
from tkinter import filedialog
from os import listdir
def find_csv_filenames( path_to_dir, suffix=".csv" ):
filenames = listdir(path_to_dir)
return [ filename for filename in filenames if filename.endswith( suffix ) ]
root = tk.Tk()
root.withdraw()
folder_path = filedialog.askdirectory()
all_csvfiles = find_csv_filenames(folder_path, suffix= ".csv")
for filename in all_csvfiles:
print(filename)
a = filename
with open(a, 'w', newline="") as file:
csvwriter = csv.writer(file) # 2. create a csvwriter object
csvwriter.writerow(a)

Wound up doing this.
import tkinter as tk
from tkinter import filedialog
from os import listdir
# Listing all csv in folder
def find_csv_filenames(path_to_dir, suffix=".csv"):
filenames = listdir(path_to_dir) #returns all filenames
return [filename for filename in filenames if filename.endswith(suffix)]
#returns only csv filenames in a list []
#This is GUI for asking to select folder
root = tk.Tk()
root.withdraw()
folder_path = filedialog.askdirectory() #Returns the folder you selected
all_csvfiles = find_csv_filenames(folder_path, suffix=".csv") #lists filenames
print(folder_path)
for filename in all_csvfiles: #begin loop thru all csv files
print(filename)
# a = filename
InsertedName = filename[:-4] #removes last 4 chars from filename
print(InsertedName)
tempfile = open(folder_path + "/temp.csv", "w") # creates a tempfile for
writing(w) in the same dir
tempfile.write(InsertedName+"\n") #will write filename to temp and instruct
for newline
sourcefile = open(folder_path + "/" + filename, "r") #creates a sourcefile
for reading original
for line in sourcefile: #begins loop for writing original data to tempfile
tempfile.write(line) #writes the data
sourcefile.close() #closes sourcefile
Finalfile = open(folder_path + "/" + filename, "w") #creating finalfile to
overwrite existing file in dir
tempfile.close() #closes tempfile to return pointer to the top of file
tempfile = open(folder_path + "/temp.csv", "r") #opens tempfile to write
tempfile data to finalfile
for line in tempfile: #loops the lines to write
Finalfile.write(line)
tempfile.close()
Finalfile.close()

python file name change

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)

python How do I import multiple .txt files in a folder to add characters to each .txt file?

There are text files of various names in the folder 'a'. I want to read all of these text files and add the letter 'b' to each text file. What should I do?
cwd = os.getcwd()
input_dir = os.path.join(cwd, "my .txt files dir")
sorts = sorted(glob(input_dir), key = lambda x:(len(x) , x))
for f in sorts :
f = open(input_dir, 'a')
data = "add text"
f.write(data)
f.close()

Append data to file:
- first: get all file in folder a.
- second: find extension with .txt.
- third: open it and do something('append', or 'rewrite').
Demo:
import os
# your .txt files dir
path = 'a'
# append data what you want
appendData = 'b'
fileNames = list(os.walk(path))[0][2]
fileNames.sort(key=len)
fileNums = len(fileNames)
# your dst file extension
fileExt = '.txt'
# # Extract extension from filename
# fileExt = os.path.splitext(fileNames[0])[1]
for fileName in fileNames:
if fileName.endswith(fileExt):
fileFullPath = os.path.join(path, fileName)
with open(fileFullPath, 'a') as f:
f.write(appendData)

Like the others said, this is an easy question that could easily be find on google. Anyway here's how to do it:
from os import listdir
from os.path import isfile, isdir, join
files = [file for file in listdir("files") if isfile(join("files", file))]
directories = [directory for directory in listdir("files") if isdir(join("files", directory))]
print(files)
for file_name in files:
try:
file = open("files/" + file_name, "a")
file.write("b")
file.close()
except IOError as err:
print("Could not open file because : ", err)
Replace "file" with the directory where your files are or the path to that directory like "directory0/directory1/directory_with_files"

Avoid to open files with
f = open(input_dir, 'a')
f.close()
Instead
with open(input_dir, 'a') as inputFile:
Do something
Also what you want is
import os
import glob # We will use this module to open only .txt files
path = 'your/path'
for filename in glob.glob(os.path.join(path, '*.txt'))
with open(filename, 'a') as inputFile:
inputFile.write('b')

Change a filename?

I have some files in a folder named like this test_1999.0000_seconds.vtk. What I would like to do is to is to change the name of the file to test_1999.0000.vtk.

You can use os.rename
os.rename("test_1999.0000_seconds.vtk", "test_1999.0000.vtk")

import os
currentPath = os.getcwd() # get the current working directory
unWantedString = "_seconds"
matchingFiles =[]
for path, subdirs, files in os.walk(currentPath):
for f in files:
if f.endswith(".vtk"): # To group the vtk files
matchingFiles.append(path+"\\"+ f) #
print matchingFiles
for mf in matchingFiles:
if unWantedString in mf:
oldName = mf
newName = mf.replace(unWantedString, '') # remove the substring from the string
os.rename(oldName, newName) # rename the old files with new name without the string

How do I apply my python code to all of the files in a folder at once, and how do I create a new name for each subsequent output file?

The code I am working with takes in a .pdf file, and outputs a .txt file. My question is, how do I create a loop (probably a for loop) which runs the code over and over again on all files in a folder which end in ".pdf"? Furthermore, how do I change the output each time the loop runs so that I can write a new file each time, that has the same name as the input file (ie. 1_pet.pdf > 1_pet.txt, 2_pet.pdf > 2_pet.txt, etc.)
Here is the code so far:
path="2_pet.pdf"
content = getPDFContent(path)
encoded = content.encode("utf-8")
text_file = open("Output.txt", "w")
text_file.write(encoded)
text_file.close()

The following script solve your problem:
import os
sourcedir = 'pdfdir'
dl = os.listdir('pdfdir')
for f in dl:
fs = f.split(".")
if fs[1] == "pdf":
path_in = os.path.join(dl,f)
content = getPDFContent(path_in)
encoded = content.encode("utf-8")
path_out = os.path.join(dl,fs[0] + ".txt")
text_file = open(path_out, 'w')
text_file.write(encoded)
text_file.close()

Create a function that encapsulates what you want to do to each file.
import os.path
def parse_pdf(filename):
"Parse a pdf into text"
content = getPDFContent(filename)
encoded = content.encode("utf-8")
## split of the pdf extension to add .txt instead.
(root, _) = os.path.splitext(filename)
text_file = open(root + ".txt", "w")
text_file.write(encoded)
text_file.close()
Then apply this function to a list of filenames, like so:
for f in files:
parse_pdf(f)

One way to operate on all PDF files in a directory is to invoke glob.glob() and iterate over the results:
import glob
for path in glob.glob('*.pdf')
content = getPDFContent(path)
encoded = content.encode("utf-8")
text_file = open("Output.txt", "w")
text_file.write(encoded)
text_file.close()
Another way is to allow the user to specify the files:
import sys
for path in sys.argv[1:]:
...
Then the user runs your script like python foo.py *.pdf.

You could use a recursive function to search the folders and all subfolders for files that end with pdf. Than take those files and then create a text file for it.
It could be something like:
import os
def convert_PDF(path, func):
d = os.path.basename(path)
if os.path.isdir(path):
[convert_PDF(os.path.join(path,x), func) for x in os.listdir(path)]
elif d[-4:] == '.pdf':
funct(path)
# based entirely on your example code
def convert_to_txt(path):
content = getPDFContent(path)
encoded = content.encode("utf-8")
file_path = os.path.dirname(path)
# replace pdf with txt extension
file_name = os.path.basename(path)[:-4]+'.txt'
text_file = open(file_path +'/'+file_name, "w")
text_file.write(encoded)
text_file.close()
convert_PDF('path/to/files', convert_to_txt)
Because the actual operation is changeable, you can replace the function with whatever operation you need to perform (like using a different library, converting to a different type, etc.)