I want to change filename for all my files in a folder. They all end with a date and time like "filename 2019-05-20 1357" and I want the date first for all files. How can I do that simplest way?
#!/usr/bin/python3
import shutil, os, re
r = re.compile(r"^(.*) (\d{4}-\d{2}-\d{2} \d{4})$")
for f in os.listdir():
m = r.match(f)
if m:
shutil.move(f, "{} {}".format(m.group(2), m.group(1)))
Quick and roughly tested version
Here is my Implementation:
from datetime import datetime
import os
path = '/Users/name/desktop/directory'
for _, file in enumerate(os.listdir(path)):
os.rename(os.path.join(path, file), os.path.join(path, str(datetime.now().strftime("%d-%m-%Y %H%M"))+str(file)))
Output Format:
20-05-2019 1749filename.ext
import os
import re
import shutil
dir_path = '' # give the dir name
comp = re.compile(r'\d{4}-\d{2}-\d{2}')
for file in os.listdir(dir_path):
if '.' in file:
index = [i for i, v in enumerate(file,0) if v=='.'][-1]
name = file[:index]
ext = file[index+1:]
else:
ext=''
name = file
data = comp.findall(name)
if len(data)!=0:
date= comp.findall(name)[0]
rest_name = ' '.join(comp.split(name)).strip()
new_name = '{} {}{}'.format(date,rest_name,'.'+ext)
print('changing {} to {}'.format(name, new_name))
shutil.move(os.path.join(dir_path,name), os.path.join(dir_path, new_name))
else:
print('file {} is not change'.format(name))
Related
I have a couple slides, each slide corresponds to a person. I need to name each file (.pptx) after the individual name it references. A lot of the examples I see on mass renaming have the renaming become sequential like:
file1
file2
file3
I need:
bob.pptx
sue.pptx
jack.pptx
I was able to change names using os found on this site https://www.marsja.se/rename-files-in-python-a-guide-with-examples-using-os-rename/:
import os, fnmatch
file_path = 'C:\\Users\\Documents\\Files_To_Rename\\Many_Files\\'
files_to_rename = fnmatch.filter(os.listdir(file_path), '*.pptx')
print(files_to_rename)
new_name = 'Datafile'
for i, file_name in enumerate(files_to_rename):
new_file_name = new_name + str(i) + '.pptx'
os.rename(file_path + file_name,
file_path + new_file_name)
But again, this just names it:
Datafile1
Datafile2
etc
my example
import os from pathlib
import Path
files = os.listdir("c:\\tmp\\")
for key in range(0, len(files)):
print (files[key])
os.rename("c:\\tmp\\" + files[key], "c:\\tmp\\" + files[key].replace("-",""))
Path("c:\\tmp\\" + files[key] + '.ok').touch() # if u need add some extension
Here's how I ran your code (avoiding file paths I don't have!), getting it to print output not just rename
import os, fnmatch
file_path = '.\\'
files_to_rename = fnmatch.filter(os.listdir(file_path), '*.pptx')
print(files_to_rename)
new_name = 'Datafile'
for i, file_name in enumerate(files_to_rename):
new_file_name = new_name + str(i) + '.pptx'
print (file_path + new_file_name)
os.rename(file_path + file_name,
file_path + new_file_name)
This gave me
.\Datafile0.pptx
.\Datafile1.pptx
...
and did give me the correct sequence of pptx files in that folder.
So I suspect the problem is that you are getting the file names you want, but you can't see them in Windows. Solution: show file types in Windows. Here's one of many available links as to how: https://www.thewindowsclub.com/show-file-extensions-in-windows
Thank you everyone for your suggestions, I think I found it with a friend's help:
import os, fnmatch
import pandas as pd
file_path = 'C:\\Users\\Documents\\FolderwithFiles\\'
files_to_rename = fnmatch.filter(os.listdir(file_path), '*.pptx') #looks for any .ppt in path, can make any ext
df = pd.read_excel('Names.xlsx') #make a list of names in an xl, this won't read the header, header should be Names, then list your names)
for i, file_name in zip(df['Names'], files_to_rename): #zip instead of a nest for loop
new_file_name = i + '.pptx'
os.rename(file_path + file_name, file_path + new_file_name)
print(new_file_name)
I just start python and i have to compare filename with folder name to launch the good sh script. (i'm using airflow)
import glob
import os
import shutil
from os import path
odsPath = '/apps/data/02_ODS/'
receiptPath = '/apps/data/80_DATA/01_Receipt/'
for files in os.listdir(receiptPath):
if(files.startswith('MEM_ZMII') or files.startswith('FMS') and files.endswith('.csv')):
parsedFiles = files.split('_')
pattern = '_'.join(parsedFiles[0:2])
fileName = '_'.join(parsedFiles[2:5])
fileName = fileName.split('-')[0].lower()
# print('appCode: ', pattern)
# print('fileName: ', fileName)
for odsFolder in os.listdir(odsPath):
if(odsFolder == fileName):
print('it exist: ', str(fileName))
else:
print('it\'s not')
I got 3 files in receiptPath , it only matching for 1 file, but not the others. Can someone help me?
Thank a lot!
Ok, your problem is that you overwrite your variable fileName, so at the end of the first for loop, it only keeps the last value, which is material_makt. The solution consists in saving all the filenames in a list fileNames_list, and then you can check if (odsFolder in fileNames_list) :
import glob
import os
import shutil
from os import path
odsPath = '/apps/data/02_ODS/'
receiptPath = '/apps/data/80_DATA/01_Receipt/'
fileNames_list = []
for files in os.listdir(receiptPath):
if(files.startswith('MEM_ZMII') or files.startswith('FMS') and files.endswith('.csv')):
parsedFiles = files.split('_')
pattern = '_'.join(parsedFiles[0:2])
fileName = '_'.join(parsedFiles[2:5])
fileName = fileName.split('-')[0].lower()
fileNames_list.append(fileName)
for odsFolder in os.listdir(odsPath):
if (odsFolder in fileNames_list):
print('it exist:', str(odsFolder))
else:
print('it\'s not')
Output :
it exist: zcormm_familymc
it exist: kpi_obj_data
it exist: material_makt
I have a list of files with names such as these:
20140911_085234.csv
20140912_040056.csv
What is known is the first part which is the date (the second is a random number). How can I open the correct file if I know the date?
Update: There is one file per day.
As #isedev says, you could use the fnmatch method to find all the files with the "date" pattern. The code could be like this:
from fnmatch import fnmatch
import os
folder_path = '/home/Desktop/project'
all_files = os.listdir(folder_path)
content_file = 'Hello World'
_date = '20140911'
_pattern = _date + '*'
for file_name in all_files:
if fnmatch(file_name, _pattern):
with open(os.path.join(folder_path, file_name), 'wb') as f:
f.write(content_file)
I hope it helps you!
Using glob :
import time
import glob
import os
def open_file_by_date(date):
path = "/path/to/file"
files = glob.glob1(path, date + "_*.csv")
for file in files:
with open(os.path.join(path, file), 'wb') as f:
#do your stuff with file
if __name__ == "__main__":
today = time.strftime("%Y%m%d")
open_file_by_date(today)
I have the same problem as here but now I'm trying to do the same with python because it's more suited to the task.
I've started with this:
import os
import shutil
import random
import glob
root_dir = '/home/leonardo/Desktop/python_script/rfe'
output_dir = '/home/leonardo/Desktop/python_script/output_folder'
ref = 200
folders_root_dir = os.listdir(root_dir)
print folders_root_dir
count = len(folders_root_dir)
print count
for i in xrange(count):
folder_inside = root_dir + '/' + folders_root_dir[i]
print folder_inside
number_files_folder_inside = len(os.listdir(folder_inside))
print number_files_folder_inside
if number_files_folder_inside > ref:
ref_copy = round(0.2*number_files_folder_inside)
print ref_copy
# here I have to copy 20% of the files in this folder to the output folder
else:
# here I have to copy all files from the folder to the output_dir
I tried to use os.walk() but I'm new to python and selecting files while the function is working proved to be really tough.
You'll need to import these:
import os
import shutil
import random
You can get all the files in a directory like this:
files = [file for file in os.listdir(dir) if os.path.isfile(os.path.join(dir, file))]
Then use a conditional:
if len(files) < 200:
for file in files:
shutil.copyfile(os.path.join(dir, file), dst)
else:
# Amount of random files you'd like to select
random_amount = 1000
for x in xrange(random_amount):
if len(files) == 0:
break
else:
file = random.choice(files)
shutil.copyfile(os.path.join(dir, file), outputdir)
A more compact solution (also noticing that copyfile does not really do the job properly unless one specifies the target file name as well):
import os
import shutil
import random
def get_file_list(input_dir):
return [file for file in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, file))]
def get_random_files(file_list, N):
return random.sample(file_list, N)
def copy_files(random_files, input_dir, output_dir):
for file in random_files:
shutil.copy(os.path.join(input_dir, file), output_dir)
def main(input_dir, output_dir, N):
file_list = get_file_list(input_dir)
random_files = get_random_files(file_list, N)
copy_files(random_files, input_dir, output_dir)
import os
import shutil
import random
root_dir = '/home/leonardo/Desktop/python_script/qar'
output_dir = '/home/leonardo/Desktop/python_script/output_folder'
ref = 1
for root, dirs, files in os.walk(root_dir):
number_of_files = len(os.listdir(root))
if number_of_files > ref:
ref_copy = int(round(0.2 * number_of_files))
for i in xrange(ref_copy):
chosen_one = random.choice(os.listdir(root))
file_in_track = root
file_to_copy = file_in_track + '/' + chosen_one
if os.path.isfile(file_to_copy) == True:
shutil.copy(file_to_copy,output_dir)
print file_to_copy
else:
for i in xrange(len(files)):
track_list = root
file_in_track = files[i]
file_to_copy = track_list + '/' + file_in_track
if os.path.isfile(file_to_copy) == True:
shutil.copy(file_to_copy,output_dir)
print file_to_copy
print 'Finished !'
The final code has this face
thank you guys for the help !
cheers !
I want this for splitting my dataset to train,test and validation.
here is my code :
import os
import shutil
import random
import numpy as np
dir = r'E:\down\imgs'
train_dir = r'E:/train_test_split/train'
test_dir = r'E:/train_test_split/test'
valid_dir = r'E:/train_test_split/validation'
files = [file for file in os.listdir(dir) if os.path.isfile(os.path.join(dir, file))]
train_count = np.round(50/100*len(files))
test_count = np.round(30/100*len(files))
valid_count = np.round(20/100*len(files))
rndnums = list(random.sample(range(0, len(files)), len(files)))
print("len(files)",len(files))
# print("all",len(files))
# print("train",np.round(train*len(files)))
# print("test",np.round(test*len(files)))
# print("valid",np.round(valid*len(files)))
#
# print("sum",np.round(train*len(files)) + np.round(test*len(files)) + np.round(valid*len(files)))
# Amount of random files you'd like to select
##train_files
print(rndnums)
train_file_index = rndnums[0:int(train_count)+1]
train_file_name = [files[i] for i in train_file_index]
test_file_index = rndnums[int(train_count)+1:int(train_count + test_count)+1]
test_file_name = [files[i] for i in test_file_index]
valid_file_index = rndnums[int(train_count + test_count)+1:]
valid_file_name = [files[i] for i in valid_file_index]
for x in train_file_name:
file = x
shutil.copyfile(os.path.join(dir, file), os.path.join(train_dir, file))
##test_files
for y in test_file_name:
file = y
shutil.copyfile(os.path.join(dir, file), os.path.join(test_dir, file))
##valid_files
for z in valid_file_name:
file = z
shutil.copyfile(os.path.join(dir, file), os.path.join(valid_dir, file))
maybe something like (untested)
import os
THRESHOLD = 200
root_dir = "\home..."
output_dir = "\home....."
for top, dirs, nondirs in os.walk(root_dir):
for name in nondirs[:THRESHOLD]:
path = os.path.join(top, name)
destination = os.path.join(output_dir, name)
os.rename(path, destination)
import random
import shutil
import os
rootdir = '/home/leonardo/Desktop/python_script/qar'
outdir = '/home/leonardo/Desktop/python_script/output_folder'
ref = 200
dirsAndFiles = {} # here we store a structure {folder: [file1, file2], folder2: [file2, file4] }
dirs = [x[0] for x in os.walk(rootdir)] # here we store all sub-dirs
for dir in dirs:
dirsAndFiles[dir] = [f for f in os.listdir(dir) if os.path.isfile(os.path.join(dir, f))]
for (dir, files) in dirsAndFiles.iteritems():
if len(files) > ref:
for i in xrange(int(0.2*len(files))): # copy 20% of files
fe = random.choice(files)
files.remove(fe)
shutil.copy(os.path.join(dir, fe), outdir)
else: # copy all files
for file in files:
shutil.copy(os.path.join(dir, file), outdir)
I have 300 XML files, in each file there is a path (see code) and i want to make a list (.CSV) of this Paths with Python.
<da:AdminData>
<da:Datax />
<da:DataID>223</da:DataID>
<da:Date>2013-08-19</da:Date>
<da:Time>13:27:25</da:Time>
<da:Modification>2013-08-19</da:Modification>
<da:ModificationTime>13:27:25</da:ModificationTime>
**<da:Path>D:\08\06\xxx-aaa_20130806_111339.dat</da:Path>**
<da:ID>xxx-5225-fff</da:ID>
I wrote the following code, but does not work for subdirectories
import os, glob, re, time, shutil
xmlpath = r'D:'
outfilename = "result.csv"
list = glob.glob(os.path.join(xmlpath,'*.xml'))
output = ""
for file in list :
fh = open(file)
text = fh.read()
pattern = "<da:Path>(.*)</da:Path>"
pattern = re.compile(pattern);
a = pattern.search(text)
if a:
output += '\n' + a.group(1)
logfile = open(outfile, "w")
logfile.write(output)
logfile.close()
To glob recursively, it is best to use a combination of os.walk and fnmatch.fnmatch. Example:
import os
import fnmatch
def recursive_glob(rootdir, pattern):
matching_files = []
for d, _, fnames in os.walk(rootdir):
matching_files.extend(
os.path.join(d, fname) for fname in fnames
if fnmatch.fnmatch(fname, pattern)
)
return matching_files
xmlfiles = recursive_glob(r"D:\", "*.xml")