Reputation: 845
I have the following structure:
Folder1
ZZ-20201201-XX.zip
Folder2
XX-20201201-XX.zip
XX-20201202-XX.zip
Folder3
YY-20201201-XX.zip
YY-20201202-XX.zip
With below code Im creating a counterpart of Folder1, Folder2
and Folder3
and directly unzipping the zipped files inside those 3 folders. So I receive this:
Folder1
ZZ-.txt
Folder2
XX-.txt
Folder3
YY.txt
As you can see the files lose the date once they get unzipped so if a folder contains 2 zipped files they will get the same name and thus the files will be rewritten. Now I want to add the date of the zipped files to the files once they are unzipped. How can I do this?
import fnmatch
pattern = '*.zip'
for root, dirs, files in os.walk(my_files):
for filename in fnmatch.filter(files, pattern):
path = os.path.join(root, filename)
date_zipped_file = re.search('-(.\d+)-', filename).group(1) #<-- this is the date of the zipped files and I want this to be included in the name of the unzipped files once they get unzipped.
# Store the new directory so that it can be recreated
new_dir = os.path.normpath(os.path.join(os.path.relpath(path, start=my_files), ".."))
# Join your target directory with newly created directory
new = os.path.join(counter_part, new_dir)
# Create those folders, works even with nested folders
if (not os.path.exists(new)):
os.makedirs(new)
zipfile.ZipFile(path).extractall(new)
my desired outcome:
Folder1
ZZ-20201201.txt
Folder2
XX-20201201.txt
XX-20201202.txt
Folder3
YY-20201201.txt
XX-20201202.txt
Upvotes: 1
Views: 141
Reputation: 1569
You could just rename the files after you have unzipped each folder. Something like this:
#get all files in that unzipped folder
files = os.listdir(path)
#rename all files in that dir
for file in files:
filesplit = os.path.splitext(os.path.basename(file))
os.rename(os.path.join(path, file), os.path.join(path, filesplit[0]+'_'+date_zipped_file+filesplit[1]))
but that also renames files which might actually have already a date
in the name. So you would also need to integrate a check if the file was already renamed. Either by maintaining a list
with file names or a simple regex
which looks for 8 digit string between a '_' and a '.', e.g. text_20201207.txt.
#get all files in that unzipped folder
files = os.listdir(path)
#rename all files in that dir
for file in files:
filesplit = os.path.splitext(os.path.basename(file))
if not re.search(r'_\d{8}.', file):
os.rename(os.path.join(path, file), os.path.join(path, filesplit[0]+'_'+date_zipped_file+filesplit[1]))
your final solution would then look something like this:
import fnmatch
pattern = '*.zip'
for root, dirs, files in os.walk(my_files):
for filename in fnmatch.filter(files, pattern):
path = os.path.join(root, filename)
date_zipped_file = re.search('-(.\d+)-', filename).group(1) #<-- this is the date of the zipped files and I want this to be included in the name of the unzipped files once they get unzipped.
# Store the new directory so that it can be recreated
new_dir = os.path.normpath(os.path.join(os.path.relpath(path, start=my_files), ".."))
# Join your target directory with newly created directory
new = os.path.join(counter_part, new_dir)
# Create those folders, works even with nested folders
if (not os.path.exists(new)):
os.makedirs(new)
zipfile.ZipFile(path).extractall(new)
#get all files in that unzipped folder
files = os.listdir(new)
#rename all files in that dir
for file in files:
filesplit = os.path.splitext(os.path.basename(file))
if not re.search(r'_\d{8}.', file):
os.rename(os.path.join(new, file), os.path.join(new, filesplit[0]+'_'+date_zipped_file+filesplit[1]))
Upvotes: 1