Keep latest file and delete all other

Question

In my folder there are many pdf files with date-timestamp format such as shown in the last. I would like to keep the latest file for the day and delete the rest for that day

Answer 1

Sort the list and delete files if the next file in the list is on the same day,

import glob
import os
files = glob.glob("*.pdf")
files.sort()

for ifl, fl in enumerate(files[:-1]):
    if files[ifl+1].startswith(fl[:10]):    #Check if next file is same day
        os.unlink(fl)                       # It is - delete current file

Edit:

As the OPs question became clearer it became evident that not just the last file of the list is required, but the latest file of each day - to achieve this I included a "same day" conditioned unlinking.

Answer 2

You could do it that way. The following code is untested, but may work:

import os

names = os.listdir()
names.sort()
for f in names[:-1]:
    os.unlink(f)

Fortunately your file names use ISO8601 date format so the textual sort achieves the desired result with no need to parse the dates.

Answer 3

The following snippet works with the test case given.

files = os.listdir(".")
days = set(fname[8:10] for fname in files)

for d in days:
    f = [i for i in files if i[8:10] == d]
    for x in sorted(f)[:-1]:
        os.remove(x)

Answer 4

Your desired list can also be achieved using groupby .

from itertools import groupby
from os import listdir,unlink

filtered_list = list()
names = os.listdir()

for key,group in groupby(names,lambda x : x[:10]): # groups based on the start 10 characters of file
  filtered_list.append([item for item in group][-1]) #picks the last file from the group

print filtered_list

Answer 5

Using dictionary You can keep one value. This can be dirty and quickest solution, maybe not the best.

#!/usr/bin/env python
import os
import datetime
import stat
import shutil

filelist=[]
lst=[]
dc={}

os.chdir(".")
for files in os.listdir("."):
    if files.endswith(".pdf"):
        lst.append(files)

for x in lst:
    print x[0:10].replace("-","")
    dc[int(x[0:10].replace("-",""))]=x

a = dc.items()
flist=[]
for k, v in a:
    flist.append(v)

dir="tmpdir"    
if not os.path.exists(dir):
    os.makedirs(dir)

from shutil import copyfile
for x in flist:
    print x
    copyfile(x, dir + "/" + x)

#os.chdir(".")
for files in os.listdir("."):
    if files.endswith(".pdf"):
            os.unlink(files)

os.chdir("./tmpdir")
for files in os.listdir("."):
    if files.endswith(".pdf"):
        copyfile(files, "../"+files)

os.chdir("../")
shutil.rmtree(os.path.abspath(".")+"/tmpdir")