Develop Reference

Python - copy specific file from subfolder to destination, get filename from text file

I want to get my script to read a list of names from a list(txt), then search for those in a selected folder with subfolders, then copy and paste those files to another selected folder. My script running without error but no result.
My script:
import os
import os.path
import shutil
textFile = ("D:\\Test\\list.txt")
sourceFolder = ("D:\\Test")
destinationFolder = ("D:\\")
filesToFind = []
with open(textFile, "r") as tx:
for row in tx:
filesToFind.append(row.strip())
for root, dirs, filename in os.walk(sourceFolder):
if filename in filesToFind:
f = os.path.join(root, filename)
shutil.copy(f, destinationFolder)

Haven’t test it but I think this will work - change this:
for root, dirs, filename in os.walk(sourceFolder):
if filename in filesToFind:
f = os.path.join(root, filename)
shutil.copy(f, destinationFolder)
To this:
for root, dirs, filenames in os.walk(sourceFolder):
for filename in filenames:
if filename in filesToFind:
f = os.path.join(root, filename)
shutil.copy(f, destinationFolder)

# Same code using glob #
## More efficient and also tested one ##
## One more feature added- checks file name given present or not ##
import os
import os.path
import shutil
import glob
textFile = ("D:\\Test\\list.txt")
sourceFolder = ("D:\Test")
destinationFolder = ("D:\\")
f = open(textFile, "r").readlines()
for i in f:
ListFile= glob.glob(os.path.join(sourceFolder,"**",i.strip()),recursive=True)
if len(ListFile):
print(ListFile[0],destinationFolder,os.path.basename(ListFile[0]))
destinationfile=os.path.join(destinationFolder,os.path.basename(ListFile[0]))
shutil.copyfile(ListFile[0],destinationfile)
else:
print(i,"-File not found")

Move file to new directory only if it contains specified string

I have 1 folder with thousands of files and I need to loop through every single file and see if that file contains a specific string, once it has concluded that it has a specific string, it must then be moved to the correct folder. So far I have:
for filename in glob.iglob('*.txt'):
f = open(filename)
s = mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ)
if s.find('* Test Outcome : FAIL') != -1:
src_file = os.path.join(dirSTART, filename)
dst_file = os.path.join(dirFAIL, filename)
shutil.move(src_file, dst_file + filename)
At the moment, it only moves the first file but I know for a fact there's more.
Thanks

You can use the os module alone to do this.
import os
import shutil
source_dir = "this/is/source/folder"
dest_dir = "this/is/destination/folder"
for top, dirs, files in os.walk(source_dir):
for filename in files:
if not filename.endswith('.txt'):
continue
file_path = os.path.join(top, filename)
with open(file_path, 'r') as f:
if '* Test Outcome : FAIL' in f.read():
shutil.move(file_path, os.path.join(dest_dir, filename))
CAUTION: Since I don't know much about your code, I am assuming all of the files are txt, that they are small and the string you are matching will always be the same.

from re import compile
pattern = compile("\* Test Outcome : FAIL")
for filename in glob.iglob('*.txt'):
fl = open(filename, 'r')
for i in fl.readlines():
if pattern.search(i):
fl.close()
src_file = os.path.join(dirSTART, filename)
dst_file = os.path.join(dirFAIL, filename)
shutil.move(src_file, dst_file + filename)
break #To stop checking other lines

Use a contextmanager and with to open your files so they will be closed each time:
from mmap import mmap, ACCESS_READ
import contextlib
from os import path
from shutil import move
for filename in glob.iglob('*.txt'):
with open(filename) as f:
with contextlib.closing(mmap(f.fileno(), 0, access=ACCESS_READ)) as s:
if s.find('* Test Outcome : FAIL') != -1:
src_file = path.join(dirSTART, filename)
dst_file = path.join(dirFAIL, filename)
move(src_file, dst_file)

Try to do f.close() after s = mmap.mmap(...)
Are you on Linux? If so, might be quicker to this in a shell command with grep and mv.

Moving large files using shutil.move

I have written a code for moving files from one folder to another .I moved only those files whose names are present in my text file(aiq.txt).
It works fine when files are less in number say(10) but when number goes to around 500 the program terminates.
Each file is of 50 Mb
Here is my code:
import os
import shutil
destination=r"dstpath"
with open("aiq.txt") as infile:
for line in infile:
line=line.strip('\n)
for root,dirs,filenames in os.walk(r"H:\test_vectors"):
for filename in filenames:
if line in filename:
shutil.move(os.path.join(root,filename),destination)

import os
import shutil
root = r"H:\test_vectors"
destination = r"dstpath"
file_list = []
dir_dict = {}
with open('aiq.txt', 'r') as f:
for line in f:
file_list.append(line.strip())
for d, dirs, files in os.walk(root):
if files:
dir_dict[d] = files
for key, item in dir_dict.items():
for x in item:
if x in file_list:
try:
shutil.move(os.path.join(key, x), destination)
except:
pass

I have a ".txt "file which consists of various filenames and I want to search each filename in a folder where these files are actually kept

Suppose I have a text file aiq_hits.txt.
Each line in this file corresponds a filename
ant1.aiq
ant2.aiq
ant3.aiq
ant4.aiq
I want to match each line of my textfile (ant1.aiq,ant2.aiq and so on) with filenames which are present at some specific place(R:\Sample) and extract matching files into some other place (R:\sample\wsa).
I have an idea that I need to use functions like os.walk() and fnmatch.fnmatch(), shutil.copy() but I am not able to implement them
My code:
import os
import shutil
import fnmatch
with open("aiq_hits.txt","r") as in_file:
for line in in_file:
I am stuck here

import os
import shutil
sourceDir = "R:\\Sample"
targetDir = "R:\\Sample\\wsa"
existingFiles = set(f for f in os.listdir(sourceDir) if os.path.isfile(os.path.join(sourceDir, f)))
infilepath = "aiq_hits.txt"
with open(infilepath) as infile:
for line in infile:
fname = line.strip()
if fname not in existingFiles: continue
shutil.move(os.path.join(sourceDir, fname), os.path.join(targetDir, fname))

I hope this will suffice:
import os
def match_files(url,file_read, dest):
f = open(file_read, 'rb')
file_list = os.listdir(url)
print(file_list)
saved_path = os.getcwd()
print("Current working directory is " + saved_path)
os.chdir(url)
match = []
for file_name in f:
file_name = file_name.strip()
if file_name in file_list:
match.append(file_name)
os.rename(os.path.join(url, file_name), os.path.join(dest, file_name))
os.chdir(saved_path)
print match
here, url is source directory or folder from which u want to match files, file_read is the name of file (with path) in which list of file names is given, dest is the destination folder.
this code moves the matching files from url to dest, i.e. these files won't remin in url after running the code.

Alternatively you could use the glob module which allows you to enter in a expression for the file name\extension which will then return a list that you can loop over.
I'd use this module if the source directory can have files with the same extension that you want to exclude from being looped over
Also I'm assuming that the file name list is not large and so storing it in a list wont be an issue
eg (I haven't tested the below )
from glob import glob
import os
import shutil
src = 'R:\\Sample'
dst = "R:\\Sample\\wsa"
in_file_list = "aiq_hits.txt"
list_Of_files = glob(os.path.join(src, 'ant*.aiq'))
data = []
with open(in_file_list) as reader:
data += reader.readlines()
for row in list_Of_files:
file_path, file_name = os.path.split(row)
if file_name in data:
shutil.copy2(row, os.path.join(dst, file_name))
# or if you want to move the file
# shutil.move(row, os.path.join(dst, file_name))

Get rows from all .txt files in directory using python

I have some txt files in a directory and I need to get the last 15 lines from all of them. How could I do it using python?
I chose this code:
from os import listdir
from os.path import isfile, join
dir_path= './'
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
out = []
for file in files:
filedata = open(join(dir_path, file), "r").readlines()[-15:]
out.append(filedata)
f = open(r'./fin.txt','w')
f.writelines(out)
f.close()
but I get the error "TypeError: writelines() argument must be a sequence of strings". I think it's because of Russian letters in the lines.

import os
from collections import deque
for filename in os.listdir('/some/path'):
# might want to put a check it's actually a file here...
# (join it to a root path, or anything else....)
# and sanity check it's text of a usable kind
with open(filename) as fin:
last_15 = deque(fin, 15)
deque will automatically discard the oldest entry and peak the max size to be 15, so it's an efficient way of keeping just the "last" 'n' items.

Try this:
from os import listdir
from os.path import isfile
for filepath in listdir("/path/to/folder")
if isfile(filepath): # if need
last_five_lines = open(filepath).readlines()[-15:]
# or, one line:
x = [open(f).readlines()[-15:] for f in listdir("/path/to/folder") if isfile(f)]
Updated:
lastlines = []
for file in files:
lastlines += open(join(dir_path, file), "r").readlines()[-15:]
with open('./fin.txt', 'w') as f:
f.writelines(lastlines)

from os import listdir
from os.path import isfile, join
dir_path= '/usr/lib/something'
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
for file in files:
filedata = open(join(dir_path, file), "r").readlines()[-15:]
#do something with the filedata

Hope this helps:
import os
current_dir = os.getcwd()
dir_objects = os.listdir(current_dir)
dict_of_last_15 = {}
for file in dir_objects:
file_obj = open(file, 'rb')
content = file_obj.readlines()
last_15_lines = content[-15:]
dict_of_last_15[file] = last_15_lines
print "#############: %s" % file
print dict_of_last_15[file]
file_to_check.close()