Making a method select the location of a file using recursion - python

I'm trying to create a recursive method; the goal of this method is to find the deepest directory that could contain this file and determine if the file belongs here. If the file does I want it to return the full file location. the first method was the original, but it didn't work with a return statement.
import zipfile, lxml.etree, os, xml.etree.ElementTree as ET, sys, shutil, re
from docx import Document
path = #Directory where you want files sorted to
Orignial method
def findSubDir(file,dire):
tempPath = os.path.join(path,dire.replace(" ",""))
for dirs in os.listdir(tempPath):
if os.path.isdir(os.path.join(tempPath,dirs)):
for names in re.findall('[A-Z][^A-Z]+', dirs):
if names in file:
print(os.path.join(tempPath,dirs))
findSubDir(file,os.path.join(dire,dirs))
Modified method
def reFindSubDir(file,dire):
tempPath = os.path.join(path,dire.replace(" ",""))
dirs = [dirs for dirs in os.listdir(tempPath)
if os.path.isdir(os.path.join(tempPath,dirs))]
if(any(os.path.isdir(os.path.join(tempPath,dirs)) for dirs in os.listdir(tempPath))):
print("passed")
folder = "".join([names for dires in dirs for names in re.findall('[A-Z][^A-Z]+', dires)if names in file])
print("folder")
if folder != "":
reFindSubDir(file,os.path.join(dire,folder))
else:
print("Steve2")
return "Steve"
else:
print(tempPath)
return(tempPath)

There are multiple issues I immediately see in your code. First, in your original attempt it appears you are missing a base case. Second, you're not returning anything in your recursive case.
Try using this first without your regex, then you can incorporate it into your code.
def findSubDir(file, dire=""):
tempPath = os.path.join(path, dire)
for dirs in os.listdir(tempPath):
if os.path.isdir(os.path.join(tempPath, dirs)):
return findSubDir(file,os.path.join(tempPath,dirs))
if dirs == file:
return os.path.join(tempPath, file)

Related

How to loop and optimise data extraction - Python [duplicate]

I need to iterate through all .asm files inside a given directory and do some actions on them.
How can this be done in a efficient way?
Python 3.6 version of the above answer, using os - assuming that you have the directory path as a str object in a variable called directory_in_str:
import os
directory = os.fsencode(directory_in_str)
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith(".asm") or filename.endswith(".py"):
# print(os.path.join(directory, filename))
continue
else:
continue
Or recursively, using pathlib:
from pathlib import Path
pathlist = Path(directory_in_str).glob('**/*.asm')
for path in pathlist:
# because path is object not string
path_in_str = str(path)
# print(path_in_str)
Use rglob to replace glob('**/*.asm') with rglob('*.asm')
This is like calling Path.glob() with '**/' added in front of the given relative pattern:
from pathlib import Path
pathlist = Path(directory_in_str).rglob('*.asm')
for path in pathlist:
# because path is object not string
path_in_str = str(path)
# print(path_in_str)
Original answer:
import os
for filename in os.listdir("/path/to/dir/"):
if filename.endswith(".asm") or filename.endswith(".py"):
# print(os.path.join(directory, filename))
continue
else:
continue
This will iterate over all descendant files, not just the immediate children of the directory:
import os
for subdir, dirs, files in os.walk(rootdir):
for file in files:
#print os.path.join(subdir, file)
filepath = subdir + os.sep + file
if filepath.endswith(".asm"):
print (filepath)
You can try using glob module:
import glob
for filepath in glob.iglob('my_dir/*.asm'):
print(filepath)
and since Python 3.5 you can search subdirectories as well:
glob.glob('**/*.txt', recursive=True) # => ['2.txt', 'sub/3.txt']
From the docs:
The glob module finds all the pathnames matching a specified pattern according to the rules used by the Unix shell, although results are returned in arbitrary order. No tilde expansion is done, but *, ?, and character ranges expressed with [] will be correctly matched.
Since Python 3.5, things are much easier with os.scandir() and 2-20x faster (source):
with os.scandir(path) as it:
for entry in it:
if entry.name.endswith(".asm") and entry.is_file():
print(entry.name, entry.path)
Using scandir() instead of listdir() can significantly increase the
performance of code that also needs file type or file attribute
information, because os.DirEntry objects expose this information if
the operating system provides it when scanning a directory. All
os.DirEntry methods may perform a system call, but is_dir() and
is_file() usually only require a system call for symbolic links;
os.DirEntry.stat() always requires a system call on Unix but only
requires one for symbolic links on Windows.
Python 3.4 and later offer pathlib in the standard library. You could do:
from pathlib import Path
asm_pths = [pth for pth in Path.cwd().iterdir()
if pth.suffix == '.asm']
Or if you don't like list comprehensions:
asm_paths = []
for pth in Path.cwd().iterdir():
if pth.suffix == '.asm':
asm_pths.append(pth)
Path objects can easily be converted to strings.
Here's how I iterate through files in Python:
import os
path = 'the/name/of/your/path'
folder = os.fsencode(path)
filenames = []
for file in os.listdir(folder):
filename = os.fsdecode(file)
if filename.endswith( ('.jpeg', '.png', '.gif') ): # whatever file types you're using...
filenames.append(filename)
filenames.sort() # now you have the filenames and can do something with them
NONE OF THESE TECHNIQUES GUARANTEE ANY ITERATION ORDERING
Yup, super unpredictable. Notice that I sort the filenames, which is important if the order of the files matters, i.e. for video frames or time dependent data collection. Be sure to put indices in your filenames though!
You can use glob for referring the directory and the list :
import glob
import os
#to get the current working directory name
cwd = os.getcwd()
#Load the images from images folder.
for f in glob.glob('images\*.jpg'):
dir_name = get_dir_name(f)
image_file_name = dir_name + '.jpg'
#To print the file name with path (path will be in string)
print (image_file_name)
To get the list of all directory in array you can use os :
os.listdir(directory)
I'm not quite happy with this implementation yet, I wanted to have a custom constructor that does DirectoryIndex._make(next(os.walk(input_path))) such that you can just pass the path you want a file listing for. Edits welcome!
import collections
import os
DirectoryIndex = collections.namedtuple('DirectoryIndex', ['root', 'dirs', 'files'])
for file_name in DirectoryIndex(*next(os.walk('.'))).files:
file_path = os.path.join(path, file_name)
I really like using the scandir directive that is built into the os library. Here is a working example:
import os
i = 0
with os.scandir('/usr/local/bin') as root_dir:
for path in root_dir:
if path.is_file():
i += 1
print(f"Full path is: {path} and just the name is: {path.name}")
print(f"{i} files scanned successfully.")
Get all the .asm files in a directory by doing this.
import os
path = "path_to_file"
file_type = '.asm'
for filename in os.listdir(path=path):
if filename.endswith(file_type):
print(filename)
print(f"{path}/{filename}")
# do something below
I don't understand why some answers are complicated. This is how I would do it with Python 2.7. Replace DIRECTORY_TO_LOOP with the directory you want to use.
import os
DIRECTORY_TO_LOOP = '/var/www/files/'
for root, dirs, files in os.walk(DIRECTORY_TO_LOOP, topdown=False):
for name in files:
print(os.path.join(root, name))

python check if the folder content existed

The purpose of this code is:
Read a csv file which contains a column for a list of file names
here is the csv file:
https://drive.google.com/open?id=0B5bJvxM9TZkhVGI5dkdLVzAyNTA
Then check a specific folder to check if the files exist or not
If its found a file is not in the list delete it
here is the code:
import pandas as pd
import os.path
data = pd.read_csv('data.csv')
names = data['title']
path = "C:\\Users\\Sayed\\Desktop\\Economic Data"
for file in os.listdir(path):
os.path.exists(file)
print(file)
file = os.path.join(path, file)
fileName = os.path.splitext(file)
if fileName not in names:
print('error')
os.remove(file)
I modified the first code, and this is the new code and I got no error but the simply delete all the files in the directory
os.chdir does not return anything, so assigning the result to path means that path has None, which causes the error.
Since you're using pandas, here's a little trick to speed this up using pd.Series.isin.
root = "C:\Users\Sayed\Desktop\Economic Data"
files = os.listdir(root)
for f in data.loc[~data['title'].isin(files), 'title'].tolist():
try:
os.remove(os.path.join(root, f))
except OSError:
pass
Added a try-except check in accordance with EAFP (since I'm not doing an os.path.exists check here). Alternatively, you could add a filter based on existence using pd.Series.apply:
m = ~data['title'].isin(files) & data['title'].apply(os.path.exists)
for f in data.loc[m, 'title'].tolist():
os.remove(os.path.join(root, f))
Your path is the return value of the os.chdir() call. Which is obviously None.
You want to set path to the string representing the path ... leave the chdir out.

Move pairs of files (.txt & .xml) into their corresponding folder using Python

I have been working this challenge for about a day or so. I've looked at multiple questions and answers asked on SO and tried to 'MacGyver' the code used for my purpose, but still having issues.
I have a directory (lets call it "src\") with hundreds of files (.txt and .xml). Each .txt file has an associated .xml file (let's call it a pair). Example:
src\text-001.txt
src\text-001.xml
src\text-002.txt
src\text-002.xml
src\text-003.txt
src\text-003.xml
Here's an example of how I would like it to turn out so each pair of files are placed into a single unique folder:
src\text-001\text-001.txt
src\text-001\text-001.xml
src\text-002\text-002.txt
src\text-002\text-002.xml
src\text-003\text-003.txt
src\text-003\text-003.xml
What I'd like to do is create an associated folder for each pair and then move each pair of files into its respective folder using Python. I've already tried working from code I found (thanks to a post from Nov '12 by Sethdd, but am having trouble figuring out how to use the move function to grab pairs of files. Here's where I'm at:
import os
import shutil
srcpath = "PATH_TO_SOURCE"
srcfiles = os.listdir(srcpath)
destpath = "PATH_TO_DEST"
# grabs the name of the file before extension and uses as the dest folder name
destdirs = list(set([filename[0:9] for filename in srcfiles]))
def create(dirname, destpath):
full_path = os.path.join(destpath, dirname)
os.mkdir(full_path)
return full_path
def move(filename, dirpath):
shutil.move(os.path.join(srcpath, filename)
,dirpath)
# create destination directories and store their names along with full paths
targets = [
(folder, create(folder, destpath)) for folder in destdirs
]
for dirname, full_path in targets:
for filename in srcfile:
if dirname == filename[0:9]:
move(filename, full_path)
I feel like it should be easy, but Python isn't something I work with everyday and it's been a while since my scripting days... Any help would be greatly appreciated!
Thanks,
WK2EcoD
Use the glob module to interate all of the 'txt' files. From that you can parse and create the folders and copy the files.
The process should be as simple as it appears to you as a human.
for file_name in os.listdir(srcpath):
dir = file_name[:9]
# if dir doesn't exist, create it
# move file_name to dir
You're doing a lot of intermediate work that seems to be confusing you.
Also, insert some simple print statements to track data flow and execution flow. It appears that you have no tracing output so far.
You can do it with os module. For every file in directory check if associated folder exists, create if needed and then move the file. See the code below:
import os
SRC = 'path-to-src'
for fname in os.listdir(SRC):
filename, file_extension = os.path.splitext(fname)
if file_extension not in ['xml', 'txt']:
continue
folder_path = os.path.join(SRC, filename)
if not os.path.exists(folder_path):
os.mkdir(folderpath)
os.rename(
os.path.join(SRC, fname),
os.path.join(folder_path, fname)
)
My approach would be:
Find the pairs that I want to move (do nothing with files without a pair)
Create a directory for every pair
Move the pair to the directory
#! /usr/bin/env python
# -*- coding: utf-8 -*-
import os, shutil
import re
def getPairs(files):
pairs = []
file_re = re.compile(r'^(.*)\.(.*)$')
for f in files:
match = file_re.match(f)
if match:
(name, ext) = match.groups()
if ext == 'txt' and name + '.xml' in files:
pairs.append(name)
return pairs
def movePairsToDir(pairs):
for name in pairs:
os.mkdir(name)
shutil.move(name+'.txt', name)
shutil.move(name+'.xml', name)
files = os.listdir()
pairs = getPairs(files)
movePairsToDir(pairs)
NOTE: This script works when called inside the directory with the pairs.

Locating files by name for copying elsewhere

New to Python...
I'm trying to have python take a text file of file names (new name on each row), and store them as strings ...
i.e
import os, shutil
files_to_find = []
with open('C:\\pathtofile\\lostfiles.txt') as fh:
for row in fh:
files_to_find.append(row.strip)
...in order to search for these files in directories and then copy any found files somewhere else...
for root, dirs, files in os.walk('D:\\'):
for _file in files:
if _file in files_to_find:
print ("Found file in: " + str(root))
shutil.copy(os.path.abspath(root + '/' + _file), 'C:\\destination')
print ("process completed")
Despite knowing these files exist, the script runs without any errors but without finding any files.
I added...
print (files_to_find)
...after the first block of code to see if it was finding anything and saw screeds of "built-in method strip of str object at 0x00000000037FC730>,
Does this tell me it's not successfully creating strings to compare file names against? I wonder where I'm going wrong?
Use array to create a list of files.
import os
import sys
import glob
import shutil
def file_names(self,filepattern,dir):
os.chdir(dir)
count = len(glob.glob(filepattern))
file_list = []
for line in sorted(glob.glob(filepattern)):
line = line.split("/")
line = line[-1]
file_list.append(line)
return file_list
The loop over the array list to compare.

How can I iterate over files in a given directory?

I need to iterate through all .asm files inside a given directory and do some actions on them.
How can this be done in a efficient way?
Python 3.6 version of the above answer, using os - assuming that you have the directory path as a str object in a variable called directory_in_str:
import os
directory = os.fsencode(directory_in_str)
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith(".asm") or filename.endswith(".py"):
# print(os.path.join(directory, filename))
continue
else:
continue
Or recursively, using pathlib:
from pathlib import Path
pathlist = Path(directory_in_str).glob('**/*.asm')
for path in pathlist:
# because path is object not string
path_in_str = str(path)
# print(path_in_str)
Use rglob to replace glob('**/*.asm') with rglob('*.asm')
This is like calling Path.glob() with '**/' added in front of the given relative pattern:
from pathlib import Path
pathlist = Path(directory_in_str).rglob('*.asm')
for path in pathlist:
# because path is object not string
path_in_str = str(path)
# print(path_in_str)
Original answer:
import os
for filename in os.listdir("/path/to/dir/"):
if filename.endswith(".asm") or filename.endswith(".py"):
# print(os.path.join(directory, filename))
continue
else:
continue
This will iterate over all descendant files, not just the immediate children of the directory:
import os
for subdir, dirs, files in os.walk(rootdir):
for file in files:
#print os.path.join(subdir, file)
filepath = subdir + os.sep + file
if filepath.endswith(".asm"):
print (filepath)
You can try using glob module:
import glob
for filepath in glob.iglob('my_dir/*.asm'):
print(filepath)
and since Python 3.5 you can search subdirectories as well:
glob.glob('**/*.txt', recursive=True) # => ['2.txt', 'sub/3.txt']
From the docs:
The glob module finds all the pathnames matching a specified pattern according to the rules used by the Unix shell, although results are returned in arbitrary order. No tilde expansion is done, but *, ?, and character ranges expressed with [] will be correctly matched.
Since Python 3.5, things are much easier with os.scandir() and 2-20x faster (source):
with os.scandir(path) as it:
for entry in it:
if entry.name.endswith(".asm") and entry.is_file():
print(entry.name, entry.path)
Using scandir() instead of listdir() can significantly increase the
performance of code that also needs file type or file attribute
information, because os.DirEntry objects expose this information if
the operating system provides it when scanning a directory. All
os.DirEntry methods may perform a system call, but is_dir() and
is_file() usually only require a system call for symbolic links;
os.DirEntry.stat() always requires a system call on Unix but only
requires one for symbolic links on Windows.
Python 3.4 and later offer pathlib in the standard library. You could do:
from pathlib import Path
asm_pths = [pth for pth in Path.cwd().iterdir()
if pth.suffix == '.asm']
Or if you don't like list comprehensions:
asm_paths = []
for pth in Path.cwd().iterdir():
if pth.suffix == '.asm':
asm_pths.append(pth)
Path objects can easily be converted to strings.
Here's how I iterate through files in Python:
import os
path = 'the/name/of/your/path'
folder = os.fsencode(path)
filenames = []
for file in os.listdir(folder):
filename = os.fsdecode(file)
if filename.endswith( ('.jpeg', '.png', '.gif') ): # whatever file types you're using...
filenames.append(filename)
filenames.sort() # now you have the filenames and can do something with them
NONE OF THESE TECHNIQUES GUARANTEE ANY ITERATION ORDERING
Yup, super unpredictable. Notice that I sort the filenames, which is important if the order of the files matters, i.e. for video frames or time dependent data collection. Be sure to put indices in your filenames though!
You can use glob for referring the directory and the list :
import glob
import os
#to get the current working directory name
cwd = os.getcwd()
#Load the images from images folder.
for f in glob.glob('images\*.jpg'):
dir_name = get_dir_name(f)
image_file_name = dir_name + '.jpg'
#To print the file name with path (path will be in string)
print (image_file_name)
To get the list of all directory in array you can use os :
os.listdir(directory)
I'm not quite happy with this implementation yet, I wanted to have a custom constructor that does DirectoryIndex._make(next(os.walk(input_path))) such that you can just pass the path you want a file listing for. Edits welcome!
import collections
import os
DirectoryIndex = collections.namedtuple('DirectoryIndex', ['root', 'dirs', 'files'])
for file_name in DirectoryIndex(*next(os.walk('.'))).files:
file_path = os.path.join(path, file_name)
I really like using the scandir directive that is built into the os library. Here is a working example:
import os
i = 0
with os.scandir('/usr/local/bin') as root_dir:
for path in root_dir:
if path.is_file():
i += 1
print(f"Full path is: {path} and just the name is: {path.name}")
print(f"{i} files scanned successfully.")
Get all the .asm files in a directory by doing this.
import os
path = "path_to_file"
file_type = '.asm'
for filename in os.listdir(path=path):
if filename.endswith(file_type):
print(filename)
print(f"{path}/{filename}")
# do something below
I don't understand why some answers are complicated. This is how I would do it with Python 2.7. Replace DIRECTORY_TO_LOOP with the directory you want to use.
import os
DIRECTORY_TO_LOOP = '/var/www/files/'
for root, dirs, files in os.walk(DIRECTORY_TO_LOOP, topdown=False):
for name in files:
print(os.path.join(root, name))

Categories