python操作文件，文件夹

前言： 当当当~转载stackoverflow上的答案，学习python操作文件，文件夹的一些栗子。这对于读取文件蛮有用的。这里说明一下，我只记录了python3的。

正文：
os.listdir(): get files in current dir (Python 3)

>>> import os
>>> arr = os.listdir()
>>> arr
['$RECYCLE.BIN', 'work.txt', '3ebooks.txt', 'documents']

To go up in the directory tree

>>> # method 1
>>> x = os.listdir('..')

# method 2
>>> x= os.listdir('/')

get files: os.listdir() in a particular directory (Python 2 and 3)

>>> import os
>>> arr = os.listdir('F:\\python')
>>> arr
['$RECYCLE.BIN', 'work.txt', '3ebooks.txt', 'documents']

Get files of a particular subdirectory with os.listdir()

import os

x = os.listdir("./content")
os.walk('.') - current directory

>>> import os
>>> arr = next(os.walk('.'))[2]
>>> arr
['5bs_Turismo1.pdf', '5bs_Turismo1.pptx', 'esperienza.txt']

glob module - all files

import glob
print(glob.glob("*"))

out:['content', 'start.py']

next(os.walk(‘.’)) and os.path.join(‘dir’,’file’)

>>> import os
>>> arr = []
>>> for d,r,f in next(os.walk("F:\_python)):
>>>     for file in f:
>>>         arr.append(os.path.join(r,file))
...
>>> for f in arr:
>>>     print(files)

>output

F:\\_python\\dict_class.py
F:\\_python\\programmi.txt

next(os.walk(‘F:\’) - get the full path - list comprehension

>>> [os.path.join(r,file) for r,d,f in next(os.walk("F:\\_python")) for file in f]
['F:\\_python\\dict_class.py', 'F:\\_python\\programmi.txt']
os.walk - get full path - all files in sub dirs

x = [os.path.join(r,file) for r,d,f in os.walk("F:\\_python") for file in f]

>>>x
['F:\\_python\\dict.py', 'F:\\_python\\progr.txt', 'F:\\_python\\readl.py']

os.listdir() - get only txt files

>>> arr_txt = [x for x in os.listdir() if x.endswith(".txt")]
>>> print(arr_txt)
['work.txt', '3ebooks.txt']

glob - get only txt files

>>> import glob
>>> x = glob.glob("*.txt")
>>> x
['ale.txt', 'alunni2015.txt', 'assenze.text.txt', 'text2.txt', 'untitled.txt']

Using glob to get the full path of the files

If I should need the absolute path of the files:

>>> from path import path
>>> from glob import glob
>>> x = [path(f).abspath() for f in glob("F:\*.txt")]
>>> for f in x:
...  print(f)
...
F:\acquistionline.txt
F:\acquisti_2018.txt
F:\bootstrap_jquery_ecc.txt

Other use of glob

If I want all the files in the directory:

>>> x = glob.glob("*")
Using os.path.isfile to avoid directories in the list*

import os.path
listOfFiles = [f for f in os.listdir() if os.path.isfile(f)]
print(listOfFiles)

> output

['a simple game.py', 'data.txt', 'decorator.py']

Using pathlib from (Python 3.4)

import pathlib

>>> flist = []
>>> for p in pathlib.Path('.').iterdir():
...  if p.is_file():
...   print(p)
...   flist.append(p)
...
error.PNG
exemaker.bat
guiprova.mp3
setup.py
speak_gui2.py
thumb.PNG

If you want to use list comprehension

>>> flist = [p for p in pathlib.Path('.').iterdir() if p.is_file()]

Get all and only files with os.walk

import os
x = [i[2] for i in os.walk('.')]
y=[]
for t in x:
    for f in t:
        y.append(f)

>>> y
['append_to_list.py', 'data.txt', 'data1.txt', 'data2.txt', 'data_180617', 'os_walk.py', 'READ2.py', 'read_data.py', 'somma_defaltdic.py', 'substitute_words.py', 'sum_data.py', 'data.txt', 'data1.txt', 'data_180617']

Get only files with next and walk in a directory

>>> import os
>>> x = next(os.walk('F://python'))[2]
>>> x
['calculator.bat','calculator.py']

Get only directories with next and walk in a directory

>>> import os
>>> next(os.walk('F://python'))[1] # for the current dir use ('.')
['python3','others']

**Get all the subdir names with walk

>>> for r,d,f in os.walk("F:\_python"):
...  for dirs in d:
...   print(dirs)
...
.vscode
pyexcel
pyschool.py
subtitles
_metaprogramming
.ipynb_checkpoints


os.scandir() from python 3.5 on

>>> import os
>>> x = [f.name for f in os.scandir() if f.is_file()]
>>> x
['calculator.bat','calculator.py']

# Another example with scandir (a little variation from docs.python.org)
# This one is more efficient than os.listdir. 
# In this case, it shows the files only in the current directory 
# where the script is executed.

>>> import os
>>> with os.scandir() as i:
...  for entry in i:
...   if entry.is_file():
...    print(entry.name)
...
ebookmaker.py
error.PNG
exemaker.bat
guiprova.mp3
setup.py
speakgui4.py
speak_gui2.py
speak_gui3.py
thumb.PNG
>>>

How many files are there in the subdirectories?
In this example, we look for the number of files that are included in all the directory and its subdirectories.

import os

def count(dir, counter=0):
    "returns number of files in dir and subdirs"
    for pack in os.walk(dir):
        for f in pack[2]:
            counter += 1
    return dir + " : " + str(counter) + "files"


print(count("F:\\python"))

> output

>'F:\\\python' : 12057 files'

How to copy all files from a dir to another?
A script to make order in your computer finding all files of a type (default: pptx) and copying them in a new folder.

import shutil
from path import path

destination = "F:\\file_copied"
# os.makedirs(destination)


def copyfile(dir, filetype='pptx', counter=0):
    "Searches for pptx (or other - pptx is the default) files and copies them"
    for pack in os.walk(dir):
        for f in pack[2]:
            if f.endswith(filetype):
                fullpath = pack[0] + "\\" + f
                print(fullpath)
                shutil.copy(fullpath, destination)
                counter += 1
    if counter > 0:
        print("------------------------")
        print("\t==> Found in: `" + dir + "` : " + str(counter) + " files\n")


for dir in os.listdir():
    "searches for folders that starts with `_`"
    if dir[0] == '_':
        # copyfile(dir, filetype='pdf')
        copyfile(dir, filetype='txt')


> Output

_compiti18\Compito Contabilità 1\conti.txt
_compiti18\Compito Contabilità 1\modula4.txt
_compiti18\Compito Contabilità 1\moduloa4.txt
------------------------
==> Found in: `_compiti18` : 3 files