python文件操作（明细）

1
2
3
import sys
print(sys.getdefaultencoding())

1
2
3
utf-8
#type : str

1
2
open('XXX', encoding='utf-8')

1
2
3
4
5
f = open('XXX.txt', 'r', encoding='ascill', errors='replace)
f.read()
#####
g = open('XXX.txt', 'w', encoding='ascill', errors='ignore')

1
2
3
with open('', 'w') as fp:
	print('hello world', file=fp)

1
2
3
#使用该函数需要经过特殊的处理
print(','.join(str(x) for x in row))

1
2
3
4
b = b'Hello World'
for c in b:
	print(c)

1
2
3
4
5
6
7
with open('somefile.bin', 'rb') as f:    
	data = f.read(16)   
    text = data.decode('utf-8')
with open('somefile.bin', 'wb') as f:    
	text = 'Hello World'    
	f.write(text.encode('utf-8'))

1
2
3
4
5
6
7
import os
if not os.path.exits('somefile')
	with open('somefile', 'w') as f:
		f.write('whllo world')
else:
	print('File')

1
2
3
4
5
6
import io
s = io.StringIO()
s.write('hello world')
print('This is a test')
s.getvalue()

1
2
3
4
5
6
>>> s = io.StringIO('HellonWorldn') 
>>>> s.read(4) 
'Hell' 
>>>> s.read() 
>'onWorldn' 

1
2
3
4
5
>>> s = io.BytesIO() 
>>> s.write(b'binary data') 
>>> s.getvalue() 
b'binary data

1
2
3
4
5
6
7
8
import gzip 
with gzip.open('somefile.gz', 'rt') as f:    
	text = f.read()
# bz2 compression 
import bz2 
with bz2.open('somefile.bz2', 'rt') as f:    
	text = f.read()

1
2
3
with gzip.open('somefile.gz', 'w', compresslevel=5) as f:
	f.write(text)

1
2
3
4
5
6
7
from functools import partial

RECORD_SIZE = 32
with open('somefile.data', 'rb') as f:
	records = iter(partial(f.read, RECORD_SIZE), b'')
	for r in records:	

1
2
3
4
5
6
7
8
import os.path

def read_into_buffer(filename):#读取文件到缓冲区
	buf = bytearray(os.path.getsize(filename))
	with open(filename, 'rb') ad fp:
		fp.readinto(buf)
	return buf

1
2
3
4
5
6
7
record_size = 32
buf = bytearray(record_size)
with open('somefile', 'rb') as fp:
	n= f.readinto(buf)
	if n < record_size:
		break

1
2
3
4
5
6
7
8
9
>>> buf bytearray(b'Hello World') 
>>> m1 = memoryview(buf) 
>>> m2 = m1[-5:] 
>>> m2 <memory at 0x100681390> 
>>> m2[:] = b'WORLD' 
>>> buf 
bytearray(b'Hello WORLD') 
>>>

1
2
3
4
5
6
7
8
import  os
import mmap

def memory_map(filename, access=mmap.ACCESS_WRITE):
	size = os.path.getsize(filename)
	fd = os.open(filename, os.O_RDWR)
	return mmap.mmap(fd, size, access=access)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
size =1000000
with open('data' ,'wb') as fp:
	f.seek(size-1)
	f.write(b'x00')
#创建一个文件并且扩充到指定的大小
m = memory_map('data')
print(len(m))
print(m[0:10])
print(m[0])
m[0:11] = b'Hello World'
m.close()

with open('data', 'rb') as fp:
    print(fp.read(11))

1
2
3
4
5
1000000
b'x00x00x00x00x00x00x00x00x00x00'
0
b'Hello World'

1
2
3
4
5
6
7
8
9
10
11
12
13
14
import os
path = '/Users/Data/data.csv'
os.path.basename(path)
#data.csv
os.path.dirname(path)#获取目录名
#/Users/Data
os.path.join('tmp', 'data', os.path.basename(path))#将路径组件连接在一起
#tmp/data/data.csv
path = '~/Data/data.csv'
os.path.expanduser(path)#展开用户的主目录
#C:Userslenovo/Data/data.csv
os.path.splitext(path)#拆分文件扩展名
#('~/Data/data', '.csv')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
import os
os.path.exists('ppt.py')
#True
####
###还可以判断文件类型
####
os.path.isfile('ppt.py')#是常规文件
#True
os.path.iddir('ppt.py')#是目录
#False
os.path.islink("/usr/local/bin/python3")#是一个符号链接
#True
os.path.realpath('/usr/local/bin/python3')#将文件链接到
#'/usr/local/bin/python3.3'

1
2
3
4
5
6
os.path.getsize('ppt.py')
#909
import time
print(time.ctime(os.path.getmtime('ppt.py')))
#Wed May 22 13:41:01 2019

1
2
3
4
5
import os
names = os.listdir('class_work')
print(names)
#['data', 'data.txt', 'exal.py', 'input_class.py', 'ppt.py', 'tang', 'word.py', '__init__.py', '__pycache__']

1
2
3
4
5
6
7
import os.path

names = [name for name in os.listdir('class_work')
if os.path.isfile(os.path.join('somedir', name))]#得到所有的正确格式的文件。
dirnames = [name for name in os.listdir('somedir')       
 if os.path.isdir(os.path.join('somedir', name))]#得到所有的文件目录

1
2
pyfiles = [name for name in os.listdir('somedir')            if name.endswith('.py')]

1
2
3
4
5
6
7
import glob
pyfiles = glob.glob('somedir/*.py')

from fnmatch import fnmatch
pyfiles = [name for name in os.listdir('somedir')
if fnmatch(name, '*.py')]

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
import os
import os.path
import glob
pyfiles = glob.glob('*.py')#会匹配当前目录中的所有文件名
# Get file sizes and modification dates
name_sz_date = [(name, os.path.getsize(name), os.path.getmtime(name))
                for name in pyfiles]
for name, size, mtime in name_sz_date:
    print(name, size, mtime)

# Alternative: Get file metadata
file_metadata = [(name, os.stat(name)) for name in pyfiles]
for name, meta in file_metadata:
    print(name, meta.st_size, meta.st_mtime)
#os.stat()返回一个包含文件内容和文件时间。

1
2
3
4
5
6
7
8
9
10
11
12
>>> Directory listing (decoded) 
>>> import os 
>>> os.listdir('.') 
['jalapeño.txt']
>>> # Directory listing (raw) 
>>> os.listdir(b'.') # Note: byte string 
[b'jalapenxccx83o.txt']
>>> # Open file with raw filename 
>>> with open(b'jalapenxccx83o.txt') as fp: 
     	print(f.read()) 
 Spicy! 

1
2
3
4
5
6
7
def bad_filename(filename):    
	return repr(filename)[1:-1]
try:    
	print(filename) 
except UnicodeEncodeError:    
	print(bad_filename(filename))

1
2
3
4
5
>>>import os 
>>>files = os.listdir('.')
>>>files
['spam.py', 'budce4d.txt', 'foo.txt']

1
2
3
4
5
6
7
>>> for name in files:      
	print(name) 
spam.py
Traceback (most recent call last):    
File "<stdin>", line 2, in <module> 
UnicodeEncodeError: 'utf-8' codec can't encode character'udce4' in position 1: surrogates not allowed 

1
2
3
4
5
6
7
8
9
>>> for name in files: 
	try: 
	 	print(name) 
	except UnicodeEncodeError: 
	    print(bad_filename(name))
spam.py 
budce4d.txt 
foo.txt 

1
2
3
4
def bad_filename(filename):    
	temp = filename.encode(sys.getfilesystemencoding(),errors='surrogateescape')    
	return temp.decode('latin-1')