python处理技巧_Python小技巧1

一. 打印并输出到文件

>>> print("aa","bb","11","ddddd",sep='-',end='ok/t',file=open("c:/test.txt",'w'))

>>> print("-" *40)#打印40个"-">>> print("aa","bb","11","ddddd",sep='-',end='ok/t',file=open("c:/test.txt",'w'))

>>> print("-" *40)#打印40个"-"

二. 打印字典的值

>>> d = {"a":1,"b":2}

>>> print('%(a)s...%(b)s' %d)

1...2

>>> s = ('%(a)s...%(b)s' %d)

>>> s

'1...2'

>>> s = ['%(a)s...%(b)s' %d]

>>> s

['1...2']

>>> print("%(__builtins__)s...%(d)s" %vars())

...{'a': 1, 'b': 2}

>>> vars()

{'__builtins__': , '__name__': '__main__', '__doc__': None, 'd': {'a': 1, 'b': 2}, '__package__': None}

>>> locals()

{'__builtins__': , '__name__': '__main__', '__doc__': None, 'd': {'a': 1, 'b': 2}, '__package__': None}

>>> vars() is locals() #vars()无参数的情况等同locals()True

>>> vars() == locals()

True

>>> a = vars()

>>> b = locals()

>>> a is b

True

>>> d = {"a":1,"b":2}

>>> print('%(a)s...%(b)s' %d)

1...2

>>> s = ('%(a)s...%(b)s' %d)

>>> s

'1...2'

>>> s = ['%(a)s...%(b)s' %d]

>>> s

['1...2']

>>> print("%(__builtins__)s...%(d)s" %vars())

...{'a': 1, 'b': 2}

>>> vars()

{'__builtins__': , '__name__': '__main__', '__doc__': None, 'd': {'a': 1, 'b': 2}, '__package__': None}

>>> locals()

{'__builtins__': , '__name__': '__main__', '__doc__': None, 'd': {'a': 1, 'b': 2}, '__package__': None}

>>> vars() is locals() #vars()无参数的情况等同locals()True

>>> vars() == locals()

True

>>> a = vars()

>>> b = locals()

>>> a is b

True

三. pprint整洁打印

>>> import pprint

>>> pprint.pprint(data)

('this is a string',

[1, 2, 3, 4],

('more tuples', 1.0, 2.3, 4.5),

'this is yet another string')

>>> print(data)

('this is a string', [1, 2, 3, 4], ('more tuples', 1.0, 2.3, 4.5), 'this is yet another string')

>>> pp = pprint.PrettyPrinter(indent=4) #缩进4空格>>> pp.pprint(data)

( 'this is a string',

[1, 2, 3, 4],

('more tuples', 1.0, 2.3, 4.5),

'this is yet another string')

>>> import pprint

>>> pprint.pprint(data)

('this is a string',

[1, 2, 3, 4],

('more tuples', 1.0, 2.3, 4.5),

'this is yet another string')

>>> print(data)

('this is a string', [1, 2, 3, 4], ('more tuples', 1.0, 2.3, 4.5), 'this is yet another string')

>>> pp = pprint.PrettyPrinter(indent=4) #缩进4空格>>> pp.pprint(data)

( 'this is a string',

[1, 2, 3, 4],

('more tuples', 1.0, 2.3, 4.5),

'this is yet another string')

四. 打印输出重定向

>>> import sys

>>> sys.stdout = open('c:/log123.txt','w')

>>> print ("aa","bb","1111111112213123")

>>> sys.stdout = sys.__stdout__

>>> import sys

>>> sys.stdout = open('c:/log123.txt','w')

>>> print ("aa","bb","1111111112213123")

>>> sys.stdout = sys.__stdout__

>>> import sys

>>> t = sys.stdout

>>> sys.stdout = open("c:/log123.txt",'w')

>>> print('1234abcd')

>>> sys.stdout = t

>>> print("11")

11

>>>

>>> import sys

>>> t = sys.stdout

>>> sys.stdout = open("c:/log123.txt",'w')

>>> print('1234abcd')

>>> sys.stdout = t

>>> print("11")

11

>>>

五. with方式读取文件直到某行停止

读取文件，直到某一行的文本等于"STOP"停止读取。否则，将一直读取下去。

(注意：停止读取的行文本只能是iter()的第二个参数值，不能包含其他的，空格都不行)

with open("c:/test.txt") as fp:

for line in iter(fp.readline,"STOP"):

print(line)

with open("c:/test.txt") as fp:

for line in iter(fp.readline,"STOP"):

print(line)

六. 搜索目录树中包含有某个字符串的文件名的所有文件列表

>>> import glob

>>> import fileinput

>>> import os

>>> import re

>>> glob.glob("E:/cdr01")

['E:/cdr01']

>>> glob.glob("E:/cdr01/*")#只返回当前cdr01下面的子目录名和文件名(带路径，但不包含目录树中的所有子目录与文件)['E:/cdr01//20110113', 'E:/cdr01//20110114', 'E:/cdr01//20110115', 'E:/cdr01//20110116', 'E:/cdr01//20110117', 'E:/cdr01//20110118', 'E:/cdr01//20110119', 'E:/cdr01//20110120', 'E:/cdr01//20110121', 'E:/cdr01//20110122', 'E:/cdr01//20110123', 'E:/cdr01//20110124', 'E:/cdr01//cdr01.rar']

>>> [(a,b,c) for a , b , c in os.walk("E:/cdr01")] #os.walk返回目录树中的所有目录与文件，他将每一目录的子目录与文件都按一个元组来返回。a代表当前搜索目录(或者子目录)，b代表当前搜索目录下面所包含的子目录列表，c代表当前搜索目录下面的所有文件名列表。(不带路径(但可以通过与元组第一项进行拼接为目录或者文件路径)，并且包含目录树中的所有子目录与文件)[('E:/cdr01', ['20110113', '20110114', '20110115', '20110116', '20110117', '20110118', '20110119', '20110120', '20110121', '20110122', '20110123', '20110124'], ['cdr01.rar']), ('E:/cdr01//20110113', [], ['20110113_6042488744.csv']), ('E:/cdr01//20110114', [], ['20110114_6042488744.csv']), ('E:/cdr01//20110115', [], ['20110115_6042488744.csv']), ('E:/cdr01//20110116', [], ['20110116_6042488744.csv']), ('E:/cdr01//20110117', [], ['20110117_6042488744.csv']), ('E:/cdr01//20110118', [], ['20110118_6042488744.csv']), ('E:/cdr01//20110119', [], ['20110119_6042488744.csv']), ('E:/cdr01//20110120', [], ['20110120_6042488744.csv']), ('E:/cdr01//20110121', [], ['20110121_6042488744.csv']), ('E:/cdr01//20110122', [], ['20110122_6042488744.csv']), ('E:/cdr01//20110123', [], ['20110123_6042488744.csv']), ('E:/cdr01//20110124', [], ['20110124_6042488744.csv'])]

>>> list((os.path.join(a,f)) for a , b , c in os.walk("E:/cdr201101") for f in c if re.search('6042488744',os.path.basename(f))) #E:/cdr201101包含很多CSV文件，此方法将搜索目录树中的文件名包含字符串"6042488744"的文件，并将文件名与路径拼接作为绝对路径返回。['E:/cdr201101//20110113//20110113_6042488744.csv', 'E:/cdr201101//20110114//20110114_6042488744.csv', 'E:/cdr201101//20110115//20110115_6042488744.csv', 'E:/cdr201101//20110116//20110116_6042488744.csv', 'E:/cdr201101//20110117//20110117_6042488744.csv', 'E:/cdr201101//20110118//20110118_6042488744.csv', 'E:/cdr201101//20110119//20110119_6042488744.csv', 'E:/cdr201101//20110120//20110120_6042488744.csv', 'E:/cdr201101//20110121//20110121_6042488744.csv', 'E:/cdr201101//20110122//20110122_6042488744.csv', 'E:/cdr201101//20110123//20110123_6042488744.csv', 'E:/cdr201101//20110124//20110124_6042488744.csv']

>>> import glob

>>> import fileinput

>>> import os

>>> import re

>>> glob.glob("E:/cdr01")

['E:/cdr01']

>>> glob.glob("E:/cdr01/*")#只返回当前cdr01下面的子目录名和文件名(带路径，但不包含目录树中的所有子目录与文件)['E:/cdr01//20110113', 'E:/cdr01//20110114', 'E:/cdr01//20110115', 'E:/cdr01//20110116', 'E:/cdr01//20110117', 'E:/cdr01//20110118', 'E:/cdr01//20110119', 'E:/cdr01//20110120', 'E:/cdr01//20110121', 'E:/cdr01//20110122', 'E:/cdr01//20110123', 'E:/cdr01//20110124', 'E:/cdr01//cdr01.rar']

>>> [(a,b,c) for a , b , c in os.walk("E:/cdr01")] #os.walk返回目录树中的所有目录与文件，他将每一目录的子目录与文件都按一个元组来返回。a代表当前搜索目录(或者子目录)，b代表当前搜索目录下面所包含的子目录列表，c代表当前搜索目录下面的所有文件名列表。(不带路径(但可以通过与元组第一项进行拼接为目录或者文件路径)，并且包含目录树中的所有子目录与文件)[('E:/cdr01', ['20110113', '20110114', '20110115', '20110116', '20110117', '20110118', '20110119', '20110120', '20110121', '20110122', '20110123', '20110124'], ['cdr01.rar']), ('E:/cdr01//20110113', [], ['20110113_6042488744.csv']), ('E:/cdr01//20110114', [], ['20110114_6042488744.csv']), ('E:/cdr01//20110115', [], ['20110115_6042488744.csv']), ('E:/cdr01//20110116', [], ['20110116_6042488744.csv']), ('E:/cdr01//20110117', [], ['20110117_6042488744.csv']), ('E:/cdr01//20110118', [], ['20110118_6042488744.csv']), ('E:/cdr01//20110119', [], ['20110119_6042488744.csv']), ('E:/cdr01//20110120', [], ['20110120_6042488744.csv']), ('E:/cdr01//20110121', [], ['20110121_6042488744.csv']), ('E:/cdr01//20110122', [], ['20110122_6042488744.csv']), ('E:/cdr01//20110123', [], ['20110123_6042488744.csv']), ('E:/cdr01//20110124', [], ['20110124_6042488744.csv'])]

>>> list((os.path.join(a,f)) for a , b , c in os.walk("E:/cdr201101") for f in c if re.search('6042488744',os.path.basename(f))) #E:/cdr201101包含很多CSV文件，此方法将搜索目录树中的文件名包含字符串"6042488744"的文件，并将文件名与路径拼接作为绝对路径返回。['E:/cdr201101//20110113//20110113_6042488744.csv', 'E:/cdr201101//20110114//20110114_6042488744.csv', 'E:/cdr201101//20110115//20110115_6042488744.csv', 'E:/cdr201101//20110116//20110116_6042488744.csv', 'E:/cdr201101//20110117//20110117_6042488744.csv', 'E:/cdr201101//20110118//20110118_6042488744.csv', 'E:/cdr201101//20110119//20110119_6042488744.csv', 'E:/cdr201101//20110120//20110120_6042488744.csv', 'E:/cdr201101//20110121//20110121_6042488744.csv', 'E:/cdr201101//20110122//20110122_6042488744.csv', 'E:/cdr201101//20110123//20110123_6042488744.csv', 'E:/cdr201101//20110124//20110124_6042488744.csv']

七. 字符串转成字节数组，字节数组转成字节串

>>> s = 'abcd123'

>>> b = bytearray(s,sys.stdin.encoding) #sys.stdin.encoding相当于locale.getdefaultlocale()[1]获得当前操作系统的编码方式>>> b

bytearray(b'abcd123')

>>> b = bytes(s,sys.stdin.encoding)

>>> b

b'abcd123'

>>> s = 'abcd123'

>>> b = bytearray(s,sys.stdin.encoding) #sys.stdin.encoding相当于locale.getdefaultlocale()[1]获得当前操作系统的编码方式>>> b

bytearray(b'abcd123')

>>> b = bytes(s,sys.stdin.encoding)

>>> b

b'abcd123'

八. 字符串与字节的编码与解码

>>> a = b'abc'

>>> a.decode() #字节解码为字符串'abc'

>>> b = aa.encode() #字符串编码为字节>>> b

b'abc'

>>>

>>> a = b'abc'

>>> a.decode() #字节解码为字符串'abc'

>>> b = aa.encode() #字符串编码为字节>>> b

b'abc'

>>>

九. 处理zip压缩文件

>>> import zipfile

>>> f = zipfile.ZipFile("E:/CodeBuilder.zip","r")

>>> for name in f.namelist():

data = f.read(name)

print(name,len(data),repr(data[:10]))

>>> f.close()

>>> import zipfile

>>> f = zipfile.ZipFile("E:/CodeBuilder.zip","r")

>>> for name in f.namelist():

data = f.read(name)

print(name,len(data),repr(data[:10]))

>>> f.close()

>>> import zipfile

>>> z = zipfile.ZipFile("E:/test1.zip","w") #创建zip压缩文件包>>> z.write("E:/testSqliteDB.db.txt") #压缩一个txt文件>>> z.close()

>>> z = zipfile.ZipFile("E:/test1.zip","r") #读取zip压缩文件包>>> z.extractall()#解压到当前目录，extract可以具体指定解压哪个文件到哪个目录>>> z.extractall("E:/123/")#解压到指定目录>>> z.close()

>>> import os

>>> os.getcwd() #getcwd()可以查看解压的当前目录位置'C://Python31'

>>> import zipfile

>>> z = zipfile.ZipFile("E:/test1.zip","w") #创建zip压缩文件包>>> z.write("E:/testSqliteDB.db.txt") #压缩一个txt文件>>> z.close()

>>> z = zipfile.ZipFile("E:/test1.zip","r") #读取zip压缩文件包>>> z.extractall()#解压到当前目录，extract可以具体指定解压哪个文件到哪个目录>>> z.extractall("E:/123/")#解压到指定目录>>> z.close()

>>> import os

>>> os.getcwd() #getcwd()可以查看解压的当前目录位置'C://Python31'

十. glob遍历文件夹下面的所有文件并读取内容

>>> import fileinput

>>> import glob

>>> for line in fileinput.input(glob.glob("E:/TestFolder/*.txt")):

print("File name:" + fileinput.filename() + "line length:" + str(len(line)))

>>> fileinput.close()

>>> import fileinput

>>> import glob

>>> for line in fileinput.input(glob.glob("E:/TestFolder/*.txt")):

print("File name:" + fileinput.filename() + "line length:" + str(len(line)))

>>> fileinput.close()

十一. shutil拷贝目录树

>>> import shutil

>>> shutil.copytree("E:/TestFolder","F:/TestFolder-bak")

>>> shutil.copytree("E:/TestFolder","xx") #在TestFolder文件夹里面创建XX目录，并拷贝TestFolder目录到XX目录>>> import shutil

>>> shutil.copytree("E:/TestFolder","F:/TestFolder-bak")

>>> shutil.copytree("E:/TestFolder","xx") #在TestFolder文件夹里面创建XX目录，并拷贝TestFolder目录到XX目录

十二. 获得文件大小的两种方式(二进制读取)

>>> import os

>>> os.stat(f).st_size

4753

>>> os.path.getsize(f)

4753

>>> import os

>>> os.stat(f).st_size

4753

>>> os.path.getsize(f)

4753

十三. mmap 模块提供了操作系统内存映射函数的接口,可以映射字符串与文件内容

可以执行譬如查找、统计、写入等一些操作，但就是基于字节的。

>>> map = mmap.mmap(-1,13)

>>> map.write(b"Hello world!")

>>> map.readline()

b'/x00'

>>> map.seek(0)

>>> map.readline()

b'Hello world!/x00'

>>> map.seek(0)

>>> map.find(b'w')

6

>>> map.close()

>>> map = mmap.mmap(-1,13)

>>> map.write(b"Hello world!")

>>> map.readline()

b'/x00'

>>> map.seek(0)

>>> map.readline()

b'Hello world!/x00'

>>> map.seek(0)

>>> map.find(b'w')

6

>>> map.close()

十四. dis反编译对象为字节码

>>> import dis

>>> def showMsg(xx):

print("abc")

>>> dis.dis(showMsg)

2 0 LOAD_GLOBAL 0 (print)

3 LOAD_CONST 1 ('abc')

6 CALL_FUNCTION 1

9 POP_TOP

10 LOAD_CONST 0 (None)

13 RETURN_VALUE

>>> import dis

>>> def showMsg(xx):

print("abc")

>>> dis.dis(showMsg)

2 0 LOAD_GLOBAL 0 (print)

3 LOAD_CONST 1 ('abc')

6 CALL_FUNCTION 1

9 POP_TOP

10 LOAD_CONST 0 (None)

13 RETURN_VALUE

十五。profile 与 cProfile分析程序执行性能

profile 模块是标准 Python 分析器，用Python写的。

而cProfile是用C写的，运行起来比profile快，官方推荐用cProfile.

pstats可以处理分析报告。

>>> import profile

>>> def testss(n):

i = 0

for i in range(n):

i = i + 1

return i

>>> profile.run("testss(1000000)")

5 function calls in 0.269 CPU seconds

Ordered by: standard name

ncalls tottime percall cumtime percall filename:lineno(function)

1 0.000 0.000 0.266 0.266 :0(exec)

1 0.002 0.002 0.002 0.002 :0(setprofile)

1 0.266 0.266 0.266 0.266 :1(testss) 1 0.000 0.000 0.266 0.266 :1()

0 0.000 0.000 profile:0(profiler)

1 0.000 0.000 0.269 0.269 profile:0(testss(1000000))

>>> import cProfile

>>> cProfile.run("testss(1000000)") #分析速度快些 4 function calls in 0.212 CPU seconds

Ordered by: standard name

ncalls tottime percall cumtime percall filename:lineno(function)

1 0.212 0.212 0.212 0.212 :1(testss) 1 0.000 0.000 0.212 0.212 :1()

1 0.000 0.000 0.212 0.212 {built-in method exec}

1 0.000 0.000 0.000 0.000 {method 'disable' of '_lsprof.Profiler' objects}

>>> import profile

>>> def testss(n):

i = 0

for i in range(n):

i = i + 1

return i

>>> profile.run("testss(1000000)")

5 function calls in 0.269 CPU seconds

Ordered by: standard name

ncalls tottime percall cumtime percall filename:lineno(function)

1 0.000 0.000 0.266 0.266 :0(exec)

1 0.002 0.002 0.002 0.002 :0(setprofile)

1 0.266 0.266 0.266 0.266 :1(testss) 1 0.000 0.000 0.266 0.266 :1()

0 0.000 0.000 profile:0(profiler)

1 0.000 0.000 0.269 0.269 profile:0(testss(1000000))

>>> import cProfile

>>> cProfile.run("testss(1000000)") #分析速度快些 4 function calls in 0.212 CPU seconds

Ordered by: standard name

ncalls tottime percall cumtime percall filename:lineno(function)

1 0.212 0.212 0.212 0.212 :1(testss) 1 0.000 0.000 0.212 0.212 :1()

1 0.000 0.000 0.212 0.212 {built-in method exec}

1 0.000 0.000 0.000 0.000 {method 'disable' of '_lsprof.Profiler' objects}

pstats处理分析报告：

>>> import pstats

>>> pr = profile.Profile()

>>> pr.run("testss(1000000)")

>>> p = pstats.Stats(pr)

>>> pstats = p.sort_stats("time") #按时间排序>>> pstats.print_stats() #打印在profile.run()中形成的分析报告 5 function calls in 38.856 CPU seconds

Ordered by: internal time

ncalls tottime percall cumtime percall filename:lineno(function)

1 25.843 25.843 25.843 25.843 :0(setprofile)

1 12.760 12.760 38.856 38.856 profile:0(testss(1000000))

1 0.253 0.253 0.253 0.253 :1(testss) 1 0.000 0.000 0.253 0.253 :0(exec)

1 0.000 0.000 0.253 0.253 :1()

0 0.000 0.000 profile:0(profiler)

>>> import pstats

>>> pr = profile.Profile()

>>> pr.run("testss(1000000)")

>>> p = pstats.Stats(pr)

>>> pstats = p.sort_stats("time") #按时间排序>>> pstats.print_stats() #打印在profile.run()中形成的分析报告 5 function calls in 38.856 CPU seconds

Ordered by: internal time

ncalls tottime percall cumtime percall filename:lineno(function)

1 25.843 25.843 25.843 25.843 :0(setprofile)

1 12.760 12.760 38.856 38.856 profile:0(testss(1000000))

1 0.253 0.253 0.253 0.253 :1(testss) 1 0.000 0.000 0.253 0.253 :0(exec)

1 0.000 0.000 0.253 0.253 :1()

0 0.000 0.000 profile:0(profiler)