Python标准库学习笔记

操作系统接口

通过导入：

import os

比较有用的方法为：

os.system('shell command')

调用了shell命令

此外，dir()和help()将帮助学习模块的方法。

跟文件有关的操作需要导入：

>>> import shutil
>>> shutil.copyfile('data.db', 'archive.db')
>>> shutil.move('/build/executables', 'installdir')

文件通配符号

glob模块提供文件查找的功能。

>>> import glob
>>> glob.glob('*.py')
['primes.py', 'random.py', 'quote.py']

操作系统参数

通过导入：

import sys

>>> import sys
>>> print sys.argv
['demo.py', 'one', 'two', 'three']

标准错误输出

>>> sys.stderr.write('Warning, log file not found starting a new one\n')
Warning, log file not found starting a new one

The most direct way to terminate a script is to use sys.exit().

字符串模式匹配

通过导入：

import re

>>> import re
>>> re.findall(r'\bf[a-z]*', 'which foot or hand fell fastest')
['foot', 'fell', 'fastest']
>>> re.sub(r'(\b[a-z]+) \1', r'\1', 'cat in the the hat')
'cat in the hat'

#just string methos
>>> 'tea for too'.replace('too', 'two')
'tea for two'

数学相关

很简单：

>>> import math
>>> math.cos(math.pi / 4.0)
0.70710678118654757
>>> math.log(1024, 2)
10.0

>>> import random
>>> random.choice(['apple', 'pear', 'banana'])
'apple'
>>> random.sample(xrange(100), 10)   # sampling without replacement
[30, 83, 16, 4, 8, 81, 41, 50, 18, 33]
>>> random.random()    # random float
0.17970987693706186
>>> random.randrange(6)    # random integer chosen from range(6)
4

网络读取

>>> import urllib2
>>> for line in urllib2.urlopen('http://tycho.usno.navy.mil/cgi-bin/timer.pl'):
    ...     if 'EST' in line or 'EDT' in line:  # look for Eastern Time
    ...         print line

    <BR>Nov. 25, 09:43:32 PM EST

    >>> import smtplib
    >>> server = smtplib.SMTP('localhost')
    >>> server.sendmail('[email protected]', '[email protected]',
                        ... """To: [email protected]
                        ... From: [email protected]
                        ...
                        ... Beware the Ides of March.
                        ... """)
    >>> server.quit()

日期和时间

>>> # dates are easily constructed and formatted
>>> from datetime import date
>>> now = date.today()
>>> now
datetime.date(2003, 12, 2)
>>> now.strftime("%m-%d-%y. %d %b %Y is a %A on the %d day of %B.")
'12-02-03. 02 Dec 2003 is a Tuesday on the 02 day of December.'

>>> # dates support calendar arithmetic
>>> birthday = date(1964, 7, 31)
>>> age = now - birthday
>>> age.days
14368

数据压缩

>>> import zlib
>>> s = 'witch which has which witches wrist watch'
>>> len(s)
41
>>> t = zlib.compress(s)
>>> len(t)
37
>>> zlib.decompress(t)
'witch which has which witches wrist watch'
>>> zlib.crc32(s)
226805979

性能测量

>>> from timeit import Timer
>>> Timer('t=a; a=b; b=t', 'a=1; b=2').timeit()
0.57535828626024577
>>> Timer('a,b = b,a', 'a=1; b=2').timeit()
0.54962537085770791

质量控制-也就是QC

def average(values):
        """Computes the arithmetic mean of a list of numbers.

            >>> print average([20, 30, 70])
                40.0
                    """
                        return sum(values, 0.0) / len(values)

                    import doctest
                    doctest.testmod()   # automatically validate the embedded tests

import unittest

class TestStatisticalFunctions(unittest.TestCase):

        def test_average(self):
                    self.assertEqual(average([20, 30, 70]), 40.0)
                            self.assertEqual(round(average([1, 5, 7]), 1), 4.3)
                                    with self.assertRaises(ZeroDivisionError):
                                                    average([])
                                                            with self.assertRaises(TypeError):
                                                                            average(20, 30, 70)

                                                                            unittest.main() # Calling from the command line invokes all tests

输出格式化

>>> import repr
>>> repr.repr(set('supercalifragilisticexpialidocious'))
"set(['a', 'c', 'd', 'e', 'f', 'g', ...])"

>>> import pprint
>>> t = [[[['black', 'cyan'], 'white', ['green', 'red']], [['magenta',
                                                            ...     'yellow'], 'blue']]]
...
>>> pprint.pprint(t, width=30)
[[[['black', 'cyan'],
      'white',
      ['green', 'red']],
    [['magenta', 'yellow'],
        'blue']]]


>>> import textwrap
>>> doc = """The wrap() method is just like fill() except that it returns
... a list of strings instead of one big string with newlines to separate
... the wrapped lines."""
...
>>> print textwrap.fill(doc, width=40)
The wrap() method is just like fill()
except that it returns a list of strings
instead of one big string with newlines
to separate the wrapped lines.

模板

字符串提供了一个通用的模板类，可以在使用的才确定字符串内的内容。

>>> from string import Template
>>> t = Template('${village}folk send $$10 to $cause.')
>>> t.substitute(village='Nottingham', cause='the ditch fund')
'Nottinghamfolk send $10 to the ditch fund.'

>>> t = Template('Return the $item to $owner.')
>>> d = dict(item='unladen swallow')
>>> t.substitute(d)
Traceback (most recent call last):
    ...
KeyError: 'owner'
>>> t.safe_substitute(d)
'Return the unladen swallow to $owner.'

二进制数据记录布局的工作

看这个例子：

import struct

data = open('myfile.zip', 'rb').read()
start = 0
for i in range(3):                      # show the first 3 file headers
    start += 14
        fields = struct.unpack('<IIIHH', data[start:start+16])
            crc32, comp_size, uncomp_size, filenamesize, extra_size = fields

                start += 16
                    filename = data[start:start+filenamesize]
                        start += filenamesize
                            extra = data[start:start+extra_size]
                                print filename, hex(crc32), comp_size, uncomp_size

                                    start += extra_size + comp_size     # skip to the next header

多线程

import threading, zipfile

class AsyncZip(threading.Thread):
        def __init__(self, infile, outfile):
                    threading.Thread.__init__(self)
                            self.infile = infile
                                    self.outfile = outfile
                                        def run(self):
                                                    f = zipfile.ZipFile(self.outfile, 'w', zipfile.ZIP_DEFLATED)
                                                            f.write(self.infile)
                                                                    f.close()
                                                                            print 'Finished background zip of: ', self.infile

                                                                            background = AsyncZip('mydata.txt', 'myarchive.zip')
                                                                            background.start()
                                                                            print 'The main program continues to run in foreground.'

                                                                            background.join()    # Wait for the background task to finish
                                                                            print 'Main program waited until background was done.'

日志相关

import logging
logging.debug('Debugging information')
logging.info('Informational message')
logging.warning('Warning:config file %s not found', 'server.conf')
logging.error('Error occurred')
logging.critical('Critical error -- shutting down')

弱引用

>>> import weakref, gc
>>> class A:
    ...     def __init__(self, value):
        ...         self.value = value
        ...     def __repr__(self):
            ...         return str(self.value)
            ...
            >>> a = A(10)                   # create a reference
            >>> d = weakref.WeakValueDictionary()
            >>> d['primary'] = a            # does not create a reference
            >>> d['primary']                # fetch the object if it is still alive
            10
            >>> del a                       # remove the one reference
            >>> gc.collect()                # run garbage collection right away
            0
            >>> d['primary']                # entry was automatically removed
            Traceback (most recent call last):
                  File "<stdin>", line 1, in <module>
                      d['primary']                # entry was automatically removed
                        File "C:/python26/lib/weakref.py", line 46, in __getitem__
                            o = self.data[key]()
                            KeyError: 'primary'

针对list的工作工具

比如说：
array
connection
biset
heapq

分别举例：

>>> from array import array
>>> a = array('H', [4000, 10, 700, 22222])
>>> sum(a)
26932
>>> a[1:3]
array('H', [10, 700])

>>> from collections import deque
>>> d = deque(["task1", "task2", "task3"])
>>> d.append("task4")
>>> print "Handling", d.popleft()
Handling task1

unsearched = deque([starting_node])
def breadth_first_search(unsearched):
        node = unsearched.popleft()
            for m in gen_moves(node):
                        if is_goal(m):
                                        return m
                                            unsearched.append(m)

>>> import bisect
>>> scores = [(100, 'perl'), (200, 'tcl'), (400, 'lua'), (500, 'python')]
>>> bisect.insort(scores, (300, 'ruby'))
>>> scores
[(100, 'perl'), (200, 'tcl'), (300, 'ruby'), (400, 'lua'), (500, 'python')]

>>> from heapq import heapify, heappop, heappush
>>> data = [1, 3, 5, 7, 9, 2, 4, 6, 8, 0]
>>> heapify(data)                      # rearrange the list into heap order
>>> heappush(data, -5)                 # add a new entry
>>> [heappop(data) for i in range(3)]  # fetch the three smallest entries
[-5, 0, 1]

十进制浮点数运算

>>> from decimal import *
>>> x = Decimal('0.70') * Decimal('1.05')
>>> x
Decimal('0.7350')
>>> x.quantize(Decimal('0.01'))  # round to nearest cent
Decimal('0.74')
>>> round(.70 * 1.05, 2)         # same calculation with floats
0.73

>>> Decimal('1.00') % Decimal('.10')
Decimal('0.00')
>>> 1.00 % 0.10
0.09999999999999995

>>> sum([Decimal('0.1')]*10) == Decimal('1.0')
True
>>> sum([0.1]*10) == 1.0
False

>>> getcontext().prec = 36
>>> Decimal(1) / Decimal(7)
Decimal('0.142857142857142857142857142857142857')