0213-内置模块

collections

namedtuple

>>> from collections import namedtuple
>>> Point = namedtuple('Point', ['x', 'y'])
>>> p = Point(1, 2)
>>> p.x
>>> 1
>>> p.y
>>> 2

deque
支持appendleft()和popleft();

>>> from collections import deque
>>> q = deque(['a', 'b', 'c'])
>>> q.append('x')
>>> q.appendleft('y')
>>> q
deque(['y', 'a', 'b', 'c', 'x'])

defaultdict

>> from collections import defaultdict
>> dd = defaultdict(lambda: 'N/A')
>> dd['key1'] = 'abc'
>> dd['key1'] # key1存在
   'abc'
>> dd['key2'] # key2不存在，返回默认值
   'N/A'

OrderedDict

>>> from collections import OrderedDict
>>> d = dict([('a', 1), ('b', 2), ('c', 3)])
>>> d # dict的Key是无序的
{'a': 1, 'c': 3, 'b': 2}
>>> od = OrderedDict([('a', 1), ('b', 2), ('c', 3)])
>>> od # OrderedDict的Key是有序的
OrderedDict([('a', 1), ('b', 2), ('c', 3)])

ChainMap

from collections import ChainMap
import os, argparse

# 构造缺省参数:
defaults = {
    'color': 'red',
    'user': 'guest'
}

# 构造命令行参数:
parser = argparse.ArgumentParser()
parser.add_argument('-u', '--user')
parser.add_argument('-c', '--color')
namespace = parser.parse_args()
command_line_args = { k: v for k, v in vars(namespace).items() if v }

# 组合成ChainMap:
combined = ChainMap(command_line_args, os.environ, defaults)

# 打印参数:
print('color=%s' % combined['color'])
print('user=%s' % combined['user'])

Counter

>>> from collections import Counter
>>> c = Counter()
>>> for ch in 'programming':
...     c[ch] = c[ch] + 1
...
>>> c
Counter({'g': 2, 'm': 2, 'r': 2, 'a': 1, 'i': 1, 'o': 1, 'n': 1, 'p': 1})
>>> c.update('hello') # 也可以一次性update
>>> c
Counter({'r': 2, 'o': 2, 'g': 2, 'm': 2, 'l': 2, 'p': 1, 'a': 1, 'i': 1, 'n': 1, 'h': 1, 'e': 1})

base64

>>> import base64
>>> base64.b64encode(b'binary\x00string')
b'YmluYXJ5AHN0cmluZw=='
>>> base64.b64decode(b'YmluYXJ5AHN0cmluZw==')
b'binary\x00string'
>>> base64.b64encode(b'i\xb7\x1d\xfb\xef\xff')
b'abcd++//'
>>> base64.urlsafe_b64encode(b'i\xb7\x1d\xfb\xef\xff')
b'abcd--__'
>>> base64.urlsafe_b64decode('abcd--__')
b'i\xb7\x1d\xfb\xef\xff'

struct

>>> import struct
>>> struct.pack('>I', 10240099)
b'\x00\x9c@c'

检查任意文件是否是位图文件，如果是，打印出图片大小和颜色数(只需检测bmp文件)：

# -*- coding: utf-8 -*-
import base64, struct
bmp_data = 图片的base64码
def bmp_info(data):
    s = struct.unpack('<ccIIIIIIHH', data[:30])
    if s[0] == b'B' and s[1] == b'M' :
        print ('这是位图')
        return {
            'width': s[6],
            'height': s[7],
            'color': s[9]
        }

hashlib/哈希算法
用户密码“加盐”存储MD5的作用与方法；

import hashlib

md5 = hashlib.md5()
md5.update('how to use md5 in python hashlib?'.encode('utf-8'))
print(md5.hexdigest())
sha1 = hashlib.sha1()
sha1.update('how to use sha1 in '.encode('utf-8'))
sha1.update('python hashlib?'.encode('utf-8'))
print(sha1.hexdigest())

hmac

>>> import hmac
>>> message = b'Hello, world!'
>>> key = b'secret'
>>> h = hmac.new(key, message, digestmod='MD5')
>>> # 如果消息很长，可以多次调用h.update(msg)
>>> h.hexdigest()
'fa4ee7d173f2d97ee79022d1a7355bcf'

itertools
count()创建一个无限的迭代器，打印出自然数序列:

>>> import itertools
>>> natuals = itertools.count(1)
>>> for n in natuals:
...     print(n)
...
1
2
3
...

cycle()会把传入的一个序列无限重复下去：

>>> import itertools
>>> cs = itertools.cycle('ABC') # 注意字符串也是序列的一种
>>> for c in cs:
...     print(c)
...
'A'
'B'
'C'
'A'
'B'
'C'
...

repeat()负责把一个元素无限重复下去，不过如果提供第二个参数就可以限定重复次数：

>>> ns = itertools.repeat('A', 3)
>>> for n in ns:
...     print(n)
...
A
A
A

takewhile()等函数根据条件判断来截取出一个有限的序列：

>>> natuals = itertools.count(1)
>>> ns = itertools.takewhile(lambda x: x <= 10, natuals)
>>> list(ns)
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

chain()

>>> for c in itertools.chain('ABC', 'XYZ'):
...     print(c)
# 迭代效果：'A' 'B' 'C' 'X' 'Y' 'Z'

groupby()

>>> for key, group in itertools.groupby('AAABBBCCAAA'):
...     print(key, list(group))
...
A ['A', 'A', 'A']
B ['B', 'B', 'B']
C ['C', 'C']
A ['A', 'A', 'A']

忽略大小写分组:

>>> for key, group in itertools.groupby('AaaBBbcCAAa', lambda c: c.upper()):
...     print(key, list(group))
...
A ['A', 'a', 'a']
B ['B', 'B', 'b']
C ['c', 'C']
A ['A', 'A', 'a']

contextlib
from contextlib import contextmanager 连接上下文用来使用with语句:

@contextmanager
def tag(name):
    print("<%s>" % name)
    yield
    print("</%s>" % name)

with tag("h1"):
    print("hello")
    print("world")
#结果
<h1>
hello
world
</h1>

用closing()来把该对象变为上下文对象:

from contextlib import closing
from urllib.request import urlopen

with closing(urlopen('https://www.python.org')) as page:
    for line in page:
        print(line)

urllib
urllib的request模块

---

下一篇： 0212-爬取图片-随想→