python 常用内建模块

Prerequisite

参考文章：廖雪峰

包含：datetime、collections（parser：构造命令行参数）、base64、hashlib、hmac、itertools、contextlib、string

datetime#

注意：我没记录 本地时间转换为UTC时间 和 时区转换 的方法，需要的自行参考廖雪峰的文章

Copy
from datetime import datetime, timedelta

# 获取当前 datetime
# 默认是操作系统的时间，即北京时间
now = datetime.now()
# 2022-08-09 15:57:49.629587

# 获取指定 datetime
dt = datetime(2022, 4, 6, 6, 6, 6)
# 2022-04-06 06:06:06

# datetime 转换 timestamp
# timestamp（时间戳）是从 1970年1月1日 00:00:00 到当今的秒数
now.timestamp()
# 1660032186.291992

# timestamp 转换 datetime
t = 1660032186.291992
datetime.fromtimestamp(t)
# 2022-08-09 16:03:06.291992

# str 转换 datetime
cday = datetime.strptime('2022-08-09 16:03:06', '%Y-%m-%d %H:%M:%S')
# 2022-08-09 16:03:06

# datetime 转换 str
cnow = now.strftime('%Y-%m-%d %H:%M:%S')
# 2022-08-09 16:09:07

# datetime 加减
# 直接在 timedelta 中进行运算
tomorrow = now + timedelta(hours = 24)
# 2022-08-10 16:11:16.693899

collections#

Copy
# namedtuple 类似类的元组
from collections import namedtuple
Point = namedtuple('Point', ['x', 'y'])
p = Point(1, 2)
p.x # 1
p.y # 2

# deque 队列
# deque 默认向右侧插入和删除
from collections import deque
q = deque(['a', 'b', 'c'])
q.append('x')
q # deque(['a', 'b', 'c', 'x'])
q.appendleft('y')
q # deque(['y', 'a', 'b', 'c', 'x'])
# 类似的函数还有 pop() 和 popleft()

# defaultdict 自定义异常
from collections import defaultdict
dd = defaultdict(lambda: 'N/A')
dd['key1'] = 'abc'
dd['key1'] # 'abc'
dd['key2'] # 'N/A'

# OrderedDict 有序字典
from collections import OrderedDict
d = dict([('a', 1), ('b', 2), ('c', 3)])
od = OrderedDict([('a', 1), ('b', 2), ('c', 3)])
d # {'a': 1, 'c': 3, 'b': 2}
od # OrderedDict([('a', 1), ('b', 2), ('c', 3)])
# OrderedDict 的 Key 会按照插入的顺序排列，如 od['x'] = 1

# Counter 计数器
from collections import Counter
c = Counter()
c.update('hello')
c # Counter({'l': 2, 'h': 1, 'e': 1, 'o': 1})


# ChainMap 包含了多个字典的字典
# 适用场景：多种情况的传参
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'])

# 没有任何参数时，打印出默认参数
$ python3 use_chainmap.py 
# color=red
# user=guest

# 当传入命令行参数时，优先使用命令行参数
$ python3 use_chainmap.py -u bob
# color=red
# user=bob

# 同时传入命令行参数和环境变量，命令行参数的优先级较高
$ user=admin color=green python3 use_chainmap.py -u bob
# color=green
# user=bob

base64#

Copy
import base64
base64.b64encode(b'xxx') # 正常编码
base64.b64decode(b'xxx') # 正常解码

base64.urlsafe_b64encode(b'xxx') # 把字符 + 和 / 分别变成 - 和 _
base64.urlsafe_b64decode(b'xxx') # 同理

hashlib / hmac#

分别是计算哈希值和带盐的哈希值

Copy
# 计算哈希值
# 略

# 计算带盐哈希值
import hmac
message = b'Hello, world!'
key = b'secret'
h = hmac.new(key, message, digestmod='MD5')
h.hexdigest()
# fa4ee7d173f2d97ee79022d1a7355bcf

itertools#

Copy
import itertools

# count 无限自然数
natruals = itertools.count()
for n in natruals:
    print(n, end=" ")
# 0 1 2 3 ...

# cycle 无限循环序列
cs = itertools.cycle('ABC')
for c in cs:
    print(c, end=" ")
# A B C A B C A B C ...

# repeat 限定重复次数
ns = itertools.repeat('A', 3)
for n in ns:
    print(n, end=" ")
# A A A

# takewhile 截取有限序列
natruals = itertools.count()
ns = itertools.takewhile(lambda x: x <= 10, natruals)
list(ns)
# [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

# chain 串联迭代对象成迭代器
for c in itertools.chain('ABC', 'XYZ'):
    print(c, end=" ")
# A B C X Y Z

# groupby 把迭代器中相邻的重复元素挑出来放在一起
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#

上下文管理器

• 对于读写文件函数来说，事后要关闭函数，这就需要用到上下文管理器 with
• 对于类来说，可以通过 __enter__ 和 __exit__ 实现
• 对于类和函数来说，都可以通过 @contextmanager 这个装饰器实现

Copy
from contextlib import contextmanager

# 针对类
class Query(object):

    def __init__(self, name):
        self.name = name

    def query(self):
        print('Query info about %s...' % self.name)

@contextmanager
def create_query(name):
    print('Begin')
    q = Query(name)
    yield q
    print('End')

with create_query('Bob') as q:
    q.query()
"""
Begin
Query info about Bob...
End
"""


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

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


# 针对没有上下文的单个函数
from urllib.request import urlopen

@contextmanager
def closing(thing):
    try:
        yield thing
    finally:
        thing.close()

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

string#

我之前都没注意到这个库这么好用！！

Copy
# string.ascii_lowercase
abcdefghijklmnopqrstuvwxyz

# string.ascii_letters
abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ

# string.ascii_uppercase
ABCDEFGHIJKLMNOPQRSTUVWXYZ

# string.digits
0123456789

# string.hexdigits
0123456789abcdefABCDEF

# string.octdigits
01234567

# string.printable
0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~ + " \t\n" + chr(13) + chr(11) + chr(12)

# string.punctuation
!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~ + " \t\n" + chr(13) + chr(11) + chr(12)

# string.whitespace
" \t\n" + chr(13) + chr(11) + chr(12)