Python 常用标准库

17.1 collections 模块

提供额外的数据结构。

Counter - 计数器

from collections import Counter

text = "hello world"
counter = Counter(text)
print(counter)  # Counter({'l': 3, 'o': 2, ...})

# 最常见元素
print(counter.most_common(3))  # [('l', 3), ('o', 2), ('h', 1)]

# 统计单词
words = ["apple", "banana", "apple", "orange", "banana", "apple"]
word_count = Counter(words)
print(word_count["apple"])  # 3

defaultdict - 默认字典

from collections import defaultdict

# 普通字典
d = {}
# d["key"]  # KeyError

# 默认字典
dd = defaultdict(int)  # 默认值为 0
dd["count"] += 1
print(dd["count"])  # 1

# 分组
students = [
    ("Alice", "A"),
    ("Bob", "B"),
    ("Charlie", "A"),
    ("David", "B")
]

groups = defaultdict(list)
for name, grade in students:
    groups[grade].append(name)

print(groups)
# defaultdict(<class 'list'>, {'A': ['Alice', 'Charlie'], 'B': ['Bob', 'David']})

deque - 双端队列

from collections import deque

d = deque([1, 2, 3])

d.append(4)       # 右端添加
d.appendleft(0)   # 左端添加
print(d)  # deque([0, 1, 2, 3, 4])

d.pop()           # 右端删除
d.popleft()       # 左端删除
print(d)  # deque([1, 2, 3])

# 限制长度
d = deque(maxlen=3)
d.append(1)
d.append(2)
d.append(3)
d.append(4)  # 自动移除最左边
print(d)  # deque([2, 3, 4])

17.2 itertools 模块

提供高效的迭代工具。

常用函数

import itertools

# count - 无限计数
for i in itertools.count(10, 2):
    if i > 20:
        break
    print(i, end=" ")  # 10 12 14 16 18 20

# cycle - 循环
count = 0
for item in itertools.cycle(["A", "B", "C"]):
    print(item, end=" ")
    count += 1
    if count >= 6:
        break
# A B C A B C

# repeat - 重复
print(list(itertools.repeat("X", 3)))  # ['X', 'X', 'X']

# chain - 链式迭代
for item in itertools.chain([1, 2], [3, 4]):
    print(item, end=" ")  # 1 2 3 4

# combinations - 组合
print(list(itertools.combinations([1, 2, 3], 2)))
# [(1, 2), (1, 3), (2, 3)]

# permutations - 排列
print(list(itertools.permutations([1, 2, 3])))
# [(1, 2, 3), (1, 3, 2), (2, 1, 3), ...]

17.3 functools 模块

提供高阶函数工具。

lru_cache - 缓存装饰器

from functools import lru_cache

@lru_cache(maxsize=128)
def fibonacci(n):
    if n <= 1:
        return n
    return fibonacci(n - 1) + fibonacci(n - 2)

print(fibonacci(100))  # 瞬间完成
print(fibonacci.cache_info())
# CacheInfo(hits=196, misses=101, maxsize=128, currsize=101)

reduce - 归约函数

from functools import reduce

# 求和
numbers = [1, 2, 3, 4, 5]
total = reduce(lambda x, y: x + y, numbers)
print(total)  # 15

# 求最大值
max_val = reduce(lambda x, y: x if x > y else y, numbers)
print(max_val)  # 5

# 字符串拼接
words = ["Hello", "World", "Python"]
sentence = reduce(lambda x, y: x + " " + y, words)
print(sentence)  # Hello World Python

17.4 re 模块（正则表达式）

import re

text = "Email: test@example.com, Phone: 123-456-7890"

# 查找
email = re.search(r"\w+@\w+\.\w+", text)
print(email.group())  # test@example.com

# 查找所有
numbers = re.findall(r"\d+", text)
print(numbers)  # ['123', '456', '7890']

# 替换
result = re.sub(r"\d+", "XXX", text)
print(result)  # Email: test@example.com, Phone: XXX-XXX-XXX

# 分割
words = re.split(r"[,\s]+", "one,two three four")
print(words)  # ['one', 'two', 'three', 'four']

17.5 os 与 sys 模块

os 模块

import os

# 路径操作
print(os.getcwd())           # 当前目录
print(os.listdir("."))       # 列出文件
print(os.path.exists("file.txt"))
print(os.path.isfile("file.txt"))
print(os.path.isdir("dir"))

# 创建/删除
os.makedirs("test/nested", exist_ok=True)
os.rmdir("test/nested")

# 环境变量
print(os.environ.get("PATH"))

sys 模块

import sys

print(sys.version)     # Python 版本
print(sys.platform)    # 操作系统
print(sys.argv)        # 命令行参数
print(sys.path)        # 模块搜索路径

# 退出
# sys.exit(0)

17.6 math 与 decimal 模块

math 模块

import math

print(math.pi)         # 3.141592653589793
print(math.e)          # 2.718281828459045
print(math.sqrt(16))   # 4.0
print(math.ceil(3.2))  # 4
print(math.floor(3.8)) # 3
print(math.factorial(5))  # 120
print(math.log(100, 10))  # 2.0

decimal 模块（高精度）

from decimal import Decimal

# 浮点数精度问题
print(0.1 + 0.2)  # 0.30000000000000004

# Decimal 解决
a = Decimal("0.1")
b = Decimal("0.2")
print(a + b)  # 0.3

17.7 本章小结

collections：Counter、defaultdict、deque
itertools：chain、combinations、permutations
functools：lru_cache、reduce
re：正则表达式操作
os/sys：系统和路径操作
math/decimal：数学运算

练习题

使用 Counter 统计文本中单词频率
使用 defaultdict 实现电话簿分组
使用正则表达式验证邮箱格式
使用 lru_cache 优化递归函数性能