标准库
os / sys
import os, sys
# 当前目录与路径
os.getcwd()
os.path.join("/tmp", "a", "b.txt")
os.path.exists("file.txt")
os.path.abspath(".")
os.path.dirname(__file__)
# 目录操作
os.makedirs("a/b/c", exist_ok=True)
os.listdir(".")
os.rename("old.txt", "new.txt")
os.remove("file.txt")
# 环境变量
os.environ.get("HOME", "/tmp")
os.environ["MY_VAR"] = "value"
# sys
sys.argv # 命令行参数列表
sys.exit(0) # 退出，0 为成功
sys.path # 模块搜索路径
sys.version # Python 版本字符串
print("err", file=sys.stderr)
pathlib
from pathlib import Path
p = Path("data") / "file.txt"
p.read_text(encoding="utf-8")
p.write_text("hello", encoding="utf-8")
p.exists()
p.is_file()
p.parent # Path("data")
p.stem # "file"
p.suffix # ".txt"
p.resolve() # 绝对路径
for f in Path(".").rglob("*.py"):
print(f)
datetime
from datetime import datetime, date, timedelta, timezone
now = datetime.now()
today = date.today()
# 格式化
now.strftime("%Y-%m-%d %H:%M:%S")
datetime.strptime("2024-01-15", "%Y-%m-%d")
# 运算
deadline = now + timedelta(days=7)
delta = deadline - now
delta.days # 7
delta.total_seconds()
# 时区（UTC）
utc_now = datetime.now(tz=timezone.utc)
collections
from collections import defaultdict, Counter, deque, namedtuple, OrderedDict
# defaultdict：键不存在时自动创建默认值
word_count = defaultdict(int)
for w in ["a", "b", "a"]:
word_count[w] += 1 # {'a': 2, 'b': 1}
# Counter：计数器
c = Counter("mississippi")
c.most_common(3) # [('i',4),('s',4),('p',2)]
c["i"] # 4
# deque：双端队列（O(1) 两端操作）
dq = deque([1, 2, 3], maxlen=5)
dq.appendleft(0)
dq.rotate(1) # [3, 0, 1, 2]
# namedtuple：具名元组
Point = namedtuple("Point", ["x", "y"])
p = Point(1.0, 2.0)
p.x, p.y # 1.0, 2.0
import itertools
list(itertools.chain([1,2], [3,4])) # [1,2,3,4]
list(itertools.islice(range(100), 5)) # [0,1,2,3,4]
list(itertools.combinations("ABC", 2)) # [('A','B'),('A','C'),('B','C')]
list(itertools.product([0,1], repeat=3)) # 8 个三元组
list(itertools.accumulate([1,2,3,4])) # [1,3,6,10]
# 分组（数据需预先排序）
for key, grp in itertools.groupby([1,1,2,3,3], key=lambda x: x):
print(key, list(grp))
from functools import lru_cache, partial, reduce, wraps, cached_property
# LRU 缓存
@lru_cache(maxsize=256)
def fib(n):
return n if n < 2 else fib(n-1) + fib(n-2)
fib.cache_info() # CacheInfo(hits=..., misses=..., ...)
# 偏函数
def power(base, exp): return base ** exp
square = partial(power, exp=2)
square(5) # 25
# reduce
reduce(lambda a, b: a * b, [1,2,3,4,5]) # 120
# cached_property（3.8+）：计算一次后缓存
class Circle:
def __init__(self, r): self.r = r
@cached_property
def area(self): return 3.14159 * self.r ** 2
re（正则表达式）
import re
# 搜索与匹配
re.match(r"\d+", "123abc") # 从头匹配
re.search(r"\d+", "abc123") # 任意位置
re.findall(r"\d+", "a1 b2 c3") # ['1','2','3']
# 替换与分割
re.sub(r"\s+", " ", "a b c") # 'a b c'
re.split(r"[,;]+", "a,b;;c") # ['a','b','c']
# 预编译（复用时更高效）
pattern = re.compile(r"(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})")
m = pattern.match("2024-01-15")
m.group("year") # '2024'
m.groupdict() # {'year':'2024','month':'01','day':'15'}
# 常用修饰符
re.IGNORECASE # 忽略大小写
re.MULTILINE # ^ $ 匹配每行首尾
re.DOTALL # . 匹配换行符
json / pickle
import json, pickle
# JSON（跨语言，仅支持基础类型）
data = {"name": "Alice", "scores": [95, 87]}
json.dumps(data, ensure_ascii=False, indent=2)
json.loads('{"x": 1}')
# Pickle（Python 专用，支持任意对象）
with open("data.pkl", "wb") as f:
pickle.dump(data, f)
with open("data.pkl", "rb") as f:
loaded = pickle.load(f)
threading / concurrent.futures
import threading
from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor
# 基本线程
def task(n):
print(f"Task {n}")
t = threading.Thread(target=task, args=(1,))
t.start()
t.join()
# 线程池（I/O 密集型）
with ThreadPoolExecutor(max_workers=4) as pool:
results = list(pool.map(task, range(10)))
# 进程池（CPU 密集型）
with ProcessPoolExecutor() as pool:
results = list(pool.map(heavy_compute, data))
subprocess
import subprocess
# 捕获输出
result = subprocess.run(
["git", "log", "--oneline", "-5"],
capture_output=True,
text=True,
check=True # 非零退出码抛 CalledProcessError
)
print(result.stdout)
# 管道组合
p = subprocess.Popen(["ls", "-la"], stdout=subprocess.PIPE)
out, _ = p.communicate()
logging
import logging
logging.basicConfig(
level=logging.DEBUG,
format="%(asctime)s %(levelname)s %(name)s: %(message)s",
handlers=[
logging.StreamHandler(), # 控制台
logging.FileHandler("app.log"), # 文件
]
)
logger = logging.getLogger(__name__)
logger.debug("调试信息")
logger.info("正常信息")
logger.warning("警告")
logger.error("错误")
logger.exception("含 traceback 的错误") # 在 except 块内使用
argparse
import argparse
parser = argparse.ArgumentParser(description="示例 CLI 工具")
parser.add_argument("input", help="输入文件")
parser.add_argument("-o", "--output", default="out.txt", help="输出文件")
parser.add_argument("-v", "--verbose", action="store_true")
parser.add_argument("-n", "--count", type=int, default=10)
args = parser.parse_args()
print(args.input, args.output, args.verbose, args.count)
相关链接