pathlib — 现代路径处理
from pathlib import Path
# 路径构建
p = Path.home() / "projects" / "myapp" / "config.json"
# / 运算符自动处理分隔符
# 属性
p.name # "config.json"
p.stem # "config"（无后缀）
p.suffix # ".json"
p.parent # Path("/home/user/projects/myapp")
p.parts # ('/', 'home', 'user', 'projects', 'myapp', 'config.json')
# 操作
p.exists() # 是否存在
p.is_file() / p.is_dir() # 类型判断
p.mkdir(parents=True) # 递归创建目录
text = p.read_text() # 读取文本
p.write_text("content") # 写入
data = p.read_bytes() # 读取二进制
# 遍历
for f in Path("src").rglob("*.cpp"): # 递归 glob
print(f)
# 相对路径
Path("a/b/c").relative_to("a") # Path("b/c")
os / sys / shutil
import os, sys, shutil
# os
os.getcwd() # 当前目录
os.chdir("/tmp") # 切换目录
os.environ["HOME"] # 环境变量
os.path.join("a", "b") # 路径拼接（pathlib 更好）
os.path.exists("file.txt") # 是否存在
# sys
sys.argv # 命令行参数
sys.exit(0) # 退出
sys.platform # "linux" / "darwin" / "win32"
# shutil
shutil.copy("a.txt", "b.txt") # 复制
shutil.move("a.txt", "/tmp/") # 移动
shutil.rmtree("/tmp/build") # 递归删除
shutil.make_archive("dist", "zip", "build/") # 打包
subprocess — 执行命令
import subprocess
# 运行 + 捕获输出（推荐）
result = subprocess.run(
["git", "status", "--short"],
capture_output=True,
text=True, # 返回 str 而非 bytes
timeout=10,
check=True # 非零退出码抛异常
)
print(result.stdout)
# 管道
p1 = subprocess.Popen(["ls"], stdout=subprocess.PIPE)
p2 = subprocess.Popen(["grep", ".cpp"], stdin=p1.stdout,
stdout=subprocess.PIPE, text=True)
output, _ = p2.communicate()
# 快捷版（仅获取输出不检查退出码）
out = subprocess.check_output(["echo", "hello"], text=True)
json
import json
# 读取
with open("config.json") as f:
config = json.load(f)
# 写入
with open("output.json", "w") as f:
json.dump(data, f, indent=2, ensure_ascii=False)
# 字符串 ↔ 对象
s = json.dumps({"key": "值"}, indent=2) # 对象 → 字符串
obj = json.loads(s) # 字符串 → 对象
# 自定义序列化
class Point:
def __init__(self, x, y): self.x, self.y = x, y
def point_encoder(obj):
if isinstance(obj, Point):
return {"x": obj.x, "y": obj.y}
raise TypeError
json.dumps(Point(1, 2), default=point_encoder)
csv
import csv
# 读取
with open("data.csv") as f:
reader = csv.reader(f)
header = next(reader) # 跳过表头
for row in reader:
print(row[0], row[1])
# 字典读取
with open("data.csv") as f:
for row in csv.DictReader(f):
print(row["Name"], row["Age"])
# 写入
with open("out.csv", "w", newline="") as f:
writer = csv.writer(f)
writer.writerow(["Name", "Age"]) # 表头
writer.writerows([("Alice", 25), ("Bob", 30)])
# 字典写入
with open("out.csv", "w", newline="") as f:
writer = csv.DictWriter(f, fieldnames=["Name", "Age"])
writer.writeheader()
writer.writerow({"Name": "Alice", "Age": 25})
datetime
from datetime import datetime, timedelta
now = datetime.now()
ts = now.timestamp() # Unix 时间戳
# 格式化
now.strftime("%Y-%m-%d %H:%M:%S") # "2025-01-15 14:30:00"
datetime.strptime("2025-01-15", "%Y-%m-%d") # 字符串 → datetime
# 运算
tomorrow = now + timedelta(days=1)
diff = tomorrow - now # timedelta
collections
from collections import defaultdict, Counter, deque
# defaultdict — 自动默认值
d = defaultdict(list)
d["key"].append(1) # 不需要先 d["key"] = []
# Counter — 计数
c = Counter("abracadabra")
c.most_common(3) # [('a', 5), ('b', 2), ('r', 2)]
# deque — 双端队列
q = deque(maxlen=100) # 自动丢弃旧元素
q.append(1); q.appendleft(0)
from itertools import chain, groupby, product, combinations
list(chain([1,2], [3,4])) # [1,2,3,4]
list(combinations("ABC", 2)) # [('A','B'),('A','C'),('B','C')]
list(product("AB", "12")) # [('A','1'),('A','2'),('B','1'),('B','2')]