Python pathlib 简明教程

from pathlib import Path

# 方法1：基于当前文件位置（最常用）
# 假设 config.py 在 scripts/ 目录下
ROOT_DIR = Path(__file__).parent.parent  # 上两级目录

# 方法2：基于工作目录
import os
ROOT_DIR = Path(os.getcwd())

# 方法3：固定路径（不推荐，换电脑会坏）
ROOT_DIR = Path("C:/Users/xxx/project")  # ❌ 别这样

import os

# 字符串拼接，要考虑 / 和 \
watch_dir = os.path.join(ROOT_DIR, "watch")
extract_dir = os.path.join(ROOT_DIR, "extracted")

# 还要手动创建目录
os.makedirs(watch_dir, exist_ok=True)

from pathlib import Path

ROOT_DIR = Path(__file__).parent.parent

# 用 / 直接拼接路径
WATCH_DIR = ROOT_DIR / "watch"
EXTRACT_DIR = ROOT_DIR / "extracted"
COMPRESSED_DIR = ROOT_DIR / "compressed"

# 自动创建目录（包括父目录）
WATCH_DIR.mkdir(parents=True, exist_ok=True)

base = Path("/home/user/project")

# 拼接子目录
subdir = base / "data" / "2024"          # /home/user/project/data/2024

# 拼接文件
file = base / "config" / "settings.json"  # /home/user/project/config/settings.json

# 在 config.py 中的实际应用
PATHS = {
    "watch": ROOT_DIR / "watch",
    "extracted": ROOT_DIR / "extracted",
    "compressed": ROOT_DIR / "compressed",
}

from pathlib import Path

root = Path("./watch")

# 遍历所有文件和子目录
for item in root.iterdir():
    print(item)  # 可能是文件或目录

# 只遍历文件
for file in root.iterdir():
    if file.is_file():
        print(f"文件: {file.name}")

# 只遍历 .jpg 文件
for jpg in root.glob("*.jpg"):
    print(jpg)

# 递归遍历所有图片（包括子目录）
for img in root.rglob("*.jpg"):  # rglob = recursive glob
    print(img)

from pathlib import Path

# 项目根目录
PROJECT_ROOT = Path(__file__).parent.parent

# 各种路径
PATHS = {
    "watch": PROJECT_ROOT / "watch",
    "extracted": PROJECT_ROOT / "extracted",
    "compressed": PROJECT_ROOT / "compressed",
    "archived": PROJECT_ROOT / "archived",
    "logs": PROJECT_ROOT / "logs",
}

# 确保目录都存在
for name, path in PATHS.items():
    path.mkdir(parents=True, exist_ok=True)
    print(f"✓ {name}: {path}")

from pathlib import Path
from config import ALLOWED_IMAGE_EXTS

def is_allowed_image(file_path: Path) -> bool:
    """检查是否是允许的图片格式"""
    return file_path.suffix.lower() in ALLOWED_IMAGE_EXTS

# 使用
file = Path("photo.JPG")
if is_allowed_image(file):
    print("是合法图片")

from pathlib import Path

def batch_rename(directory: Path, old_ext: str, new_ext: str):
    """批量修改文件后缀"""
    for file in directory.glob(f"*{old_ext}"):
        new_name = file.with_suffix(new_ext)
        file.rename(new_name)
        print(f"{file.name} -> {new_name.name}")

# 使用
batch_rename(Path("./images"), ".jpeg", ".jpg")

from pathlib import Path

root = Path("./project")
# 错！不能直接用 +
# path = root + "/subdir"  # ❌ 报错

# 对！用 /
path = root / "subdir"  # ✅

from pathlib import Path
import os

p = Path("./test.txt")

# 一些旧库只接受字符串
# os.system(f"cat {p}")  # 可能有问题

# 转字符串
os.system(f"cat {str(p)}")  # ✅
# 或
os.system(f"cat {p.as_posix()}")  # ✅ 用正斜杠

from pathlib import Path

p = Path("C:/Users/name/file.txt")
print(p)           # C:\Users\name\file.txt (Windows 自动转)
print(str(p))      # C:\Users\name\file.txt
print(p.as_posix()) # C:/Users/name/file.txt (正斜杠，用于 URL)

"""
配置文件
"""
from pathlib import Path

# ==================== 基础路径 ====================
# 项目根目录：config.py 在 scripts/ 下，所以上两级是根目录
PROJECT_ROOT = Path(__file__).parent.parent

# ==================== 各阶段目录 ====================
PATHS = {
    "watch": PROJECT_ROOT / "watch",           # 监听文件夹
    "extracted": PROJECT_ROOT / "extracted",   # 解压目录
    "compressed": PROJECT_ROOT / "compressed", # 压缩后图片
    "archived": PROJECT_ROOT / "archived",     # 最终分卷压缩
    "logs": PROJECT_ROOT / "logs",             # 日志目录
}

# ==================== 辅助函数 ====================
def ensure_dirs():
    """确保所有目录都存在"""
    for path in PATHS.values():
        path.mkdir(parents=True, exist_ok=True)

# 测试
if __name__ == "__main__":
    ensure_dirs()
    for name, path in PATHS.items():
        print(f"{name}: {path}")