py-os-walk

import os

for root, dirs, files in os.walk(top, topdown=True, onerror=None, followlinks=False):
    # 处理逻辑

import os

# 遍历当前目录
for root, dirs, files in os.walk('.'):
    print(f"当前目录: {root}")
    print(f"子目录: {dirs}")
    print(f"文件: {files}")
    print("-" * 50)

import os

def get_all_files(directory):
    """获取目录下所有文件的完整路径"""
    all_files = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            full_path = os.path.join(root, file)
            all_files.append(full_path)
    return all_files

# 使用示例
files = get_all_files('.')
for file in files:
    print(file)

import os

def find_files_by_extension(directory, extensions):
    """查找指定扩展名的文件"""
    found_files = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if any(file.endswith(ext) for ext in extensions):
                full_path = os.path.join(root, file)
                found_files.append(full_path)
    return found_files

# 查找所有Python和文本文件
python_and_txt_files = find_files_by_extension('.', ['.py', '.txt', '.md'])
for file in python_and_txt_files:
    print(file)

import os

print("自上而下遍历 (默认):")
for root, dirs, files in os.walk('.', topdown=True):
    print(f"访问: {root}")

print("\n自下而上遍历:")
for root, dirs, files in os.walk('.', topdown=False):
    print(f"访问: {root}")

import os

def walk_with_filter(directory, exclude_dirs=None):
    """遍历时排除特定目录"""
    if exclude_dirs is None:
        exclude_dirs = ['.git', '__pycache__', 'node_modules']
    
    for root, dirs, files in os.walk(directory):
        # 从dirs中移除要排除的目录（防止os.walk进入这些目录）
        dirs[:] = [d for d in dirs if d not in exclude_dirs]
        
        print(f"当前目录: {root}")
        print(f"过滤后子目录: {dirs}")
        print(f"文件: {files}")
        print("-" * 50)

# 使用示例
walk_with_filter('.')

import os

def handle_walk_error(error):
    """错误处理函数"""
    print(f"遍历错误: {error}")

# 带有错误处理的遍历
try:
    for root, dirs, files in os.walk('/some/path', onerror=handle_walk_error):
        print(f"处理: {root}")
except Exception as e:
    print(f"严重错误: {e}")

import os

def get_directory_size(directory):
    """计算目录总大小"""
    total_size = 0
    for root, dirs, files in os.walk(directory):
        for file in files:
            file_path = os.path.join(root, file)
            try:
                total_size += os.path.getsize(file_path)
            except OSError:
                # 忽略无法访问的文件
                pass
    return total_size

# 使用示例
size = get_directory_size('.')
print(f"目录总大小: {size} bytes ({size / 1024 / 1024:.2f} MB)")

import os
import hashlib

def get_file_hash(filepath):
    """计算文件的MD5哈希值"""
    hash_md5 = hashlib.md5()
    with open(filepath, "rb") as f:
        for chunk in iter(lambda: f.read(4096), b""):
            hash_md5.update(chunk)
    return hash_md5.hexdigest()

def find_duplicate_files(directory):
    """查找重复文件"""
    file_hashes = {}
    duplicates = []
    
    for root, dirs, files in os.walk(directory):
        for file in files:
            file_path = os.path.join(root, file)
            try:
                file_hash = get_file_hash(file_path)
                if file_hash in file_hashes:
                    duplicates.append((file_path, file_hashes[file_hash]))
                else:
                    file_hashes[file_hash] = file_path
            except (OSError, IOError):
                # 忽略无法读取的文件
                continue
    
    return duplicates

# 使用示例
duplicates = find_duplicate_files('.')
for dup in duplicates:
    print(f"重复文件: {dup[0]} 和 {dup[1]}")

import os

def analyze_directory(directory):
    """分析目录结构"""
    stats = {
        'total_dirs': 0,
        'total_files': 0,
        'file_types': {},
        'largest_file': ('', 0)
    }
    
    for root, dirs, files in os.walk(directory):
        stats['total_dirs'] += len(dirs)
        stats['total_files'] += len(files)
        
        for file in files:
            # 统计文件类型
            _, ext = os.path.splitext(file)
            file_type = ext.lower() if ext else '无扩展名'
            stats['file_types'][file_type] = stats['file_types'].get(file_type, 0) + 1
            
            # 查找最大文件
            file_path = os.path.join(root, file)
            try:
                file_size = os.path.getsize(file_path)
                if file_size > stats['largest_file'][1]:
                    stats['largest_file'] = (file_path, file_size)
            except OSError:
                pass
    
    return stats

# 使用示例
stats = analyze_directory('.')
print(f"总目录数: {stats['total_dirs']}")
print(f"总文件数: {stats['total_files']}")
print("文件类型分布:")
for file_type, count in stats['file_types'].items():
    print(f"  {file_type}: {count}")
print(f"最大文件: {stats['largest_file'][0]} ({stats['largest_file'][1]} bytes)")

import os

def rename_files_in_directory(directory, old_ext, new_ext):
    """批量重命名指定扩展名的文件"""
    renamed_count = 0
    
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith(old_ext):
                old_path = os.path.join(root, file)
                new_file = file.replace(old_ext, new_ext)
                new_path = os.path.join(root, new_file)
                
                try:
                    os.rename(old_path, new_path)
                    print(f"重命名: {old_path} -> {new_path}")
                    renamed_count += 1
                except OSError as e:
                    print(f"重命名失败 {old_path}: {e}")
    
    return renamed_count

# 使用示例：将所有的.txt文件改为.md
# renamed = rename_files_in_directory('.', '.txt', '.md')
# print(f"重命名了 {renamed} 个文件")