Python中如何遍历目录下的文件？遍历时如何过滤特定文件类型？

import os

def traverse_directory(directory):
    for dirpath, dirnames, filenames in os.walk(directory):
        print(f"当前目录：{dirpath}")
        for filename in filenames:
            print(f"  文件：{filename}")
        print(f"  子目录：{dirnames}")

# 使用示例
traverse_directory("/path/to/your/directory")

import os
import fnmatch

def traverse_and_filter(directory, pattern):
    for dirpath, dirnames, filenames in os.walk(directory):
        for filename in filenames:
            if filename.endswith(pattern): # 使用endswith
                print(f"找到 {pattern} 文件：{os.path.join(dirpath, filename)}")

def traverse_and_filter_fnmatch(directory, pattern):
    for dirpath, dirnames, filenames in os.walk(directory):
        for filename in filenames:
            if fnmatch.fnmatch(filename, pattern): # 使用fnmatch
                print(f"找到匹配 {pattern} 的文件：{os.path.join(dirpath, filename)}")


# 使用示例
traverse_and_filter("/path/to/your/directory", ".txt")
traverse_and_filter_fnmatch("/path/to/your/directory", "*.log") # 匹配所有.log文件

import os

def traverse_directory_safe(directory):
    for dirpath, dirnames, filenames in os.walk(directory):
        try:
            print(f"当前目录：{dirpath}")
            for filename in filenames:
                print(f"  文件：{filename}")
            print(f"  子目录：{dirnames}")
        except OSError as e:
            print(f"  警告：无法访问 {dirpath} - {e}")

# 使用示例
traverse_directory_safe("/path/to/your/directory")

import os

def traverse_without_links(directory):
    for dirpath, dirnames, filenames in os.walk(directory, followlinks=False):
        print(f"当前目录：{dirpath}")
        for filename in filenames:
            print(f"  文件：{filename}")
        print(f"  子目录：{dirnames}")

# 使用示例
traverse_without_links("/path/to/your/directory")

import os

def file_path_generator(directory, pattern):
    for dirpath, dirnames, filenames in os.walk(directory):
        for filename in filenames:
            if filename.endswith(pattern):
                yield os.path.join(dirpath, filename)

# 使用示例
file_generator = file_path_generator("/path/to/your/directory", ".txt")

# 延迟处理文件
for file_path in file_generator:
    # 对 file_path 进行处理
    print(f"处理文件：{file_path}")

import os
import concurrent.futures

def process_file(file_path):
    # 对文件进行处理
    print(f"处理文件：{file_path}")
    # 模拟耗时操作
    import time
    time.sleep(0.1) # 模拟IO操作

def traverse_and_process_parallel(directory, pattern, num_workers=4):
    with concurrent.futures.ThreadPoolExecutor(max_workers=num_workers) as executor:
        for dirpath, dirnames, filenames in os.walk(directory):
            for filename in filenames:
                if filename.endswith(pattern):
                    file_path = os.path.join(dirpath, filename)
                    executor.submit(process_file, file_path)

# 使用示例
traverse_and_process_parallel("/path/to/your/directory", ".txt", num_workers=8)