如何用python批量读取文件名

使用Python批量读取文件名可以通过多种方式实现，其中包括使用os库、glob库以及pathlib库。这些方法各有优点，例如os库具有广泛的适用性、glob库提供了强大的模式匹配功能、pathlib库则是更现代的面向对象的解决方案。在实际应用中，选择适合的方式可以大大提高工作效率。

os库：os库是Python的标准库，提供了与操作系统交互的一些方法，是处理文件和目录的基础工具。通过os.listdir()方法可以获取指定目录下的所有文件和子目录的名称。os.walk()方法可以递归遍历目录树，获取所有子目录和文件的名称。

import os
使用os.listdir()方法
def list_files_with_listdir(directory):
    try:
        files = os.listdir(directory)
        for file in files:
            print(file)
    except Exception as e:
        print(f"An error occurred: {e}")
使用os.walk()方法
def list_files_with_walk(directory):
    try:
        for dirpath, dirnames, filenames in os.walk(directory):
            print(f"Found directory: {dirpath}")
            for file in filenames:
                print(file)
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
list_files_with_listdir(directory_path)
list_files_with_walk(directory_path)

glob库：glob库提供了更强大的文件名模式匹配功能，可以通过通配符匹配特定模式的文件名。glob.glob()方法可以获取指定目录下的所有文件和子目录的名称，支持递归遍历。

import glob
使用glob.glob()方法
def list_files_with_glob(directory, pattern):
    try:
        files = glob.glob(directory + pattern)
        for file in files:
            print(file)
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory/'
pattern = '*.*'  # 匹配所有文件
list_files_with_glob(directory_path, pattern)

pathlib库：pathlib库是Python 3.4引入的一个面向对象的文件系统路径操作库，通过Path对象可以方便地进行文件和目录的操作。Path.iterdir()方法可以获取指定目录下的所有文件和子目录的名称，Path.glob()方法可以进行模式匹配，支持递归遍历。

from pathlib import Path
使用Path.iterdir()方法
def list_files_with_iterdir(directory):
    try:
        path = Path(directory)
        for file in path.iterdir():
            print(file)
    except Exception as e:
        print(f"An error occurred: {e}")
使用Path.glob()方法
def list_files_with_pathlib_glob(directory, pattern):
    try:
        path = Path(directory)
        for file in path.glob(pattern):
            print(file)
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
list_files_with_iterdir(directory_path)
list_files_with_pathlib_glob(directory_path, '/*.*')  # 匹配所有文件，递归遍历

一、使用os库批量读取文件名

os库是Python标准库的一部分，提供了与操作系统交互的多种方法。通过os库，可以轻松地实现文件和目录的操作。

os.listdir()方法

os.listdir()方法返回指定目录下的所有文件和子目录的名称（包括隐藏文件），并以列表的形式返回。如果目录不存在，会抛出FileNotFoundError异常。

import os
def list_files_with_listdir(directory):
    try:
        files = os.listdir(directory)
        for file in files:
            print(file)
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
list_files_with_listdir(directory_path)

os.walk()方法

os.walk()方法生成目录树下的所有文件名，通过遍历目录树，可以获取所有子目录和文件的名称。os.walk()方法返回一个三元组(root, dirs, files)。

import os
def list_files_with_walk(directory):
    try:
        for dirpath, dirnames, filenames in os.walk(directory):
            print(f"Found directory: {dirpath}")
            for file in filenames:
                print(os.path.join(dirpath, file))
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
list_files_with_walk(directory_path)

二、使用glob库批量读取文件名

glob库提供了强大的文件名模式匹配功能，可以通过通配符匹配特定模式的文件名。glob库的glob()方法可以获取指定目录下的所有文件和子目录的名称，支持递归遍历。

glob.glob()方法

glob.glob()方法返回所有匹配的文件路径，支持通配符模式，例如*、?、[]等。

import glob
def list_files_with_glob(directory, pattern):
    try:
        files = glob.glob(os.path.join(directory, pattern))
        for file in files:
            print(file)
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
pattern = '*.*'  # 匹配所有文件
list_files_with_glob(directory_path, pattern)

glob.iglob()方法

glob.iglob()方法返回一个迭代器，而不是一个列表，这样可以在处理大量文件时节省内存。

import glob
def list_files_with_iglob(directory, pattern):
    try:
        files = glob.iglob(os.path.join(directory, pattern))
        for file in files:
            print(file)
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
pattern = '/*.*'  # 匹配所有文件，递归遍历
list_files_with_iglob(directory_path, pattern)

三、使用pathlib库批量读取文件名

pathlib库是Python 3.4引入的一个面向对象的文件系统路径操作库，通过Path对象可以方便地进行文件和目录的操作。

Path.iterdir()方法

Path.iterdir()方法返回目录中所有文件和子目录的Path对象。

from pathlib import Path
def list_files_with_iterdir(directory):
    try:
        path = Path(directory)
        for file in path.iterdir():
            print(file)
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
list_files_with_iterdir(directory_path)

Path.glob()方法

Path.glob()方法可以进行模式匹配，支持递归遍历。

from pathlib import Path
def list_files_with_pathlib_glob(directory, pattern):
    try:
        path = Path(directory)
        for file in path.glob(pattern):
            print(file)
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
list_files_with_pathlib_glob(directory_path, '/*.*')  # 匹配所有文件，递归遍历

四、结合多种方法的最佳实践

在实际项目中，可能需要结合多种方法来实现批量读取文件名，以应对不同的需求和场景。下面是一个结合多种方法的最佳实践示例：

import os
import glob
from pathlib import Path
def list_files(directory, method='os'):
    if method == 'os':
        return list_files_with_listdir(directory)
    elif method == 'os_walk':
        return list_files_with_walk(directory)
    elif method == 'glob':
        return list_files_with_glob(directory, '*.*')
    elif method == 'glob_recursive':
        return list_files_with_glob(directory, '/*.*')
    elif method == 'pathlib':
        return list_files_with_iterdir(directory)
    elif method == 'pathlib_recursive':
        return list_files_with_pathlib_glob(directory, '/*.*')
    else:
        raise ValueError("Unknown method: choose from 'os', 'os_walk', 'glob', 'glob_recursive', 'pathlib', 'pathlib_recursive'.")
def list_files_with_listdir(directory):
    try:
        files = os.listdir(directory)
        return [os.path.join(directory, file) for file in files]
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
def list_files_with_walk(directory):
    try:
        file_list = []
        for dirpath, dirnames, filenames in os.walk(directory):
            for file in filenames:
                file_list.append(os.path.join(dirpath, file))
        return file_list
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
def list_files_with_glob(directory, pattern):
    try:
        return glob.glob(os.path.join(directory, pattern))
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
def list_files_with_iterdir(directory):
    try:
        path = Path(directory)
        return [file for file in path.iterdir()]
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
def list_files_with_pathlib_glob(directory, pattern):
    try:
        path = Path(directory)
        return [file for file in path.glob(pattern)]
    except FileNotFoundError:
        print(f"The directory {directory} does not exist.")
    except PermissionError:
        print(f"Permission denied to access {directory}.")
    except Exception as e:
        print(f"An error occurred: {e}")
directory_path = '/path/to/your/directory'
files = list_files(directory_path, method='pathlib_recursive')
for file in files:
    print(file)