python 遍历目录

递归遍历所有目录

import os

dir_addr = './nlp-stopwords'

def walk_dir(dir_addr):
    '''
    遍历列出当前目录下的所有的文件
    root_dir: 根目录
    subdirs: 子目录
    files: 文件列表
    '''
    for root_dir, subdirs, files in os.walk(dir_addr):
        print(root_dir, subdirs, files)

walk_dir(dir_addr)

输出：

/Users/momo/Documents/code/nlp-stopwords ['.git'] ['baidu_stopwords.txt', 'common_stopwords.txt', 'SCU_stopwords.txt', 'README.md', 'HIT_stopwords.txt']
/Users/momo/Documents/code/nlp-stopwords/.git ['objects', 'info', 'logs', 'hooks', 'refs'] ['config', 'HEAD', 'description', 'index', 'packed-refs', 'COMMIT_EDITMSG']
/Users/momo/Documents/code/nlp-stopwords/.git/objects ['58', 'bb', 'pack', '42', '7b', 'info', 'd2', '14'] []
/Users/momo/Documents/code/nlp-stopwords/.git/objects/58 [] ['ea97fd757e6a0ddb4420ea45e4d4d859605957']
/Users/momo/Documents/code/nlp-stopwords/.git/objects/bb [] ['47a8b01a9a940d299154713b2911ee02755b4a']
/Users/momo/Documents/code/nlp-stopwords/.git/objects/pack [] ['pack-4e2fbdec7a023665bf89864c72f96bdc9ddff3b2.idx', 'pack-4e2fbdec7a023665bf89864c72f96bdc9ddff3b2.pack']
/Users/momo/Documents/code/nlp-stopwords/.git/objects/42 [] ['10f2808a943567fa5e8fc41eeafba7e9c3bbe0']
/Users/momo/Documents/code/nlp-stopwords/.git/objects/7b [] ['f86ad3023db60f9452ba4ca6c2eb08ca276e1e']
/Users/momo/Documents/code/nlp-stopwords/.git/objects/info [] []
/Users/momo/Documents/code/nlp-stopwords/.git/objects/d2 [] ['f08c173eac503b713e00a14a2a1f9d7c00c0f9']
/Users/momo/Documents/code/nlp-stopwords/.git/objects/14 [] ['eb732aacbc1b3196b092da09a2c1a126d7b8c1']
/Users/momo/Documents/code/nlp-stopwords/.git/info [] ['exclude']
/Users/momo/Documents/code/nlp-stopwords/.git/logs ['refs'] ['HEAD']
/Users/momo/Documents/code/nlp-stopwords/.git/logs/refs ['heads', 'remotes'] []
/Users/momo/Documents/code/nlp-stopwords/.git/logs/refs/heads [] ['master']
/Users/momo/Documents/code/nlp-stopwords/.git/logs/refs/remotes ['origin'] []
/Users/momo/Documents/code/nlp-stopwords/.git/logs/refs/remotes/origin [] ['HEAD', 'master']
/Users/momo/Documents/code/nlp-stopwords/.git/hooks [] ['commit-msg.sample', 'pre-rebase.sample', 'pre-commit.sample', 'applypatch-msg.sample', 'fsmonitor-watchman.sample', 'pre-receive.sample', 'prepare-commit-msg.sample', 'post-update.sample', 'pre-applypatch.sample', 'pre-push.sample', 'update.sample']
/Users/momo/Documents/code/nlp-stopwords/.git/refs ['heads', 'tags', 'remotes'] []
/Users/momo/Documents/code/nlp-stopwords/.git/refs/heads [] ['master']
/Users/momo/Documents/code/nlp-stopwords/.git/refs/tags [] []
/Users/momo/Documents/code/nlp-stopwords/.git/refs/remotes ['origin'] []
/Users/momo/Documents/code/nlp-stopwords/.git/refs/remotes/origin [] ['HEAD', 'master']

仅遍历当前目录

def listdir(dir_addr):
    filenames = os.listdir(dir_addr)
    print(filenames)

输出：

['baidu_stopwords.txt', 'common_stopwords.txt', 'SCU_stopwords.txt', 'README.md', '.git', 'HIT_stopwords.txt']

文件名匹配

import os
import re

dir_addr = './nlp-stopwords'

filenames = listdir(dir_addr)

for item in filenames:
#     match = re.match('(.*)txt(.*?)', item)
#     match = re.search('.txt', item)
#     match = re.match('\.', item)
    match = re.match('(.*).txt', item)
    if match:
        print(item)

输出：

baidu_stopwords.txt
common_stopwords.txt
SCU_stopwords.txt
HIT_stopwords.txt