有没有更好的方法来使用glob。Glob在python中获取多个文件类型的列表，如.txt， .mdown和.markdown?现在我有这样的东西:
projectFiles1 = glob.glob( os.path.join(projectDir, '*.txt') )
projectFiles2 = glob.glob( os.path.join(projectDir, '*.mdown') )
projectFiles3 = glob.glob( os.path.join(projectDir, '*.markdown') )
当前回答
import glob
import pandas as pd
df1 = pd.DataFrame(columns=['A'])
for i in glob.glob('C:\dir\path\*.txt'):
df1 = df1.append({'A': i}, ignore_index=True)
for i in glob.glob('C:\dir\path\*.mdown'):
df1 = df1.append({'A': i}, ignore_index=True)
for i in glob.glob('C:\dir\path\*.markdown):
df1 = df1.append({'A': i}, ignore_index=True)
其他回答
如果你使用pathlib，试试这个:
import pathlib
extensions = ['.py', '.txt']
root_dir = './test/'
files = filter(lambda p: p.suffix in extensions, pathlib.Path(root_dir).glob('**/*'))
print(list(files))
链接结果:
import itertools as it, glob
def multiple_file_types(*patterns):
return it.chain.from_iterable(glob.iglob(pattern) for pattern in patterns)
然后:
for filename in multiple_file_types("*.txt", "*.sql", "*.log"):
# do stuff
您可以尝试制作一个手动列表，将现有扩展与所需扩展进行比较。
ext_list = ['gif','jpg','jpeg','png'];
file_list = []
for file in glob.glob('*.*'):
if file.rsplit('.',1)[1] in ext_list :
file_list.append(file)
我也有同样的问题，这是我想到的
import os, sys, re
#without glob
src_dir = '/mnt/mypics/'
src_pics = []
ext = re.compile('.*\.(|{}|)$'.format('|'.join(['png', 'jpeg', 'jpg']).encode('utf-8')))
for root, dirnames, filenames in os.walk(src_dir):
for filename in filter(lambda name:ext.search(name),filenames):
src_pics.append(os.path.join(root, filename))
files = glob.glob('*.txt')
files.extend(glob.glob('*.dat'))
