如何使用glob（）递归查找文件？

#1 楼

from pathlib import Path

for path in Path('src').rglob('*.c'):
    print(path.name)

import fnmatch
import os

matches = []
for root, dirnames, filenames in os.walk('src'):
    for filename in fnmatch.filter(filenames, '*.c'):
        matches.append(os.path.join(root, filename))

#2 楼

import os, fnmatch


def find_files(directory, pattern):
    for root, dirs, files in os.walk(directory):
        for basename in files:
            if fnmatch.fnmatch(basename, pattern):
                filename = os.path.join(root, basename)
                yield filename


for filename in find_files('src', '*.c'):
    print 'Found C source:', filename

#3 楼

>>> import glob2
>>> all_header_files = glob2.glob('src/**/*.c')

#4 楼

 from pathlib import Path

for file_path in Path('src').glob('**/*.c'):
    print(file_path) # do whatever you need with these files
 

#5 楼

import glob
for x in glob.glob('/path/**/*.c', recursive=True):
    print(x)

#6 楼

import os
import fnmatch


def recursive_glob(treeroot, pattern):
    results = []
    for base, dirs, files in os.walk(treeroot):
        goodfiles = fnmatch.filter(files, pattern)
        results.extend(os.path.join(base, f) for f in goodfiles)
    return results

#7 楼

import os
cfiles = []
for root, dirs, files in os.walk('src'):
  for file in files:
    if file.endswith('.c'):
      cfiles.append(os.path.join(root, file))

#8 楼

import os
cfiles = [os.path.join(root, filename)
          for root, dirnames, filenames in os.walk('src')
          for filename in filenames if filename.endswith('.c')]

import os;cfiles=[os.path.join(r,f) for r,d,fs in os.walk('src') for f in fs if f.endswith('.c')]

import os

def recursive_glob(rootdir='.', suffix=''):
    return [os.path.join(looproot, filename)
            for looproot, _, filenames in os.walk(rootdir)
            for filename in filenames if filename.endswith(suffix)]

cfiles = recursive_glob('src', '.c')

import fnmatch
import os

def recursive_glob(rootdir='.', pattern='*'):
    return [os.path.join(looproot, filename)
            for looproot, _, filenames in os.walk(rootdir)
            for filename in filenames
            if fnmatch.fnmatch(filename, pattern)]

cfiles = recursive_glob('src', '*.c')

#9 楼

import pathlib


for p in pathlib.Path("src").rglob("*.c"):
    print(p)

#10 楼

#!/usr/binenv python2.7

import glob
import shutil
import os

src_dir = "/home/mustafa/Masaüstü/yedek"
dst_dir = "/home/mustafa/Genel/media"
for mediafile in glob.iglob(os.path.join(src_dir, "*", "*.jpg")): #"*" is for subdirectory
    shutil.copy(mediafile, dst_dir)

#11 楼

files = []
for root, dirnames, filenames in os.walk(myDir):
    files.extend(glob.glob(root + "/*.xml"))

#12 楼

import formic
fileset = formic.FileSet(include="/src/**/*.c")
for file_name in fileset.qualified_files():
    print file_name

#13 楼

import glob

#file_names_array = glob.glob('path/*.c', recursive=True)
#above works for files directly at path/ as guided by NeStack

#updated version
file_names_array = glob.glob('path/**/*.c', recursive=True)

for full_path_in_src in  file_names_array:
    print (full_path_in_src ) # be like 'abc/xyz.c'
    #Full system path of this would be like => 'path till src/abc/xyz.c'

#14 楼

import glob
import os

def _getDirs(base):
    return [x for x in glob.iglob(os.path.join( base, '*')) if os.path.isdir(x) ]

def rglob(base, pattern):
    list = []
    list.extend(glob.glob(os.path.join(base,pattern)))
    dirs = _getDirs(base)
    if len(dirs):
        for d in dirs:
            list.extend(rglob(os.path.join(base,d), pattern))
    return list

#15 楼

 >>> base = r"c:\User\xtofl"
 >>> binfiles = [ os.path.join(base,f) 
            for base, _, files in os.walk(root) 
            for f in files if f.endswith(".jpg") ] 

#16 楼

 import os, glob

for each in glob.glob('path/**/*.c', recursive=True):
    print(f'Name with path: {each} \nName without path: {os.path.basename(each)}')
 

#17 楼

#!/usr/bin/python

import os,glob,sys

def dirlist(path, c = 1):

        for i in glob.glob(os.path.join(path, "*")):
                if os.path.isfile(i):
                        filepath, filename = os.path.split(i)
                        print '----' *c + filename

                elif os.path.isdir(i):
                        dirname = os.path.basename(i)
                        print '----' *c + dirname
                        c+=1
                        dirlist(i,c)
                        c-=1


path = os.path.normpath(sys.argv[1])
print(os.path.basename(path))
dirlist(path)

#18 楼

import fnmatch, os

def filepaths(directory, pattern):
    for root, dirs, files in os.walk(directory):
        for basename in files:
            try:
                matched = pattern.match(basename)
            except AttributeError:
                matched = fnmatch.fnmatch(basename, pattern)
            if matched:
                yield os.path.join(root, basename)

# usage
if __name__ == '__main__':
    from pprint import pprint as pp
    import re
    path = r'/Users/hipertracker/app/myapp'
    pp([x for x in filepaths(path, re.compile(r'.*\.py$'))])
    pp([x for x in filepaths(path, '*.py')])

#19 楼

import os, glob, itertools

results = itertools.chain.from_iterable(glob.iglob(os.path.join(root,'*.c'))
                                               for root, dirs, files in os.walk('src'))

for f in results: print(f)

#20 楼

import os

matches = []
for root, dirnames, filenames in os.walk('src'):
  matches += [os.path.join(root, f) for f in filenames if f[-2:] == '.c']

#21 楼

import os, glob

def _globrec(path, *exts):
""" Glob recursively a directory and all subdirectories for multiple file extensions 
    Note: Glob is case-insensitive, i. e. for '\*.jpg' you will get files ending
    with .jpg and .JPG

    Parameters
    ----------
    path : str
        A directory name
    exts : tuple
        File extensions to glob for

    Returns
    -------
    files : list
        list of files matching extensions in exts in path and subfolders

    """
    dirs = [a[0] for a in os.walk(path)]
    f_filter = [d+e for d in dirs for e in exts]    
    return [f for files in [glob.iglob(files) for files in f_filter] for f in files]

my_pictures = _globrec(r'C:\Temp', '\*.jpg','\*.bmp','\*.png','\*.gif')
for f in my_pictures:
    print f

#22 楼

def flipProperties(searchDir):
   print "Flipping properties to point to live DB"
   for root, dirnames, filenames in os.walk(searchDir):
      for filename in fnmatch.filter(filenames, 'live-*.*'):
        targetFileName = os.path.join(root, filename.split("live-")[1])
        print "File "+ os.path.join(root, filename) + "will be moved to " + targetFileName
        shutil.move(os.path.join(root, filename), targetFileName)

flipProperties(searchDir)

#23 楼

import glob
import json
import fnmatch
import os
from pathlib import Path
from time import time


def find_files_iglob():
    return glob.iglob("./data/**/data.json", recursive=True)


def find_files_oswalk():
    for root, dirnames, filenames in os.walk('data'):
        for filename in fnmatch.filter(filenames, 'data.json'):
            yield os.path.join(root, filename)

def find_files_rglob():
    return Path('data').rglob('data.json')

t0 = time()
for f in find_files_oswalk(): pass    
t1 = time()
for f in find_files_rglob(): pass
t2 = time()
for f in find_files_iglob(): pass 
t3 = time()
print(t1-t0, t2-t1, t3-t2)

#24 楼

import sys, os, glob

dir_list = ["c:\books\heap"]

while len(dir_list) > 0:
    cur_dir = dir_list[0]
    del dir_list[0]
    list_of_files = glob.glob(cur_dir+'\*')
    for book in list_of_files:
        if os.path.isfile(book):
            print(book)
        else:
            dir_list.append(book)

#25 楼

import time
import fnmatch
import os

def fileinfo(file):
    filename = os.path.basename(file)
    rootdir = os.path.dirname(file)
    lastmod = time.ctime(os.path.getmtime(file))
    creation = time.ctime(os.path.getctime(file))
    filesize = os.path.getsize(file)

    print "%s**\t%s\t%s\t%s\t%s" % (rootdir, filename, lastmod, creation, filesize)

searchdir = r'D:\Your\Directory\Root'
matches = []

for root, dirnames, filenames in os.walk(searchdir):
    ##  for filename in fnmatch.filter(filenames, '*.c'):
    for filename in filenames:
        ##      matches.append(os.path.join(root, filename))
        ##print matches
        fileinfo(os.path.join(root, filename))

#26 楼

import fnmatch
import os
import re

def findfiles(dir, pattern):
    patternregex = fnmatch.translate(pattern)
    for root, dirs, files in os.walk(dir):
        for basename in files:
            filename = os.path.join(root, basename)
            if re.search(patternregex, filename, re.IGNORECASE):
                yield filename

#27 楼

 from fsspec.implementations.zip import ZipFileSystem
fs = ZipFileSystem("/tmp/test.zip")
fs.glob("/**")  # equivalent: fs.find("/")
 

 from s3fs import S3FileSystem
fs_s3 = S3FileSystem(anon=True)
fs_s3.glob("noaa-goes16/ABI-L1b-RadF/2020/045/**")  # or use fs_s3.find
 

 from fsspec.implementations.local import LocalFileSystem
fs = LocalFileSystem()
fs.glob("/tmp/test/**")
 

#28 楼

import subprocess
foundfiles= subprocess.check_output("ls src/*.c src/**/*.c", shell=True)
for foundfile in foundfiles.splitlines():
    print foundfile