python3 yield 实现 os.walk 的功能

centos6.7         python-3.5.2

os.walk(dir) 函数生成一个generator 

用for遍历可以访问dir文件夹下所有的文件或文件夹

#!/usr/bin/env python3
import os
from os.path import isdir,join
def conv(f):
    lf=os.listdir(f) #获取f目录下的一级子目录和文件
    df=[i for i in lf if isdir(join(f,i))] #一级子目录
    ff=list(set(lf)-set(df))    #f目录下的文件
    return (f,df,ff)
    
def walk(f):              
    yield conv(f)
    for e in conv(f)[1]:
        tf=join(conv(f)[0],e) #给目录名加上前导路径
        yield conv(tf)
        for a,b,c in walk(tf):  #遍历子目录的文件和目录
 	        for k in b:
 	            yield conv(join(a,k))
 	         	                 	             	    
for i in walk('.'):
    print(i)

运行结果：

[willie@localhost .walker]$ python3 ../walk.py
('.', ['a', 'b'], ['d', 'c'])
('./a', ['ac'], ['aa', 'ab'])
('./a/ac', [], ['aca'])
('./b', [], [])

[willie@localhost .walker]$ python3
Python 3.5.2 (default, Dec  7 2016, 23:38:49) 
[GCC 4.4.7 20120313 (Red Hat 4.4.7-17)] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import os
>>> for i in os.walk('.'):
... print(i)
... 
('.', ['a', 'b'], ['d', 'c'])
('./a', ['ac'], ['ab', 'aa'])
('./a/ac', [], ['aca'])
('./b', [], [])

百度得 os.walk 的官方源码为：

def walk(top, topdown=True, οnerrοr=None, followlinks=False):  
    """Directory tree generator. 
 
    For each directory in the directory tree rooted at top (including top 
    itself, but excluding '.' and '..'), yields a 3-tuple 
 
        dirpath, dirnames, filenames 
 
    dirpath is a string, the path to the directory.  dirnames is a list of 
    the names of the subdirectories in dirpath (excluding '.' and '..'). 
    filenames is a list of the names of the non-directory files in dirpath. 
    Note that the names in the lists are just names, with no path components. 
    To get a full path (which begins with top) to a file or directory in 
    dirpath, do os.path.join(dirpath, name). 
 
    If optional arg 'topdown' is true or not specified, the triple for a 
    directory is generated before the triples for any of its subdirectories 
    (directories are generated top down).  If topdown is false, the triple 
    for a directory is generated after the triples for all of its 
    subdirectories (directories are generated bottom up). 
 
    When topdown is true, the caller can modify the dirnames list in-place 
    (e.g., via del or slice assignment), and walk will only recurse into the 
    subdirectories whose names remain in dirnames; this can be used to prune 
    the search, or to impose a specific order of visiting.  Modifying 
    dirnames when topdown is false is ineffective, since the directories in 
    dirnames have already been generated by the time dirnames itself is 
    generated. 
 
    By default errors from the os.listdir() call are ignored.  If 
    optional arg 'onerror' is specified, it should be a function; it 
    will be called with one argument, an os.error instance.  It can 
    report the error to continue with the walk, or raise the exception 
    to abort the walk.  Note that the filename is available as the 
    filename attribute of the exception object. 
 
    By default, os.walk does not follow symbolic links to subdirectories on 
    systems that support them.  In order to get this functionality, set the 
    optional argument 'followlinks' to true. 
 
    Caution:  if you pass a relative pathname for top, don't change the 
    current working directory between resumptions of walk.  walk never 
    changes the current directory, and assumes that the client doesn't 
    either. 
 
    Example: 
 
    import os 
    from os.path import join, getsize 
    for root, dirs, files in os.walk('python/Lib/email'): 
        print root, "consumes", 
        print sum([getsize(join(root, name)) for name in files]), 
        print "bytes in", len(files), "non-directory files" 
        if 'CVS' in dirs: 
            dirs.remove('CVS')  # don't visit CVS directories 
    """  
  
    islink, join, isdir = path.islink, path.join, path.isdir  
  
    # We may not have read permission for top, in which case we can't  
    # get a list of the files the directory contains.  os.path.walk  
    # always suppressed the exception then, rather than blow up for a  
    # minor reason when (say) a thousand readable directories are still  
    # left to visit.  That logic is copied here.  
    try:  
        # Note that listdir and error are globals in this module due  
        # to earlier import-*.  
        names = listdir(top)  
    except error, err:  
        if onerror is not None:  
            onerror(err)  
        return  
  
    dirs, nondirs = [], []  
    for name in names:  
        if isdir(join(top, name)):  
            dirs.append(name)  
        else:  
            nondirs.append(name)  
  
    if topdown:  
        yield top, dirs, nondirs  
    for name in dirs:  
        new_path = join(top, name)  
        if followlinks or not islink(new_path):  
            for x in walk(new_path, topdown, onerror, followlinks):  
                yield x  
    if not topdown:  
        yield top, dirs, nondirs