from pathlib import Path


def generate_all_files(root: Path, only_files: bool = True):
    for p in root.rglob("*"):
        if only_files and not p.is_file():
            continue
        yield p


for p in generate_all_files(Path("."), only_files=False):
    print(p)

如果你想得到一些复制件:

Example

颜色结构:

$ tree . -a
.
├── a.txt
├── bar
├── b.py
├── collect.py
├── empty
├── foo
│   └── bar.bz.gz2
├── .hidden
│   └── secrect-file
└── martin
    └── thoma
        └── cv.pdf

说明:

$ python collect.py 
bar
empty
.hidden
collect.py
a.txt
b.py
martin
foo
.hidden/secrect-file
martin/thoma
martin/thoma/cv.pdf
foo/bar.bz.gz2

import os

root = r"\mycompany.sharepoint.com@SSLDavWWWRoot	eamsMyFolderPolicies and ProceduresDeal DocsMy Deals"
list = [os.path.join(path, name) for path, subdirs, files in os.walk(root) for name in files]
print(list)

一种简单的解决办法是,将多个次程序要求将档案出口到特别安全局格式:

import subprocess

# Global variables for directory being mapped

location =  .  # Enter the path here.
pattern =  *.py  # Use this if you want to only return certain filetypes
rootDir = location.rpartition( / )[-1]
outputFile = rootDir +  _directory_contents.csv 

# Find the requested data and export to CSV, specifying a pattern if needed.
find_cmd =  find   + location +   -name   + pattern +    -fprintf   + outputFile +    "%Y%M,%n,%u,%g,%s,%A+,%P
" 
subprocess.call(find_cmd, shell=True)

该指挥部产生了可轻易在Excel分析的混合价值。

f-rwxrwxrwx,1,cathy,cathy,2642,2021-06-01+00:22:00.2970880000,content-audit.py

由此而来的CSV档案没有头盔,但可以使用第二部指挥来补充。

# Add headers to the CSV
headers_cmd =  sed -i.bak 1i"Permissions,Links,Owner,Group,Size,ModifiedTime,FilePath"   + outputFile
subprocess.call(headers_cmd, shell=True)

增加进口:

import numpy as np
import pandas as pd

接着,在您的法典中加入:

# Create DataFrame from the CSV file created above.
df = pd.read_csv(outputFile)

# Format columns
# Get the filename and file extension from the filepath
df[ FileName ] = df[ FilePath ].str.rsplit("/", 1).str[-1]
df[ FileExt ] = df[ FileName ].str.rsplit( . , 1).str[1]

# Get the full path to the files. If the path doesn t include a "/" it s the root directory
df[ FullPath ] = df["FilePath"].str.rsplit("/", 1).str[0]
df[ FullPath ] = np.where(df[ FullPath ].str.contains("/"), df[ FullPath ], rootDir)

# Split the path into columns for the parent directory and its children
df[ ParentDir ] = df[ FullPath ].str.split("/", 1).str[0]
df[ SubDirs ] = df[ FullPath ].str.split("/", 1).str[1]
# Account for NaN returns, indicates the path is the root directory
df[ SubDirs ] = np.where(df.SubDirs.str.contains( NaN ),   , df.SubDirs)

# Determine if the item is a directory or file.
df[ Type ] = np.where(df[ Permissions ].str.startswith( d ),  Dir ,  File )

# Split the time stamp into date and time columns
df[[ ModifiedDate ,  Time ]] = df.ModifiedTime.str.rsplit( + , 1, expand=True)
df[ Time ] = df[ Time ].str.split( . ).str[0]

# Show only files, output includes paths so you don t necessarily need to display the individual directories.
df = df[df[ Type ].str.contains( File )]

# Set columns to show and their order.
df = df[[ FileName ,  ParentDir ,  SubDirs ,  FullPath ,  DocType ,  ModifiedDate ,  Time ,  Size ]]

filesize = [] # Create an empty list to store file sizes to convert them to something more readable.

# Go through the items and convert the filesize from bytes to something more readable.
for items in df[ Size ].items():
    filesize.append(convert_bytes(items[1]))
    df[ Size ] = filesize

# Send the data to an Excel workbook with sheets by parent directory
with pd.ExcelWriter("scripts_directory_contents.xlsx") as writer:
    for directory, data in df.groupby( ParentDir ):
    data.to_excel(writer, sheet_name = directory, index=False)


# To convert sizes to be more human readable
def convert_bytes(size):
    for x in [ b ,  K ,  M ,  G ,  T ]:
        if size < 1024:
            return "%3.1f %s" % (size, x)
        size /= 1024

    return size