我正在尝试编写一个脚本来列出给定目录中的所有目录、子目录和文件。
我尝试了这个：
import sys, os
root = "/home/patate/directory/"
path = os.path.join(root, "targetdirectory")
for r, d, f in os.walk(path):
for file in f:
print(os.path.join(root, file))
很遗憾，它不能正常工作。我可以获取所有文件，但无法获取它们的完整路径。
例如，如果目录结构如下：
/home/patate/directory/targetdirectory/123/456/789/file.txt
它会打印：
/home/patate/directory/targetdirectory/file.txt
我需要第一个结果。
这只是一个附加功能。有了它，您可以将数据以CSV格式获取：
import sys, os
try:
import pandas as pd
except:
os.system("pip3 install pandas")
root = "/home/kiran/Downloads/MainFolder" # It may have many subfolders and files inside
lst = []
from fnmatch import fnmatch
pattern = "*.csv" # I want to get only csv files
pattern = "*.*" # Note: Use this pattern to get all types of files and folders
for path, subdirs, files in os.walk(root):
for name in files:
if fnmatch(name, pattern):
lst.append((os.path.join(path, name)))
df = pd.DataFrame({"filePaths":lst})
df.to_csv("filepaths.csv")
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\n"'
subprocess.call(find_cmd, shell=True)
该命令会生成逗号分隔的值，可在Excel中轻松分析。
f-rwxrwxrwx,1,cathy,cathy,2642,2021-06-01+00:22:00.2970880000,content-audit.py
生成的 CSV 文件没有标题行，但您可以使用第二个命令添加它们。
# 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)
根据你接收到的数据量，你可以使用Pandas进一步处理它。以下是我发现的一些有用的东西，特别是如果你正在处理许多级别的目录来查找。
将这些添加到你的导入中：
import numpy as np
import pandas as pd
然后将此添加到您的代码中：
# 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