对Python 检查文件名是否规范的实例详解

如下所示：

# coding=utf-8
import os
import os.path
import re
import array
import cmd
import pdb
import pickle
import tempfile
import subprocess

# rootPath = os.getcwd()
# print rootPath
rootPath = raw_input('The Check Path:')
nonCheckDir = raw_input('The Non Check DirName(DirName1;DirName2):')
nonCheckDirList = []
if nonCheckDir:
 nonCheckDirList = nonCheckDir.split(';')
# 路径字典
pathDic = {}

# 新建文件夹 os.path.isdir(rootdir+'/logout') 判断指定目录下该文件夹是否存在
if not os.path.isdir(rootPath+'/logout'):
 os.makedirs(rootPath + '/logout')
logPath=os.path.join(rootPath,'logout')

nonstandard_filename_path = open(logPath+'/nonstandard_filename_path.txt','w')

# 标准的符号库
num = "0123456789"
word = "abcdefghijklmnopqrstuvwxyz"
sym = "_."
# 符号库
symBank = []
for key in word:
 symBank.append(key)
for key in num:
 symBank.append(key)
for key in sym:
 symBank.append(key)

def GetAllDir(getPath):
 # print (getPath)
 paths = os.listdir(getPath)
 for dirName in paths:
   dirPath = os.path.join(getPath,dirName)
   if os.path.isdir(dirPath) and dirName != '.svn':
     # print dirPath
     relPath = dirPath[len(rootPath)+1:len(dirPath)]
     # print relPath
     if not nonCheckDirList.__contains__(relPath):
       pathDic[relPath] = dirPath
       GetAllDir(dirPath)

def GetAllFile(getPath):
 files = os.listdir(getPath)
 for fileName in files:
   filePath = os.path.join(getPath,fileName)
   if fileName.endswith('.png') or fileName.endswith('.PNG'):
     fileName = fileName[0:fileName.index('.')]
     if not set(fileName).issubset(symBank):
       # print fileName
       # print filePath
       nonstandard_filename_path.write(filePath + '\n')
     else:
       # (r'_[\d]*[x|X][\d]*\d') 正则表达式 （_100x100）
       sign = re.search(r'_[\d]*[x|X][\d]*\d',fileName,re.M|re.I)
       if sign:
         nonstandard_filename_path.write(filePath + '\n')

if __name__ == '__main__':
 print ('main')
 pathDic['curPath'] = rootPath
 GetAllDir(rootPath)
 for key in pathDic:
   # print key
   GetAllFile(pathDic[key])

# line = "image_500100000"
 # obj = re.search(r'_[\d]*[x|X][\d]*\d',line,re.M|re.I)
 # line = line.replace(obj.group(),'=')
 # if obj:
 #   print obj.group()
 # else:
 #   print ("==-")
 # line1 = "image_500x100"
 # obj1 = re.search(r'[a-z0-9_]*',line1,re.M)
 # print obj1.group()

新建bat后缀文件

find_nonstandard_name.exe -c
@pause

修改后脚本

# coding=utf-8
import os
import os.path
import re
import array
import cmd
import pdb
import pickle
import tempfile
import subprocess
import sys
import getopt

rootPath = ""
nonCheckDirList = sys.argv[1:]
opts, args = getopt.getopt(sys.argv[1:],"cs:",["cPath="])
for opt,arg in opts:
 if opt == '-c':
   rootPath = os.getcwd()
 elif opt in ("-s","--cPath"):
   rootPath = arg
# 路径字典
pathDic = {}

# 新建文件夹 os.path.isdir(rootdir+'/logout') 判断指定目录下该文件夹是否存在
if not os.path.isdir(rootPath+'/logout'):
 os.makedirs(rootPath + '/logout')
logPath=os.path.join(rootPath,'logout')

nonstandard_filename_path = open(logPath+'/nonstandard_filename_path.txt','w')

def GetAllDir(getPath):
 # print (getPath)
 paths = os.listdir(getPath)
 for dirName in paths:
   dirPath = os.path.join(getPath,dirName)
   if os.path.isdir(dirPath) and dirName != '.svn':
     # print dirPath
     relPath = dirPath[len(rootPath)+1:len(dirPath)]
     # print relPath
     if not nonCheckDirList.__contains__(relPath):
       pathDic[relPath] = dirPath
       GetAllDir(dirPath)

def GetAllFile(getPath):
 files = os.listdir(getPath)
 for fileName in files:
   filePath = os.path.join(getPath,fileName)
   if fileName.endswith('.png') or fileName.endswith('.PNG'):
     fileName = fileName[0:fileName.index('.')]
     firstSign = re.search(r'^[a-z0-9_]*$',line1,re.M)
     if firstSign:
       # print filePath
       # (r'_[\d]*[x|X][\d]*\d') 正则表达式 （_100x100）
       sign = re.search(r'_[\d]*[x|X][\d]*\d', fileName, re.M | re.I)
       if sign:
         print fileName
         nonstandard_filename_path.write(filePath + '\n')
     else:
       print fileName
       nonstandard_filename_path.write(filePath + '\n')

if __name__ == '__main__':
 print ('main')
 pathDic['curPath'] = rootPath
 GetAllDir(rootPath)
 for key in pathDic:
   # print key
   GetAllFile(pathDic[key])

添加检查文件重名功能

# coding=utf-8
import os
import os.path
import re
import array
import cmd
import pdb
import pickle
import tempfile
import subprocess
import sys
import getopt

nonCheckDirList = sys.argv[1:]
rootPath = os.getcwd()
checkRepetPathList = []
if nonCheckDirList:
 rootPath = os.path.realpath(os.path.join(os.getcwd(),nonCheckDirList[0]))
 if nonCheckDirList[0] == "./":
   rootPath = os.getcwd()
 for _path in nonCheckDirList:
   # -- 检查重命名路径
   _cmdRepet = _path[0:2]
   if _cmdRepet == "/r":
     repetPath = _path[len(_cmdRepet):len(_path)]
     print repetPath
     checkRepetPathList.append(repetPath)
print rootPath + '\n'
# 路径字典
pathDic = {}
# 重名路径字典
repetDic = {}
# 新建文件夹 os.path.isdir(rootdir+'/logout') 判断指定目录下该文件夹是否存在

# if not os.path.isdir(rootPath+'/logout'):
#   os.makedirs(rootPath + '/logout')
# logPath=os.path.join(rootPath,'logout')
logPath = os.getcwd()
nonstandard_filename_path = open(logPath+"\\"+u"不规范命名文件".encode("GBK") + ".txt",'w')

def GetAllDir(getPath):
 # print (getPath)
 paths = os.listdir(getPath)
 for dirName in paths:
   dirPath = os.path.join(getPath,dirName)
   if os.path.isdir(dirPath) and dirName != '.svn':
     # print dirPath
     relPath = dirPath[len(rootPath)+1:len(dirPath)]
     # print relPath
     if not nonCheckDirList.__contains__(relPath):
       pathDic[relPath] = dirPath
       GetAllDir(dirPath)

def GetAllFile(getPath):
 files = os.listdir(getPath)
 for fileName in files:
   filePath = os.path.join(getPath,fileName)
   if fileName.endswith('.png') or fileName.endswith('.PNG'):
     fileName = fileName[0:fileName.index('.')]
     firstSign = re.search(r'^[a-z0-9_]*$',fileName,re.M)
     if firstSign:
       # print filePath
       # (r'_[\d]*[x|X][\d]*\d') 正则表达式 （_100x100）
       sign = re.search(r'_[\d]*[x|X][\d]*\d', fileName, re.M | re.I)
       if sign:
         print fileName
         nonstandard_filename_path.write(filePath + '\n')
     else:
       print fileName
       nonstandard_filename_path.write(filePath + '\n')

def CheckRepetFile(getPath):
 if checkRepetPathList:
   paths = os.listdir(getPath)
   for dirName in paths:
     dirPath = os.path.join(getPath, dirName)
     if os.path.isdir(dirPath) and dirName != '.svn':
       # print dirPath
       relPath = dirPath[len(rootPath) + 1:len(dirPath)]
       # print relPath
       repetDic[relPath] = dirPath
       CheckRepetFile(dirPath)

imageList = []
repetImagePath = []
def GetCheckRepetFile(getPath):
 files = os.listdir(getPath)
 for fileName in files:
   filePath = os.path.join(getPath, fileName)
   if fileName.endswith('.png') or fileName.endswith('.PNG'):
     # print filePath
     imageList.append(fileName)
     repetImagePath.append(filePath)

repet_filename_path = open(logPath+"\\"+u"重复命名文件".encode("GBK") + ".txt",'w')

if __name__ == '__main__':
 # print ('main')
 pathDic['curPath'] = rootPath
 GetAllDir(rootPath)
 for key in pathDic:
   # print key
   GetAllFile(pathDic[key])
 print '\n' + "The Logout Path:" + logPath+"\\"+u"不规范命名文件".encode("GBK") + ".txt"

repetDic['curPath'] = rootPath
 # 检查重复文件路径列表
 for __path in checkRepetPathList:
   _repetPath = os.path.join(rootPath, __path)
   CheckRepetFile(_repetPath)
 # 遍历路径获得所有图片
 for key in repetDic:
   GetCheckRepetFile(repetDic[key])
 _newImageList = []
 for image in imageList:
   repetCount = imageList.count(image)
   if repetCount > 1 :
     if not image in _newImageList:
       _newImageList.append(image)
 for repetImage in _newImageList:
   print repetImage
   repet_filename_path.write(repetImage + '\n')
   for repetPathPath in repetImagePath:
     fileNameName = os.path.basename(repetPathPath)
     if repetImage == fileNameName:
       repet_filename_path.write(repetPathPath + '\n')
       # print repetPathPath
 print '\n' + "The Logout Path:" + logPath+"\\"+u"重复命名文件".encode("GBK") + ".txt"

来源：https://blog.csdn.net/sinat_36373961/article/details/76559513