Python与文件搜索

 最近在用Python写一个文件管理程序，积累了不少的经验。Python 有个os的模块，对目录文件的操作很好用。

 

(1) 显示在给定目录的所有给定扩展名的文件( import os first) 

 17 def listFileExt(directory, fileExtList):
 18     '''Only list files with specified extension in the given dir
 19     @return specified file list'''
 20     fileList = []
 21     for f in os.listdir(directory):
 22         fileList.append(os.path.normcase(f))
 23     newfileList = []
 24     for f in fileList:
 25         if os.path.splitext(f)[1] in fileExtList:
 26             newfileList.append(os.path.join(directory, f))
 27     return newfileList

(2) 在一个文件中搜索指定的字符串

171 '''---------------------------------------------------------------
172 used to search a specified substring in files in a given directory
173 '''
174 def searchSubstrInFile(filepath, Substr,DETAIL=0):
175     '''initally use it to search Cheetah path
176     then use it for general search'''
177     try:
178         fsock = open(os.path.normcase(filepath), "r")
179         try:
180             fLines = fsock.readlines()
181             fsock.close()
182             import re
183             pattern = re.compile(Substr)
184             lineNum = []
185             index = 0
186             for line in fLines:
187                 result = pattern.search(line)
188                 if result:
189                     lineNum.append(index)
190                 index = index +1
191             if len(lineNum) > 0:
192                 if DETAIL:
193                     print "filepath: ",filepath
194                     for index in lineNum:
195                         print "lineNum",index+1,": ",fLines[index].strip('/n')
196                     print ""
197                 else:
198                     print filepath
199                 return 1
200             else:
201                 return 0
202         except IOError:
203             print "Internal IOError"
204             pass
205 
206     except IOError:
207         print "IOError"
208         pass

(3) 在一个文件夹中搜索指定的字符串，采用广度优先(BFA)

312 def searchSubstrInDir(directory, Substr,DETAIL=0):
313     (fileList, dirList) = listFileDir(directory)
314     "existed = searchFileName(fileList,searchSubstr)"
315     existed = 0
316     for f in fileList:
317         hit = searchSubstrInFile(f,Substr,DETAIL)
318         if hit:
319             existed = 1
320 
321     for dir in dirList:
322         searchSubstrInDir(dir, Substr, DETAIL)
323     if existed:
324         return 1
325     else:
326         return 0
(4) 在一组文件夹中搜索指定的字符串，简单的调用(3)即可

328 def searchSubstrInDirlist(dirlist, Substr, DETAIL=0):
329     for dir  in dirlist:
330         searchSubstrInDir(dir, Substr, DETAIL) 

(5) 在某个文件夹中搜索文件名中包含指定字符串的文件

332 '''---------------------------------------------------------------------
333 search files whose name contains specified substring in a directory
334 '''
335 def searchNameInFilelist(fileList, Substr):
336     hitList = []
337     import re
338     pattern = re.compile(Substr)
339     for f in fileList:
340         hit = pattern.search(f)
341         if hit:
342             hitList.append(f)
343 
344     for f in hitList:
345         print f
346 
347     return hitList
348 
349 
350 def searchNameInDir(directory, Substr):
351     (fileList, dirList) = listFileDir(directory)
352     mainHitlist = []
353     mainHitlist = mainHitlist + searchNameInFilelist(fileList,Substr)
354 
355     for dir in dirList:
356         mainHitlist = mainHitlist + searchNameInDir(dir, Substr)
357     return mainHitlist