algorithm - Extending Python's os.walk function on FTP server -

how can make os.walk traverse directory tree of ftp database (located on remote server)? way code structured (comments provided):

import fnmatch, os, ftplib  def find(pattern, startdir=os.curdir): #find function taking variables both desired file , starting directory     (thisdir, subshere, fileshere) in os.walk(startdir): #each of variables change directory tree walked         name in subshere + fileshere: #going through of files , subdirectories             if fnmatch.fnmatch(name, pattern): #if name of 1 of files or subs same inputted name                 fullpath = os.path.join(thisdir, name) #fullpath equals concatenation of directory , name                 yield fullpath #return fullpath anew each time  def findlist(pattern, startdir = os.curdir, dosort=false):     matches = list(find(pattern, startdir)) #find arguments pattern , startdir put list data structure     if dosort: matches.sort() #isn't dosort automatically false? statement different same thing line in between     return matches  #def ftp( #specifying search.  if __name__ == '__main__':     import sys     namepattern, startdir = sys.argv[1], sys.argv[2]     name in find(namepattern, startdir): print (name) 

i thinking need define new function (i.e., def ftp()) add functionality code above. however, afraid os.walk function will, default, walk directory trees of computer code run from.

is there way can extend functionality of os.walk able traverse remote directory tree (via ftp)?

all need utilizing python's ftplib module. since os.walk() based on breadth-first search algorithm need find directories , file names @ each iteration, continue traversing recursively first directory. implemented this algorithm 2 years ago using heart of ftpwalker, optimum package traversing extremely large directory trees through ftp.

from os import path ospath   class ftpwalk:     """     class contain corresponding functions traversing ftp     servers using bfs algorithm.     """     def __init__(self, connection):         self.connection = connection      def listdir(self, _path):         """         return files , directory names within path (directory)         """          file_list, dirs, nondirs = [], [], []         try:             self.connection.cwd(_path)         except exception exp:             print ("the current path : ", self.connection.pwd(), exp.__str__(),_path)             return [], []         else:             self.connection.retrlines('list', lambda x: file_list.append(x.split()))             info in file_list:                 ls_type, name = info[0], info[-1]                 if ls_type.startswith('d'):                     dirs.append(name)                 else:                     nondirs.append(name)             return dirs, nondirs      def walk(self, path='/'):         """         walk through ftp server's directory tree, based on bfs algorithm.         """         dirs, nondirs = self.listdir(path)         yield path, dirs, nondirs         name in dirs:             path = ospath.join(path, name)             yield self.walk(path)             # in python2 use:             # path, dirs, nondirs in self.walk(path):             #     yield path, dirs, nondirs             self.connection.cwd('..')             path = ospath.dirname(path) 

now using class, can create connection object using ftplib module , pass the object ftpwalk object , loop on walk() function:

in [2]: test import ftpwalk  in [3]: import ftplib  in [4]: connection = ftplib.ftp("ftp.uniprot.org")  in [5]: connection.login() out[5]: '230 login successful.'  in [6]: ftpwalk = ftpwalk(connection)  in [7]: in ftpwalk.walk():             print(i)    ...:      ('/', ['pub'], []) ('/pub', ['databases'], ['robots.txt']) ('/pub/databases', ['uniprot'], []) ('/pub/databases/uniprot', ['current_release', 'previous_releases'], ['license', 'current_release/readme', 'current_release/knowledgebase/complete', 'previous_releases/', 'current_release/relnotes.txt', 'current_release/uniref']) ('/pub/databases/uniprot/current_release', ['decoy', 'knowledgebase', 'rdf', 'uniparc', 'uniref'], ['readme', 'release.metalink', 'changes.html', 'news.html', 'relnotes.txt']) ... ... ...