Extending Python's os.walk function on FTP server
All you need is utilizing the python's ftplib
module. Since os.walk()
is based on a Breadth-first search algorithm you need to find the directories and file names at each iteration, then continue the traversing recursively from the first directory. I implemented this algorithm about 2 years ago for using as the heart of FTPwalker, which is an optimum package for traversing extremely large directory trees Through FTP.
from os import path as ospath
class FTPWalk:
"""
This class is contain corresponding functions for traversing the FTP
servers using BFS algorithm.
"""
def __init__(self, connection):
self.connection = connection
def listdir(self, _path):
"""
return files and directory names within a path (directory)
"""
file_list, dirs, nondirs = [], [], []
try:
self.connection.cwd(_path)
except Exception as exp:
print ("the current path is : ", self.connection.pwd(), exp.__str__(),_path)
return [], []
else:
self.connection.retrlines('LIST', lambda x: file_list.append(x.split()))
for 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 a BFS algorithm.
"""
dirs, nondirs = self.listdir(path)
yield path, dirs, nondirs
for name in dirs:
path = ospath.join(path, name)
yield from self.walk(path)
# In python2 use:
# for path, dirs, nondirs in self.walk(path):
# yield path, dirs, nondirs
self.connection.cwd('..')
path = ospath.dirname(path)
Now for using this class, you can simply create a connection object using ftplib
module and pass the the object to FTPWalk
object and just loop over the walk()
function:
In [2]: from 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]: for i 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'])
...
...
...