def get_all_psps(basedir, exchange, kind):
directory = basedir + '/' + exchange + '_' + kind
if not _os.path.isdir(directory):
_os.mkdir(directory)
ftp = _FTP('ftp.abinit.org') # connect to host, default port
ftp.login() # user anonymous, passwd anonymous@
for i in range(1, 113):
filename = psp_name(i, exchange, kind)
if not _os.path.isfile(directory + '/' + filename):
print('Getting...' + filename)
nofile = True
while nofile:
try:
res = ftp.retrbinary('RETR ' + get_ftp_psp(i, exchange, kind) + filename,
open(directory + '/' + filename, 'wb').write)
if _os.path.getsize(directory + '/' + filename) == 0:
_os.remove(directory + '/' + filename)
nofile = False
else:
nofile = False
except ValueError:
print('Could not download ' + filename)
ftp.close()
if _os.path.isfile(directory + '/' + filename):
_os.remove(directory + '/' + filename)
ftp = _FTP('ftp.abinit.org') # connect to host, default port
ftp.login() # user anonymous, passwd anonymous@
nofile = False
ftp.close()
def connect(self):
with Timeout(self.timeout):
# parse ipaddress with urllib, "//" needed
result = urllib.parse.urlsplit('//' + self.host)
if (result.port):
ftp = _FTP()
ftp.connect(result.hostname, result.port)
else:
ftp = _FTP(result.hostname)
ftp.login(self.user, self.password)
try:
yield ftp
finally:
ftp.close()
def list_order_files(user, order_id):
"""
List the file in an ARM Archive order.
Parameters
----------
user : str
Username
order_id : str or int
Order id.
Returns
-------
files : list
List of files in the order.
"""
# log into the FTP server
ftp = _FTP(_ARM_FTP)
ftp.login()
# change to the correct directory
ftp.cwd(user)
ftp.cwd(str(order_id))
return ftp.nlst()
def order_download(user, order_id, files=None):
"""
Download files from a ARM Archive order.
Files are stored in the current working directory, no return.
Parameters
----------
user : str
Username
order_id : str or int
Order id.
files : list, str or None, optional.
Files to download, either a single file, a list of files, or None
to retrieve all files in the order.
"""
# log into the FTP server
ftp = _FTP(_ARM_FTP)
ftp.login()
# change to the correct directory
ftp.cwd(user)
ftp.cwd(str(order_id))
# grab the files
if files is None:
files = ftp.nlst()
if isinstance(files, str):
files = [files]
for filename in files:
print("Retrieving:", filename)
ftp.retrbinary('RETR ' + filename, open(filename, 'wb').write)
ftp.quit()
return
def __init__(self, target, opts):
""" init """
Base.__init__(self, target, opts)
self.ftp = _FTP(timeout=3) # ftplib FTP instance
return
def connect(self):
with Timeout(self.timeout):
ftp = _FTP(self.host)
ftp.login(self.user, self.password)
try:
yield ftp
finally:
ftp.close()
def connect(self):
with Timeout(self.timeout):
ftp = _FTP(self.host)
ftp.login(self.user, self.password)
try:
yield ftp
finally:
ftp.close()
def _avail_files_dict(repository):
# Login to the FTP and get available files
iftp = _FTP(repository[0])
iftp.login()
# Go to subdirectories
for idir in repository[1:]:
iftp.cwd(idir)
# Get the ls -l output
afd = {tup[0]: tup[1] for tup in iftp.mlsd() if tup[0] not in ['.', '..']}
iftp.close()
return afd
def __init__(self, dwx_ftp_user='******',
dwx_ftp_pass='******',
dwx_ftp_hostname='<insert Darwinex Tick Data FTP host>',
dwx_ftp_port=21):
if dwx_ftp_hostname[:6] == 'ftp://':
dwx_ftp_hostname = dwx_ftp_hostname[6:]
# # Dictionary DB to hold dictionary objects in FX/Hour format
# self._asset_db = {}
self._ftpObj = _FTP(dwx_ftp_hostname)
self._ftpObj.login(dwx_ftp_user, dwx_ftp_pass)
self._virtual_dl = None
self.available_assets = self._dir('')
self._widgets_available = True
self.num_retries = 3
self.await_time = 10
print('Connected Darwinex Ticks Data Server')
def list_orders_ready(user):
"""
List all Archive orders which are ready for download.
Parameters
----------
user : str
Username
Returns
-------
order_ids : list
List of open order ids for the user.
"""
# log into the FTP server, change to users directory
ftp = _FTP(_ARM_FTP)
ftp.login()
ftp.cwd(user)
return ftp.nlst()
def getFromENA(self, run_acc_list,
ftp_server_url = 'ftp.sra.ebi.ac.uk',
local_reads_path = ['reads']):
'''
Given a list of 'run' accession numbers for paired end short read analyses,
download the read files from the European Nucleotide Archive.
If using a mirror server, supply an alternative for 'ftp_server_url'.
'local_reads_path' can be a path string or list or folder names.
'''
if isinstance(local_reads_path, list):
local_reads_path = _os.path.sep.join(local_reads_path)
if not _os.path.exists(local_reads_path):
_os.makedirs(local_reads_path)
print('Logging in to %s' % ftp_server_url)
ftp = _FTP(ftp_server_url)
# anonymous login
print(ftp.login())
def check_connection(ftp):
try:
print('FTP: %s' % ftp.voidcmd("NOOP"))
# http://docs.python.org/2/library/ftplib.html
return(True)
except IOError as e:
print('Seems to be a problem with the connection to FTP server:')
print('I/O error({0}): {1}'.format(e.errno, e.strerror) )
return(False)
def calc_checksum(filepath):
hasher = _md5()
handle = open(filepath, 'rb')
buff = handle.read(65536)
while len(buff) > 0:
hasher.update(buff)
buff = handle.read(65536)
return(hasher.hexdigest())
downloaded_read_files = {}
start_time = _time.time()
failed = []
for cnum,run_acc in enumerate(run_acc_list):
query_url_base = 'http://www.ebi.ac.uk/ena/data/warehouse/search?query='
success = False
tries = 0
max_tries = 5
while not success:
rest_req = '"run_accession=%s"&result=read_run&fields=fastq_ftp,fastq_md5&display=report' % run_acc
print('Sending query to ENA:\n%s' % rest_req)
result = _urllib2.urlopen(query_url_base + rest_req).read()
print('ENA accession numbers query result:\n%s' % result)
if result.count('ERR') == 7:
success = True
else:
print('Query result from ENA was unexpected on attempt %s of %s' % (tries, max_tries))
_time.sleep(0.5)
tries += 1
if tries == max_tries:
print('Attempt %s failed. Try again later and if problem persists, report bug.' % tries)
failed += [run_acc]
break
#_sys.exit(1)
if not success:
continue
md5s = result.split('\n')[-2].split('\t')[-1][:-1].split(';')
ENA_paths = result.split('\n')[-2].split('\t')[-2][:-1].split(';')
ENA_reads_pair_paths = {}
ENA_reads_pair_paths[1] = ENA_paths[0].replace(ftp_server_url, '')
ENA_reads_pair_paths[2] = ENA_paths[1].replace(ftp_server_url, '')
local_reads_pair_paths = {}
local_reads_pair_paths[1] = local_reads_path + \
_os.path.sep + \
ENA_reads_pair_paths[1].split('/')[-1]
local_reads_pair_paths[2] = local_reads_path + \
_os.path.sep + \
ENA_reads_pair_paths[2].split('/')[-1]
downloaded_read_files[run_acc] = {}
for f in (1,2):
# ensure connection is still open
while not check_connection(ftp):
_sleep(0.5)
print('Attempting to re-establish connection . . .')
ftp = _FTP(ftp_server_url)
# anonymous login
print(ftp.login())
pass
expected_checksum = md5s[f - 1]
exists = _os.path.exists(local_reads_pair_paths[f])
if exists:
print('File %s for %s exists locally: %s' % (f, run_acc, local_reads_pair_paths[f]))
actual_checksum = calc_checksum(local_reads_pair_paths[f])
if actual_checksum == expected_checksum:
print('File checksum matches: %s. Skipping download' % (expected_checksum))
downloaded_read_files[run_acc][f] = local_reads_pair_paths[f]
continue
else:
print('Checksum mismatch')
print('Downloading via %s: %s' % (ftp_server_url, ENA_reads_pair_paths[f]))
res = ftp.retrbinary('RETR %s' % ENA_reads_pair_paths[f],
open(local_reads_pair_paths[f], 'wb').write)
print('FTP: %s' % res)
print('Calculating checksum . . .')
actual_checksum = calc_checksum(local_reads_pair_paths[f])
if actual_checksum == expected_checksum:
print('File checksum matches: %s.' % (expected_checksum))
downloaded_read_files[run_acc][f] = local_reads_pair_paths[f]
else:
print('Checksum mismatch for: %s')
if len(run_acc_list) > 1:
# report durations, time left etc
_report_time(start_time, cnum, len(run_acc_list))
if len(failed) > 0:
print('WARNING: some accession numbers did not return a result from ENA')
print('Try searching http://www.ebi.ac.uk/ena in a web-browser for:')
print(', '.join(failed))
self.read_files = downloaded_read_files
def __init__(self, host, initpath='.'):
from ftplib import FTP as _FTP
self.conn = _FTP(host)
self.conn.login('anonymous', '*****@*****.**')
self.conn.cwd(initpath)
def getFromENA(self,
run_acc_list,
ftp_server_url='ftp.sra.ebi.ac.uk',
local_reads_path=['reads']):
'''
Given a list of 'run' accession numbers for paired end short read analyses,
download the read files from the European Nucleotide Archive.
If using a mirror server, supply an alternative for 'ftp_server_url'.
'local_reads_path' can be a path string or list or folder names.
'''
if isinstance(local_reads_path, list):
local_reads_path = _os.path.sep.join(local_reads_path)
if not _os.path.exists(local_reads_path):
_os.makedirs(local_reads_path)
print('Logging in to %s' % ftp_server_url)
ftp = _FTP(ftp_server_url)
# anonymous login
print(ftp.login())
def check_connection(ftp):
try:
print('FTP: %s' % ftp.voidcmd("NOOP"))
# http://docs.python.org/2/library/ftplib.html
return (True)
except IOError as e:
print(
'Seems to be a problem with the connection to FTP server:')
print('I/O error({0}): {1}'.format(e.errno, e.strerror))
return (False)
def calc_checksum(filepath):
hasher = _md5()
handle = open(filepath, 'rb')
buff = handle.read(65536)
while len(buff) > 0:
hasher.update(buff)
buff = handle.read(65536)
return (hasher.hexdigest())
downloaded_read_files = {}
start_time = _time.time()
failed = []
for cnum, run_acc in enumerate(run_acc_list):
query_url_base = 'http://www.ebi.ac.uk/ena/data/warehouse/search?query='
success = False
tries = 0
max_tries = 5
while not success:
rest_req = '"run_accession=%s"&result=read_run&fields=fastq_ftp,fastq_md5&display=report' % run_acc
print('Sending query to ENA:\n%s' % rest_req)
result = _urllib2.urlopen(query_url_base + rest_req).read()
print('ENA accession numbers query result:\n%s' % result)
if result.count('ERR') == 7:
success = True
else:
print(
'Query result from ENA was unexpected on attempt %s of %s'
% (tries, max_tries))
_time.sleep(0.5)
tries += 1
if tries == max_tries:
print(
'Attempt %s failed. Try again later and if problem persists, report bug.'
% tries)
failed += [run_acc]
break
#_sys.exit(1)
if not success:
continue
md5s = result.split('\n')[-2].split('\t')[-1][:-1].split(';')
ENA_paths = result.split('\n')[-2].split('\t')[-2][:-1].split(';')
ENA_reads_pair_paths = {}
ENA_reads_pair_paths[1] = ENA_paths[0].replace(ftp_server_url, '')
ENA_reads_pair_paths[2] = ENA_paths[1].replace(ftp_server_url, '')
local_reads_pair_paths = {}
local_reads_pair_paths[1] = local_reads_path + \
_os.path.sep + \
ENA_reads_pair_paths[1].split('/')[-1]
local_reads_pair_paths[2] = local_reads_path + \
_os.path.sep + \
ENA_reads_pair_paths[2].split('/')[-1]
downloaded_read_files[run_acc] = {}
for f in (1, 2):
# ensure connection is still open
while not check_connection(ftp):
_sleep(0.5)
print('Attempting to re-establish connection . . .')
ftp = _FTP(ftp_server_url)
# anonymous login
print(ftp.login())
pass
expected_checksum = md5s[f - 1]
exists = _os.path.exists(local_reads_pair_paths[f])
if exists:
print('File %s for %s exists locally: %s' %
(f, run_acc, local_reads_pair_paths[f]))
actual_checksum = calc_checksum(local_reads_pair_paths[f])
if actual_checksum == expected_checksum:
print('File checksum matches: %s. Skipping download' %
(expected_checksum))
downloaded_read_files[run_acc][
f] = local_reads_pair_paths[f]
continue
else:
print('Checksum mismatch')
print('Downloading via %s: %s' %
(ftp_server_url, ENA_reads_pair_paths[f]))
res = ftp.retrbinary(
'RETR %s' % ENA_reads_pair_paths[f],
open(local_reads_pair_paths[f], 'wb').write)
print('FTP: %s' % res)
print('Calculating checksum . . .')
actual_checksum = calc_checksum(local_reads_pair_paths[f])
if actual_checksum == expected_checksum:
print('File checksum matches: %s.' % (expected_checksum))
downloaded_read_files[run_acc][f] = local_reads_pair_paths[
f]
else:
print('Checksum mismatch for: %s')
if len(run_acc_list) > 1:
# report durations, time left etc
_report_time(start_time, cnum, len(run_acc_list))
if len(failed) > 0:
print(
'WARNING: some accession numbers did not return a result from ENA'
)
print(
'Try searching http://www.ebi.ac.uk/ena in a web-browser for:')
print(', '.join(failed))
self.read_files = downloaded_read_files
def _create_ftp(self) -> _FTP:
return _FTP(self.host, **self.__kwargs)
