尝试使用python ftplib从NCBI ftp下载一系列存档,但ftplib在长时间文件传输结束时冻结
我正在尝试下载nr blastdabase表单NCBIs ftp站点()。其中一个文件相当大(16GB),下载需要一些时间。在下载完这个文件后,程序就挂起了,它不会移动到下一个文件 我的程序中与下载文件相关的部分是:尝试使用python ftplib从NCBI ftp下载一系列存档,但ftplib在长时间文件传输结束时冻结,python,ftplib,ncbi,Python,Ftplib,Ncbi,我正在尝试下载nr blastdabase表单NCBIs ftp站点()。其中一个文件相当大(16GB),下载需要一些时间。在下载完这个文件后,程序就挂起了,它不会移动到下一个文件 我的程序中与下载文件相关的部分是: from pathlib import Path import ftplib from tqdm import tqdm def _file_write_progress(block, fh, pbar): """Write ftp file
from pathlib import Path
import ftplib
from tqdm import tqdm
def _file_write_progress(block, fh, pbar):
"""Write ftp file and updates progress bar.
Args:
block (binary): Block of data received from ftp.retrbinary
fh (BufferedWriter): Open file to write to in wb mode
pbar (ProgressBar): Progress bar to update with download progress
"""
fh.write(block)
pbar.update(len(block))
def _download_ftp_files(url, remote_path, files_list, db_dir):
"""Download ftp file and update progress bar.
Args:
url (str): Url of ftp server to connect to
remote_path (str): Path to directory containing tartget files
files_list (list(str)): List of files to download
db_dir (Path): Path to local directory to download files to
"""
ftp = ftplib.FTP(url, timeout=3600)
ftp.login()
ftp.cwd(remote_path)
for fn in tqdm(files_list, desc="Downloading file #"):
with (db_dir / fn).open('wb') as fh:
pbar = tqdm(desc=fn, total=ftp.size(fn))
ftp.retrbinary(
'RETR ' + fn,
lambda block: _file_write_progress(block, fh, pbar),
1024*1024
)
ftp.close()
我认为这个问题与ftp连接超时有关,但我似乎无法修复它
我在和尝试过解决方案,但似乎无法使其发挥作用
根据这些答案修改了上述代码:
def _background(sock, fh, pbar):
while True:
block = sock.recv(1024*1024)
if not block:
break
fh.write(block)
pbar.update(len(block))
def _download_ftp_files(url, remote_path, files_list, db_dir):
ftp = ftplib.FTP(url)
ftp.login()
ftp.cwd(remote_path)
for fn in tqdm(files_list, desc="Downloading file #"):
try:
sock, size = ftp.ntransfercmd('RETR ' + fn)
pbar = tqdm(desc=fn, total=size)
with (db_dir / fn).open('wb') as fh:
t = threading.Thread(target=_background(sock, fh, pbar))
t.start()
while t.is_alive():
t.join(60)
ftp.voidcmd('NOOP')
sock.close()
except ftplib.error_reply as e:
print(e)
这将返回ftplib.error_reply 226由于某种原因而作为异常完成的传输。我试图处理它,但程序只是冻结
我可以提供更多的信息,如果需要,任何帮助是非常感谢 好吧,我换成了ftputil,它包装了ftplib,目前似乎效果更好 以下是修改后的代码:
def _download_ftp_files(url, remote_path, files_list, db_dir):
"""Download ftp file and update progress bar.
Args:
url (str): URL of ftp server to connect to
remote_path (str): Path to directory containing tartget files
files_list (list(str)): List of files to download
db_dir (Path): Path to local directory to download files to
"""
with ftputil.FTPHost(url, user='anonymous', passwd='@anonymous') as ftp_host:
ftp_host.chdir(remote_path)
for fn in tqdm(files_list, desc="Downloading file #"):
pbar = tqdm(desc=fn, total=ftp_host.path.getsize(fn))
ftp_host.download(
fn, str(db_dir / fn),
lambda block: pbar.update(len(block)))