urlretrieve python3_python3 retrieve()

retreive()被认为是个老旧函数，可能会在将来抛弃。

urllib.request.urlretrieve(url, filename=None, reporthook=None, data=None)

Exceptions和函数urlopen()相同。

具体文档，参见https://docs.python.org/3/library/urllib.request.html#module-urllib.request

代码片段

from urllib.request import urlretrieve

import socket

import os

import sys

def reporthook(blocknum, bs, size):

# blocknum:已经下载的数据块 bs:数据块的大小 size:远程文件的大小

per = 100.0 * blocknum * bs / size

if per > 100 :

per = 100

sys.stdout.write('Download progress: %.2f%% \r'%per)

sys.stdout.flush()

class ClassName():

def __init__(self):

socket.setdefaulttimeout(30)

def run(self):

...

while True:

.....

try:

urlretrieve(url,localfile, reporthook= reporthook)

except socket.timeout:

self.redownload(url,localfile)

except Exception as e:

StatusCode=e.getcode()

if StatusCode == 404:

print(e)

break

self.redownload(url,localfile)

def redownload(self,url,localfile):

count = 1

while count <= 5:

try:

urlretrieve(url,localfile, reporthook= reporthook)

break

except socket.timeout:

err_info = 'Reloading for %d time.....'%count if count == 1 else 'Reloading for %d times.....'%count

print(err_info)

count += 1

if count > 5:

print("download job failed!")