我试图使用 tqdm 报告从三个链接下载每个文件的进度,我想使用多线程从每个链接同时下载,同时更新进度条。
但是当我执行脚本时,有多行进度条,似乎线程正在同时更新 tqdm 进度条。
我问我应该如何运行多线程来下载文件,同时保持每次下载的进度条而不让重复的进度条填满整个屏幕?
这是我的代码。
import os
import sys
import requests
from pathlib import Path
from tqdm import tqdm
from concurrent.futures import ThreadPoolExecutor as PE
def get_filename(url):
filename = os.path.basename(url)
fname, extension = os.path.splitext(filename)
if extension:
return filename
header = requests.head(url).headers
if "Location" in header:
return os.path.basename(header["Location"])
return fname
def get_file_size(url):
header = requests.head(url).headers
if "Content-Length" in header and header["Content-Length"] != 0:
return int(header["Content-Length"])
elif "Location" in header and "status" not in header:
redirect_link = header["Location"]
r = requests.head(redirect_link).headers
return int(r["Content-Length"])
def download_file(url, filename=None):
# Download to the Downloads folder in user's home folder.
download_dir = os.path.join(Path.home(), "Downloads")
if not os.path.exists(download_dir):
os.makedirs(download_dir, exist_ok=True)
if not filename:
filename = get_filename(url)
file_size = get_file_size(url)
abs_path = os.path.join(download_dir, filename)
chunk_size = 1024
with open(abs_path, "wb") as f, requests.get(url, stream=True) as r, tqdm(
unit="B",
unit_scale=True,
unit_divisor=chunk_size,
desc=filename,
total=file_size,
file=sys.stdout
) as progress:
for chunk in r.iter_content(chunk_size=chunk_size):
data = f.write(chunk)
progress.update(data)
if __name__ == "__main__":
urls = ["http://mirrors.evowise.com/linuxmint/stable/20/linuxmint-20-xfce-64bit.iso",
"https://www.vmware.com/go/getworkstation-win",
"https://download.geany.org/geany-1.36_setup.exe"]
with PE(max_workers=len(urls)) as ex:
ex.map(download_file, urls)
我稍微修改了我的代码,这是我从将 tqdm 与并发.futures 一起使用吗?.
def download_file(url, filename=None):
# Download to the Downloads folder in user's home folder.
download_dir = os.path.join(Path.home(), "Downloads")
if not os.path.exists(download_dir):
os.makedirs(download_dir, exist_ok=True)
if not filename:
filename = get_filename(url)
# file_size = get_file_size(url)
abs_path = os.path.join(download_dir, filename)
chunk_size = 1024
with open(abs_path, "wb") as f, requests.get(url, stream=True) as r:
for chunk in r.iter_content(chunk_size=chunk_size):
f.write(chunk)
if __name__ == "__main__":
urls = ["http://mirrors.evowise.com/linuxmint/stable/20/linuxmint-20-xfce-64bit.iso",
"https://www.vmware.com/go/getworkstation-win",
"https://download.geany.org/geany-1.36_setup.exe"]
with PE() as ex:
for url in urls:
tqdm(ex.submit(download_file, url),
total=get_file_size(url),
unit="B",
unit_scale=True,
unit_divisor=1024,
desc=get_filename(url),
file=sys.stdout)
但在我修改代码后,该栏没有更新......
My problem:
I have no problem with concurrent download, but has problem implementing tqdm to update individual progress for each link, below is what I want to achieve:
我使用了其中一种解决方案:
if __name__ == "__main__":
urls = ["http://mirrors.evowise.com/linuxmint/stable/20/linuxmint-20-xfce-64bit.iso",
"https://www.vmware.com/go/getworkstation-win",
"https://download.geany.org/geany-1.36_setup.exe"]
with tqdm(total=len(urls)) as pbar:
with ThreadPoolExecutor() as ex:
futures = [ex.submit(download_file, url) for url in urls]
for future in as_completed(futures):
result = future.result()
pbar.update(1)
But this is the result: