Created
April 17, 2020 18:14
-
-
Save PathToLife/e7945b11d07c2032b2ed6d5e0b753834 to your computer and use it in GitHub Desktop.
Simple Python3 Multithreaded Downloading with auto directory creation and incomplete download file marking. Multiprocessing pools
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import requests | |
from time import time as timer | |
from typing import List, Tuple | |
from multiprocessing.pool import ThreadPool | |
import shutil | |
def download_file(entry: Tuple[str, str]): | |
path, uri = entry | |
dirname = os.path.dirname(path) | |
if not os.path.exists(dirname): | |
try: | |
os.makedirs(dirname) | |
except FileExistsError: | |
pass | |
if not os.path.exists(path): | |
r = requests.get(uri, stream=True) | |
if r.status_code == 200: | |
with open(path + '.crdownload', 'wb') as f: | |
for chunk in r: | |
f.write(chunk) | |
shutil.move(path + '.crdownload', path) | |
return path | |
def bulk_download(path_url_list: List[Tuple[str, str]]): | |
start = timer() | |
print(f"Downloading {len(path_url_list)} files...") | |
results = ThreadPool(8).imap_unordered(download_file, path_url_list) | |
for res in results: | |
print(res) | |
print(f"Elapsed Time: {timer() - start}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment