How to parallelize file downloads?

You could use a thread pool to download files in parallel:

#!/usr/bin/env python3
from multiprocessing.dummy import Pool # use threads for I/O bound tasks
from urllib.request import urlretrieve

urls = [...]
result = Pool(4).map(urlretrieve, urls) # download 4 files at a time

You could also download several files at once in a single thread using asyncio:

#!/usr/bin/env python3
import asyncio
import logging
from contextlib import closing
import aiohttp # $ pip install aiohttp

@asyncio.coroutine
def download(url, session, semaphore, chunk_size=1<<15):
    with (yield from semaphore): # limit number of concurrent downloads
        filename = url2filename(url)
        logging.info('downloading %s', filename)
        response = yield from session.get(url)
        with closing(response), open(filename, 'wb') as file:
            while True: # save file
                chunk = yield from response.content.read(chunk_size)
                if not chunk:
                    break
                file.write(chunk)
        logging.info('done %s', filename)
    return filename, (response.status, tuple(response.headers.items()))

urls = [...]
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
with closing(asyncio.get_event_loop()) as loop, \
     closing(aiohttp.ClientSession()) as session:
    semaphore = asyncio.Semaphore(4)
    download_tasks = (download(url, session, semaphore) for url in urls)
    result = loop.run_until_complete(asyncio.gather(*download_tasks))

where url2filename() is defined here.

Leave a Comment