Downloading multiple urls with threadpool

Question

I having problem downloading multiple urls. My code still only download 1 url per session. Still need to finish the first one before downloading the next one.

I want to download like 3 urls at the same time.

Here's my code:

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:67.0) Gecko/20100101 Firefox/67.0'
}

def download(path, video_url, bar: tqdm):
    
    res = requests.get(video_url, headers, stream=True)

    with open(path, 'wb') as f:
        for b in res.iter_content(1024):
            f.write(b)
            bar.update(len(b))

def get_length(video_url):
    res = requests.get(video_url, headers, stream=True)
    le = int(res.headers['Content-Length'])
    return le

def download_all(urls: list, thread: int = cpu_count()):

    total = len(urls)
    count = 0

    pool = ThreadPool(thread)  # https://stackoverflow.com/a/56528204/14951175

    for url in urls:
        output_file = get_url_path(url)
        count += 1
        content_length = get_length(video_url=url)
        with tqdm(total=content_length, unit='B', ncols=(150-1), desc=f'Downloading {count} of {total}', unit_divisor=1024, ascii=True, unit_scale=True) as bar:
            pool.apply_async(download(output_file, url, bar))
    pool.close()
    pool.join()


  urls = read_lines('urls.txt')
  download_all(urls)

Answer 1

This line

pool.apply_async(download(output_file, url, bar))

must be

pool.apply_async(download, (output_file, url, bar))

Otherwise you call the download method instead of passing it (and the args) to the ThreadPool.

---

Edit

Use starmap to map the urls to func where you perform the download (btw: you can safe the duplicate get-request). And add the position argument.
To be honest, the bars don't works very smooth, but I don't really have experience with tqdm or ThreadPool . But in general the downloads seem to work.

def download_all(urls: list, thread: int = cpu_count()):
    total = len(urls)

    pool = ThreadPool(thread)

    def func(count, url):
        output_file = get_url_path(url)
        req = requests.get(url, headers=headers, stream=True)
        content_length = int(req.headers['Content-Length'])
        with tqdm(total=content_length, unit='B', desc=f'Downloading {count + 1} of {total}',
                  unit_divisor=1024, ascii=True, unit_scale=True, position=count, file=sys.stdout) as bar:
            with open(output_file, 'wb') as f:
                for b in req.iter_content(1024):
                    f.write(b)
                    bar.update(len(b))

    pool.starmap(func, enumerate(urls))

    pool.close()
    pool.join()