Python progress bar and downloads

Question

I have a python script that launches a URL that is a downloadable file. Is there some way to have python use commandline to display the download progress as oppose to launch

Answer 1

The tqdm package now includes a function designed to handle exactly this type of situation: wrapattr. You just wrap an object's read (or write) attribute, and tqdm handles the rest. Here's a simple download function that puts it all together with requests:

def download(url, filename):
    import functools
    import pathlib
    import shutil
    import requests
    import tqdm
    
    r = requests.get(url, stream=True, allow_redirects=True)
    if r.status_code != 200:
        r.raise_for_status()  # Will only raise for 4xx codes, so...
        raise RuntimeError(f"Request to {url} returned status code {r.status_code}")
    file_size = int(r.headers.get('Content-Length', 0))

    path = pathlib.Path(filename).expanduser().resolve()
    path.parent.mkdir(parents=True, exist_ok=True)

    desc = "(Unknown total file size)" if file_size == 0 else ""
    r.raw.read = functools.partial(r.raw.read, decode_content=True)  # Decompress if needed
    with tqdm.tqdm.wrapattr(r.raw, "read", total=file_size, desc=desc) as r_raw:
        with path.open("wb") as f:
            shutil.copyfileobj(r_raw, f)

    return path

Answer 2

Python 3 with TQDM

This is the suggested technique from the TQDM docs.

import urllib.request

from tqdm import tqdm


class DownloadProgressBar(tqdm):
    def update_to(self, b=1, bsize=1, tsize=None):
        if tsize is not None:
            self.total = tsize
        self.update(b * bsize - self.n)


def download_url(url, output_path):
    with DownloadProgressBar(unit='B', unit_scale=True,
                             miniters=1, desc=url.split('/')[-1]) as t:
        urllib.request.urlretrieve(url, filename=output_path, reporthook=t.update_to)

Answer 3

There is an answer with requests and tqdm.

import requests
from tqdm import tqdm


def download(url: str, fname: str):
    resp = requests.get(url, stream=True)
    total = int(resp.headers.get('content-length', 0))
    with open(fname, 'wb') as file, tqdm(
        desc=fname,
        total=total,
        unit='iB',
        unit_scale=True,
        unit_divisor=1024,
    ) as bar:
        for data in resp.iter_content(chunk_size=1024):
            size = file.write(data)
            bar.update(size)

Gist: https://gist.github.com/yanqd0/c13ed29e29432e3cf3e7c38467f42f51

Answer 4

You can stream a downloads as it is here -> Stream a Download.

Also you can Stream Uploads.

The most important streaming a request is done unless you try to access the response.content with just 2 lines

for line in r.iter_lines():    
    if line:
        print(line)

Stream Requests

Answer 5

I think you can also use click , and it has a good library for progress bar also.

import click
with click.progressbar(length=total_size, label='Downloading files') as bar:
    for file in files:
        download(file)
        bar.update(file.size)

Enjoy !

Answer 6

Sorry for being late with an answer; just updated the tqdm docs:

https://github.com/tqdm/tqdm/#hooks-and-callbacks

Using urllib.urlretrieve and OOP:

import urllib
from tqdm.auto import tqdm

class TqdmUpTo(tqdm):
    """Provides `update_to(n)` which uses `tqdm.update(delta_n)`."""
    def update_to(self, b=1, bsize=1, tsize=None):
        """
        b  : Blocks transferred so far
        bsize  : Size of each block
        tsize  : Total size
        """
        if tsize is not None:
            self.total = tsize
        self.update(b * bsize - self.n)  # will also set self.n = b * bsize

eg_link = "https://github.com/tqdm/tqdm/releases/download/v4.46.0/tqdm-4.46.0-py2.py3-none-any.whl"
eg_file = eg_link.split('/')[-1]
with TqdmUpTo(unit='B', unit_scale=True, unit_divisor=1024, miniters=1,
              desc=eg_file) as t:  # all optional kwargs
    urllib.urlretrieve(
        eg_link, filename=eg_file, reporthook=t.update_to, data=None)
    t.total = t.n

or using requests.get and file wrappers:

import requests
from tqdm.auto import tqdm

eg_link = "https://github.com/tqdm/tqdm/releases/download/v4.46.0/tqdm-4.46.0-py2.py3-none-any.whl"
eg_file = eg_link.split('/')[-1]
response = requests.get(eg_link, stream=True)
with tqdm.wrapattr(open(eg_file, "wb"), "write", miniters=1,
                   total=int(response.headers.get('content-length', 0)),
                   desc=eg_file) as fout:
    for chunk in response.iter_content(chunk_size=4096):
        fout.write(chunk)

You could of course mix & match techniques.