A script to collect the names of the most downloaded python packages

get_top_pypi_packages.py

# script to retrieve most downloaded packages on the python package index
# also, oh yeah, chatgpt wrote some of this. I changed a little though.
# I'm not redundant yet.

import json
import urllib.request

def get_top_packages(top_n=1000):
    """Identify top packages by download count on pypi.

    A friendly person has already provided an occasionally
    updated JSON feed to enable this program to build a list
    of the top pypi packages by download count. The default
    does a fresh pull of this feed.

    Args:
        top_n (int): the number of top packages to retrieve

    Returns:
        dict: top packages
    """

    top_packages_url = (
        "https://hugovk.github.io/top-pypi-packages/top-pypi-packages-30-days.json"
    )
    with urllib.request.urlopen(top_packages_url) as url:
        data = json.loads(url.read().decode())

    # Place top_n packages in list
    top_pypi_pkgs = []
    i = 0
    for pkg in data["rows"]:
        if i == top_n:
            break
        top_pypi_pkgs.append(pkg["project"])
        i += 1
    return top_pypi_pkgs

def save_list_to_file(pkg_list):
    """Save package list to a file.

    For each package, save to a .txt file with each
    package on a new line.

    Args:
        pkg_list (list): a list of top packages

    Returns:
        Nothing
    """
    with open('top-pypi-package-list.txt', 'w') as file:
        for pkg in pkg_list:
            file.write(str(pkg) + '\n')

if __name__ == "__main__":
    pkgs = get_top_packages(1000)
    save_list_to_file(pkgs)