Github repo downloader

github_downloader.py

import os
import subprocess
import requests
from scrapy import Selector
from rich import print as rprint
from rich.prompt import Prompt
import click
from urllib.parse import urljoin

@click.command()
@click.option('--all', is_flag=True, help='Download all repositories without asking.')
def main(all):
    rprint("[bold cyan]GitHub Repository Downloader[/bold cyan]")
    rprint("=" * 30)
    
    home_url = "https://github.com/"

    # Prompt user for repository owner's name
    repo_owner = Prompt.ask("[bright_red]Enter the repository owner's name for the repositories you want to download[/bright_red]")

    # Construct URL for the owner's repositories
    all_repos_url = f"https://github.com/{repo_owner}?tab=repositories"

    # Make a request to fetch the repository data
    data = requests.get(url=all_repos_url)
    response = Selector(text=data.text)
    
    repos_list = response.css("a[itemprop='name codeRepository'] ::attr(href)").getall()
    while response.css("a.next_page"):
        data = requests.get(url=urljoin(home_url, response.css("a.next_page ::attr(href)").get()))
        response = Selector(text=data.text)
        repos_list.extend(response.css("a[itemprop='name codeRepository'] ::attr(href)").getall())        

    rprint(f"There are {len(repos_list)} repositories in {repo_owner} account.")
    # Extract repository URLs
    repo_names = [repo.split("/")[-1] for repo in repos_list]
    repos_urls = [f"https://github.com/{repo_owner}/{repo_name}.git" for repo_name in repo_names]

    # Process each repository URL
    for repo_url in repos_urls:
        repo_name = repo_url.split("/")[-1][:-4]  # Remove '.git' extension

        # Check if repository already exists
        if os.path.exists(repo_name):
            rprint(f"Repository '[cyan]{repo_name}[/cyan]' already exists. [dim]Skipping...[/dim]")
        elif all or Prompt.ask(f"[bright_red]Do you want to download repository '{repo_name}'? (y/n)[/bright_red]").lower() == 'y':
            # Clone the repository using git
            subprocess.run(["git", "clone", repo_url])
            rprint(f"Repository '[cyan]{repo_name}[/cyan]' downloaded [bold green]successfully[/bold green].")
        else:
            rprint(f"Repository '[cyan]{repo_name}[/cyan]' [dim]skipped[/dim].")

if __name__ == "__main__":
    main()