download-md-links.py

#!/usr/bin/python3
import tempfile
import subprocess
import requests
import sys
import re
import os
from typing import List


def get_links(filepath) -> List[str]:
    links = []
    with open(filepath, 'r') as f:
        link_re = re.compile(r'\[.*\]\((.*)\)')
        for line in f:
            m = re.search(link_re, line)
            if m:
                uri = m.groups()[0]
                if "github.com" in uri:
                    links.append(uri)
    return links


def download_links(filepath, source_dir):
    links = get_links(filepath)
    if not links:
        return
    try:
        os.makedirs(source_dir)
    except FileExistsError:
        pass
    os.chdir(source_dir)
    for link in links:
        subprocess.run(["git", "clone", link])


def download_uri(uri):
    r = requests.get(uri, allow_redirects=True)
    f = tempfile.NamedTemporaryFile(delete=False)
    f.write(r.content)
    f.close()
    return f.name


def download(md, source_dir):
    if md.startswith("http"):
        filepath = download_uri(md)
    else:
        filepath = md
    return download_links(os.path.expanduser(filepath),
                          os.path.expanduser(source_dir))


if __name__ == '__main__':
    if len(sys.argv) != 3:
        print(f"Usage: {sys.argv[0]} <markdown file> <destination directory>")
        print("Example:")
        print(f"  {sys.argv[0]} 'https://raw.githubusercontent.com/rockerBOO/awesome-neovim/main/README.md' ~/Sources/")
        sys.exit(1)
    download(sys.argv[1], sys.argv[2])