# MarkdownLoader

HackMD and other editors may leave linked media in a markdown document. While this is convenient, links break and media is generally not available when offline.

The `download_md_media.py` script below
- accepts a list of files `file1.md file2.md` (should also work per drag&drop)
- creates a `data/` subdirectory
- finds and attempts to download linked media
- subsequently replaces links to successfully downloaded media with relative paths

## download_md_media.py

#!python3
# Auto-install missing modules
import sys
import subprocess

required_modules = ["argparse", "requests", "urllib"]

for module in required_modules:
    try:
        __import__(module)
    except ImportError:
        try:
            print(f"Module '{module}' not found. Attempting to install...")
            subprocess.check_call([sys.executable, "-m", "pip", "install", module])
        except:
            print(f"Required module '{module}' is missing and cannot be installed automatically.")
            sys.exit(1)

# Application code 
import argparse
import os
import re
import requests
from urllib.parse import urlparse

def download_file(url, dest_folder):
    os.makedirs(dest_folder, exist_ok=True)
    local_filename = os.path.basename(urlparse(url).path)
    local_path = os.path.join(dest_folder, local_filename)
    
    try:
        with requests.get(url, stream=True, timeout=15) as r:
            r.raise_for_status()
            with open(local_path, 'wb') as f:
                for chunk in r.iter_content(chunk_size=8192):
                    f.write(chunk)
        print(f"Downloaded: {url} -> {local_path}")
        return local_path
    except Exception as e:
        print(f"Failed to download {url}: {e}")
        return None

def find_media_links(markdown_text):
    # Match images and other media (basic pattern for ![alt](url) or [alt](url))
    pattern = r'(!?\[.*?\])\((https?://[^\s)]+)\)'
    return re.findall(pattern, markdown_text)

def update_markdown(markdown_text, url_map):
    def replacer(match):
        alt_text, url = match.groups()
        new_url = url_map.get(url)

        # Only replace if local copy was downloaded successfully
        if new_url and os.path.exists(new_url):
            return f"{alt_text}({new_url})"
        else:
            return f"{alt_text}({url})"

    pattern = re.compile(r'(!?\[.*?\])\((https?://[^\s)]+)\)')
    return pattern.sub(replacer, markdown_text)

def main():
    parser = argparse.ArgumentParser(description="Download media from one or more markdown files.")
    parser.add_argument("md_file", nargs='+', help="Paths to one or more Markdown (.md) files")
    args = parser.parse_args()

    for md_path in args.md_file:
        if not os.path.isfile(md_path):
            print(f"File not found: {md_path}")
            continue

        print(f"\nProcessing: {md_path}")

        with open(md_path, 'r', encoding='utf-8') as f:
            markdown_text = f.read()

        media_links = find_media_links(markdown_text)
        if not media_links:
            print("  No media links found.")
            continue

        md_dir = os.path.dirname(md_path)
        data_dir = os.path.join(md_dir, "data")
        url_map = {}

        for alt_text, url in media_links:
            print(f"downloading {url} ...")
            local_path = download_file(url, data_dir)
            if local_path:
                rel_path = os.path.relpath(local_path, md_dir)
                url_map[url] = rel_path.replace("\\", "/")  # Normalize for Markdown

        updated_text = update_markdown(markdown_text, url_map)

        with open(md_path, 'w', encoding='utf-8') as f:
            f.write(updated_text)

        print("  Markdown file updated with local media paths.")

if __name__ == "__main__":
    main()