uv run git_to_md.py

git_to_md.py

import os
import sys
import subprocess
import tempfile
import shutil

def main():
    if len(sys.argv) != 2:
        print("Usage: python script.py <github_repo_url>")
        sys.exit(1)

    repo_url = sys.argv[1]

    # Create a temporary directory
    temp_dir = tempfile.mkdtemp()

    try:
        # Clone the repository into the temporary directory
        subprocess.check_call(['git', 'clone', repo_url, temp_dir], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)

        # Define the output directory
        output_dir = 'output_folder'
        if not os.path.exists(output_dir):
            os.makedirs(output_dir)

        # Define the file extensions to include
        code_extensions = {
            '.py', '.c', '.cpp', '.ipynb', '.java', '.js', '.rb', '.go', '.cs',
            '.php', '.html', '.css', '.swift', '.kt', '.m', '.mm', '.ts', '.rs',
            '.scala', '.pl', '.sh', '.bat', '.ps1', '.lua', '.erl', '.ex', '.dart',
            '.r', '.jl', '.md', ".MD"
        }

        # Walk through the cloned repository
        for root, dirs, files in os.walk(temp_dir):
            # Ignore the .git directory
            if '.git' in dirs:
                dirs.remove('.git')
            for file in files:
                file_path = os.path.join(root, file)
                filename, file_extension = os.path.splitext(file)
                if file_extension.lower() in code_extensions:
                    # Read the file content
                    with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
                        content = f.read()
                    # Prepare the markdown content
                    md_content = f'# {file}\n\n```{file_extension[1:]}\n{content}\n```'
                    # Define the output file path
                    output_file = os.path.join(output_dir, filename + '.md')
                    # Ensure unique filenames in the output directory
                    count = 1
                    while os.path.exists(output_file):
                        output_file = os.path.join(output_dir, f"{filename}_{count}.md")
                        count += 1
                    # Write the markdown file
                    with open(output_file, 'w', encoding='utf-8') as f:
                        f.write(md_content)
        print(f"Markdown files have been saved in the folder '{output_dir}'.")
    except subprocess.CalledProcessError as e:
        print(f"Error cloning repository: {e}")
    finally:
        # Remove the temporary directory
        shutil.rmtree(temp_dir)

if __name__ == '__main__':
    main()