Batch Markdownify URLs

urltomd.py

import requests
from bs4 import BeautifulSoup
import sys

def get_page_title(url):
    """
    Fetch the title of a webpage from its URL.

    Args:
        url (str): The URL of the webpage.

    Returns:
        str: The title of the webpage or an empty string if unable to fetch.
    """
    try:
        response = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'})
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
        title = soup.title.string.strip()
        return title
    except (requests.exceptions.RequestException, AttributeError):
        return ''

def generate_markdown_file(input_file, output_file):
    """
    Generate a Markdown file with links to webpage titles from URLs.

    Args:
        input_file (str): The name of the input file containing URLs.
        output_file (str): The name of the output Markdown file.
    """
    try:
        with open(input_file, 'r', encoding='utf-8') as file:
            urls = file.read().splitlines()

        with open(output_file, 'w', encoding='utf-8') as file:
            for url in urls:
                if title := get_page_title(url):
                    markdown_link = f"[{title}]({url})"
                    file.write(markdown_link + '\n\n')
                else:
                    file.write(f"{url}\n\n")

        print(f"✅ Markdown file '{output_file}' generated successfully.")
    except FileNotFoundError:
        print("❌ Error: Input file not found.")
    except Exception as e:
        print(f"❌ Error: {e}")

if __name__ == "__main__":
    # Check for command line arguments
    if len(sys.argv) != 3:
        print("❌ Usage: python script.py <input_file> <output_file>")
        sys.exit(1)

    input_file = sys.argv[1]
    output_file = sys.argv[2]

    # Generate Markdown file
    generate_markdown_file(input_file, output_file)