Fetch source maps for a website that exposes them

get_original_files.py

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

def fetch_html(url):
    try:
        response = requests.get(url)
        response.raise_for_status()  # This will raise an exception for HTTP errors
        return response.text
    except requests.RequestException as e:
        print(f"Request failed: {e}")
        return None

def fetch_js_files_and_sourcemaps(html_content, base_url):
    soup = BeautifulSoup(html_content, 'html.parser')
    script_tags = soup.find_all('script', src=True)

    for script_tag in script_tags:
        js_url = urljoin(base_url, script_tag['src'])
        map_url = js_url + '.map'

        try:
            # Fetch Source Map
            map_response = requests.get(map_url)
            if map_response.status_code == 200:
                map_data = map_response.json()
                sources = map_data.get('sources', [])
                for source in sources:
                    source_index = sources.index(source)
                    original_content = map_data.get('sourcesContent', [])[source_index]
                    source_filename = source.split('/')[-1]
                    with open(source_filename, 'w') as source_file:
                        source_file.write(original_content)
                    print(f"Re-created original source file: {source_filename}")
            else:
                print(f"Source map not found or failed to fetch: {map_url}")

        except Exception as e:
            print(f"Error processing {js_url}: {e}")

def main():
    url = 'https://trading.galaxydigital.io'
    base_url = url  # Assuming the base URL is the same as the fetched URL
    html_content = fetch_html(url)

    if html_content:
        fetch_js_files_and_sourcemaps(html_content, base_url)

if __name__ == "__main__":
    main()