import re
import sys

def extract_mp3_links(file_path, output_file='free-output.txt'):
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            html_content = file.read()
    except FileNotFoundError:
        print(f"Error: File not found at {file_path}")
        return
    except Exception as e:
        print(f"Error: {e}")
        return

    # Find all .mp3 and then capture from the preceding http to .mp3
    pattern = r'http[s]?://.*?\.mp3'
    all_links = re.findall(pattern, html_content)
    mp3_links = []

    for link in all_links:
        # Check if .mp3 is in the link and find the last http before .mp3
        if '.mp3' in link:
            # Split the string by http and take the last part
            parts = link.rsplit('http', 1)
            if len(parts) == 2:
                mp3_link = 'http' + parts[1]
                mp3_links.append(mp3_link)

    with open(output_file, 'w', encoding='utf-8') as output:
        for link in mp3_links:
            output.write(link + '\n')

    print(f"Extraction complete. {len(mp3_links)} links written to {output_file}")

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python script_name.py <path_to_html_file>")
    else:
        extract_mp3_links(sys.argv[1])