import sys
import re
import requests
from youtube_transcript_api import YouTubeTranscriptApi

def extract_video_id(input_str):
    """Extract the video ID from a full YouTube URL or use it directly if an ID is given."""
    if "youtube.com" in input_str or "youtu.be" in input_str:
        return input_str.split("v=")[-1].split("&")[0].split("?")[0]
    return input_str  # Assume it's a video ID

def get_video_title(video_id):
    """Try to get the video title without using pytube."""
    try:
        url = f"https://www.youtube.com/watch?v={video_id}"
        response = requests.get(url)
        if response.status_code == 200:
            match = re.search(r'<title>(.*?) - YouTube</title>', response.text)
            if match:
                return match.group(1).strip()
    except Exception as e:
        print(f"Warning: Failed to fetch title ({e})")
    return "UnknownTitle"  # Fallback if title cannot be fetched

def get_youtube_transcript(video_id):
    """Retrieve transcript for a given YouTube video ID."""
    try:
        transcript = YouTubeTranscriptApi.get_transcript(video_id)
        return "\n".join([entry["text"] for entry in transcript])
    except Exception as e:
        return f"Error retrieving transcript: {e}"

def sanitize_filename(name):
    """Sanitize filename to remove special characters."""
    return re.sub(r'[\/:*?"<>|]', "", name)

def main():
    if len(sys.argv) < 2:
        print("Usage: python script.py '<YouTube video URL or ID>'")
        sys.exit(1)

    input_str = sys.argv[1]
    video_id = extract_video_id(input_str)
    video_title = get_video_title(video_id)

    transcript = get_youtube_transcript(video_id)

    # Save transcript to a file with title and video ID
    filename = f"{sanitize_filename(video_title)}_{video_id}_transcript.txt"
    with open(filename, "w", encoding="utf-8") as f:
        f.write(transcript)

    print(f"Transcript saved as: {filename}")

if __name__ == "__main__":
    main()