from youtube_transcript_api import YouTubeTranscriptApi


def extract_video_id(url: str) -> str:
    """YouTube URL에서 video ID 추출."""
    if "youtu.be/" in url:
        return url.split("youtu.be/")[1].split("?")[0]
    if "v=" in url:
        return url.split("v=")[1].split("&")[0]
    raise ValueError(f"유효하지 않은 YouTube URL: {url}")


def fetch_transcript(video_id: str) -> str:
    """YouTube 자막을 텍스트로 추출."""
    ytt_api = YouTubeTranscriptApi()
    transcript = ytt_api.fetch(video_id, languages=["ko", "en"])

    texts = [entry.text for entry in transcript if entry.text.strip()]
    return " ".join(texts)