"""
Service for fetching YouTube transcripts directly without downloading audio.
Uses youtube-transcript-api for efficient text extraction.
"""

from typing import Optional, List
from youtube_transcript_api import YouTubeTranscriptApi
from src.utils.logger import setup_logger
import re

logger = setup_logger(__name__)


class TranscriptFetcher:
    """Handles fetching transcripts from YouTube videos."""

    @staticmethod
    def extract_video_id(url: str) -> Optional[str]:
        """Extract the 11-character video ID from a YouTube URL."""
        reg_exp = re.compile(
            r"(?:youtube\.com\/watch\?v=|youtu\.be\/|youtube\.com\/embed\/|youtube\.com\/v\/|youtube\.com\/watch\?.*v=)([a-zA-Z0-9_-]{11})"
        )
        match = reg_exp.search(url)
        return match.group(1) if match else None

    def fetch_transcript(
        self, video_url: str, languages: List[str] = ["en", "ar"]
    ) -> Optional[str]:
        """
        Attempt to fetch the transcript for a video.
        Returns the combined text if successful, None otherwise.
        """
        video_id = self.extract_video_id(video_url)
        if not video_id:
            logger.error(f"Could not extract video ID from URL: {video_url}")
            return None

        try:
            logger.info(f"Attempting to fetch transcript for video: {video_id}")
            # Try to get transcript in the requested languages
            transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)

            # Find the best transcript (manual preferred over auto-generated)
            try:
                # Try finding a manual one first
                transcript = transcript_list.find_manually_created_transcript(languages)
            except Exception:
                try:
                    # Fallback to auto-generated
                    transcript = transcript_list.find_generated_transcript(languages)
                except Exception:
                    # Fallback to anything available
                    transcript = transcript_list.find_transcript(languages)

            data = transcript.fetch()
            text = " ".join([entry["text"] for entry in data])

            logger.info(
                f"Successfully fetched transcript for {video_id} ({len(text)} chars)"
            )
            return text

        except Exception as e:
            logger.warning(f"Could not fetch transcript for {video_id}: {e}")
            return None