tools/youtube_transcript.py

import re
import requests
from bs4 import BeautifulSoup

def youtube_transcript(url: str) -> str:
    match = re.search(r"(?:v=|youtu\.be/|/shorts/|/embed/)([0-9A-Za-z_-]{11})", url)
    video_id = match.group(1) if match else url.strip()
    # 尝试获取字幕
    try:
        from youtube_transcript_api import YouTubeTranscriptApi
        if hasattr(YouTubeTranscriptApi, "get_transcript"):
            chunks = YouTubeTranscriptApi.get_transcript(video_id)
        else:
            fetched = YouTubeTranscriptApi().fetch(video_id)
            chunks = [{"text": snippet.text} for snippet in fetched]
        transcript = " ".join(c["text"] for c in chunks)
        if transcript.strip():
            return f"Transcript:\n{transcript[:8000]}"
    except Exception:
        pass
    # 降级：获取视频描述
    try:
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
        resp = requests.get(url, headers=headers, timeout=15)
        resp.raise_for_status()
        soup = BeautifulSoup(resp.text, "html.parser")
        desc_meta = soup.find("meta", {"name": "description"})
        if desc_meta and desc_meta.get("content"):
            description = desc_meta["content"]
            return f"Video description: {description[:4000]}"
        else:
            return "Video has no transcript or description."
    except Exception:
        return "Video information unavailable."