mirror of
https://github.com/JefferyHcool/BiliNote.git
synced 2026-09-07 00:27:37 +08:00
huangjianwuandClaude Opus 4.6
f4801d5be7
- 新增 YouTubeSubtitleFetcher 模块，通过 youtube-transcript-api 获取字幕 - 重构笔记生成流程：缓存 → 平台字幕 → 按需下载 → 转写 fallback - 有字幕时仅提取视频元信息，不下载音视频文件 - 添加 youtube-transcript-api 依赖 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
124 lines
4.1 KiB
Python
124 lines
4.1 KiB
Python
import os
|
|
import logging
|
|
from abc import ABC
|
|
from typing import Union, Optional, List
|
|
|
|
import yt_dlp
|
|
|
|
from app.downloaders.base import Downloader, DownloadQuality
|
|
from app.downloaders.youtube_subtitle import YouTubeSubtitleFetcher
|
|
from app.models.notes_model import AudioDownloadResult
|
|
from app.models.transcriber_model import TranscriptResult
|
|
from app.utils.path_helper import get_data_dir
|
|
from app.utils.url_parser import extract_video_id
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class YoutubeDownloader(Downloader, ABC):
|
|
def __init__(self):
|
|
|
|
super().__init__()
|
|
|
|
def download(
|
|
self,
|
|
video_url: str,
|
|
output_dir: Union[str, None] = None,
|
|
quality: DownloadQuality = "fast",
|
|
need_video: Optional[bool] = False,
|
|
skip_download: bool = False,
|
|
) -> AudioDownloadResult:
|
|
if output_dir is None:
|
|
output_dir = get_data_dir()
|
|
if not output_dir:
|
|
output_dir = self.cache_data
|
|
os.makedirs(output_dir, exist_ok=True)
|
|
|
|
output_path = os.path.join(output_dir, "%(id)s.%(ext)s")
|
|
|
|
ydl_opts = {
|
|
'format': 'bestaudio[ext=m4a]/bestaudio/best',
|
|
'outtmpl': output_path,
|
|
'noplaylist': True,
|
|
'quiet': False,
|
|
}
|
|
|
|
if skip_download:
|
|
ydl_opts['skip_download'] = True
|
|
|
|
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
|
info = ydl.extract_info(video_url, download=not skip_download)
|
|
video_id = info.get("id")
|
|
title = info.get("title")
|
|
duration = info.get("duration", 0)
|
|
cover_url = info.get("thumbnail")
|
|
ext = info.get("ext", "m4a")
|
|
audio_path = os.path.join(output_dir, f"{video_id}.{ext}")
|
|
|
|
return AudioDownloadResult(
|
|
file_path=audio_path,
|
|
title=title,
|
|
duration=duration,
|
|
cover_url=cover_url,
|
|
platform="youtube",
|
|
video_id=video_id,
|
|
raw_info={'tags': info.get('tags')},
|
|
video_path=None,
|
|
)
|
|
|
|
def download_video(
|
|
self,
|
|
video_url: str,
|
|
output_dir: Union[str, None] = None,
|
|
) -> str:
|
|
"""
|
|
下载视频，返回视频文件路径
|
|
"""
|
|
if output_dir is None:
|
|
output_dir = get_data_dir()
|
|
video_id = extract_video_id(video_url, "youtube")
|
|
video_path = os.path.join(output_dir, f"{video_id}.mp4")
|
|
if os.path.exists(video_path):
|
|
return video_path
|
|
os.makedirs(output_dir, exist_ok=True)
|
|
output_path = os.path.join(output_dir, "%(id)s.%(ext)s")
|
|
|
|
ydl_opts = {
|
|
'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]',
|
|
'outtmpl': output_path,
|
|
'noplaylist': True,
|
|
'quiet': False,
|
|
'merge_output_format': 'mp4', # 确保合并成 mp4
|
|
}
|
|
|
|
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
|
info = ydl.extract_info(video_url, download=True)
|
|
video_id = info.get("id")
|
|
video_path = os.path.join(output_dir, f"{video_id}.mp4")
|
|
|
|
if not os.path.exists(video_path):
|
|
raise FileNotFoundError(f"视频文件未找到: {video_path}")
|
|
|
|
return video_path
|
|
|
|
def download_subtitles(self, video_url: str, output_dir: str = None,
|
|
langs: List[str] = None) -> Optional[TranscriptResult]:
|
|
"""
|
|
通过 YouTube InnerTube API 直接获取字幕（优先人工字幕，其次自动生成）。
|
|
比 yt_dlp 方式更轻量，无需写临时文件到磁盘。
|
|
|
|
:param video_url: 视频链接
|
|
:param output_dir: 未使用（保留接口兼容）
|
|
:param langs: 优先语言列表
|
|
:return: TranscriptResult 或 None
|
|
"""
|
|
if langs is None:
|
|
langs = ['zh-Hans', 'zh', 'zh-CN', 'zh-TW', 'en', 'en-US', 'ja']
|
|
|
|
video_id = extract_video_id(video_url, "youtube")
|
|
fetcher = YouTubeSubtitleFetcher()
|
|
print(
|
|
f"尝试获取字幕，video_id={video_id}, langs={langs}"
|
|
)
|
|
return fetcher.fetch_subtitles(video_id, langs)
|