GithubBackup/BiliNote
1
0
Fork 0
mirror of https://github.com/JefferyHcool/BiliNote.git synced 2026-05-06 20:42:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into feature/update-readme-v2

Browse Source
This commit is contained in:
Jianwu Huang
2026-03-23 17:56:07 +08:00
committed by GitHub
parent 6090982261 90aeb22853
commit a40bb19743
16 changed files with 427 additions and 549 deletions
Download Patch File Download Diff File Expand all files Collapse all files

334
.dockerignore
View File

@@ -1,321 +1,35 @@
# Logs
logs
*.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
.pnpm-debug.log*
# Git 和 IDE
.git
.github
.idea/
.vscode/
.DS_Store
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
BiliNote/pnpm-lock.yaml
# Runtime data
pids
*.pid
*.seed
*.pid.lock
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Tauri 构建产物（非常大）
BillNote_frontend/src-tauri/target
BillNote_frontend/src-tauri/bin
# Coverage directory used by tools like istanbul
coverage
*.lcov
# 运行时数据
backend/data
backend/static
backend/models
backend/logs
backend/uploads
backend/*.db
backend/note_results
backend/bin/
# nyc test coverage
.nyc_output
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
.grunt
# Bower dependency directory (https://bower.io/)
bower_components
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
# 依赖和构建缓存
node_modules/
jspm_packages/
# Snowpack dependency directory (https://snowpack.dev/)
web_modules/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional stylelint cache
.stylelintcache
# Microbundle cache
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
.BiliNote-dev/*
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Yarn Integrity file
.yarn-integrity
# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
.env.local
!.env.example
# parcel-bundler cache (https://parceljs.org/)
.cache
.parcel-cache
# Next.js build output
.next
out
# Nuxt.js build / generate output
.nuxt
dist
# Gatsby files
.cache/
# Comment in the public line in if your project uses Gatsby and not Next.js
# https://nextjs.org/blog/next-9-1#public-directory-support
# public
# vuepress build output
.vuepress/dist
# vuepress v2.x temp and cache directory
.temp
.cache
# vitepress build output
**/.vitepress/dist
# vitepress cache directory
**/.vitepress/cache
# Docusaurus cache and generated files
.docusaurus
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# TernJS port file
.tern-port
# Stores VSCode versions used for testing VSCode extensions
.vscode-test
# yarn v2
.yarn/cache
.yarn/unplugged
.yarn/build-state.yml
.yarn/install-state.gz
.pnp.*
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
build/
*.tar
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
.idea/
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# UV
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
#uv.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
# 环境文件
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
# Ruff stuff:
.ruff_cache/
# PyPI configuration file
.pypirc
/backend/data/*
/backend/static/*
/backend/note_tasks.db
/backend/bin/
/backend/logs/
/backend/note_results
/backend/models
/backend/.idea/*
/backend/bili_note.db
/backend/uploads/*
/BiliNote_frontend/.idea/*
.env.local
.env.*.local
!.env.example

99
.github/workflows/docker-build.yml vendored
View File

@@ -1,76 +1,73 @@
name: Build Complete Docker Image
name: Build and Publish Docker Image
on:
push:
tags:
- 'v*' # 在推送 tag 时触发 (如 v1.0.0)
- 'v*'
workflow_dispatch:
env:
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
jobs:
build:
build-and-push:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout Code
uses: actions/checkout@v4
- name: Extract Version from Tag
id: get_version
run: |
# 获取 tag 名称 (如 refs/tags/v1.0.0 -> v1.0.0)
VERSION=${GITHUB_REF#refs/tags/}
echo "version=$VERSION" >> $GITHUB_OUTPUT
echo "Tag version: $VERSION"
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Build Docker Image
run: |
VERSION="${{ steps.get_version.outputs.version }}"
IMAGE_NAME="bilinote:${VERSION}"
echo "Building image: ${IMAGE_NAME}"
# 构建镜像
docker build -f Dockerfile.complete -t ${IMAGE_NAME} .
# 保存镜像为 tar 文件
docker save ${IMAGE_NAME} -o bilinote-${VERSION}.tar
# 显示镜像信息
echo "Image built successfully!"
docker images bilinote:${VERSION}
- name: Upload Docker Image Artifact
uses: actions/upload-artifact@v4
- name: Log in to GitHub Container Registry
uses: docker/login-action@v3
with:
name: bilinote-${{ steps.get_version.outputs.version }}
path: bilinote-${{ steps.get_version.outputs.version }}.tar
retention-days: 90
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata (tags, labels)
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
tags: |
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
type=sha,prefix=
type=raw,value=latest,enable={{is_default_branch}}
- name: Build and Push Docker Image
uses: docker/build-push-action@v6
with:
context: .
file: Dockerfile.complete
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
platforms: linux/amd64,linux/arm64
- name: Generate Usage Instructions
run: |
VERSION="${{ steps.get_version.outputs.version }}"
echo "=========================================="
echo "Docker Image Build Complete!"
echo "Docker Image Published!"
echo "=========================================="
echo ""
echo "Image Name: bilinote:${VERSION}"
echo "Artifact: bilinote-${VERSION}.tar"
echo "Pull the image:"
echo " docker pull ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest"
echo ""
echo "To use this Docker image:"
echo "1. Download the artifact from this workflow run"
echo "2. Load the image:"
echo " docker load < bilinote-${VERSION}.tar"
echo "3. Run the container:"
echo " docker run -d -p 80:80 --name bilinote bilinote:${VERSION}"
echo "Run the container:"
echo " docker run -d -p 80:80 \\"
echo " -v bilinote-data:/app/backend/data \\"
echo " --name bilinote \\"
echo " ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest"
echo ""
echo "Or with environment variables:"
echo " docker run -d -p 80:80 \\"
echo " -e BACKEND_PORT=8483 \\"
echo " -e BACKEND_HOST=0.0.0.0 \\"
echo " -v /path/to/data:/app/backend/data \\"
echo " --name bilinote bilinote:${VERSION}"
echo ""
echo "Access the application at: http://localhost:80"
echo "Access the application at: http://localhost"
echo "=========================================="

68
.github/workflows/main.yml vendored
View File

@@ -6,25 +6,38 @@ on:
tags:
- 'v*' # 发布 tag 时触发
workflow_dispatch:
jobs:
build:
strategy:
matrix:
platform: [macos-latest, windows-latest]
include:
- platform: macos-latest
- platform: ubuntu-22.04
- platform: windows-latest
runs-on: ${{ matrix.platform }}
steps:
- name: Checkout Code
uses: actions/checkout@v3
uses: actions/checkout@v4
# 设置 Python 环境
# Linux 系统依赖（Tauri 需要）
- name: Install Linux Dependencies
if: matrix.platform == 'ubuntu-22.04'
run: |
sudo apt-get update
sudo apt-get install -y libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf
# 设置 Python 环境（带 pip 缓存）
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.10'
python-version: '3.11'
cache: 'pip'
cache-dependency-path: backend/requirements.txt
# 安装 Python 依赖并执行你的 build.sh
# 安装 Python 依赖并执行构建
- name: Install Python dependencies & Build backend
shell: bash
run: |
@@ -38,30 +51,57 @@ jobs:
./backend/build.sh
fi
# 设置 Node 环境 + 安装前端依赖
# 设置 pnpm
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
version: 'latest'
# 设置 Node 环境（带 pnpm 缓存）
- name: Set up Node.js
uses: actions/setup-node@v3
uses: actions/setup-node@v4
with:
node-version: '20'
cache: 'pnpm'
cache-dependency-path: BillNote_frontend/pnpm-lock.yaml
- name: Enable Corepack + Install pnpm
- name: Install frontend dependencies
working-directory: BillNote_frontend
run: |
corepack enable
pnpm install
run: pnpm install --frozen-lockfile
# 设置 Rust 环境
- name: Set up Rust
uses: dtolnay/rust-toolchain@stable
# Cargo 缓存
- name: Cache Cargo
uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
BillNote_frontend/src-tauri/target/
key: ${{ runner.os }}-cargo-${{ hashFiles('BillNote_frontend/src-tauri/Cargo.lock') }}
restore-keys: ${{ runner.os }}-cargo-
# 打包 Tauri 应用
- name: Build Tauri App
working-directory: BillNote_frontend
run: pnpm tauri build
# 可选：上传构建产物
# 生成 SHA256 校验和
- name: Generate Checksums
shell: bash
run: |
cd BillNote_frontend/src-tauri/target/release/bundle/
find . -type f \( -name "*.dmg" -o -name "*.msi" -o -name "*.deb" -o -name "*.AppImage" \) -exec sha256sum {} \; > checksums.sha256 || true
# 上传构建产物
- name: Upload Desktop Bundle
uses: actions/upload-artifact@v4
with:
name: app-${{ matrix.platform }}
path: BillNote_frontend/src-tauri/target/release/bundle/
path: |
BillNote_frontend/src-tauri/target/release/bundle/

16
BillNote_frontend/Dockerfile
View File

@@ -1,25 +1,23 @@
# === 前端构建阶段 ===
FROM node:18-alpine AS builder
# 安装 pnpm
RUN npm install -g pnpm
RUN corepack enable && corepack prepare pnpm@latest --activate
# 设置工作目录
WORKDIR /app
# 拷贝前端源码
COPY ./BillNote_frontend /app
# 先复制 lockfile 利用依赖层缓存
COPY ./BillNote_frontend/package.json ./BillNote_frontend/pnpm-lock.yaml ./
RUN pnpm install --frozen-lockfile
# 安装依赖并构建
RUN pnpm install && pnpm run build
# 再复制源代码并构建
COPY ./BillNote_frontend/ ./
RUN pnpm run build
# --- 阶段2：使用 nginx 作为静态服务器 ---
FROM nginx:1.25-alpine
# 删除默认配置（可选）
RUN rm -rf /etc/nginx/conf.d/default.conf
COPY ./BillNote_frontend/deploy/default.conf /etc/nginx/conf.d/default.conf
# 拷贝构建产物
COPY --from=builder /app/dist /usr/share/nginx/html

37
Dockerfile.complete
View File

@@ -1,41 +1,56 @@
# === 阶段1：构建 Backend ===
FROM python:3.11-slim AS backend-builder
ARG APT_MIRROR=mirrors.tuna.tsinghua.edu.cn
ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple
RUN rm -f /etc/apt/sources.list && \
rm -rf /etc/apt/sources.list.d/* && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
apt-get update && \
apt-get install -y ffmpeg && \
apt-get install -y --no-install-recommends ffmpeg && \
rm -rf /var/lib/apt/lists/*
ENV PATH="/usr/bin:${PATH}"
ENV HF_ENDPOINT=https://hf-mirror.com
WORKDIR /tmp/backend
# 先复制 requirements.txt 利用层缓存
COPY ./backend/requirements.txt /tmp/backend/requirements.txt
RUN pip install --no-cache-dir -i ${PIP_INDEX} -r requirements.txt
COPY ./backend /tmp/backend
RUN pip install --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
# === 阶段2：构建 Frontend ===
FROM node:18-alpine AS frontend-builder
RUN npm install -g pnpm
RUN corepack enable && corepack prepare pnpm@latest --activate
WORKDIR /tmp/frontend
# 先复制 lockfile 利用依赖层缓存
COPY ./BillNote_frontend/package.json ./BillNote_frontend/pnpm-lock.yaml ./
RUN pnpm install --frozen-lockfile
COPY ./BillNote_frontend /tmp/frontend
RUN pnpm install && pnpm run build
RUN pnpm run build
# === 阶段3：完整应用镜像 ===
FROM python:3.11-slim
ARG APT_MIRROR=mirrors.tuna.tsinghua.edu.cn
# 安装必要的运行时依赖
RUN rm -f /etc/apt/sources.list && \
rm -rf /etc/apt/sources.list.d/* && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
apt-get update && \
apt-get install -y ffmpeg nginx supervisor procps && \
apt-get install -y --no-install-recommends ffmpeg nginx supervisor procps && \
rm -rf /var/lib/apt/lists/*
ENV PATH="/usr/bin:${PATH}"

27
README.md
View File

@@ -150,6 +150,33 @@ sudo apt install ffmpeg
具体 `fast-whisper` 配置方法，请参考：[fast-whisper 项目地址](http://github.com/SYSTRAN/faster-whisper#requirements)
### 🐳 使用 Docker 一键部署
确保你已安装 Docker，然后直接拉取预构建镜像运行：
```bash
# 拉取最新镜像
docker pull ghcr.io/jefferyhcool/bilinote:latest
# 运行容器
docker run -d -p 80:80 \
-v bilinote-data:/app/backend/data \
--name bilinote \
ghcr.io/jefferyhcool/bilinote:latest
```
访问：`http://localhost`
也可以使用 docker-compose 本地构建：
```bash
# 标准部署
docker-compose up -d
# GPU 加速部署（需要 NVIDIA GPU）
docker-compose -f docker-compose.gpu.yml up -d
```
## 🧠 TODO
- [x] 支持抖音及快手等视频平台

20
backend/Dockerfile
View File

@@ -1,23 +1,27 @@
FROM python:3.11-slim
ARG APT_MIRROR=mirrors.tuna.tsinghua.edu.cn
ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple
RUN rm -f /etc/apt/sources.list && \
rm -rf /etc/apt/sources.list.d/* && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
apt-get update && \
apt-get install -y ffmpeg && \
apt-get install -y --no-install-recommends ffmpeg curl && \
rm -rf /var/lib/apt/lists/*
# 确保 PATH 中包含 ffmpeg 路径（可选）
ENV PATH="/usr/bin:${PATH}"
# 设置 Hugging Face 镜像源环境变量
ENV HF_ENDPOINT=https://hf-mirror.com
WORKDIR /app
# 先复制 requirements.txt 利用层缓存
COPY ./backend/requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir -i ${PIP_INDEX} -r requirements.txt
# 再复制应用代码（频繁变动不影响 pip 缓存层）
COPY ./backend /app
RUN pip install --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
CMD ["python", "main.py"]

23
backend/Dockerfile.gpu
View File

@@ -1,16 +1,27 @@
FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
RUN apt update && \
apt install -y ffmpeg python3-pip && \
apt clean all && \
ARG APT_MIRROR=mirrors.tuna.tsinghua.edu.cn
ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple
RUN rm -f /etc/apt/sources.list && \
rm -rf /etc/apt/sources.list.d/* && \
echo "deb https://${APT_MIRROR}/ubuntu jammy main restricted universe multiverse" > /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/ubuntu jammy-updates main restricted universe multiverse" >> /etc/apt/sources.list && \
echo "deb https://${APT_MIRROR}/ubuntu jammy-security main restricted universe multiverse" >> /etc/apt/sources.list && \
apt-get update && \
apt-get install -y --no-install-recommends ffmpeg python3-pip curl && \
rm -rf /var/lib/apt/lists/*
# 设置 Hugging Face 镜像源环境变量
ENV HF_ENDPOINT=https://hf-mirror.com
WORKDIR /app
# 先复制 requirements.txt 利用层缓存
COPY ./backend/requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir -i ${PIP_INDEX} -r requirements.txt && \
pip install --no-cache-dir -i ${PIP_INDEX} 'transformers[torch]>=4.23'
# 再复制应用代码
COPY ./backend /app
RUN pip install --no-cache-dir -i https://pypi.mirrors.ustc.edu.cn/simple -r requirements.txt
RUN pip install --no-cache-dir -i https://pypi.mirrors.ustc.edu.cn/simple 'transformers[torch]>=4.23'
CMD ["python3", "main.py"]

3
backend/app/downloaders/base.py
View File

@@ -22,7 +22,8 @@ class Downloader(ABC):
@abstractmethod
def download(self, video_url: str, output_dir: str = None,
quality: DownloadQuality = "fast", need_video: Optional[bool] = False) -> AudioDownloadResult:
quality: DownloadQuality = "fast", need_video: Optional[bool] = False,
skip_download: bool = False) -> AudioDownloadResult:
'''
:param need_video:

134
backend/app/downloaders/youtube_downloader.py
View File

@@ -1,5 +1,4 @@
import os
import json
import logging
from abc import ABC
from typing import Union, Optional, List
@@ -7,8 +6,9 @@ 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, TranscriptSegment
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
@@ -25,12 +25,13 @@ class YoutubeDownloader(Downloader, ABC):
video_url: str,
output_dir: Union[str, None] = None,
quality: DownloadQuality = "fast",
need_video:Optional[bool]=False
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
output_dir = self.cache_data
os.makedirs(output_dir, exist_ok=True)
output_path = os.path.join(output_dir, "%(id)s.%(ext)s")
@@ -42,15 +43,17 @@ class YoutubeDownloader(Downloader, ABC):
'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=True)
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") # 兜底用 m4a
ext = info.get("ext", "m4a")
audio_path = os.path.join(output_dir, f"{video_id}.{ext}")
print('os.path.join(output_dir, f"{video_id}.{ext}")',os.path.join(output_dir, f"{video_id}.{ext}"))
return AudioDownloadResult(
file_path=audio_path,
@@ -59,8 +62,8 @@ class YoutubeDownloader(Downloader, ABC):
cover_url=cover_url,
platform="youtube",
video_id=video_id,
raw_info={'tags':info.get('tags')}, #全部返回会报错
video_path=None # ❗音频下载不包含视频路径
raw_info={'tags': info.get('tags')},
video_path=None,
)
def download_video(
@@ -101,115 +104,20 @@ class YoutubeDownloader(Downloader, ABC):
def download_subtitles(self, video_url: str, output_dir: str = None,
langs: List[str] = None) -> Optional[TranscriptResult]:
"""
尝试获取YouTube视频字幕（优先人工字幕，其次自动生成）
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: 输出路径
: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 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)
if langs is None:
langs = ['zh-Hans', 'zh', 'zh-CN', 'zh-TW', 'en', 'en-US']
langs = ['zh-Hans', 'zh', 'zh-CN', 'zh-TW', 'en', 'en-US', 'ja']
video_id = extract_video_id(video_url, "youtube")
ydl_opts = {
'writesubtitles': True,
'writeautomaticsub': True,
'subtitleslangs': langs,
'subtitlesformat': 'json3',
'skip_download': True,
'outtmpl': os.path.join(output_dir, f'{video_id}.%(ext)s'),
'quiet': True,
}
try:
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
info = ydl.extract_info(video_url, download=True)
# 查找下载的字幕文件
subtitles = info.get('requested_subtitles') or {}
if not subtitles:
logger.info(f"YouTube视频 {video_id} 没有可用字幕")
return None
# 按优先级查找字幕文件
subtitle_file = None
detected_lang = None
for lang in langs:
if lang in subtitles:
subtitle_file = os.path.join(output_dir, f"{video_id}.{lang}.json3")
detected_lang = lang
break
# 如果按优先级没找到，取第一个可用的
if not subtitle_file:
for lang, sub_info in subtitles.items():
subtitle_file = os.path.join(output_dir, f"{video_id}.{lang}.json3")
detected_lang = lang
break
if not subtitle_file or not os.path.exists(subtitle_file):
logger.info(f"字幕文件不存在: {subtitle_file}")
return None
# 解析字幕文件
return self._parse_json3_subtitle(subtitle_file, detected_lang)
except Exception as e:
logger.warning(f"获取YouTube字幕失败: {e}")
return None
def _parse_json3_subtitle(self, subtitle_file: str, language: str) -> Optional[TranscriptResult]:
"""
解析 json3 格式字幕文件
:param subtitle_file: 字幕文件路径
:param language: 语言代码
:return: TranscriptResult
"""
try:
with open(subtitle_file, 'r', encoding='utf-8') as f:
data = json.load(f)
segments = []
events = data.get('events', [])
for event in events:
# json3 格式中时间单位是毫秒
start_ms = event.get('tStartMs', 0)
duration_ms = event.get('dDurationMs', 0)
# 提取文本
segs = event.get('segs', [])
text = ''.join(seg.get('utf8', '') for seg in segs).strip()
if text: # 只添加非空文本
segments.append(TranscriptSegment(
start=start_ms / 1000.0,
end=(start_ms + duration_ms) / 1000.0,
text=text
))
if not segments:
return None
full_text = ' '.join(seg.text for seg in segments)
logger.info(f"成功解析YouTube字幕，共 {len(segments)} 段")
return TranscriptResult(
language=language,
full_text=full_text,
segments=segments,
raw={'source': 'youtube_subtitle', 'file': subtitle_file}
)
except Exception as e:
logger.warning(f"解析字幕文件失败: {e}")
return None
fetcher = YouTubeSubtitleFetcher()
print(
f"尝试获取字幕，video_id={video_id}, langs={langs}"
)
return fetcher.fetch_subtitles(video_id, langs)

98
backend/app/downloaders/youtube_subtitle.py Normal file
View File

@@ -0,0 +1,98 @@
"""
通过 youtube-transcript-api 获取 YouTube 字幕。
优先人工字幕，其次自动生成字幕。不依赖 yt_dlp，无需下载任何文件。
"""
from typing import Optional, List
from youtube_transcript_api import YouTubeTranscriptApi
from app.models.transcriber_model import TranscriptResult, TranscriptSegment
from app.utils.logger import get_logger
logger = get_logger(__name__)
class YouTubeSubtitleFetcher:
"""通过 youtube-transcript-api 获取 YouTube 字幕。"""
def __init__(self):
self._api = YouTubeTranscriptApi()
def fetch_subtitles(
self,
video_id: str,
langs: Optional[List[str]] = None,
) -> Optional[TranscriptResult]:
if langs is None:
langs = ["zh-Hans", "zh", "zh-CN", "zh-TW", "en", "en-US", "ja"]
try:
# 1. 列出所有可用字幕
transcript_list = self._api.list(video_id)
available = []
for t in transcript_list:
available.append(
f"{t.language_code}({'auto' if t.is_generated else 'manual'})"
)
logger.info(f"可用字幕轨道: {', '.join(available)}")
# 2. 按优先级查找：先人工字幕，再自动字幕
transcript = None
try:
transcript = transcript_list.find_manually_created_transcript(langs)
logger.info(f"选中人工字幕: {transcript.language_code} ({transcript.language})")
except Exception:
try:
transcript = transcript_list.find_generated_transcript(langs)
logger.info(f"选中自动字幕: {transcript.language_code} ({transcript.language})")
except Exception:
# 都没匹配，取第一个可用的
for t in transcript_list:
transcript = t
source = "auto" if t.is_generated else "manual"
logger.info(f"使用首个可用字幕: {t.language_code} ({source})")
break
if not transcript:
logger.info(f"YouTube 视频 {video_id} 没有任何可用字幕")
return None
# 3. 获取字幕内容
fetched = transcript.fetch()
segments = []
for snippet in fetched:
text = snippet.get("text", "").strip() if isinstance(snippet, dict) else str(snippet).strip()
if not text:
continue
start = snippet.get("start", 0) if isinstance(snippet, dict) else 0
duration = snippet.get("duration", 0) if isinstance(snippet, dict) else 0
segments.append(TranscriptSegment(
start=float(start),
end=float(start) + float(duration),
text=text,
))
if not segments:
logger.warning(f"YouTube 字幕内容为空: {video_id}")
return None
full_text = " ".join(seg.text for seg in segments)
logger.info(f"成功获取 YouTube 字幕，共 {len(segments)} 段")
return TranscriptResult(
language=transcript.language_code,
full_text=full_text,
segments=segments,
raw={
"source": "youtube_transcript_api",
"language": transcript.language,
"language_code": transcript.language_code,
"is_generated": transcript.is_generated,
},
)
except Exception as e:
logger.warning(f"YouTube 字幕获取失败: {e}")
return None

105
backend/app/services/note.py
View File

@@ -133,8 +133,46 @@ class NoteGenerator:
audio_cache_file = NOTE_OUTPUT_DIR / f"{task_id}_audio.json"
transcript_cache_file = NOTE_OUTPUT_DIR / f"{task_id}_transcript.json"
markdown_cache_file = NOTE_OUTPUT_DIR / f"{task_id}_markdown.md"
print(audio_cache_file)
# 1. 下载音频/视频
# 1. 获取字幕/转写：优先缓存 → 平台字幕 → 音频转写
transcript = None
# 尝试读取缓存
if transcript_cache_file.exists():
logger.info(f"检测到转写缓存 ({transcript_cache_file})，尝试读取")
try:
data = json.loads(transcript_cache_file.read_text(encoding="utf-8"))
segments = [TranscriptSegment(**seg) for seg in data.get("segments", [])]
transcript = TranscriptResult(
language=data.get("language"),
full_text=data["full_text"],
segments=segments,
)
logger.info(f"已从缓存加载转写结果，共 {len(segments)} 段")
except Exception as e:
logger.warning(f"加载转写缓存失败: {e}")
# 缓存没有，尝试获取平台字幕
if transcript is None:
logger.info("尝试获取平台字幕（优先于音频下载）...")
try:
transcript = downloader.download_subtitles(video_url)
if transcript and transcript.segments:
logger.info(f"成功获取平台字幕，共 {len(transcript.segments)} 段")
transcript_cache_file.write_text(
json.dumps(asdict(transcript), ensure_ascii=False, indent=2),
encoding="utf-8",
)
else:
transcript = None
logger.info("平台无可用字幕，将下载音频后转写")
except Exception as e:
logger.warning(f"获取平台字幕失败: {e}，将下载音频后转写")
transcript = None
# 2. 下载音频/视频
# 有字幕时只提取元信息，不下载音视频文件（除非需要截图/视频理解）
has_transcript = transcript is not None
need_full_download = not has_transcript or screenshot or video_understanding
audio_meta = self._download_media(
downloader=downloader,
video_url=video_url,
@@ -147,18 +185,19 @@ class NoteGenerator:
video_understanding=video_understanding,
video_interval=video_interval,
grid_size=grid_size,
skip_download=not need_full_download,
)
# 2. 获取字幕/转写文字
# 优先尝试获取平台字幕，没有再 fallback 到音频转写
transcript = self._get_transcript(
downloader=downloader,
video_url=video_url,
audio_file=audio_meta.file_path,
transcript_cache_file=transcript_cache_file,
status_phase=TaskStatus.TRANSCRIBING,
task_id=task_id,
)
# 3. 如果前面没拿到字幕，走转写流程
if transcript is None:
transcript = self._get_transcript(
downloader=downloader,
video_url=video_url,
audio_file=audio_meta.file_path,
transcript_cache_file=transcript_cache_file,
status_phase=TaskStatus.TRANSCRIBING,
task_id=task_id,
)
# 3. GPT 总结
markdown = self._summarize_text(
@@ -331,6 +370,7 @@ class NoteGenerator:
video_understanding: bool,
video_interval: int,
grid_size: List[int],
skip_download: bool = False,
) -> AudioDownloadResult | None:
"""
1. 检查音频缓存；若不存在，则根据需要下载音频或视频（若需截图/可视化）。
@@ -353,7 +393,34 @@ class NoteGenerator:
task_id = audio_cache_file.stem.split("_")[0]
self._update_status(task_id, status_phase)
# 已有缓存，尝试加载
if audio_cache_file.exists():
logger.info(f"检测到音频缓存 ({audio_cache_file})，直接读取")
try:
data = json.loads(audio_cache_file.read_text(encoding="utf-8"))
return AudioDownloadResult(**data)
except Exception as e:
logger.warning(f"读取音频缓存失败，将重新下载：{e}")
# 有字幕且不需要截图/视频理解时，只提取元信息不下载文件
if skip_download:
logger.info("已有字幕，仅提取视频元信息（不下载音视频）")
try:
audio = downloader.download(
video_url=video_url,
quality=quality,
output_dir=output_path,
need_video=False,
skip_download=True,
)
audio_cache_file.write_text(
json.dumps(asdict(audio), ensure_ascii=False, indent=2),
encoding="utf-8",
)
logger.info(f"元信息提取完成 ({audio_cache_file})")
return audio
except Exception as exc:
logger.warning(f"元信息提取失败，将尝试完整下载: {exc}")
# 判断是否需要下载视频
need_video = screenshot or video_understanding
@@ -368,9 +435,8 @@ class NoteGenerator:
self.video_path = Path(video_path_str)
logger.info(f"视频下载完成：{self.video_path}")
# 若指定了 grid_size，则生成缩略图
if grid_size:
self.video_img_urls=VideoReader(
self.video_img_urls = VideoReader(
video_path=str(self.video_path),
grid_size=tuple(grid_size),
frame_interval=frame_interval,
@@ -382,17 +448,9 @@ class NoteGenerator:
logger.info("未指定 grid_size，跳过缩略图生成")
except Exception as exc:
logger.error(f"视频下载失败：{exc}")
self._handle_exception(task_id, exc)
raise
# 已有缓存，尝试加载
if audio_cache_file.exists():
logger.info(f"检测到音频缓存 ({audio_cache_file})，直接读取")
try:
data = json.loads(audio_cache_file.read_text(encoding="utf-8"))
return AudioDownloadResult(**data)
except Exception as e:
logger.warning(f"读取音频缓存失败，将重新下载：{e}")
# 下载音频
try:
logger.info("开始下载音频")
@@ -402,7 +460,6 @@ class NoteGenerator:
output_dir=output_path,
need_video=need_video,
)
# 缓存 audio 元信息到本地 JSON
audio_cache_file.write_text(json.dumps(asdict(audio), ensure_ascii=False, indent=2), encoding="utf-8")
logger.info(f"音频下载并缓存成功 ({audio_cache_file})")
return audio

1
backend/build.sh
View File

@@ -25,6 +25,7 @@ cp .env.example backend/.env
# 步骤 2: PyInstaller 打包，直接添加已存在的 .env 文件
echo "开始 PyInstaller 打包..."
pyinstaller \
-y \
--name BiliNoteBackend \
--paths backend \
--distpath ./BillNote_frontend/src-tauri/bin \

1
backend/requirements.txt
View File

@@ -124,5 +124,6 @@ weasyprint==65.1
webencodings==0.5.1
websockets==15.0.1
yarl==1.19.0
youtube-transcript-api>=1.0.0
yt-dlp==2025.3.31
zopfli==0.2.3.post1

3
docker-compose.gpu.yml
View File

@@ -5,6 +5,9 @@ services:
build:
context: .
dockerfile: backend/Dockerfile.gpu
args:
APT_MIRROR: ${APT_MIRROR:-mirrors.tuna.tsinghua.edu.cn}
PIP_INDEX: ${PIP_INDEX:-https://pypi.tuna.tsinghua.edu.cn/simple}
env_file:
- .env
environment:

3
docker-compose.yml
View File

@@ -5,6 +5,9 @@ services:
build:
context: .
dockerfile: backend/Dockerfile
args:
APT_MIRROR: ${APT_MIRROR:-mirrors.tuna.tsinghua.edu.cn}
PIP_INDEX: ${PIP_INDEX:-https://pypi.tuna.tsinghua.edu.cn/simple}
env_file:
- .env
environment: