获取音频时长
parent
a2a8a48fad
commit
5b1ab08a77
|
|
@ -4,7 +4,8 @@
|
|||
|
||||
```bash
|
||||
cd /Users/jiliu/工作/projects/imeeting/backend
|
||||
pip install mutagen
|
||||
source venv/bin/activate
|
||||
pip install tinytag
|
||||
```
|
||||
|
||||
## 2. 执行数据库迁移
|
||||
|
|
@ -28,8 +29,10 @@ mysql -u root -p imeeting < sql/migrations/add_duration_to_audio_files.sql
|
|||
|
||||
### 3.2 音频处理优化
|
||||
**音频时长计算：**
|
||||
- 使用mutagen库自动识别音频格式并提取时长
|
||||
- 支持mp3, m4a, mp4, wav等常见格式
|
||||
- 使用TinyTag库读取音频文件时长
|
||||
- 纯Python实现，无需外部依赖
|
||||
- 支持mp3, m4a, mp4, wav, ogg, flac等常见格式
|
||||
- 能处理特殊/损坏元数据的文件
|
||||
- 时长保存到audio_files.duration字段（单位：秒）
|
||||
- 时长读取功能位于`app/utils/audio_parser.py`
|
||||
|
||||
|
|
@ -47,8 +50,9 @@ mysql -u root -p imeeting < sql/migrations/add_duration_to_audio_files.sql
|
|||
## 4. 代码变更清单
|
||||
|
||||
### 后端变更：
|
||||
- `/backend/app/utils/audio_parser.py` - 新增音频时长解析工具
|
||||
- `/backend/app/api/endpoints/meetings.py` - 音频上传时调用audio_parser获取时长，修复Safari播放问题
|
||||
- `/backend/app/utils/audio_parser.py` - 新增音频时长解析工具（使用TinyTag）
|
||||
- `/backend/app/api/endpoints/meetings.py` - 完整文件上传时调用audio_parser获取时长，修复Safari播放问题
|
||||
- `/backend/app/api/endpoints/audio.py` - Stream上传完成时调用audio_parser获取时长
|
||||
- `/backend/app/services/audio_service.py` - 增加duration参数
|
||||
- `/backend/app/api/endpoints/auth.py` - 登录时记录日志
|
||||
- `/backend/app/api/endpoints/admin_dashboard.py` - 更新用户统计查询
|
||||
|
|
@ -81,9 +85,10 @@ mysql -u root -p imeeting < sql/migrations/add_duration_to_audio_files.sql
|
|||
## 6. 注意事项
|
||||
|
||||
1. **音频时长计算**：
|
||||
- 使用mutagen自动识别格式
|
||||
- 使用TinyTag纯Python库
|
||||
- 无需系统依赖，跨平台兼容
|
||||
- 计算失败时duration为0，不影响其他功能
|
||||
- 支持所有mutagen支持的格式
|
||||
- 支持所有TinyTag支持的格式
|
||||
|
||||
2. **Safari音频播放兼容性**：
|
||||
- 使用直接src属性而非source子元素
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@ from app.core.response import create_api_response
|
|||
from app.services.async_transcription_service import AsyncTranscriptionService
|
||||
from app.services.async_meeting_service import async_meeting_service
|
||||
from app.services.audio_service import handle_audio_upload
|
||||
from app.utils.audio_parser import get_audio_duration
|
||||
from pydantic import BaseModel
|
||||
from typing import Optional, List
|
||||
from datetime import datetime, timedelta
|
||||
|
|
@ -460,6 +461,14 @@ async def complete_upload(
|
|||
file_size = full_path.stat().st_size
|
||||
file_name = full_path.name
|
||||
|
||||
# 6.5 获取音频时长
|
||||
audio_duration = 0
|
||||
try:
|
||||
audio_duration = get_audio_duration(str(full_path))
|
||||
print(f"音频时长: {audio_duration}秒")
|
||||
except Exception as e:
|
||||
print(f"警告: 获取音频时长失败，但不影响后续流程: {e}")
|
||||
|
||||
# 7. 调用 audio_service 处理文件（数据库更新、启动转录和总结）
|
||||
result = handle_audio_upload(
|
||||
file_path=file_path,
|
||||
|
|
@ -469,7 +478,8 @@ async def complete_upload(
|
|||
current_user=current_user,
|
||||
auto_summarize=request.auto_summarize,
|
||||
background_tasks=background_tasks,
|
||||
prompt_id=request.prompt_id # 传递提示词模版ID
|
||||
prompt_id=request.prompt_id, # 传递提示词模版ID
|
||||
duration=audio_duration # 传递时长参数
|
||||
)
|
||||
|
||||
# 如果处理失败，返回错误
|
||||
|
|
@ -492,7 +502,7 @@ async def complete_upload(
|
|||
"meeting_id": request.meeting_id,
|
||||
"file_path": file_path,
|
||||
"file_size": file_size,
|
||||
"duration": None, # 可以通过ffprobe获取，但不是必需的
|
||||
"duration": audio_duration,
|
||||
"task_id": transcription_task_id,
|
||||
"task_status": "pending" if transcription_task_id else None,
|
||||
"auto_summarize": request.auto_summarize
|
||||
|
|
|
|||
|
|
@ -4,13 +4,15 @@
|
|||
用于解析音频文件的元数据信息，如时长、采样率、编码格式等
|
||||
"""
|
||||
|
||||
from mutagen import File as MutagenFile
|
||||
from tinytag import TinyTag
|
||||
|
||||
|
||||
def get_audio_duration(file_path: str) -> int:
|
||||
"""
|
||||
获取音频文件时长（秒）
|
||||
|
||||
使用TinyTag读取音频文件时长
|
||||
|
||||
Args:
|
||||
file_path: 音频文件的完整路径
|
||||
|
||||
|
|
@ -22,13 +24,15 @@ def get_audio_duration(file_path: str) -> int:
|
|||
- M4A (.m4a)
|
||||
- MP4 (.mp4)
|
||||
- WAV (.wav)
|
||||
- 以及mutagen支持的其他格式
|
||||
- OGG (.ogg)
|
||||
- FLAC (.flac)
|
||||
- 以及TinyTag支持的其他音频格式
|
||||
"""
|
||||
try:
|
||||
audio = MutagenFile(file_path)
|
||||
if audio is not None and hasattr(audio.info, 'length'):
|
||||
return int(audio.info.length)
|
||||
return 0
|
||||
tag = TinyTag.get(file_path)
|
||||
if tag.duration and tag.duration > 0:
|
||||
return int(tag.duration)
|
||||
except Exception as e:
|
||||
print(f"获取音频时长失败 ({file_path}): {e}")
|
||||
|
||||
return 0
|
||||
|
|
|
|||
|
|
@ -22,5 +22,6 @@ psutil
|
|||
# APK Parsing
|
||||
pyaxmlparser
|
||||
|
||||
# Audio Processing
|
||||
mutagen==1.47.0
|
||||
# Audio Metadata
|
||||
tinytag
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue