Archived
refactor: 下载/标签/格式探测改用成熟库（aria2 + mutagen + filetype）
为什么：原先三处都在手写轮子——ffmpeg CLI 拼参数写标签、aiohttp 单连接手搓 下载、自己比对魔数判格式。手写部分既难测又易错；改走成熟库后测试从 144 涨到 175，并且彻底去掉了 ffmpeg 这个外部二进制依赖。 下载 → aria2c 常驻 JSON-RPC（aria2p 客户端），新增 _aria2.py - 单例后端：首次调用时拉起 aria2c，只监听 127.0.0.1 且强制随机 secret （无鉴权的 aria2 RPC 允许本机任意进程操纵队列、读写任意文件） - split=5 / max-connection-per-server=5 多连接 + 原生断点续传 - 异常语义与内置通道逐一对齐：取消/超限清残片抛 DownloadCanceled / DownloadException，任务失败/超时保留残片抛 RequestException 供续传 - 取不到 aria2c 时 get_backend() 返回 None，自动降级到内置 aiohttp 通道 （本机无 aria2c 的降级路径已实测） 标签 → mutagen 纯 Python 写入，新增 tagging.py - 取代 _write_metadata_with_ffmpeg + _build_format_args（226 行 shell 参数拼接） - MP3(ID3v2.3)/FLAC/M4A/OGG/Opus 分容器实现，无子进程、不重编码 - 就地改帧：TXXX 等未触及的标签原样保留（ffmpeg 整帧重写会丢） - 临时文件 + os.replace 原子替换，写坏不会留下半个文件 - 为什么不是 ffmpeg-python（原方案）：实测它用 **kwargs 建模选项，无法表达 重复键（-metadata ×N），list 值还会被字符串化成 "['0', '1:v']"；-map 尚有 内置的 stream 位置参数入口，但 -metadata 无解，且 overwrite_output=True 生成的 -y 被排到输出文件之后、可能失效 格式探测 → filetype，改 _http.py - 删除手写的 _AUDIO_MAGIC 魔数表，改用 filetype.guess() 判 MIME （audio/* 放行，video/mp4 作为容器显式放行） 配套 - Dockerfile：镜像不再装 ffmpeg，改装 aria2 - pyproject：新增 filetype / aria2p / mutagen；dev 加 httpx2（消除测试里的 StarletteDeprecationWarning，现 0 warning） - __main__.py / __init__.py / models.py：清理 ffmpeg 相关导出与文案 测试：新增 31 个用例（test_aria2.py 13、test_tagging.py 21，含最小合法 FLAC 样本构造）；全套 175 passed / 0 warning
This commit is contained in:
snowy-yang committed
1 parent
183f5744d8
commit
ad8c30d932
12 files changed
+1367
-369
No files matched your search
+166
-328
@@ -8,9 +8,6 @@ from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
from pathlib import Path
|
||||
@@ -19,6 +16,7 @@ from core import sync_http as requests # 同步门面（底层 aiohttp，替代
|
||||
from core.async_bridge import run_sync
|
||||
from music_api import APIException, NeteaseAPI, load_cookies
|
||||
|
||||
from ._aria2 import Aria2Backend, get_backend
|
||||
from ._concurrency import (
|
||||
CountingSemaphore,
|
||||
get_file_lock,
|
||||
@@ -36,14 +34,16 @@ from .cover import (
|
||||
)
|
||||
from .models import (
|
||||
API_TYPE_TO_EXT,
|
||||
EXT_TO_FFMPEG_FORMAT,
|
||||
METADATA_FORMATS,
|
||||
DownloadCanceled,
|
||||
DownloadException,
|
||||
DownloadResult,
|
||||
MusicInfo,
|
||||
_RetryFromScratch,
|
||||
)
|
||||
from .tagging import build_tags, write_tags
|
||||
|
||||
# 单文件下载体积硬上限：超限即弃，防止单文件拖垮磁盘
|
||||
_MAX_DOWNLOAD_BYTES = 500 * 1024 * 1024
|
||||
|
||||
# ============ 核心实现 ============
|
||||
|
||||
@@ -59,15 +59,13 @@ class MusicDownloader:
|
||||
self,
|
||||
download_dir: str = "downloads",
|
||||
max_concurrent: int = 3,
|
||||
ffmpeg_path: str | None = None,
|
||||
global_max_concurrent: int = 10,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
download_dir: 下载目录
|
||||
max_concurrent: 单个批量任务内的最大并发下载数
|
||||
ffmpeg_path: ffmpeg 可执行文件路径，为 None 时启动时检测一次
|
||||
global_max_concurrent: 整个服务同时下载的文件数（含 ffmpeg 元数据写入）。
|
||||
global_max_concurrent: 整个服务同时下载的文件数（含标签写入）。
|
||||
所有请求共享该信号量，防止大量用户同时下载导致内存/CPU 耗尽。
|
||||
"""
|
||||
self.download_dir = Path(download_dir)
|
||||
@@ -80,15 +78,10 @@ class MusicDownloader:
|
||||
# （带计数，供前端实时展示排队情况）
|
||||
self._download_semaphore = CountingSemaphore(global_max_concurrent)
|
||||
|
||||
# ffmpeg 元数据写入专用信号量（CPU 密集操作）：
|
||||
# 与下载分离限流 —— 元数据写满时只阻塞元数据，不占下载名额、不拖慢其它文件的传输
|
||||
# 标签写入专用信号量：写标签会重写整个文件（IO 密集），
|
||||
# 与下载分离限流 —— 写满时只阻塞后来者，不占下载名额、不拖慢其它文件的传输
|
||||
cpu_count = os.cpu_count() or 2
|
||||
self._meta_semaphore = threading.BoundedSemaphore(max(1, min(4, cpu_count)))
|
||||
|
||||
# ffmpeg 路径缓存：启动时检测一次，写入时还会再懒加载一次
|
||||
self.ffmpeg_path = ffmpeg_path or shutil.which("ffmpeg")
|
||||
if not self.ffmpeg_path:
|
||||
logger.warning("未检测到 ffmpeg，写入元数据功能将不可用")
|
||||
self._tag_semaphore = threading.BoundedSemaphore(max(1, min(4, cpu_count)))
|
||||
|
||||
# ----------- 工具方法 -----------
|
||||
|
||||
@@ -142,18 +135,6 @@ class MusicDownloader:
|
||||
|
||||
return ".mp3"
|
||||
|
||||
def _resolve_ffmpeg(self) -> str | None:
|
||||
"""懒加载解析 ffmpeg 路径
|
||||
|
||||
每次写入前调用一次：若启动时未检测到，但中途已安装，下一次就能用。
|
||||
"""
|
||||
if self.ffmpeg_path:
|
||||
return self.ffmpeg_path
|
||||
path = shutil.which("ffmpeg")
|
||||
if path:
|
||||
self.ffmpeg_path = path # 回写缓存
|
||||
return path
|
||||
|
||||
@staticmethod
|
||||
def _unlink_quiet(path: Path) -> None:
|
||||
"""安静地删除文件，忽略不存在 / 权限错误"""
|
||||
@@ -328,6 +309,11 @@ class MusicDownloader:
|
||||
self._unlink_quiet(part_path0)
|
||||
raise DownloadCanceled("下载已取消")
|
||||
|
||||
# part_path 是 file_path 的 .part 别名。必须在进入下载 try 之前绑定：
|
||||
# except 分支（取消/网络错误）要清理 .part，若此处未赋值，异常处理器
|
||||
# 会以 NameError 二次崩溃、掩盖原始异常
|
||||
part_path = part_path0
|
||||
|
||||
# 同一目标文件的下载者串行化（不同文件之间仍然并行）
|
||||
with get_file_lock(file_path):
|
||||
try:
|
||||
@@ -345,8 +331,8 @@ class MusicDownloader:
|
||||
else:
|
||||
# 缓存命中也尊重本次的元数据请求（重跑一次 ffmpeg，幂等）
|
||||
if write_meta:
|
||||
with self._meta_semaphore:
|
||||
self._write_metadata_with_ffmpeg(file_path, music_info, meta_fields)
|
||||
with self._tag_semaphore:
|
||||
self._write_metadata(file_path, music_info, meta_fields)
|
||||
return DownloadResult(
|
||||
success=True,
|
||||
file_path=str(file_path),
|
||||
@@ -354,7 +340,7 @@ class MusicDownloader:
|
||||
music_info=music_info,
|
||||
)
|
||||
|
||||
part_path = file_path.with_name(file_path.name + ".part")
|
||||
# part_path 已在文件锁外绑定为 part_path0（同一路径），此处不再重复计算
|
||||
resume_from = 0
|
||||
if part_path.exists():
|
||||
existing = part_path.stat().st_size
|
||||
@@ -364,8 +350,8 @@ class MusicDownloader:
|
||||
# 改 >= 为 ==——超尺寸残片（上游多发货/坏分片）转正即交付坏文件
|
||||
os.replace(part_path, file_path)
|
||||
if write_meta:
|
||||
with self._meta_semaphore:
|
||||
self._write_metadata_with_ffmpeg(file_path, music_info, meta_fields)
|
||||
with self._tag_semaphore:
|
||||
self._write_metadata(file_path, music_info, meta_fields)
|
||||
return DownloadResult(
|
||||
success=True,
|
||||
file_path=str(file_path),
|
||||
@@ -387,85 +373,15 @@ class MusicDownloader:
|
||||
if not self._download_semaphore.acquire_cancellable(cancel_event, poll=0.5):
|
||||
raise DownloadCanceled("下载已取消")
|
||||
try:
|
||||
headers = {}
|
||||
mode = "wb"
|
||||
if resume_from > 0:
|
||||
headers["Range"] = f"bytes={resume_from}-"
|
||||
mode = "ab"
|
||||
|
||||
if progress_cb is not None:
|
||||
try:
|
||||
progress_cb(resume_from, music_info.file_size or 0)
|
||||
except Exception:
|
||||
pass # 进度回调绝不影响下载主流程
|
||||
resp: requests.SyncResponse | None = None
|
||||
try:
|
||||
resp = get_http_session().get(
|
||||
music_info.download_url,
|
||||
stream=True,
|
||||
timeout=(10, 60),
|
||||
headers=headers,
|
||||
)
|
||||
# 服务器忽略 Range 返回 200 → 从头重写而非追加
|
||||
if resume_from > 0 and resp.status_code != 206:
|
||||
mode = "wb"
|
||||
# 206 必须从我们请求的起点开始；起点错位的分片拼起来是坏文件
|
||||
if resume_from > 0 and resp.status_code == 206:
|
||||
cr = resp.headers.get('Content-Range') or ''
|
||||
m = re.match(r'bytes\s+(\d+)-', cr.strip())
|
||||
if m and int(m.group(1)) != resume_from:
|
||||
self._unlink_quiet(part_path)
|
||||
raise _RetryFromScratch(
|
||||
f"Content-Range 起点错位（{m.group(1)} != {resume_from}），已从头重新下载")
|
||||
# 206 却解析不出起点（头被中间层剥离）——盲追加可能拼坏文件，
|
||||
# 与起点错位同口径处理：清残片从头下
|
||||
if not m:
|
||||
self._unlink_quiet(part_path)
|
||||
raise _RetryFromScratch("206 响应缺少可用 Content-Range，已从头重新下载")
|
||||
resp.raise_for_status()
|
||||
# 下载体积硬上限（配置 500MB），超限即弃，防单文件拖垮磁盘
|
||||
max_bytes = 500 * 1024 * 1024
|
||||
written = resume_from if mode == 'ab' else 0
|
||||
over_limit = False
|
||||
with open(part_path, mode) as f:
|
||||
for chunk in resp.iter_content(chunk_size=DL_CHUNK_SIZE):
|
||||
if cancel_event is not None and cancel_event.is_set():
|
||||
raise DownloadCanceled("下载已取消")
|
||||
if chunk:
|
||||
f.write(chunk)
|
||||
written += len(chunk)
|
||||
if written > max_bytes:
|
||||
# 超限残片没有任何续传价值。
|
||||
# Windows 无法删除打开中的文件——置标志 break，
|
||||
# with 关闭后再清理（原实现在打开中 unlink 被静默吞掉）
|
||||
over_limit = True
|
||||
break
|
||||
if progress_cb is not None:
|
||||
try:
|
||||
progress_cb(written, music_info.file_size or 0)
|
||||
except Exception:
|
||||
pass # 进度回调绝不影响下载主流程
|
||||
if over_limit:
|
||||
self._unlink_quiet(part_path) # 文件已关闭，清理可达
|
||||
raise DownloadException(
|
||||
f"文件超过大小上限 {max_bytes // (1024*1024)}MB，已中止")
|
||||
except requests.HTTPError as e:
|
||||
# Range 起点无效（如 CDN 环节变化）：清除旧 part，从头重新下载
|
||||
status = getattr(getattr(e, "response", None), "status_code", None)
|
||||
if status == 416:
|
||||
self._unlink_quiet(part_path)
|
||||
raise _RetryFromScratch("Range 起点失效，已从头重新下载") from e
|
||||
if status is not None and 400 <= status < 500 and status != 408:
|
||||
# CDN 4xx（403 防盗链/429 风控等）是确定性
|
||||
# 失败，对同一失效直链白重试只会加剧风控、拖慢失败返回
|
||||
# （408 请求超时保留可重试）
|
||||
self._unlink_quiet(part_path)
|
||||
raise DownloadException(
|
||||
f"下载失败（HTTP {status}），下载链接可能已失效") from e
|
||||
raise
|
||||
finally:
|
||||
if resp is not None:
|
||||
resp.close()
|
||||
aria2_backend = get_backend()
|
||||
if aria2_backend is not None:
|
||||
# aria2c 通道：多连接 + 原生断点续传
|
||||
self._fetch_via_aria2(aria2_backend, music_info, part_path,
|
||||
cancel_event, progress_cb)
|
||||
else:
|
||||
# 内置通道：aiohttp 流式落盘 + Range 起点校验
|
||||
self._fetch_via_http(music_info, part_path, resume_from,
|
||||
cancel_event, progress_cb)
|
||||
finally:
|
||||
# 与 acquire_cancellable 配对释放（原 with 语义）
|
||||
self._download_semaphore.release()
|
||||
@@ -501,8 +417,8 @@ class MusicDownloader:
|
||||
# 进入信号量排队/ffmpeg 等待（有界但可达 120s），收尾不再延迟
|
||||
if cancel_event is not None and cancel_event.is_set():
|
||||
raise DownloadCanceled("下载已取消")
|
||||
with self._meta_semaphore:
|
||||
self._write_metadata_with_ffmpeg(file_path, music_info, meta_fields)
|
||||
with self._tag_semaphore:
|
||||
self._write_metadata(file_path, music_info, meta_fields)
|
||||
|
||||
return DownloadResult(
|
||||
success=True,
|
||||
@@ -548,229 +464,151 @@ class MusicDownloader:
|
||||
return DownloadResult(success=False, error_message=last_error or "下载失败")
|
||||
|
||||
|
||||
# ============ ffmpeg 元数据写入（核心） ============
|
||||
# ----------- 传输通道（二选一，产物都是 part_path） -----------
|
||||
|
||||
def _fetch_via_http(
|
||||
self,
|
||||
music_info: MusicInfo,
|
||||
part_path: Path,
|
||||
resume_from: int,
|
||||
cancel_event: threading.Event | None,
|
||||
progress_cb,
|
||||
) -> None:
|
||||
"""内置流式通道：core.sync_http 逐块落盘，支持 Range 断点续传。
|
||||
|
||||
Raises:
|
||||
DownloadCanceled: 取消事件置位
|
||||
DownloadException: 体积超限、CDN 4xx 等确定性失败
|
||||
_RetryFromScratch: 续传起点失效（残片已清，外层从头重下）
|
||||
"""
|
||||
headers = {}
|
||||
mode = "wb"
|
||||
if resume_from > 0:
|
||||
headers["Range"] = f"bytes={resume_from}-"
|
||||
mode = "ab"
|
||||
|
||||
if progress_cb is not None:
|
||||
try:
|
||||
progress_cb(resume_from, music_info.file_size or 0)
|
||||
except Exception:
|
||||
pass # 进度回调绝不影响下载主流程
|
||||
resp: requests.SyncResponse | None = None
|
||||
try:
|
||||
resp = get_http_session().get(
|
||||
music_info.download_url,
|
||||
stream=True,
|
||||
timeout=(10, 60),
|
||||
headers=headers,
|
||||
)
|
||||
# 服务器忽略 Range 返回 200 → 从头重写而非追加
|
||||
if resume_from > 0 and resp.status_code != 206:
|
||||
mode = "wb"
|
||||
# 206 必须从我们请求的起点开始；起点错位的分片拼起来是坏文件
|
||||
if resume_from > 0 and resp.status_code == 206:
|
||||
cr = resp.headers.get('Content-Range') or ''
|
||||
m = re.match(r'bytes\s+(\d+)-', cr.strip())
|
||||
if m and int(m.group(1)) != resume_from:
|
||||
self._unlink_quiet(part_path)
|
||||
raise _RetryFromScratch(
|
||||
f"Content-Range 起点错位（{m.group(1)} != {resume_from}），已从头重新下载")
|
||||
# 206 却解析不出起点（头被中间层剥离）——盲追加可能拼坏文件，
|
||||
# 与起点错位同口径处理：清残片从头下
|
||||
if not m:
|
||||
self._unlink_quiet(part_path)
|
||||
raise _RetryFromScratch("206 响应缺少可用 Content-Range，已从头重新下载")
|
||||
resp.raise_for_status()
|
||||
# 下载体积硬上限（配置 500MB），超限即弃，防单文件拖垮磁盘
|
||||
max_bytes = _MAX_DOWNLOAD_BYTES
|
||||
written = resume_from if mode == 'ab' else 0
|
||||
over_limit = False
|
||||
with open(part_path, mode) as f:
|
||||
for chunk in resp.iter_content(chunk_size=DL_CHUNK_SIZE):
|
||||
if cancel_event is not None and cancel_event.is_set():
|
||||
raise DownloadCanceled("下载已取消")
|
||||
if chunk:
|
||||
f.write(chunk)
|
||||
written += len(chunk)
|
||||
if written > max_bytes:
|
||||
# 超限残片没有任何续传价值。
|
||||
# Windows 无法删除打开中的文件——置标志 break，
|
||||
# with 关闭后再清理（原实现在打开中 unlink 被静默吞掉）
|
||||
over_limit = True
|
||||
break
|
||||
if progress_cb is not None:
|
||||
try:
|
||||
progress_cb(written, music_info.file_size or 0)
|
||||
except Exception:
|
||||
pass # 进度回调绝不影响下载主流程
|
||||
if over_limit:
|
||||
self._unlink_quiet(part_path) # 文件已关闭，清理可达
|
||||
raise DownloadException(
|
||||
f"文件超过大小上限 {max_bytes // (1024*1024)}MB，已中止")
|
||||
except requests.HTTPError as e:
|
||||
# Range 起点无效（如 CDN 环节变化）：清除旧 part，从头重新下载
|
||||
status = getattr(getattr(e, "response", None), "status_code", None)
|
||||
if status == 416:
|
||||
self._unlink_quiet(part_path)
|
||||
raise _RetryFromScratch("Range 起点失效，已从头重新下载") from e
|
||||
if status is not None and 400 <= status < 500 and status != 408:
|
||||
# CDN 4xx（403 防盗链/429 风控等）是确定性
|
||||
# 失败，对同一失效直链白重试只会加剧风控、拖慢失败返回
|
||||
# （408 请求超时保留可重试）
|
||||
self._unlink_quiet(part_path)
|
||||
raise DownloadException(
|
||||
f"下载失败（HTTP {status}），下载链接可能已失效") from e
|
||||
raise
|
||||
finally:
|
||||
if resp is not None:
|
||||
resp.close()
|
||||
|
||||
def _fetch_via_aria2(
|
||||
self,
|
||||
backend: Aria2Backend,
|
||||
music_info: MusicInfo,
|
||||
part_path: Path,
|
||||
cancel_event: threading.Event | None,
|
||||
progress_cb,
|
||||
) -> None:
|
||||
"""aria2c 通道：多连接加速 + 原生断点续传。
|
||||
|
||||
异常语义与内置通道对齐：取消抛 DownloadCanceled、体积超限抛
|
||||
DownloadException（均清残片），网络类失败抛 RequestException
|
||||
（保留残片，由外层退避重试续传）。
|
||||
"""
|
||||
backend.fetch(
|
||||
music_info.download_url,
|
||||
part_path,
|
||||
cancel_event=cancel_event,
|
||||
progress_cb=progress_cb,
|
||||
max_bytes=_MAX_DOWNLOAD_BYTES,
|
||||
)
|
||||
|
||||
|
||||
# ============ 元数据写入（mutagen，纯 Python） ============
|
||||
# download_music_to_memory / download_batch_async / get_download_progress
|
||||
# 三个方法已删除——全服务端与验证脚本零调用（CLI 遗留），且 to_memory 不接受
|
||||
# cookies 参数、真被启用会有行为差异；如需内存下载/异步批量再按当前接口重写
|
||||
|
||||
def _write_metadata_with_ffmpeg(
|
||||
def _write_metadata(
|
||||
self,
|
||||
file_path: Path,
|
||||
music_info: MusicInfo,
|
||||
fields: list[str] | None = None,
|
||||
) -> bool:
|
||||
"""使用 ffmpeg 写入音频元数据
|
||||
"""写入音频标签与封面（mutagen）；失败不影响交付，返回是否成功。
|
||||
|
||||
处理: title/artist/album/track + 封面（如果是 mp3/flac/m4a/mp4）
|
||||
fields: 可选字段列表 ['title','artist','album','cover','lyrics','date']；
|
||||
None 表示全部写入。
|
||||
Args:
|
||||
file_path: 已转正的音频文件
|
||||
music_info: 歌曲信息（标题/歌手/专辑/年份/曲号/歌词/封面地址）
|
||||
fields: 要写入的字段列表，None 表示全部写入
|
||||
|
||||
Returns:
|
||||
是否写入成功（失败不影响主流程）
|
||||
封面走共享缓存（与 ZIP 打包共用一次网络请求）；各容器的落盘细节见
|
||||
tagging.py——按扩展名分派到 ID3v2.3 / Vorbis comment / iTunes ilst。
|
||||
"""
|
||||
ffmpeg_path = self._resolve_ffmpeg()
|
||||
if not ffmpeg_path:
|
||||
logger.warning("跳过元数据写入: ffmpeg 不可用")
|
||||
return False
|
||||
|
||||
file_ext = file_path.suffix.lower()
|
||||
if file_ext not in METADATA_FORMATS:
|
||||
logger.warning(f"跳过元数据写入: 不支持的格式 {file_ext}")
|
||||
return False
|
||||
|
||||
if not file_path.exists():
|
||||
logger.warning(f"跳过元数据写入: 文件不存在 {file_path}")
|
||||
return False
|
||||
|
||||
# 临时输出文件：保留原扩展名在最后，便于 ffmpeg 识别 muxer
|
||||
# 例: 艾辰 - 错位时空.tagging.flac
|
||||
tmp_output = file_path.with_name(
|
||||
file_path.stem + ".tagging" + file_path.suffix
|
||||
)
|
||||
# 临时封面文件
|
||||
cover_tmp: str | None = None
|
||||
cover_ok = False # 创建成功与否与"路径是否需要清理"分离管理
|
||||
|
||||
try:
|
||||
# 下载封面到临时文件（走共享缓存：与 ZIP 打包共用一次网络请求）
|
||||
include_cover = fields is None or "cover" in fields
|
||||
if include_cover and music_info.pic_url:
|
||||
cover_data = fetch_cover_bytes(music_info.pic_url)
|
||||
if cover_data:
|
||||
try:
|
||||
fd, cover_tmp = tempfile.mkstemp(suffix=".jpg", dir=str(self.download_dir))
|
||||
os.close(fd)
|
||||
with open(cover_tmp, "wb") as cf:
|
||||
cf.write(cover_data)
|
||||
cover_ok = True
|
||||
except Exception as e:
|
||||
# cover_tmp 保持指向已创建的文件，finally 统一清理
|
||||
# 原实现置 None 会把已创建的零字节文件遗留在下载目录）
|
||||
logger.warning(f"封面写盘失败，跳过封面写入: {e}")
|
||||
else:
|
||||
logger.warning("封面下载失败，跳过封面写入")
|
||||
|
||||
# 构造 ffmpeg 命令
|
||||
# 顺序: global opts -> -i input1 -> -i input2 -> metadata -> mapping -> -f format -> output
|
||||
output_format = EXT_TO_FFMPEG_FORMAT.get(file_ext, "")
|
||||
cmd: list[str] = [
|
||||
ffmpeg_path, "-y", "-loglevel", "error",
|
||||
"-i", str(file_path),
|
||||
]
|
||||
use_cover = cover_ok
|
||||
# OGG/Opus 的封面流 copy 不被支持（Unsupported codec id），
|
||||
# 主动降级为"只写文本元数据"，不再让整个写入失败
|
||||
if use_cover and file_ext in (".ogg", ".opus"):
|
||||
use_cover = False
|
||||
logger.info("OGG/Opus 不支持封面写入，仅写入文本元数据")
|
||||
if use_cover and cover_tmp:
|
||||
cmd += ["-i", cover_tmp]
|
||||
|
||||
# 通用元数据（仅写入勾选的字段）
|
||||
meta = {}
|
||||
# 前端字段名为 name，与后端 title 统一映射
|
||||
if fields is None or "title" in fields or "name" in fields:
|
||||
meta["title"] = music_info.name
|
||||
if fields is None or "artist" in fields:
|
||||
meta["artist"] = music_info.artists
|
||||
meta["album_artist"] = music_info.artists
|
||||
if fields is None or "album" in fields:
|
||||
meta["album"] = music_info.album
|
||||
if fields is None or "date" in fields:
|
||||
if music_info.publish_year:
|
||||
meta["date"] = str(music_info.publish_year)
|
||||
meta["year"] = str(music_info.publish_year)
|
||||
if fields is None or "lyrics" in fields:
|
||||
if music_info.lyric and music_info.lyric.strip():
|
||||
# 去掉 LRC 时间标签，写入纯歌词
|
||||
clean_lyric = re.sub(
|
||||
r"\[\d{1,2}:\d{1,2}([.:]\d+)?\]", "", music_info.lyric
|
||||
).strip()
|
||||
if clean_lyric:
|
||||
meta["lyrics"] = clean_lyric
|
||||
if music_info.track_number > 0 and (fields is None or "track" in fields):
|
||||
# 只写当前曲号；没有真实专辑总数时不虚构 tracktotal
|
||||
meta["track"] = str(music_info.track_number)
|
||||
for k, v in meta.items():
|
||||
if v:
|
||||
cmd += ["-metadata", f"{k}={v}"]
|
||||
|
||||
# 各格式的 mapping / 编码选项
|
||||
cmd += self._build_format_args(file_ext, has_cover=use_cover)
|
||||
|
||||
# -f 必须放在所有 -i 之后（作为 output option）才生效
|
||||
if output_format:
|
||||
cmd += ["-f", output_format]
|
||||
cmd.append(str(tmp_output))
|
||||
|
||||
# 执行
|
||||
result = subprocess.run(
|
||||
cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=120,
|
||||
encoding="utf-8",
|
||||
errors="ignore",
|
||||
)
|
||||
|
||||
if result.returncode == 0 and tmp_output.exists():
|
||||
# os.replace 才是同卷原子替换——shutil.move 在目标已
|
||||
# 存在时退化为 copy2+unlink，进程中断会留半截文件
|
||||
os.replace(str(tmp_output), str(file_path))
|
||||
return True
|
||||
|
||||
# ffmpeg stderr 原文走 logger（errors='ignore' 解码后的任意 Unicode
|
||||
# 在 GBK 重定向下裸 print 会崩 worker）
|
||||
logger.warning(
|
||||
f"ffmpeg 写入元数据失败: {(result.stderr or result.stdout or '').strip()}"
|
||||
)
|
||||
return False
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.warning("ffmpeg 执行超时")
|
||||
return False
|
||||
except FileNotFoundError:
|
||||
logger.warning(f"ffmpeg 可执行文件未找到: {ffmpeg_path}")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.warning(f"ffmpeg 写入元数据异常: {e}")
|
||||
return False
|
||||
finally:
|
||||
# 清理封面临时文件
|
||||
if cover_tmp and os.path.exists(cover_tmp):
|
||||
try:
|
||||
os.unlink(cover_tmp)
|
||||
except OSError:
|
||||
pass
|
||||
# 清理可能残留的临时输出
|
||||
if tmp_output.exists():
|
||||
try:
|
||||
tmp_output.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
def _build_format_args(self, file_ext: str, has_cover: bool) -> list[str]:
|
||||
"""根据文件格式构造 mapping / 编码参数
|
||||
不写封面时用 -map 0 -c copy 保留全部既有流（含已有封面），
|
||||
原实现 -map 0:a 会把 MP3/M4A 已有封面静默删掉。"""
|
||||
if file_ext == ".mp3":
|
||||
# MP3: 封面通过 ID3v2 APIC 帧写入
|
||||
if has_cover:
|
||||
return [
|
||||
"-map", "0:a", "-map", "1:v",
|
||||
"-c:a", "copy", "-c:v", "copy",
|
||||
"-id3v2_version", "3",
|
||||
"-metadata:s:v", "title=Album cover",
|
||||
"-metadata:s:v", "comment=Cover (front)",
|
||||
]
|
||||
return ["-map", "0", "-c", "copy", "-id3v2_version", "3"]
|
||||
|
||||
if file_ext == ".flac":
|
||||
# FLAC: 原生支持封面
|
||||
if has_cover:
|
||||
return [
|
||||
"-map", "0", "-map", "1",
|
||||
"-c", "copy",
|
||||
"-disposition:v:0", "attached_pic",
|
||||
]
|
||||
return ["-map", "0", "-c", "copy"]
|
||||
|
||||
if file_ext == ".m4a":
|
||||
# M4A: AAC 音频 + mp4 容器
|
||||
if has_cover:
|
||||
return [
|
||||
"-map", "0:a", "-map", "1:v",
|
||||
"-c", "copy",
|
||||
"-disposition:v:0", "attached_pic",
|
||||
"-metadata:s:v", "title=Album cover",
|
||||
"-metadata:s:v", "comment=Cover (front)",
|
||||
]
|
||||
# 保留既有封面流（原 -map 0:a 会删掉已有封面）
|
||||
return ["-map", "0", "-c", "copy"]
|
||||
|
||||
if file_ext == ".mp4":
|
||||
# MP4 (杜比全景声 EAC3 / 其它 mp4 容器音频)
|
||||
# 杜比文件通常无视频流，封面作为 video stream 注入；+faststart 让 moov 在文件头
|
||||
if has_cover:
|
||||
return [
|
||||
"-map", "0", "-map", "1:v",
|
||||
"-c", "copy",
|
||||
"-disposition:v:0", "attached_pic",
|
||||
"-metadata:s:v", "title=Album cover",
|
||||
"-metadata:s:v", "comment=Cover (front)",
|
||||
"-movflags", "+faststart",
|
||||
]
|
||||
return ["-map", "0", "-c", "copy", "-movflags", "+faststart"]
|
||||
|
||||
if file_ext in (".ogg", ".opus"):
|
||||
if has_cover:
|
||||
return [
|
||||
"-map", "0:a", "-map", "1:v",
|
||||
"-c:a", "copy", "-c:v", "copy",
|
||||
]
|
||||
return ["-map", "0:a", "-c:a", "copy"]
|
||||
|
||||
# 默认
|
||||
if has_cover:
|
||||
return ["-map", "0:a", "-map", "1:v", "-c", "copy"]
|
||||
return ["-map", "0:a", "-c:a", "copy"]
|
||||
include_cover = fields is None or "cover" in fields
|
||||
cover: bytes | None = None
|
||||
if include_cover and music_info.pic_url:
|
||||
cover = fetch_cover_bytes(music_info.pic_url)
|
||||
if not cover:
|
||||
logger.warning("封面下载失败，跳过封面写入")
|
||||
return write_tags(file_path, build_tags(music_info, fields), cover)
|
||||
Reference in new issue
Block a user