Archived
snowy-yang
96af56cc27
拆掉两类垫片的最后一处：auth_system 原为同步 sqlite3 栈，web 层与 services 的
worker 只能靠 asyncio.to_thread 逐个桥接才不阻塞事件循环——每次 DB 访问都白付一次
线程池调度，且「同步调异步」的边界散落在 100+ 个调用点。B1 已把 worker 变成协程，
本批把访问层本身也迁到原生异步，两条线在此合拢。
改动（按子系统）：
- auth_system：db.py 照 core/db.py 现有范式重建为原生异步访问层（aiosqlite + WAL）
——读路径 _q 每次独立连接、无锁、可并发；写路径 _x / write_transaction 用
asyncio.Lock 串行化，写者不阻塞读者。users / cards / credits / ledger / logs /
settings / mail / geo / backup 九模块随之全部 async/await；security.py 是纯计算
（pbkdf2/normalize）不动。__init__ 去掉 _DB_LOCK 与 get_conn 导出。
- web：app / deps / billing / tasks_registry 与 routers/{admin_site,auth,music,
register,user} 直接 await，拆掉包裹的 to_thread。deps.secret_key 改 async，
连带 _parse_cookie 也 async（会话解析要读密钥）。
- services：_taskcore / tasks / downloads / podcast 的账本调用与查询直接 await。
4 处 start_task 调用点（download.py）确认已 await。
设计取舍（为什么这么做，而不是直接包一层）：
- 锁按**事件循环**隔离（_LOOP_LOCKS 以 id(loop) 为键）：asyncio.Lock 绑定创建它的
loop，应用主 loop 与测试各自的 loop 并存，跨 loop 复用会抛 "bound to a different
event loop"。
- WAL 切换用**独立锁** _wal_lock 而非 _write_lock：execute() 已持写锁，再在锁内
connect→_configure 会自锁死（asyncio.Lock 非重入）。切换 + 标记在专用锁内串行并
二次复查，否则并发首连会同时执行 PRAGMA journal_mode=WAL 争排他锁报
database is locked（core/db.py 同款教训，实测复现）。
- force_wal 保留：journal_mode 持久化在库文件头，库文件被删重建时新文件不继承，
必须重设。exists() 判定须在 aiosqlite.connect **之前**（connect 会创建空文件）。
- connect() 用 DB_PATH.parent 兜底建目录，优于 DATA_DIR：生产两者相同，但测试
monkeypatch 只换 DB_PATH 时兜底仍能命中正确目录。
留在 to_thread 上的仅剩**正当的阻塞卸载**，不是同步门面：PBKDF2 的 10 万次迭代
（登录链路每次都要跑）、smtplib 发信、备份文件的 copy2 / os.replace、secret.key
的文件 IO。原有 aria2 / downloader / zip 侧的 to_thread 未动。
不变量逐条保持（迁移只改执行模型，不改语义）：
- ledger_settle 幂等：账本非 open 直接 return 0，重启后重放不重复退款；
- 终态先到先得：_mark_task_terminal 对已 done/error/canceled 的任务直接 return，
堵住 canceled→error 的非法迁移边；
- settle 必须在任务锁**外**调用（ledger_settle 要抢 SQLite 写锁，busy 最长 15s，
持任务锁会让全站进度/提交/取消随库停摆）；
- reserve_and_open 的预扣与开账同事务，消除原两步之间的崩溃丢账窗口。
路径真源红线：DATA_DIR / DB_PATH / BACKUP_DIR / SECRET_KEY_PATH 仍是 auth_system.db
的**模块全局**（用与 core.db 相同的表达式，但**不是**它的别名）。测试只 patch
auth_system.db.*，若改成 core.db 的别名会静默把测试写到生产库。已核 data/site.db
读写前后 sha256 完全一致。
顺带清掉 get_conn：迁移后它只剩「转调 connect()」一层空壳、全仓零消费者（测试
直接开裸连接、备份用 db.connect()），保留等于留一条「拿裸连接自己写」的口子。
测试：19 个文件同步迁移——10 个文件的 web.deps.secret_key 替身改 async；
test_db_conn.py 的多线程首连用例按异步语义拆成 2 条（单 loop gather(16) 覆盖批量
并发首连、WAL 就绪后 8 线程各自 loop 建连覆盖跨 loop）；test_billing_scope.py 去掉
多余的 @pytest.mark.anyio；被 await 且**正常返回**的 monkeypatch 替身一律改 async
（仅 raise 的同步替身仍可用）。
门禁：ruff 全过 / pyright 0-0-0（standard 模式含 tests 与顶层模块）/ pytest
384 项全绿（0 失败 0 error 0 skipped；383→384 因 test_db_conn 拆用例）。
data/site.db 读写前后 sha256 一致（a19f5db…6487），无 -wal/-shm 边车残留。
下一步 B3：删 core/sync_http.py、core/async_bridge.py、core/http_errors.py 及
tests/test_async_bridge.py——三者在生产侧已零消费者（http_errors 仅 sync_http
自用，requests 已非声明依赖）。
574 lines
23 KiB
Python
574 lines
23 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""播客单集与整台打包 worker。
|
||
|
||
整台打包的骨架（状态机 / 暂停 / 名额 / 终态收敛 / 结算）在
|
||
:mod:`services._zipcore`，本模块只保留播客侧策略：清单组装（整台或指定单集）、
|
||
逐集顺序下载、按实际集数补扣、单条目入包（首集附封面）。
|
||
|
||
下载走 core.http_client 的流式响应（原先是 services.streaming 这个同步流垫片），
|
||
落盘写文件是阻塞 IO、ZIP 组装是整段拷贝，均经 ``asyncio.to_thread`` 卸载。
|
||
"""
|
||
|
||
import asyncio
|
||
import os
|
||
import shutil
|
||
import tempfile
|
||
import threading
|
||
import time
|
||
import traceback
|
||
import zipfile
|
||
from dataclasses import dataclass
|
||
from pathlib import Path
|
||
from typing import Any
|
||
|
||
import auth_system
|
||
from core.http_client import client as _http
|
||
from core.http_client import iter_chunks
|
||
from core.state import (
|
||
DOWNLOAD_TASKS,
|
||
DOWNLOAD_TASKS_LOCK,
|
||
)
|
||
from music_api import (
|
||
APIException,
|
||
podcast,
|
||
)
|
||
from music_downloader import (
|
||
DownloadCanceled,
|
||
DownloadException,
|
||
fetch_cover_bytes,
|
||
)
|
||
|
||
from ._shared import (
|
||
_record_log,
|
||
)
|
||
from ._taskcore import (
|
||
_mark_task_terminal,
|
||
_settle_batch_billing,
|
||
)
|
||
from ._zipcore import (
|
||
ZipContext,
|
||
ZipJob,
|
||
run_zip_job,
|
||
)
|
||
from .api_service import (
|
||
api_service,
|
||
)
|
||
from .downloads import (
|
||
_abort_if_canceled,
|
||
)
|
||
|
||
# 播客流式下载的上游头（与音频直链 CDN 的口径一致）
|
||
_STREAM_HEADERS = {
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
|
||
'(KHTML, like Gecko) Safari/537.36',
|
||
'Referer': 'https://music.163.com/',
|
||
}
|
||
|
||
|
||
def _podcast_safe_name(s: str, fallback: str = 'unknown') -> str:
|
||
"""文件名安全化（去除非法字符）"""
|
||
s = ''.join(c for c in str(s or '') if c not in r'<>:"/\|?*' and ord(c) >= 32).strip()
|
||
return s or fallback
|
||
|
||
|
||
def _remove_quietly(path: Path) -> None:
|
||
"""删除文件并忽略失败（Windows 上句柄未释放时 os.remove 会抛 OSError）。"""
|
||
try:
|
||
os.remove(str(path))
|
||
except OSError:
|
||
pass
|
||
|
||
|
||
def _report_progress(task_id: str, progress_label: str, done: int, total: int) -> None:
|
||
"""把一次进度写进任务表；task_id 为空或任务不在 running 时只计算不写。
|
||
|
||
msg 的计算与「是否真有可取的任务」无关（历史实现如此），故 task_id 为空时
|
||
仍会格式化字符串——保持这一无害的既有行为，不做「优化」。
|
||
"""
|
||
pct = 0
|
||
if total:
|
||
pct = min(99, int(done / total * 100))
|
||
msg = (f"{progress_label} {pct}% · "
|
||
f"{api_service._format_file_size(done)}/{api_service._format_file_size(total)}")
|
||
else:
|
||
msg = f"{progress_label} 已下载 {api_service._format_file_size(done)}"
|
||
if not task_id:
|
||
return
|
||
with DOWNLOAD_TASKS_LOCK:
|
||
t = DOWNLOAD_TASKS.get(task_id)
|
||
if t and t['status'] == 'running':
|
||
t['msg'] = msg
|
||
# 单集任务的字节级进度（批量任务保持按集数口径）
|
||
if t.get('type') == 'single' and total:
|
||
t['live_percent'] = min(99.0, float(pct))
|
||
|
||
|
||
async def _stream_to_part(url: str, part: Path, total_size: int, cancel_ev: threading.Event,
|
||
task_id: str, progress_label: str) -> tuple[int, int]:
|
||
"""把响应体流式写入 part，返回 (已写字节数, 期望总大小)。
|
||
|
||
期望总大小取入参，缺失时回落到 Content-Length（仍可能为 0，表示上游没给）。
|
||
"""
|
||
done = 0
|
||
last_update = 0.0
|
||
resp = await _http.open('GET', url, headers=_STREAM_HEADERS, timeout=60)
|
||
try:
|
||
if resp.status >= 400:
|
||
raise DownloadException(f"上游返回 {resp.status}")
|
||
total = total_size or int(resp.headers.get('Content-Length') or 0)
|
||
with open(part, 'wb') as f:
|
||
async for chunk in iter_chunks(resp, 256 * 1024):
|
||
if cancel_ev.is_set():
|
||
raise DownloadCanceled("任务已取消")
|
||
if not chunk:
|
||
continue
|
||
f.write(chunk)
|
||
done += len(chunk)
|
||
now = time.time()
|
||
if now - last_update > 0.5:
|
||
last_update = now
|
||
_report_progress(task_id, progress_label, done, total)
|
||
finally:
|
||
resp.close()
|
||
return done, total
|
||
|
||
|
||
def _verify_downloaded(target: Path, done: int, total_size: int) -> None:
|
||
"""完整性校验：不达标则删掉已落地的文件并抛 DownloadException。
|
||
|
||
为什么非要校验：CDN 提前断流时流式读取会「正常」结束，文件静默截断。
|
||
已知期望大小时要求**精确相等**（API 报的大小与实际一致；放宽到 95% 容差会
|
||
交付截断的坏文件还照扣次数）；期望未知时退化为非空校验——Content-Length
|
||
兜底值可能是压缩口径，不做精确比对。
|
||
"""
|
||
if total_size and done != total_size:
|
||
_remove_quietly(target)
|
||
raise DownloadException(f"下载不完整（{done}/{total_size} 字节），请重试")
|
||
if not total_size and done <= 0:
|
||
_remove_quietly(target)
|
||
raise DownloadException("下载内容为空，请重试")
|
||
|
||
|
||
async def _podcast_stream_download(url: str, target: Path, total_size: int,
|
||
cancel_ev: threading.Event,
|
||
task_id: str = '', progress_label: str = '') -> int:
|
||
"""流式下载播客音频到 target（先写 .part 再改名），返回实际字节数。
|
||
|
||
自动加入全局下载闸排队；每 0.5s 更新一次任务进度消息。
|
||
取消时 .part 会留存（不删）——下次下载同名文件直接覆盖，是既有行为。
|
||
"""
|
||
part = target.with_name(target.name + '.part')
|
||
# 等待全局下载名额期间可被取消（与音乐批量 BATCH_ZIP_SEM 同语义）
|
||
sem = api_service.downloader._download_semaphore
|
||
if not await sem.acquire_cancellable(cancel_ev):
|
||
raise DownloadCanceled("任务已取消")
|
||
try:
|
||
done, _total = await _stream_to_part(url, part, total_size, cancel_ev, task_id, progress_label)
|
||
finally:
|
||
sem.release()
|
||
if part.exists():
|
||
part.replace(target)
|
||
_verify_downloaded(target, done, total_size)
|
||
return done
|
||
|
||
|
||
async def _podcast_resolve_audio(program: dict[str, Any], quality: str,
|
||
cookies: dict[str, str]) -> dict[str, Any]:
|
||
"""解析单集音频直链，失败抛 DownloadException"""
|
||
song_id = program.get('main_song_id')
|
||
if not song_id:
|
||
raise DownloadException("该单集缺少音频信息（mainSong）")
|
||
url_info = await podcast.resolve_episode_url(song_id, cookies, quality)
|
||
if not url_info or not url_info.get('url'):
|
||
raise DownloadException("未获取到音频直链（单集可能已下架或受版权限制）")
|
||
return url_info
|
||
|
||
|
||
@dataclass(frozen=True)
|
||
class _PodcastTaskSpec:
|
||
"""worker 启动时从任务表取出的不可变执行参数。
|
||
|
||
``program_id`` 标注 Any 与单曲 worker（SingleTaskParams.music_id）同因：
|
||
任务 params 里历史存的是数字字符串，下游上游解析各自处理，worker 只透传
|
||
不做 int() 转换（那是行为变更）。
|
||
"""
|
||
|
||
program_id: Any
|
||
quality: str
|
||
need_zip: bool
|
||
cookies: dict[str, Any]
|
||
remote_ip: str
|
||
cancel_ev: threading.Event
|
||
|
||
|
||
@dataclass(frozen=True)
|
||
class _PodcastTarget:
|
||
"""单集落盘目标与交付命名。
|
||
|
||
磁盘名附节目 ID + 任务目录隔离（两个任务同下载一集互不覆盖、互不删除）；
|
||
交付名保持干净（不带 ID）。
|
||
"""
|
||
|
||
task_dir: Path
|
||
target: Path
|
||
filename: str # 交付名（含扩展名）
|
||
base: str # 交付名去扩展名（ZIP 条目名与封面名共用）
|
||
name: str # 单集原始名（info.txt 与操作记录用）
|
||
ext: str
|
||
|
||
|
||
def _begin_podcast_task(task_id: str) -> _PodcastTaskSpec:
|
||
"""置 running 并取出执行参数（任务不存在时 KeyError → 通用 except 收敛 error）。"""
|
||
with DOWNLOAD_TASKS_LOCK:
|
||
task = DOWNLOAD_TASKS[task_id]
|
||
task['status'] = 'running'
|
||
task['msg'] = '解析单集信息...'
|
||
params = task['params']
|
||
return _PodcastTaskSpec(
|
||
program_id=params['program_id'],
|
||
quality=params['quality'],
|
||
need_zip=params['need_zip'],
|
||
cookies=params['cookies'],
|
||
remote_ip=params.get('remote_ip') or '-',
|
||
cancel_ev=task['cancel'],
|
||
)
|
||
|
||
|
||
def _prepare_podcast_target(task_id: str, program_id: Any, program: dict[str, Any],
|
||
url_info: dict[str, Any]) -> _PodcastTarget:
|
||
"""组装文件名与任务专属目录（顺带 mkdir）。"""
|
||
serial = int(program.get('serial_num') or 0)
|
||
name = program.get('name') or program.get('main_song_name') or '播客单集'
|
||
prefix = f"{serial:03d} - " if serial else ''
|
||
base = _podcast_safe_name(f"{prefix}{name}")
|
||
ext = (url_info.get('type') or 'mp3').lower().lstrip('.')
|
||
task_dir = api_service.downloads_path / 'tasks' / task_id
|
||
task_dir.mkdir(parents=True, exist_ok=True)
|
||
return _PodcastTarget(
|
||
task_dir=task_dir,
|
||
target=task_dir / f"{base} [{program_id}].{ext}",
|
||
filename=f"{base}.{ext}",
|
||
base=base,
|
||
name=name,
|
||
ext=ext,
|
||
)
|
||
|
||
|
||
def _write_podcast_zip(zip_path: str, file_path_str: str, arcname: str, base: str,
|
||
name: str, program: dict[str, Any], url_info: dict[str, Any],
|
||
fallback_quality: str, cover: bytes = b'') -> None:
|
||
"""单集入包：音频 + 封面（可选，失败不炸任务）+ info.txt。
|
||
|
||
info.txt 不再写直链（真实 URL 不应随交付文件外泄）。
|
||
封面字节由调用方先取好（网络等待留在协程里），本函数只做阻塞的落盘组装。
|
||
"""
|
||
with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zf:
|
||
zf.write(file_path_str, arcname=arcname)
|
||
if cover:
|
||
zf.writestr(f"{base}.jpg", cover)
|
||
info_txt = (
|
||
f"单集: {name}\n"
|
||
f"播客: {program.get('radio_name') or ''}\n"
|
||
f"主播: {program.get('dj_name') or ''}\n"
|
||
f"时长: {program.get('duration_text') or ''}\n"
|
||
f"音质: {api_service._get_quality_display_name(url_info.get('level', fallback_quality))}\n"
|
||
)
|
||
zf.writestr("info.txt", info_txt)
|
||
|
||
|
||
def _podcast_file_result(file_path_str: str, filename: str, ext: str) -> dict[str, Any]:
|
||
"""不打包时的交付形状。"""
|
||
return {
|
||
'file_path': file_path_str,
|
||
'filename': filename,
|
||
'mimetype': f"audio/{ext}",
|
||
'audio_files': [file_path_str],
|
||
}
|
||
|
||
|
||
async def _podcast_zip_result(prep: _PodcastTarget, file_path_str: str,
|
||
program: dict[str, Any], url_info: dict[str, Any],
|
||
spec: _PodcastTaskSpec) -> dict[str, Any]:
|
||
"""打包交付形状：ZIP 中间文件建在任务目录下（失败收尾 rmtree 一并覆盖）。"""
|
||
cover: bytes = b''
|
||
cover_url = program.get('cover_url') or ''
|
||
if cover_url:
|
||
try:
|
||
cover = await fetch_cover_bytes(cover_url) or b''
|
||
except Exception:
|
||
cover = b''
|
||
fd, zip_tmp_path = tempfile.mkstemp(prefix='podcast_zip_', suffix='.zip',
|
||
dir=str(prep.task_dir))
|
||
os.close(fd)
|
||
await asyncio.to_thread(_write_podcast_zip, zip_tmp_path, file_path_str,
|
||
arcname=prep.filename, base=prep.base, name=prep.name,
|
||
program=program, url_info=url_info,
|
||
fallback_quality=spec.quality, cover=cover)
|
||
return {
|
||
'file_path': file_path_str,
|
||
'zip_path': zip_tmp_path,
|
||
'filename': f"{prep.base}.zip",
|
||
'mimetype': 'application/zip',
|
||
'audio_files': [file_path_str],
|
||
}
|
||
|
||
|
||
async def _publish_podcast_task(task_id: str, result: dict[str, Any], remote_ip: str,
|
||
name: str, filename: str) -> None:
|
||
"""最终发布：置 done（已终态不覆盖）→ 结算 → 记操作日志。
|
||
|
||
交付已落定；结算失败**不再**把任务改标 error——钱由重启对账兜底，
|
||
宁可商家小损不坑用户（与单曲 _publish_single_task 同口径）。
|
||
"""
|
||
with DOWNLOAD_TASKS_LOCK:
|
||
t = DOWNLOAD_TASKS.get(task_id)
|
||
if t is None or t.get('status') in ('canceled', 'error'):
|
||
raise DownloadCanceled("任务已取消")
|
||
t['status'] = 'done'
|
||
t['completed_at'] = time.time()
|
||
t['done'] = 1
|
||
t['msg'] = '下载完成'
|
||
t['result'] = result
|
||
try:
|
||
await auth_system.ledger_settle(task_id, 1, 'delivered')
|
||
except Exception as _e:
|
||
api_service.logger.error(f"播客单集交付结算失败（重启对账兜底）: {task_id} {_e}")
|
||
try:
|
||
_record_log('下载', remote_ip, f"[播客] {name}")
|
||
except Exception:
|
||
pass
|
||
api_service.logger.info(f"播客单集下载完成: {filename} ({task_id})")
|
||
|
||
|
||
async def _fail_podcast_task(task_id: str, status: str, msg: str, ledger_status: str,
|
||
task_dir: Path | None) -> None:
|
||
"""失败/取消的统一收尾：置终态 → 退款 → 清掉任务目录（含 ZIP 中间件）。"""
|
||
await _mark_task_terminal(task_id, status, msg)
|
||
try:
|
||
await auth_system.ledger_settle(task_id, 0, ledger_status)
|
||
except Exception:
|
||
pass
|
||
if task_dir is not None:
|
||
await asyncio.to_thread(shutil.rmtree, str(task_dir), ignore_errors=True)
|
||
|
||
|
||
async def _podcast_download_worker(task_id: str) -> None:
|
||
"""后台播客单集下载：解析单集 → 音质降级取直链 → 流式下载（可选 ZIP 打包）
|
||
|
||
任务 type 为 'single'，完成后经 /download/result 交付，与单曲下载共用交付通道。
|
||
落盘文件进入任务专属目录且带节目 ID，跨任务永不重名；清理只动本任务目录。
|
||
"""
|
||
task_dir: Path | None = None
|
||
try:
|
||
spec = _begin_podcast_task(task_id)
|
||
program = await podcast.get_program_detail(spec.program_id, spec.cookies)
|
||
url_info = await _podcast_resolve_audio(program, spec.quality, spec.cookies)
|
||
prep = _prepare_podcast_target(task_id, spec.program_id, program, url_info)
|
||
task_dir = prep.task_dir
|
||
|
||
with DOWNLOAD_TASKS_LOCK:
|
||
t = DOWNLOAD_TASKS[task_id]
|
||
t['msg'] = '下载中...'
|
||
await _podcast_stream_download(url_info['url'], prep.target, url_info.get('size', 0),
|
||
spec.cancel_ev, task_id, '下载中')
|
||
_abort_if_canceled(spec.cancel_ev)
|
||
file_path_str = str(prep.target)
|
||
|
||
if spec.need_zip:
|
||
result = await _podcast_zip_result(prep, file_path_str, program, url_info, spec)
|
||
else:
|
||
result = _podcast_file_result(file_path_str, prep.filename, prep.ext)
|
||
# 打包阶段同样以取消检查收口（末段取消不得覆盖为 done）
|
||
_abort_if_canceled(spec.cancel_ev)
|
||
|
||
await _publish_podcast_task(task_id, result, spec.remote_ip, prep.name, prep.filename)
|
||
except DownloadCanceled:
|
||
api_service.logger.info(f"播客单集下载已取消: {task_id}")
|
||
await _fail_podcast_task(task_id, 'canceled', '任务已取消', 'canceled', task_dir)
|
||
except DownloadException as e:
|
||
api_service.logger.error(f"播客单集下载失败: {task_id} {e}")
|
||
await _fail_podcast_task(task_id, 'error', str(e), 'error', task_dir)
|
||
except Exception as e:
|
||
# 非预期异常原文 logger 先行，用户可见文案泛化（教训）
|
||
api_service.logger.error(f"播客单集下载异常: {task_id} {e}\n{traceback.format_exc()}")
|
||
await _fail_podcast_task(task_id, 'error', '下载失败，请稍后重试', 'error', task_dir)
|
||
|
||
|
||
def _podcast_cleanup_files(paths: list[str | None]) -> None:
|
||
"""清理播客任务产生的临时/残留文件"""
|
||
for p in paths:
|
||
if not p:
|
||
continue
|
||
try:
|
||
os.remove(p)
|
||
except OSError:
|
||
pass
|
||
# 连带清理可能残留的 .part 文件
|
||
try:
|
||
part = Path(str(p) + '.part')
|
||
if part.exists():
|
||
part.unlink()
|
||
except OSError:
|
||
pass
|
||
|
||
|
||
@dataclass(frozen=True)
|
||
class _EpisodePayload:
|
||
"""一集下载完成后的入包素材（下载协程产出，落包协程消费）。"""
|
||
|
||
path: str
|
||
base: str
|
||
ext: str
|
||
|
||
|
||
class _PodcastZipJob(ZipJob):
|
||
"""整台播客打包：逐集顺序下载（窗口=1）→ 单条目入包，首集附封面。
|
||
|
||
并发刻意等于音乐批量：同样占用全局批量名额（BATCH_ZIP_SEM，全局 3），
|
||
逐集 acquire/release——暂停等待/取消时不长期占名额；音频本身仍受全局
|
||
下载闸约束。原实现不受批量并发控制，多用户同时打包会无限并发。
|
||
"""
|
||
|
||
tag = '播客打包'
|
||
noun = '集'
|
||
item_noun = '单集'
|
||
tmp_prefix = 'podcast_batch_'
|
||
start_msg = '解析单集列表...'
|
||
concurrency = 1
|
||
|
||
def __init__(self) -> None:
|
||
self._radio_name = ''
|
||
|
||
async def prepare(self, params: dict[str, Any], task_id: str, failed: list[str]) -> list[Any]:
|
||
cookies = params['cookies']
|
||
radio_id = params['radio_id']
|
||
limit = params['limit']
|
||
# 组装单集清单：整台电台（正序全量）或指定单集ID列表
|
||
if radio_id:
|
||
episodes = await podcast.list_radio_all_program_ids(radio_id, cookies, max_count=limit)
|
||
if not episodes:
|
||
raise DownloadException("该电台暂无可下载的单集")
|
||
else:
|
||
episodes = []
|
||
for pid in (params.get('ids') or []):
|
||
try:
|
||
prog = await podcast.get_program_detail(pid, cookies)
|
||
episodes.append({
|
||
'id': prog['id'],
|
||
'name': prog['name'],
|
||
'main_song_id': prog['main_song_id'],
|
||
'serial_num': prog['serial_num'],
|
||
'cover_url': prog['cover_url'],
|
||
'detail': prog,
|
||
})
|
||
except APIException as ae:
|
||
failed.append(f"{pid}({ae})")
|
||
episodes = episodes[:limit]
|
||
if not episodes:
|
||
raise DownloadException("没有可下载的单集")
|
||
|
||
self._radio_name = _podcast_safe_name(params.get('radio_name') or '', '播客')
|
||
return episodes
|
||
|
||
async def supplement(self, task_id: str, params: dict[str, Any], count: int) -> None:
|
||
"""按次计费补扣：整台电台提交时只预扣 1 次，此处按实际单集数补足差额。
|
||
|
||
补扣失败（余额不足/数据库异常）任务必须失败并按账本退费——不允许无账本继续交付。
|
||
"""
|
||
try:
|
||
_buid = params.get('billing_uid')
|
||
_extra = count - int(params.get('billed') or 1)
|
||
if _buid and _extra > 0:
|
||
if not await auth_system.ledger_supplement(task_id, _extra):
|
||
raise DownloadException(
|
||
f"补扣下载次数失败（需补扣 {_extra} 次），任务已取消，预扣部分将退回")
|
||
if _buid:
|
||
with DOWNLOAD_TASKS_LOCK:
|
||
DOWNLOAD_TASKS[task_id]['billing_user_id'] = int(_buid)
|
||
DOWNLOAD_TASKS[task_id]['billing_cost'] = count
|
||
except DownloadCanceled:
|
||
raise
|
||
except DownloadException:
|
||
raise
|
||
except Exception as e:
|
||
raise DownloadException(f"补扣下载次数异常: {e}") from e
|
||
|
||
async def download_one(self, item: Any, idx: int, ctx: ZipContext) -> _EpisodePayload:
|
||
ep = item
|
||
label = f"[{idx}/{ctx.total}] {ep['name'][:24]}"
|
||
ctx.progress(f"{label} 解析中...")
|
||
cookies = ctx.params['cookies']
|
||
prog = ep.get('detail') or await podcast.get_program_detail(ep['id'], cookies)
|
||
url_info = await _podcast_resolve_audio(prog, ctx.params['quality'], cookies)
|
||
ctx.progress(f"{label} 下载中...")
|
||
ext = (url_info.get('type') or 'mp3').lower().lstrip('.')
|
||
serial = int(ep.get('serial_num') or 0)
|
||
prefix = f"{serial:03d} - " if serial else ''
|
||
base = _podcast_safe_name(f"{prefix}{ep['name']}")
|
||
# 中间文件移入任务目录——落 downloads 根目录会被缓存清扫按 mtime 打断慢速
|
||
# 单集（Linux 上 unlink 打开中的文件）
|
||
tmp_audio = ctx.work_dir / f"podcast_zip_tmp_{ctx.task_id}_{idx}.{ext}"
|
||
try:
|
||
await _podcast_stream_download(url_info['url'], tmp_audio,
|
||
url_info.get('size', 0), ctx.cancel_ev)
|
||
except Exception:
|
||
# 下载失败即清（.part 残片同清）；成功时由 write_entry 的 finally 清
|
||
_podcast_cleanup_files([str(tmp_audio)])
|
||
raise
|
||
return _EpisodePayload(path=str(tmp_audio), base=base, ext=ext)
|
||
|
||
async def write_entry(self, item: Any, idx: int, payload: _EpisodePayload, ctx: ZipContext) -> None:
|
||
ep = item
|
||
try:
|
||
# 重名条目自动追加序号（同名单集/同号不同集不得互相覆盖）
|
||
arcname = f"{payload.base}.{payload.ext}"
|
||
k = 2
|
||
while arcname in ctx.used_arcnames:
|
||
arcname = f"{payload.base} ({k}).{payload.ext}"
|
||
k += 1
|
||
ctx.used_arcnames.add(arcname)
|
||
await asyncio.to_thread(ctx.zf.write, payload.path, arcname=arcname,
|
||
compress_type=zipfile.ZIP_STORED)
|
||
# 首集附带封面，便于识别
|
||
if idx == 1 and ep.get('cover_url'):
|
||
try:
|
||
cover = await fetch_cover_bytes(ep['cover_url'])
|
||
if cover:
|
||
ctx.zf.writestr("cover.jpg", cover, compress_type=zipfile.ZIP_STORED)
|
||
except Exception:
|
||
pass
|
||
finally:
|
||
# finally 连带清理 .part 残片（原实现只删正文，取消/失败时残片要等
|
||
# 1 小时缓存清扫兜底）
|
||
_podcast_cleanup_files([payload.path])
|
||
|
||
def fail_label(self, item: Any) -> str:
|
||
"""失败文案用单集名而非整个条目字典（引擎拼成「单集名(异常)」）。"""
|
||
return str(item.get('name') or '')
|
||
|
||
def done_msg(self, item: Any, idx: int, ctx: ZipContext) -> str:
|
||
return f"[{idx}/{ctx.total}] {item['name'][:24]} 完成"
|
||
|
||
def zip_filename(self, ok_count: int) -> str:
|
||
return f"播客_{self._radio_name or '打包'}_{ok_count}集.zip"
|
||
|
||
def log_label(self) -> str:
|
||
return f"{self._radio_name} "
|
||
|
||
def all_failed_msg(self, failed: list[str], refunded: int) -> str:
|
||
return f"全部单集下载失败: {'; '.join(failed[:3])}" + (
|
||
f"（已退回 {refunded} 次下载次数）" if refunded else '')
|
||
|
||
async def on_delivered(self, items: list[Any], task_id: str, params: dict[str, Any]) -> None:
|
||
try:
|
||
first_name = items[0].get('name') if items else ''
|
||
_record_log('下载', params.get('remote_ip') or '-',
|
||
f"[播客打包] {self._radio_name} · {first_name}")
|
||
except Exception:
|
||
pass
|
||
|
||
|
||
async def _podcast_zip_worker(task_id: str) -> None:
|
||
"""整台播客打包：逐集 下载→入包即删，支持取消与断线暂停（复用批量任务机制）"""
|
||
await run_zip_job(_PodcastZipJob(), task_id, settle=_settle_batch_billing)
|