NeteaseUrl/services/podcast.py

# -*- coding: utf-8 -*-
"""播客单集与整台打包 worker。
"""

import os
import shutil
import threading
import time
import traceback
import zipfile
from pathlib import Path
from typing import Any

import auth_system
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 (
    BATCH_ZIP_SEM,
    _record_log,
)
from ._taskcore import (
    _mark_task_terminal,
    _settle_batch_billing,
    _task_work_dir,
    _wait_if_paused,
)
from .api_service import (
    api_service,
)
from .streaming import (
    _stream_open,
)


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 _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

    自动加入全局下载信号量排队；每 0.5s 更新一次任务进度消息。
    """
    done = 0
    last_update = 0.0
    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 sem.acquire_cancellable(cancel_ev):
        raise DownloadCanceled("任务已取消")
    try:
        with _stream_open(url, timeout=60) as r:
            if r.status >= 400:
                raise DownloadException(f"上游返回 {r.status}")
            total = total_size or int(r.headers.get('Content-Length') or 0)
            with open(part, 'wb') as f:
                for chunk in r.iter_content(chunk_size=256 * 1024):
                    if cancel_ev.is_set():
                        raise DownloadCanceled("任务已取消")
                    if chunk:
                        f.write(chunk)
                        done += len(chunk)
                        now = time.time()
                        if now - last_update > 0.5:
                            last_update = now
                            pct = 0
                            if total:
                                pct = min(99, int(done / total * 100))
                                msg = f"{progress_label} {pct}% · {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 task_id:
                                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))
    finally:
        sem.release()
    if part.exists():
        part.replace(target)
    # 完整性校验：CDN 提前断流时 iter_content 会"正常"结束，文件静默截断
    # （API 报告的期望大小时精确相等——95% 容差会交付截断的坏文件还扣次数；
    # 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:
        try:
            os.remove(str(target))
        except OSError:
            pass
        raise DownloadException(f"下载不完整（{done}/{total_size} 字节），请重试")
    if not total_size and done <= 0:
        try:
            os.remove(str(target))
        except OSError:
            pass
        raise DownloadException("下载内容为空，请重试")
    return done


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 = 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


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。
    """
    import tempfile as _tempfile

    file_path_str: str | None = None
    zip_tmp_path: str | None = None
    task_dir: Path | None = None
    try:
        with DOWNLOAD_TASKS_LOCK:
            task = DOWNLOAD_TASKS[task_id]
            task['status'] = 'running'
            task['msg'] = '解析单集信息...'
        params = task['params']
        cancel_ev = task['cancel']
        program_id = params['program_id']
        quality = params['quality']
        need_zip = params['need_zip']
        cookies = params['cookies']
        remote_ip = params.get('remote_ip') or '-'

        program = podcast.get_program_detail(program_id, cookies)
        url_info = _podcast_resolve_audio(program, quality, cookies)

        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('.')
        # 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）
        task_dir = api_service.downloads_path / 'tasks' / task_id
        task_dir.mkdir(parents=True, exist_ok=True)
        disk_name = f"{base} [{program_id}].{ext}"
        target = task_dir / disk_name
        filename = f"{base}.{ext}"   # 交付名保持干净（不带 ID）

        with DOWNLOAD_TASKS_LOCK:
            t = DOWNLOAD_TASKS[task_id]
            t['msg'] = '下载中...'
        _podcast_stream_download(url_info['url'], target, url_info.get('size', 0),
                                 cancel_ev, task_id, '下载中')
        if cancel_ev.is_set():
            raise DownloadCanceled("任务已取消")
        file_path_str = str(target)

        result: dict[str, Any]
        if need_zip:
            fd, zip_tmp_path = _tempfile.mkstemp(prefix='podcast_zip_', suffix='.zip',
                                                 dir=str(task_dir))
            os.close(fd)
            with zipfile.ZipFile(zip_tmp_path, 'w', zipfile.ZIP_DEFLATED) as zf:
                zf.write(file_path_str, arcname=filename)
                cover_url = program.get('cover_url') or ''
                if cover_url:
                    try:
                        cover = fetch_cover_bytes(cover_url)
                        if cover:
                            zf.writestr(f"{base}.jpg", cover)
                    except Exception:
                        pass
                # info.txt 不再写直链（真实 URL 不应随交付文件外泄）
                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', quality))}\n"
                )
                zf.writestr("info.txt", info_txt)
            # 打包阶段后同样以取消检查收口
            if cancel_ev.is_set():
                raise DownloadCanceled("任务已取消")
            result = {
                'file_path': file_path_str,
                'zip_path': zip_tmp_path,
                'filename': f"{base}.zip",
                'mimetype': 'application/zip',
                'audio_files': [file_path_str],
            }
        else:
            result = {
                'file_path': file_path_str,
                'filename': filename,
                'mimetype': f"audio/{ext}",
                'audio_files': [file_path_str],
            }

        # 最终发布前的取消检查（末段取消不得覆盖为 done）
        if cancel_ev.is_set():
            raise DownloadCanceled("任务已取消")
        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
        # 交付已落定；结算失败不再把任务改标 error（同单曲）
        try:
            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})")
    except DownloadCanceled:
        _mark_task_terminal(task_id, 'canceled', '任务已取消')
        try:
            auth_system.ledger_settle(task_id, 0, 'canceled')
        except Exception:
            pass
        if task_dir is not None:
            shutil.rmtree(str(task_dir), ignore_errors=True)
        api_service.logger.info(f"播客单集下载已取消: {task_id}")
    except DownloadException as e:
        _mark_task_terminal(task_id, 'error', str(e))
        try:
            auth_system.ledger_settle(task_id, 0, 'error')
        except Exception:
            pass
        if task_dir is not None:
            shutil.rmtree(str(task_dir), ignore_errors=True)
        api_service.logger.error(f"播客单集下载失败: {task_id} {e}")
    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()}")
        _mark_task_terminal(task_id, 'error', '下载失败，请稍后重试')
        try:
            auth_system.ledger_settle(task_id, 0, 'error')
        except Exception:
            pass
        if task_dir is not None:
            shutil.rmtree(str(task_dir), ignore_errors=True)


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


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）"""
    import tempfile as _tempfile

    zip_tmp_path: str | None = None
    ok_count = 0
    failed: list[str] = []
    # zip_valid / radio_name 必须在函数头初始化——空电台/无单集/补扣失败等
    # 正常业务错误在 try 内早期 raise，异常处理器引用未绑定名会二次崩溃 worker 线程
    zip_valid = False
    radio_name = ''
    try:
        with DOWNLOAD_TASKS_LOCK:
            task = DOWNLOAD_TASKS[task_id]
            task['status'] = 'running'
            task['msg'] = '解析单集列表...'
        params = task['params']
        cancel_ev = task['cancel']
        pause_ev = task['pause']
        radio_id = params['radio_id']
        preset_ids = params.get('ids')
        limit = params['limit']
        quality = params['quality']
        cookies = params['cookies']
        remote_ip = params.get('remote_ip') or '-'

        # 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 = 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 (preset_ids or []):
                try:
                    prog = 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")

        radio_name = _podcast_safe_name(params.get('radio_name') or '', '播客')
        with DOWNLOAD_TASKS_LOCK:
            DOWNLOAD_TASKS[task_id]['total'] = len(episodes)

        # 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 = len(episodes) - int(params.get('billed') or 1)
            if _buid and _extra > 0:
                if not 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'] = len(episodes)
        except DownloadCanceled:
            raise
        except DownloadException:
            raise
        except Exception as e:
            raise DownloadException(f"补扣下载次数异常: {e}") from e

        def _update_progress(msg: str = '') -> None:
            with DOWNLOAD_TASKS_LOCK:
                t = DOWNLOAD_TASKS[task_id]
                t['done'] = ok_count + len(failed)
                t['failed'] = len(failed)
                if msg:
                    t['msg'] = msg

        # 对齐音乐批量 F-B 口径——zip_valid 仅在 ZIP with 块正常
        # 退出（中央目录完整写出）后才置 True（初始 False 已上移函数头）；
        # 未 valid 一律不发布、不按 ok_count 结算
        # 同音乐批量——ZIP 构建放 downloads 卷，不落系统 %TEMP%
        # 与音乐批量打包同口径：建在任务专属目录 tasks/<task_id>/，根目录缓存清扫不再触及交付物
        _podcast_task_dir = _task_work_dir(task_id)
        with _tempfile.NamedTemporaryFile(prefix='podcast_batch_', suffix='.zip',
                                          dir=str(_podcast_task_dir),
                                          delete=False) as zip_tmp:
            zip_tmp_path = zip_tmp.name
            used_arcnames = set()   # 包内条目名去重（同名单集/同号不同集不得互相覆盖）
            with zipfile.ZipFile(zip_tmp, 'w', zipfile.ZIP_DEFLATED) as zf:
                for idx, ep in enumerate(episodes, 1):
                    if cancel_ev.is_set():
                        raise DownloadCanceled("任务已取消")
                    _wait_if_paused(task, pause_ev, cancel_ev, ok_count + len(failed))
                    # 并发对齐音乐批量：播客打包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
                    # 全局下载信号量约束。原实现不受批量并发控制，多用户同时打包会无限并发
                    if not BATCH_ZIP_SEM.acquire_cancellable(cancel_ev):
                        raise DownloadCanceled("任务已取消")
                    try:
                        label = f"[{idx}/{len(episodes)}] {ep['name'][:24]}"
                        _update_progress(f"{label} 解析中...")
                        try:
                            prog = ep.get('detail') or podcast.get_program_detail(ep['id'], cookies)
                            url_info = _podcast_resolve_audio(prog, quality, cookies)
                            _update_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 = _podcast_task_dir / f"podcast_zip_tmp_{task_id}_{idx}.{ext}"
                            try:
                                _podcast_stream_download(url_info['url'], tmp_audio,
                                                         url_info.get('size', 0), cancel_ev)
                                # 重名条目自动追加序号
                                arcname = f"{base}.{ext}"
                                k = 2
                                while arcname in used_arcnames:
                                    arcname = f"{base} ({k}).{ext}"
                                    k += 1
                                used_arcnames.add(arcname)
                                zf.write(str(tmp_audio), arcname=arcname, compress_type=zipfile.ZIP_STORED)
                            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([str(tmp_audio)])
                            # 首集附带封面，便于识别
                            if idx == 1 and ep.get('cover_url'):
                                try:
                                    cover = fetch_cover_bytes(ep['cover_url'])
                                    if cover:
                                        zf.writestr("cover.jpg", cover, compress_type=zipfile.ZIP_STORED)
                                except Exception:
                                    pass
                            ok_count += 1
                            _update_progress(f"{label} 完成")
                        except DownloadCanceled:
                            raise
                        except Exception as e:
                            failed.append(f"{ep['name']}({e})")
                            _update_progress()
                    finally:
                        BATCH_ZIP_SEM.release()

        # 走到这里说明 ZIP with 块正常退出、中央目录完整，才允许发布
        zip_valid = True

        if ok_count == 0:
            raise DownloadException(f"全部单集下载失败: {'; '.join(failed[:3])}")

        # ZIP 未正常完成（磁盘满写坏中央目录等）——不发布坏包，按全额退费收敛
        if not zip_valid:
            if zip_tmp_path:
                try:
                    os.remove(zip_tmp_path)
                except OSError:
                    pass
                zip_tmp_path = None
            refunded = _settle_batch_billing(task_id, 0, 'error')
            _mark_task_terminal(task_id, 'error',
                                f"ZIP 打包失败（可能磁盘空间不足），已退回 {refunded} 次" if refunded
                                else "ZIP 打包失败（可能磁盘空间不足），费用未扣或已退回")
            with DOWNLOAD_TASKS_LOCK:
                t = DOWNLOAD_TASKS.get(task_id)
                if t is not None:
                    t['failed'] = t.get('failed', 0) + ok_count
                    t['refunded'] = refunded
            api_service.logger.error(f"播客打包构建失败未发布: {task_id} ok_count={ok_count} 退回{refunded}次")
            return

        # 最终发布前的取消检查（末段取消不得覆盖为 done）
        if cancel_ev.is_set():
            raise DownloadCanceled("任务已取消")
        refunded = _settle_batch_billing(task_id, ok_count)
        with DOWNLOAD_TASKS_LOCK:
            t = DOWNLOAD_TASKS.get(task_id)
            # 发布前锁内复查取消/失效状态（同音乐批量）
            if t is None or t.get('status') in ('canceled', 'error'):
                raise DownloadCanceled("任务已取消")
            if cancel_ev.is_set():
                raise DownloadCanceled("任务已取消")
            t['status'] = 'done'
            t['completed_at'] = time.time()
            t['done'] = ok_count + len(failed)
            t['failed'] = len(failed)
            t['msg'] = f"成功{ok_count} 失败{len(failed)}" + (f" 退回{refunded}次" if refunded else '')
            t['refunded'] = refunded
            t['result'] = {
                'zip_path': zip_tmp_path,
                'filename': f"播客_{radio_name}_{ok_count}集.zip",
                'audio_files': [],
            }
        try:
            first_name = episodes[0].get('name') if episodes else ''
            _record_log('下载', remote_ip, f"[播客打包] {radio_name} · {first_name}")
        except Exception:
            pass
        api_service.logger.info(f"播客打包完成: {radio_name} 成功{ok_count} 失败{len(failed)} ({task_id})")
    except DownloadCanceled:
        # 部分成功后取消——已入包部分照常交付，未完成部分按账本退费
        # ZIP 未正常完成（写坏）时不按 ok_count 交付——按全额退费收敛
        delivered = ok_count if zip_valid else 0
        refunded = _settle_batch_billing(task_id, delivered, 'canceled')
        if delivered > 0 and zip_tmp_path:
            _mark_task_terminal(task_id, 'canceled',
                                f"已取消（已打包 {ok_count} 集可领取）" +
                                (f"，退回 {refunded} 次" if refunded else ''))
            with DOWNLOAD_TASKS_LOCK:
                t = DOWNLOAD_TASKS.get(task_id)
                if t is not None:
                    t['refunded'] = refunded
                    t['result'] = {
                        'zip_path': zip_tmp_path,
                        'filename': f"播客_{radio_name or '打包'}_{ok_count}集.zip",
                        'audio_files': [],
                    }
        else:
            _mark_task_terminal(task_id, 'canceled',
                                '任务已取消' + (f"（已退回 {refunded} 次下载次数）" if refunded else ''))
            with DOWNLOAD_TASKS_LOCK:
                t = DOWNLOAD_TASKS.get(task_id)
                if t is not None:
                    t['refunded'] = refunded
            if zip_tmp_path:
                try:
                    os.remove(zip_tmp_path)
                except OSError:
                    pass
        api_service.logger.info(f"播客打包已取消: {task_id}（成功{ok_count} 退回{refunded}次）")
    except DownloadException as e:
        delivered = ok_count if zip_valid else 0
        refunded = _settle_batch_billing(task_id, delivered)
        with DOWNLOAD_TASKS_LOCK:
            _t = DOWNLOAD_TASKS.get(task_id)
            # 终态先到先得——已终态（如用户取消/超时兜底）
            # 不再被覆盖为 error（堵 canceled→error 非法迁移边）
            if _t and _t.get('status') not in ('done', 'error', 'canceled'):
                _t['status'] = 'error'
                _t['completed_at'] = time.time()   # 保留期从完成时刻起算
                _t['msg'] = str(e) + (f"（已退回 {refunded} 次下载次数）" if refunded else '')
                _t['refunded'] = refunded
            elif _t:
                _t['refunded'] = refunded
        if zip_tmp_path:
            try:
                os.remove(zip_tmp_path)
            except OSError:
                pass
        api_service.logger.error(f"播客打包失败: {task_id} {e}（退回{refunded}次）")
    except Exception as e:
        # 非预期异常原文 logger 先行，用户可见文案泛化
        # （DownloadException 的文案是我们自己拼的用户可读文本，保留 str(e)）
        api_service.logger.error(f"播客打包异常: {task_id} {e}\n{traceback.format_exc()}")
        delivered = ok_count if zip_valid else 0
        refunded = _settle_batch_billing(task_id, delivered)
        with DOWNLOAD_TASKS_LOCK:
            _t = DOWNLOAD_TASKS.get(task_id)
            # 同上——已终态不再覆盖为 error
            if _t and _t.get('status') not in ('done', 'error', 'canceled'):
                _t['status'] = 'error'
                _t['completed_at'] = time.time()   # 保留期从完成时刻起算
                _t['msg'] = '打包失败，请稍后重试' + (f"（已退回 {refunded} 次下载次数）" if refunded else '')
                _t['refunded'] = refunded
            elif _t:
                _t['refunded'] = refunded
        if zip_tmp_path:
            try:
                os.remove(zip_tmp_path)
            except OSError:
                pass
        api_service.logger.error(f"播客打包异常: {task_id} {e}（退回{refunded}次）\n{traceback.format_exc()}")