322 lines
11 KiB
Python
322 lines
11 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""库内视频管理：入库（候选确认 / Telegram 手动）、忽略、拉黑。
|
||
|
||
入库只写本地 ``video`` 表并置为 ``active``，**不再调用 B 站收藏夹写接口**
|
||
（``deal`` / ``sort``）。收藏夹由人工维护，系统仅通过 ``favsort.py`` 做重排序。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import time
|
||
from dataclasses import dataclass, field
|
||
from typing import Any
|
||
|
||
from ..bilibili.client import BilibiliError, BilibiliProtocolError
|
||
from ..config import ConfigStore
|
||
from ..repository import Repository
|
||
from ..timeutil import shanghai_date
|
||
from ..video_ref import DEFAULT_MAX_REFS, VideoRef, extract_video_refs
|
||
|
||
|
||
@dataclass
|
||
class IngestResult:
|
||
ok: bool
|
||
aid: int | None
|
||
state: str
|
||
title: str = ""
|
||
up_name: str = ""
|
||
message: str = ""
|
||
|
||
def as_dict(self) -> dict[str, Any]:
|
||
return {
|
||
"ok": self.ok,
|
||
"aid": self.aid,
|
||
"state": self.state,
|
||
"title": self.title,
|
||
"up_name": self.up_name,
|
||
"message": self.message,
|
||
}
|
||
|
||
|
||
@dataclass
|
||
class ManualIngestResult:
|
||
refs: int = 0
|
||
added: int = 0
|
||
results: list[IngestResult] = field(default_factory=list)
|
||
|
||
@property
|
||
def ok(self) -> bool:
|
||
return any(result.ok for result in self.results)
|
||
|
||
def as_dict(self) -> dict[str, Any]:
|
||
return {
|
||
"refs": self.refs,
|
||
"added": self.added,
|
||
"ok": self.ok,
|
||
"results": [result.as_dict() for result in self.results],
|
||
}
|
||
|
||
|
||
@dataclass
|
||
class ActionResult:
|
||
ok: bool
|
||
aid: int
|
||
action: str
|
||
state: str
|
||
message: str = ""
|
||
|
||
def as_dict(self) -> dict[str, Any]:
|
||
return {
|
||
"ok": self.ok,
|
||
"aid": self.aid,
|
||
"action": self.action,
|
||
"state": self.state,
|
||
"message": self.message,
|
||
}
|
||
|
||
|
||
class LibraryService:
|
||
def __init__(
|
||
self,
|
||
config_store: ConfigStore,
|
||
repository: Repository,
|
||
read_provider,
|
||
*,
|
||
up_profile_service=None,
|
||
clock=time.time,
|
||
logger=None,
|
||
max_refs: int = DEFAULT_MAX_REFS,
|
||
) -> None:
|
||
self.config_store = config_store
|
||
self.repo = repository
|
||
self.read_provider = read_provider
|
||
self.up_profile = up_profile_service
|
||
self._clock = clock
|
||
self.logger = logger
|
||
self.max_refs = max(1, int(max_refs))
|
||
|
||
def _now(self) -> int:
|
||
return int(self._clock())
|
||
|
||
def _log(self, level: str, event: str, **fields) -> None:
|
||
if self.logger is not None:
|
||
getattr(self.logger, level)(event, **fields)
|
||
|
||
# ------------------------------------------------------------ candidate
|
||
|
||
def ingest_candidate(self, aid: int) -> IngestResult:
|
||
aid = int(aid)
|
||
candidate = self.repo.get_candidate(aid)
|
||
if candidate is None:
|
||
video = self.repo.get_video(aid)
|
||
if video is not None:
|
||
return IngestResult(
|
||
ok=True, aid=aid, state="exists",
|
||
title=str(video.get("title") or ""),
|
||
up_name=str(video.get("up_name") or ""),
|
||
message="已在库，无需重复入库",
|
||
)
|
||
return IngestResult(
|
||
ok=False, aid=aid, state="missing", message="候选不存在或已处理"
|
||
)
|
||
|
||
detail = None
|
||
try:
|
||
detail = self.read_provider.get().view_detail(aid=aid)
|
||
except BilibiliError as exc: # 网络失败时用候选元数据兜底
|
||
self._log("warning", "ingest.detail_failed", aid=aid, error=str(exc))
|
||
|
||
if detail is not None:
|
||
outcome = self.repo.ingest_video(
|
||
aid=detail.aid,
|
||
bvid=detail.bvid,
|
||
title=detail.title,
|
||
up_mid=detail.up_mid,
|
||
up_name=detail.up_name,
|
||
pubdate=detail.pubdate,
|
||
duration=detail.duration,
|
||
pages=detail.pages,
|
||
cover=detail.cover,
|
||
source="candidate:telegram",
|
||
now=self._now(),
|
||
)
|
||
self._write_snapshot(detail)
|
||
result = self._result_from_outcome(
|
||
outcome, title=detail.title, up_name=detail.up_name or ""
|
||
)
|
||
up_mid = detail.up_mid
|
||
up_name = detail.up_name or ""
|
||
else:
|
||
pubdate = int(candidate.get("pubdate") or 0)
|
||
duration = int(candidate.get("duration") or 0) or None
|
||
outcome = self.repo.ingest_video(
|
||
aid=aid,
|
||
bvid=candidate.get("bvid"),
|
||
title=str(candidate.get("title") or ""),
|
||
up_mid=candidate.get("up_mid"),
|
||
up_name=candidate.get("up_name"),
|
||
pubdate=pubdate,
|
||
duration=duration,
|
||
cover=candidate.get("cover"),
|
||
source="candidate:telegram",
|
||
now=self._now(),
|
||
)
|
||
result = self._result_from_outcome(
|
||
outcome,
|
||
title=str(candidate.get("title") or ""),
|
||
up_name=str(candidate.get("up_name") or ""),
|
||
)
|
||
up_mid = candidate.get("up_mid")
|
||
up_name = str(candidate.get("up_name") or "")
|
||
|
||
self._post_ingest([(up_mid, up_name)])
|
||
self._log(
|
||
"info", "ingest.candidate",
|
||
aid=aid, state=result.state, folder=None,
|
||
)
|
||
return result
|
||
|
||
# ------------------------------------------------------------ manual
|
||
|
||
def ingest_text(self, text: object) -> ManualIngestResult:
|
||
refs = extract_video_refs(text, limit=self.max_refs)
|
||
result = ManualIngestResult(refs=len(refs))
|
||
if not refs:
|
||
return result
|
||
|
||
client = self.read_provider.get()
|
||
ups: list[tuple[int | None, str]] = []
|
||
for ref in refs:
|
||
try:
|
||
detail = self._resolve_ref(client, ref)
|
||
except BilibiliError as exc:
|
||
result.results.append(IngestResult(
|
||
ok=False, aid=None, state="error", message=str(exc),
|
||
))
|
||
self._log("warning", "ingest.manual_failed", error=str(exc))
|
||
continue
|
||
|
||
outcome = self.repo.ingest_video(
|
||
aid=detail.aid,
|
||
bvid=detail.bvid,
|
||
title=detail.title,
|
||
up_mid=detail.up_mid,
|
||
up_name=detail.up_name,
|
||
pubdate=detail.pubdate,
|
||
duration=detail.duration,
|
||
pages=detail.pages,
|
||
cover=detail.cover,
|
||
source="manual:telegram",
|
||
now=self._now(),
|
||
)
|
||
self._write_snapshot(detail)
|
||
item = self._result_from_outcome(
|
||
outcome, title=detail.title, up_name=detail.up_name or ""
|
||
)
|
||
if item.state in ("added", "recovered"):
|
||
result.added += 1
|
||
result.results.append(item)
|
||
ups.append((detail.up_mid, detail.up_name or ""))
|
||
|
||
if ups:
|
||
self._post_ingest(ups)
|
||
self._log("info", "ingest.manual", **result.as_dict())
|
||
return result
|
||
|
||
def _resolve_ref(self, client, ref: VideoRef):
|
||
if ref.kind == "bvid":
|
||
return client.view_detail(bvid=str(ref.value))
|
||
if ref.kind == "aid":
|
||
return client.view_detail(aid=int(ref.value))
|
||
if ref.kind == "short":
|
||
final = client.resolve_short_link(f"https://b23.tv/{ref.value}")
|
||
for sub in extract_video_refs(final):
|
||
if sub.kind != "short":
|
||
return self._resolve_ref(client, sub)
|
||
raise BilibiliProtocolError(f"短链未解析出视频引用: {final}")
|
||
raise ValueError(f"未知引用类型: {ref.kind}")
|
||
|
||
# ------------------------------------------------------------ actions
|
||
|
||
def ignore(self, aid: int) -> ActionResult:
|
||
aid = int(aid)
|
||
candidate = self.repo.get_candidate(aid)
|
||
if candidate is None:
|
||
return ActionResult(
|
||
ok=False, aid=aid, action="ignore", state="missing",
|
||
message="候选不存在或已处理",
|
||
)
|
||
self.repo.mark_candidate_decision(aid, "rejected", now=self._now())
|
||
self.repo.bump_cache_version("videos")
|
||
return ActionResult(
|
||
ok=True, aid=aid, action="ignore", state="rejected", message="已忽略",
|
||
)
|
||
|
||
def blacklist(self, aid: int) -> ActionResult:
|
||
aid = int(aid)
|
||
candidate = self.repo.get_candidate(aid)
|
||
if candidate is None:
|
||
return ActionResult(
|
||
ok=False, aid=aid, action="blacklist", state="missing",
|
||
message="候选不存在或已处理",
|
||
)
|
||
up_mid = candidate.get("up_mid")
|
||
if not isinstance(up_mid, int) or isinstance(up_mid, bool):
|
||
return ActionResult(
|
||
ok=False, aid=aid, action="blacklist", state="failed",
|
||
message="候选缺少 UP mid，无法拉黑",
|
||
)
|
||
self.repo.add_blacklist(
|
||
up_mid,
|
||
name=candidate.get("up_name"),
|
||
reason="telegram",
|
||
now=self._now(),
|
||
)
|
||
rejected = self.repo.reject_pending_for_up(up_mid, now=self._now())
|
||
self.repo.mark_candidate_decision(aid, "rejected", now=self._now())
|
||
self.repo.bump_cache_version("videos")
|
||
return ActionResult(
|
||
ok=True, aid=aid, action="blacklist", state="rejected",
|
||
message=f"已拉黑 UP，并忽略该 UP 的 {rejected} 条待决策候选",
|
||
)
|
||
|
||
# ------------------------------------------------------------ internals
|
||
|
||
def _result_from_outcome(self, outcome, *, title: str, up_name: str) -> IngestResult:
|
||
if outcome.created:
|
||
state, message = "added", "已入库"
|
||
elif outcome.recovered:
|
||
state, message = "recovered", "已重新入库"
|
||
else:
|
||
state, message = "exists", "已在库"
|
||
return IngestResult(
|
||
ok=True, aid=outcome.aid, state=state,
|
||
title=title, up_name=up_name, message=message,
|
||
)
|
||
|
||
def _write_snapshot(self, detail) -> None:
|
||
"""用已取到的 ``view`` 数据立即写一条当天快照（同日已有成功记录则跳过）。"""
|
||
now = self._now()
|
||
stat_date = shanghai_date(now)
|
||
existing = self.repo.get_snapshot(stat_date, detail.aid)
|
||
if existing is not None and int(existing.get("ok") or 0) == 1:
|
||
return
|
||
self.repo.upsert_snapshot(
|
||
stat_date,
|
||
detail.aid,
|
||
metrics=detail.metrics(),
|
||
ok=True,
|
||
err=None,
|
||
captured_at=now,
|
||
)
|
||
|
||
def _post_ingest(self, ups: list[tuple[int | None, str]]) -> None:
|
||
if ups and self.up_profile is not None:
|
||
mids = [mid for mid, _ in ups if isinstance(mid, int) and not isinstance(mid, bool)]
|
||
names = {mid: name for mid, name in ups if isinstance(mid, int) and not isinstance(mid, bool)}
|
||
if mids:
|
||
try:
|
||
self.up_profile.capture(mids, names=names, live_since=self._now() - 3600)
|
||
except Exception as exc: # noqa: BLE001 粉丝采集失败不影响入库
|
||
self._log("warning", "ingest.follower_failed", error=str(exc))
|
||
self.repo.bump_cache_version("videos") |