kairee
d971e718e9
Implement WBI video search with legacy fallback, classification scoring, candidate pool, permanent seen-aid dedupe, blacklist filtering, and batched Telegram notifications. Add write client for fav deal/sort, target-folder selection, insertion position calculation, read-back verification, fav_action locking, retry on failure, ignore and blacklist actions. Wire discovery, candidate cleanup, Telegram long polling, and new discover/candidates CLI commands into the scheduler. Add migration v3 for candidate duration and index stats.
207 lines
6.5 KiB
Python
207 lines
6.5 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""B 站视频搜索（WBI 签名 + 旧版降级）。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import re
|
|
import time
|
|
import urllib.parse
|
|
from dataclasses import dataclass
|
|
from typing import Any, Callable, Mapping
|
|
|
|
from ..classify import parse_duration
|
|
from .client import BASE, BilibiliClient, BilibiliError, BilibiliProtocolError
|
|
|
|
# B 站前端固定的 mixinKey 重排表。
|
|
MIXIN_KEY_ENC_TAB = (
|
|
46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35,
|
|
27, 43, 5, 49, 33, 9, 42, 19, 29, 28, 14, 39, 12, 38, 41, 13,
|
|
37, 48, 7, 16, 24, 55, 40, 61, 26, 17, 0, 1, 60, 51, 30, 4,
|
|
22, 25, 54, 21, 56, 59, 6, 63, 57, 62, 11, 36, 20, 34, 44, 52,
|
|
)
|
|
WBI_KEY_TTL = 6 * 3600
|
|
_TAG_RE = re.compile(r"<[^>]+>")
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class SearchItem:
|
|
aid: int
|
|
bvid: str | None
|
|
title: str
|
|
up_mid: int | None
|
|
up_name: str | None
|
|
pubdate: int
|
|
duration_seconds: int
|
|
cover: str | None
|
|
play: int = 0
|
|
like: int = 0
|
|
favorite: int = 0
|
|
danmaku: int = 0
|
|
review: int = 0
|
|
|
|
|
|
def key_from_url(url: str | None) -> str:
|
|
"""从 ``.../bfs/wbi/xxx.png`` 提取 ``xxx``。"""
|
|
if not isinstance(url, str) or not url:
|
|
return ""
|
|
path = urllib.parse.urlparse(url).path
|
|
name = path.rsplit("/", 1)[-1]
|
|
return name.split(".", 1)[0]
|
|
|
|
|
|
def mixin_key(img_key: str, sub_key: str) -> str:
|
|
raw = f"{img_key}{sub_key}"
|
|
if len(raw) < 64:
|
|
raise ValueError("WBI key 长度不足")
|
|
return "".join(raw[index] for index in MIXIN_KEY_ENC_TAB)[:32]
|
|
|
|
|
|
def sign_params(
|
|
params: Mapping[str, Any], key: str, *, now: float | None = None
|
|
) -> dict[str, Any]:
|
|
signed = {str(k): v for k, v in params.items()}
|
|
signed["wts"] = int(time.time() if now is None else now)
|
|
query = urllib.parse.urlencode(sorted(signed.items()))
|
|
signed["w_rid"] = hashlib.md5(f"{query}{key}".encode("utf-8")).hexdigest()
|
|
return signed
|
|
|
|
|
|
def _as_int(value: Any) -> int:
|
|
if isinstance(value, bool) or not isinstance(value, int):
|
|
return 0
|
|
return value
|
|
|
|
|
|
def _clean_title(value: Any) -> str:
|
|
text = value if isinstance(value, str) else ""
|
|
return _TAG_RE.sub("", text).strip()
|
|
|
|
|
|
def _cover(value: Any) -> str | None:
|
|
if not isinstance(value, str) or not value:
|
|
return None
|
|
if value.startswith("//"):
|
|
return f"https:{value}"
|
|
return value
|
|
|
|
|
|
def _parse_duration(value: Any) -> int:
|
|
return parse_duration(value)
|
|
|
|
|
|
def parse_search_payload(payload: Mapping[str, Any]) -> list[SearchItem]:
|
|
data = payload.get("data")
|
|
if not isinstance(data, Mapping):
|
|
raise BilibiliProtocolError("search data 不是对象")
|
|
if "result" not in data:
|
|
raise BilibiliProtocolError("search data 缺少 result 字段")
|
|
rows = data["result"]
|
|
if rows is None:
|
|
return []
|
|
if not isinstance(rows, list):
|
|
raise BilibiliProtocolError("search data.result 不是数组")
|
|
|
|
items: list[SearchItem] = []
|
|
for row in rows:
|
|
if not isinstance(row, Mapping):
|
|
raise BilibiliProtocolError("search result item 不是对象")
|
|
raw_type = row.get("type")
|
|
if isinstance(raw_type, str) and raw_type and raw_type != "video":
|
|
continue
|
|
aid = row.get("id")
|
|
if isinstance(aid, bool) or not isinstance(aid, int):
|
|
continue
|
|
up_mid = row.get("mid")
|
|
if isinstance(up_mid, bool) or not isinstance(up_mid, int):
|
|
up_mid = None
|
|
bvid = row.get("bvid")
|
|
if not isinstance(bvid, str) or not bvid:
|
|
bvid = None
|
|
up_name = row.get("author")
|
|
if not isinstance(up_name, str) or not up_name:
|
|
up_name = None
|
|
pubdate = row.get("pubdate")
|
|
if isinstance(pubdate, bool) or not isinstance(pubdate, int):
|
|
pubdate = 0
|
|
items.append(SearchItem(
|
|
aid=aid,
|
|
bvid=bvid,
|
|
title=_clean_title(row.get("title")),
|
|
up_mid=up_mid,
|
|
up_name=up_name,
|
|
pubdate=pubdate,
|
|
duration_seconds=_parse_duration(row.get("duration")),
|
|
cover=_cover(row.get("pic")),
|
|
play=_as_int(row.get("play")),
|
|
like=_as_int(row.get("like")),
|
|
favorite=_as_int(row.get("favorites")),
|
|
danmaku=_as_int(row.get("danmaku")),
|
|
review=_as_int(row.get("review")),
|
|
))
|
|
return items
|
|
|
|
|
|
class SearchClient:
|
|
"""带 WBI 密钥缓存与旧接口降级的搜索客户端。"""
|
|
|
|
def __init__(
|
|
self,
|
|
client_getter: Callable[[], BilibiliClient],
|
|
*,
|
|
clock=time.time,
|
|
) -> None:
|
|
self._client_getter = client_getter
|
|
self._clock = clock
|
|
self._keys: tuple[str, str] | None = None
|
|
self._keys_at = 0.0
|
|
|
|
def _wbi_keys(self) -> tuple[str, str]:
|
|
now = self._clock()
|
|
if self._keys is not None and now - self._keys_at < WBI_KEY_TTL:
|
|
return self._keys
|
|
payload = self._client_getter().get_json(
|
|
f"{BASE}/x/web-interface/nav", auth=True
|
|
)
|
|
data = payload.get("data")
|
|
if not isinstance(data, Mapping):
|
|
raise BilibiliProtocolError("nav data 不是对象")
|
|
wbi = data.get("wbi_img")
|
|
if not isinstance(wbi, Mapping):
|
|
raise BilibiliProtocolError("nav data.wbi_img 缺失")
|
|
img_key = key_from_url(wbi.get("img_url"))
|
|
sub_key = key_from_url(wbi.get("sub_url"))
|
|
if not img_key or not sub_key:
|
|
raise BilibiliProtocolError("WBI key 提取失败")
|
|
self._keys = (img_key, sub_key)
|
|
self._keys_at = now
|
|
return self._keys
|
|
|
|
def search(
|
|
self, keyword: str, page: int, *, page_size: int = 42
|
|
) -> list[SearchItem]:
|
|
params = {
|
|
"search_type": "video",
|
|
"keyword": keyword,
|
|
"order": "pubdate",
|
|
"page": int(page),
|
|
"page_size": int(page_size),
|
|
}
|
|
try:
|
|
img_key, sub_key = self._wbi_keys()
|
|
signed = sign_params(
|
|
params, mixin_key(img_key, sub_key), now=self._clock()
|
|
)
|
|
url = (
|
|
f"{BASE}/x/web-interface/wbi/search/type?"
|
|
f"{urllib.parse.urlencode(signed)}"
|
|
)
|
|
return parse_search_payload(self._client_getter().get_json(url))
|
|
except BilibiliError:
|
|
# WBI 失败时降级到旧接口；旧接口也失败则抛出。
|
|
url = (
|
|
f"{BASE}/x/web-interface/search/type?"
|
|
f"{urllib.parse.urlencode(params)}"
|
|
)
|
|
return parse_search_payload(self._client_getter().get_json(url))
|