butubb
8f4e5586e9
- schedule.py: 新增调度计算模块（纯函数，便于单测）。三种模式：interval（每 N 分钟）/ daily（选钟点）/ weekly（选星期 + 钟点） - 钟点模式是「固定时刻」而非「固定延迟」——从日历重算，所以某轮跑晚了不会把之后每一轮都拖晚。interval 保持原语义：从上一轮开始计时 - 抖动只加给 interval。给「每天 9:00」也加抖动就成了 9:00–9:01 随机触发，操作者选的时间被悄悄改掉，只会像 bug - 模型 / schema / service: 新增 schedule_mode / schedule_hours / schedule_days / schedule_minute。时钟字段存逗号分隔文本——几个小整数、永远整体读写，单开一张表只会换来 join。interval_minutes 保留且仍是默认值，已有任务不受影响 - service: 改动任何调度字段都按合并后的状态重算 next_run_at。重新启用也算改动，否则停用一个月再打开会带着一个月前的 next_run_at，一保存就立即触发 - 前端: 运行方式三选一 + 小时/星期胶囊多选 + 分钟下拉，并实时预览结果句子。任务卡片改显示后端拼好的 schedule_label，避免列表和编辑器对同一计划给出两种说法 - 校验: 钟点模式至少选一个时间，按周至少选一个星期 tests/test_schedule.py 新增 24 个用例，含「恰好等于当前时刻的档位归属下一天」这个会让调度器自循环的边界。
115 lines
5.4 KiB
Python
115 lines
5.4 KiB
Python
# -*- coding: utf-8 -*-
|
|
# Copyright (c) 2025 [email protected]
|
|
#
|
|
# This file is part of MediaCrawler project.
|
|
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/api/schemas/monitor.py
|
|
# GitHub: https://github.com/NanmiCoder
|
|
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
|
|
#
|
|
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
|
# 1. 不得用于任何商业用途。
|
|
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
|
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
|
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
|
# 5. 不得用于任何非法或不当的用途。
|
|
#
|
|
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
|
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
|
|
|
"""Request models for the monitoring API."""
|
|
|
|
from typing import List, Literal, Optional
|
|
|
|
from pydantic import BaseModel, Field, model_validator
|
|
|
|
# A floor on the interval is a correctness guard, not a nicety: every run
|
|
# launches a browser and hits XHS with several requests, so a short interval
|
|
# across many creators is the pattern that triggers rate limiting.
|
|
MIN_INTERVAL_MINUTES = 30
|
|
MAX_INTERVAL_MINUTES = 7 * 24 * 60
|
|
|
|
|
|
class MonitorTaskCreate(BaseModel):
|
|
name: str = Field(min_length=1, max_length=200)
|
|
platform: str = "xhs"
|
|
# One subprocess handles exactly one crawler type, so a task is either
|
|
# creator-driven or note-driven.
|
|
mode: Literal["creator", "note"]
|
|
# None means "use the value configured on the Settings page", which is what
|
|
# makes those defaults meaningful. Bounds still apply when a value is given.
|
|
interval_minutes: Optional[int] = Field(
|
|
default=None, ge=MIN_INTERVAL_MINUTES, le=MAX_INTERVAL_MINUTES
|
|
)
|
|
# --- Scheduling ---------------------------------------------------------
|
|
# All three modes are expressible with pickers; a raw cron string is
|
|
# deliberately not supported, since it is a small language to learn just to
|
|
# say "every day at nine".
|
|
schedule_mode: Literal["interval", "daily", "weekly"] = "interval"
|
|
# 0-23, e.g. [9, 12, 18]. Required for the two clock modes.
|
|
schedule_hours: List[int] = Field(default_factory=list)
|
|
# 0-6 with Monday = 0, matching Python's date.weekday(). Required for weekly.
|
|
schedule_days: List[int] = Field(default_factory=list)
|
|
# One minute for the whole schedule, so a task with three times is
|
|
# "09:30, 12:30, 18:30" rather than three separate minute choices.
|
|
schedule_minute: int = Field(default=0, ge=0, le=59)
|
|
|
|
max_notes_count: Optional[int] = Field(default=None, ge=1, le=500)
|
|
enable_comments: bool = True
|
|
# Raising this widens the comment window, which is the only lever available
|
|
# for noticing new comments -- the API has no time-sort.
|
|
max_comments_count: Optional[int] = Field(default=None, ge=1, le=500)
|
|
run_timeout_seconds: int = Field(default=3600, ge=60, le=86400)
|
|
enabled: bool = True
|
|
# Push a WeCom summary for runs that failed or found new works. Opt-in per
|
|
# task so a single webhook does not get flooded.
|
|
notify_enabled: bool = False
|
|
# Raw pasted values: full URLs or bare ids, in either form.
|
|
targets: List[str] = Field(min_length=1)
|
|
|
|
@model_validator(mode="after")
|
|
def _validate_schedule(self) -> "MonitorTaskCreate":
|
|
if any(hour < 0 or hour > 23 for hour in self.schedule_hours):
|
|
raise ValueError("小时必须在 0-23 之间")
|
|
if any(day < 0 or day > 6 for day in self.schedule_days):
|
|
raise ValueError("星期必须在 0-6 之间（周一为 0）")
|
|
# A clock mode with no chosen time can never fire. Rejecting it here is
|
|
# what keeps next_occurrence()'s None branch unreachable in practice.
|
|
if self.schedule_mode in ("daily", "weekly") and not self.schedule_hours:
|
|
raise ValueError("按钟点调度至少要选一个时间")
|
|
if self.schedule_mode == "weekly" and not self.schedule_days:
|
|
raise ValueError("按周调度至少要选一个星期")
|
|
return self
|
|
|
|
|
|
class MonitorTaskUpdate(BaseModel):
|
|
name: Optional[str] = Field(default=None, min_length=1, max_length=200)
|
|
enabled: Optional[bool] = None
|
|
interval_minutes: Optional[int] = Field(
|
|
default=None, ge=MIN_INTERVAL_MINUTES, le=MAX_INTERVAL_MINUTES
|
|
)
|
|
# None means "leave alone". Cross-field validity depends on the merged state,
|
|
# so it is checked in the service rather than here.
|
|
schedule_mode: Optional[Literal["interval", "daily", "weekly"]] = None
|
|
schedule_hours: Optional[List[int]] = None
|
|
schedule_days: Optional[List[int]] = None
|
|
schedule_minute: Optional[int] = Field(default=None, ge=0, le=59)
|
|
max_notes_count: Optional[int] = Field(default=None, ge=1, le=500)
|
|
enable_comments: Optional[bool] = None
|
|
max_comments_count: Optional[int] = Field(default=None, ge=1, le=500)
|
|
run_timeout_seconds: Optional[int] = Field(default=None, ge=60, le=86400)
|
|
notify_enabled: Optional[bool] = None
|
|
# When present, replaces the whole target list.
|
|
targets: Optional[List[str]] = None
|
|
|
|
|
|
class CookiePayload(BaseModel):
|
|
cookie: str = Field(min_length=1)
|
|
|
|
|
|
class WebhookPayload(BaseModel):
|
|
url: str = Field(default="", description="企业微信机器人 Webhook 地址，留空表示停用")
|
|
|
|
|
|
class WebhookTestPayload(BaseModel):
|
|
url: Optional[str] = Field(default=None, description="不传则使用已保存的地址")
|