LongArticleTaskServer/applications/utils/item.py

"""
@author: luojunhui
"""

import datetime

from pydantic import BaseModel, Field
from typing import Optional


class CrawlerMetaArticle(BaseModel):
    platform: str = Field(default=..., description="抓取平台")
    mode: str = Field(default=..., description="抓取模式")
    category: str = Field(
        default=..., description="抓取类型：最初设计不合理，积重难返，实际与品类无关"
    )
    out_account_id: str = Field(default=..., description="抓取账号账号id")
    article_index: int = Field(
        default=None, description="群发发文位置，常见于微信公众号"
    )
    title: str = Field(default=..., description="文章标题")
    link: str = Field(default=..., description="文章链接")
    read_cnt: int = Field(default=0, description="阅读量")
    like_cnt: int = Field(default=0, description="点赞量")
    description: Optional[str] = Field(default=None, description="文章简介")
    publish_time: int = Field(default=None, description="文章发布时间")
    crawler_time: int = Field(default=None, description="抓取时间")
    score: float = Field(default=None, description="相似度分")
    status: int = Field(default=1, description="文章状态")
    unique_index: str = Field(default=..., description="文章唯一index")
    source_article_title: str = Field(default=None, description="文章联想的种子文章")
    source_account: str = Field(default=None, description="账号联想种子账号")
    title_sensitivity: int = Field(default=0, description="标题是否敏感")
    category_status: int = Field(
        default=0,
        description="品类处理状态 0: init; 1: processing; 2: successfully; 99: fail",
    )
    has_video: int = Field(
        default=0,
        description="文章内嵌套视频状态 0: init; 1: processing; 2: successfully; 3:article link bad ;99: fail",
    )
    trace_id: str = Field(default=None, description="创建该条记录的任务ID")


class CrawlerMetaAccount(BaseModel):
    account_name: str = Field(..., description="账号名称", min_length=1)
    account_id: str = Field(..., description="账号id", min_length=1)
    title_list: str = Field(default=None, description="账号主页第一页标题list")
    score_list: str = Field(
        default=None, description="账号主页第一页标题list契合得分（By LLM）"
    )
    avg_score: float = Field(default=None, description="score_list 的平均分")
    status: int = Field(
        default=0,
        description="分析状态,0: init, 1: processing, 2: successfully, 99: fail",
    )
    platform: str = Field(default=None, description="账号来源于哪个外部平台")
    crawler_date: datetime.date = Field(
        default=None, description="账号抓取日期，格式为“YYYY-MM-DD”"
    )
    using_status: int = Field(
        default=0,
        description="账号状态, 0: init, 1: processing, 2: successfully, 99: fail",
    )
    category_status: int = Field(
        default=0,
        description="账号品类处理状态, 0: init, 1: processing, 2: successfully, 99: fail",
    )
    category: str = Field(default=None, description="账号的品类")
    media_type: int = Field(default=2, description="账号抓取模态 1: 文章 2:视频")