补充文档,修改清洗方案

This commit is contained in:
zk
2026-06-02 18:38:36 +08:00
parent 30e6a6e2a5
commit 6967e4ba54
7 changed files with 363 additions and 80 deletions
+18 -18
View File
@@ -3,7 +3,7 @@
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, DateTime, Integer, SmallInteger, String, Text
from sqlalchemy import BigInteger, DateTime, SmallInteger, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import PgBase
@@ -14,22 +14,22 @@ class AppJobData(PgBase):
__tablename__ = "app_job_data"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True, comment="自增主键")
urllistid: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联urllistid")
job_title: Mapped[Optional[str]] = mapped_column(String(255))
salary: Mapped[Optional[str]] = mapped_column(String(128))
location: Mapped[Optional[str]] = mapped_column(String(2048))
company: Mapped[Optional[str]] = mapped_column(String(255), comment="公司名")
experience: Mapped[Optional[str]] = mapped_column(String(64))
education: Mapped[Optional[str]] = mapped_column(String(64))
description: Mapped[str] = mapped_column(Text, nullable=False)
detail_url: Mapped[str] = mapped_column(String(1024), nullable=False)
recruit_category: Mapped[int] = mapped_column(SmallInteger, default=3, nullable=False, comment="招聘分类: 0=校招, 1=实习, 2=社招, 3=其他")
content_hash: Mapped[str] = mapped_column(String(64), nullable=False)
sources: Mapped[int] = mapped_column(SmallInteger, default=0, nullable=False)
job_title: Mapped[Optional[str]] = mapped_column(String(255), comment="职位名称")
salary: Mapped[Optional[str]] = mapped_column(String(128), comment="薪资")
location: Mapped[Optional[str]] = mapped_column(String(2048), comment="工作地点")
company: Mapped[Optional[str]] = mapped_column(String(255), comment="公司名")
experience: Mapped[Optional[str]] = mapped_column(String(64), comment="经验要求")
education: Mapped[Optional[str]] = mapped_column(String(64), comment="学历要求")
description: Mapped[str] = mapped_column(Text, nullable=False, comment="岗位详情(职责+要求+介绍)")
detail_url: Mapped[str] = mapped_column(String(1024), nullable=False, comment="详情页URL")
recruit_category: Mapped[int] = mapped_column(SmallInteger, default=3, nullable=False, comment="招聘分类: 0=校招 1=实习 2=社招 3=其他")
content_hash: Mapped[str] = mapped_column(String(64), nullable=False, comment="内容哈希,用于去重")
sources: Mapped[int] = mapped_column(SmallInteger, default=0, nullable=False, comment="数据来源 0=官网 1=平台")
expire_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, comment="发布日期")
created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False)
updated_at: Mapped[datetime] = mapped_column(DateTime, nullable=False)
clean_status: Mapped[str] = mapped_column(String(20), default="pending", nullable=False, comment="pending/cleaning/cleaned/discarded")
clean_started_at: Mapped[Optional[datetime]] = mapped_column(DateTime)
cleaned_at: Mapped[Optional[datetime]] = mapped_column(DateTime)
created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, comment="创建时间")
updated_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, comment="更新时间")
clean_status: Mapped[str] = mapped_column(String(20), default="pending", nullable=False, comment="清洗状态: pending/cleaning/cleaned/discarded")
clean_started_at: Mapped[Optional[datetime]] = mapped_column(DateTime, comment="清洗开始时间")
cleaned_at: Mapped[Optional[datetime]] = mapped_column(DateTime, comment="清洗完成时间")