nkey
ca460453af
All checks were successful
hufs-notice-crawler-cicd / build_push_deploy (push) Successful in 8m35s
52 lines
2.2 KiB
Python
52 lines
2.2 KiB
Python
from datetime import datetime
|
|
|
|
from sqlalchemy import JSON, CheckConstraint, DateTime, Integer, String, Text, UniqueConstraint, func
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from app.db import Base
|
|
|
|
|
|
class ScrapedPost(Base):
|
|
__tablename__ = "scraped_posts"
|
|
__table_args__ = (
|
|
UniqueConstraint("board_key", "article_id", name="uq_scraped_posts_board_article"),
|
|
CheckConstraint(
|
|
"board_key IN ('notice', 'archive', 'jobs')",
|
|
name="ck_scraped_posts_board_key",
|
|
),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
board_key: Mapped[str] = mapped_column(String(32), nullable=False)
|
|
board_name: Mapped[str] = mapped_column(String(100), nullable=False)
|
|
board_id: Mapped[int] = mapped_column(Integer, nullable=False)
|
|
article_id: Mapped[int] = mapped_column(Integer, nullable=False)
|
|
title: Mapped[str] = mapped_column(String(500), nullable=False)
|
|
post_url: Mapped[str] = mapped_column(Text, nullable=False)
|
|
author: Mapped[str | None] = mapped_column(String(100), nullable=True)
|
|
published_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=False), nullable=True)
|
|
summary: Mapped[str | None] = mapped_column(Text, nullable=True)
|
|
content_text: Mapped[str | None] = mapped_column(Text, nullable=True)
|
|
attachments: Mapped[list[dict]] = mapped_column(JSON, nullable=False, default=list)
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=False),
|
|
nullable=False,
|
|
server_default=func.now(),
|
|
)
|
|
|
|
|
|
class CrawlRun(Base):
|
|
__tablename__ = "crawl_runs"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
started_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=False),
|
|
nullable=False,
|
|
server_default=func.now(),
|
|
)
|
|
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=False), nullable=True)
|
|
status: Mapped[str] = mapped_column(String(20), nullable=False, default="running")
|
|
discovered_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
|
|
inserted_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
|
|
error_message: Mapped[str | None] = mapped_column(Text, nullable=True)
|