Refactoring: extracting SQLAlchemy-related code to its own modules

.gitignore

@@ -1 +1,2 @@
 /*.db
+/__pycache__/

models.py

@@ -0,0 +1,85 @@
+from datetime import datetime
+
+from sqlalchemy import ForeignKey, func, Integer, Boolean, String, Text, DateTime
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship
+
+
+class Base(DeclarativeBase):
+    """Base déclarative pour SQLAlchemy 2.0."""
+    pass
+
+
+class TvShowDB(Base):
+    """Modèle pour le stockage des épisodes (SQLAlchemy 2.0)."""
+
+    __tablename__: str = "tvshows"
+
+    id: Mapped[int] = mapped_column(
+        Integer,
+        primary_key=True,
+        autoincrement=True
+    )
+    post_id: Mapped[str] = mapped_column(
+        String(length=255),
+        nullable=False,
+        unique=True,
+        index=True
+    )
+    post_title: Mapped[str] = mapped_column(
+        String(255),
+        nullable=False
+    )
+    title: Mapped[str] = mapped_column(
+        String(255),
+        nullable=False,
+        index=True
+    )
+    date: Mapped[datetime] = mapped_column(
+        DateTime,
+        nullable=False,
+        index=True
+    )
+    summary: Mapped[str | None] = mapped_column(
+        Text,
+        nullable=True
+    )
+    image_url: Mapped[str | None] = mapped_column(
+        String(255),
+        nullable=True
+    )
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime,
+        server_default=func.datetime('now'),
+        nullable=False
+    )
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime,
+        server_default=func.datetime('now'),
+        onupdate=func.datetime('now'),
+        nullable=False
+    )
+    links: Mapped[list["LinkDB"]] = relationship(back_populates="show")
+
+
+class LinkDB(Base):
+    """Modèle pour le stockage des liens de téléchargement (SQLAlchemy 2.0)."""
+
+    __tablename__: str = "links"
+
+    id: Mapped[int] = mapped_column(
+        Integer,
+        primary_key=True,
+        autoincrement=True
+    )
+    link: Mapped[str] = mapped_column(
+        String(255),
+        nullable=False
+    )
+    is_downloaded: Mapped[bool] = mapped_column(
+        Boolean,
+        default=False
+    )
+    show_id: Mapped[int] = mapped_column(ForeignKey("tvshows.id"))
+    show: Mapped["TvShowDB"] = relationship(back_populates="links")
+
+

scrarls.py

@@ -10,70 +10,13 @@ from scrapy.crawler import CrawlerProcess
 from scrapy.spiders import CrawlSpider, Rule
 from scrapy.linkextractors import LinkExtractor
 
-from sqlalchemy import create_engine, func, select, Engine, Integer, String, Text, DateTime
+from sqlalchemy import create_engine, select, Engine
-from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
 from sqlalchemy.orm import sessionmaker
 
 
-class Base(DeclarativeBase):
+from models import Base, TvShowDB, LinkDB
-    """Base déclarative pour SQLAlchemy 2.0."""
-    pass
 
 
-class TvShowDB(Base):
-    """Modèle pour le stockage des épisodes (SQLAlchemy 2.0)."""
-
-    __tablename__: str = "tvshows"
-
-    id: Mapped[int] = mapped_column(
-        Integer,
-        primary_key=True,
-        autoincrement=True
-    )
-    post_id: Mapped[str] = mapped_column(
-        String(length=255),
-        nullable=False,
-        unique=True,
-        index=True
-    )
-    post_title: Mapped[str] = mapped_column(
-        String(255),
-        nullable=False
-    )
-    title: Mapped[str] = mapped_column(
-        String(255),
-        nullable=False,
-        index=True
-    )
-    date: Mapped[datetime] = mapped_column(
-        DateTime,
-        nullable=False,
-        index=True
-    )
-    summary: Mapped[str | None] = mapped_column(
-        Text,
-        nullable=True
-    )
-    image_url: Mapped[str | None] = mapped_column(
-        String(255),
-        nullable=True
-    )
-    download_url: Mapped[str | None] = mapped_column(
-        String(255),
-        nullable=True
-    )
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime,
-        server_default=func.datetime('now'),
-        nullable=False
-    )
-    updated_at: Mapped[datetime] = mapped_column(
-        DateTime,
-        server_default=func.datetime('now'),
-        onupdate=func.datetime('now'),
-        nullable=False
-    )
-
 class TvShowItem(scrapy.Item):
     post_id: scrapy.Field = scrapy.Field()
     post_title: scrapy.Field = scrapy.Field()
@@ -97,10 +40,19 @@ class SQLAlchemyPipeline:
             show = session.scalars(stmt).first()
             print(f"{show=}")
             if not show:
-                show = TvShowDB(**item)
+                show = TvShowDB(
+                    post_id=item["post_id"],
+                    post_title=item["post_title"],
+                    title=item["title"],
+                    date=item["date"],
+                    summary=item["summary"],
+                    image_url=item["image_url"],
+                    links=[LinkDB(link=url) for url in item["download_url"]]
+                )
                 session.add(show)
             else:
                 for key, value in item.items():
+                    if key != "download_url":
                         setattr(show, key, value)
             session.commit()
         except Exception as e:
@@ -136,7 +88,7 @@ class TvShow(CrawlSpider):
             item['date'] = self.parse_date(article.css('.entry-meta-header-before::text').getall()[1].strip())
             item['summary'] = "".join(article.xpath('.//div[@class="entry-summary"]/node()').extract())
             item['image_url'] = article.css('.entry-summary > p > img::attr(src)').get()
-            item['download_url'] = "#".join(article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract())
+            item['download_url'] = article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract()
             yield item
 
     def parse_date(self, formatted_date: str):