scrarls.py

@@ -10,8 +10,8 @@ from scrapy.crawler import CrawlerProcess
 from scrapy.spiders import CrawlSpider, Rule
 from scrapy.linkextractors import LinkExtractor
 
-from sqlalchemy import ForeignKey, create_engine, func, select, Engine, Integer, Boolean, String, Text, DateTime
+from sqlalchemy import create_engine, func, select, Engine, Integer, String, Text, DateTime
-from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
 from sqlalchemy.orm import sessionmaker
 
 
@@ -58,6 +58,10 @@ class TvShowDB(Base):
         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'),
@@ -69,30 +73,6 @@ class TvShowDB(Base):
         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")
-
 
 class TvShowItem(scrapy.Item):
     post_id: scrapy.Field = scrapy.Field()
@@ -117,20 +97,11 @@ class SQLAlchemyPipeline:
             show = session.scalars(stmt).first()
             print(f"{show=}")
             if not show:
-                show = TvShowDB(
+                show = TvShowDB(**item)
-                    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)
-                        setattr(show, key, value)
             session.commit()
         except Exception as e:
             session.rollback()
@@ -165,7 +136,7 @@ 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'] = article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract()
+            item['download_url'] = "#".join(article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract())
             yield item
 
     def parse_date(self, formatted_date: str):