Refactoring the main function to use multiprocessing.Process to run scrapy

.gitignore

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

models.py

@@ -1,85 +0,0 @@
-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

@@ -4,17 +4,95 @@ import re
 import sys
 
 from datetime import datetime
+from multiprocessing import Process
 
 import scrapy
 from scrapy.crawler import CrawlerProcess
 from scrapy.spiders import CrawlSpider, Rule
 from scrapy.linkextractors import LinkExtractor
 
-from sqlalchemy import create_engine, select, Engine
+from sqlalchemy import ForeignKey, create_engine, func, select, Engine, Integer, Boolean, String, Text, DateTime
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship
 from sqlalchemy.orm import sessionmaker
 
 
-from models import Base, TvShowDB, LinkDB
+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")
 
 
 class TvShowItem(scrapy.Item):
@@ -96,11 +174,25 @@ class TvShow(CrawlSpider):
         return datetime.strptime(formatted_date, "Posted on %B %d, %Y at %H:%M in")
 
 
-def main():
+def run_scrapy():
     process = CrawlerProcess()
     _ = process.crawl(TvShow)
     process.start()
-    return 0
+
+
+def main():
+    p_scrapy = Process(target=run_scrapy)
+
+    try:
+        p_scrapy.start()
+    except KeyboardInterrupt:
+        print(f"Closing...")
+        p_scrapy.terminate()
+        p_scrapy.join(timeout=30)
+        if p_scrapy.is_alive():
+            print("⚠️ Scrapy n'a pas pu s'arrêter proprement.")
+            p_scrapy.kill()
+        print(f"scrarls is stopped.")
 
 
 if __name__ == "__main__":