From 2ffa4ea4d82bdf70e416a5dd835bc912b0018b5b Mon Sep 17 00:00:00 2001
From: Cocopops16 <underbinaire.cps@gmail.com>
Date: Sun, 23 Mar 2025 13:40:47 +0100
Subject: [PATCH] v0.0.1

---
 Dockerfile       | 15 +++++++++++
 main.py          | 69 ++++++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt |  7 +++++
 3 files changed, 91 insertions(+)
 create mode 100644 Dockerfile
 create mode 100644 main.py
 create mode 100644 requirements.txt

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..75b0016
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,15 @@
+FROM python:3.9-alpine
+
+WORKDIR /app
+
+RUN apk add --no-cache gcc musl-dev libffi-dev postgresql-dev
+
+COPY requirements.txt /app/
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY main.py /app/
+
+EXPOSE 8000
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..6e5ca62
--- /dev/null
+++ b/main.py
@@ -0,0 +1,69 @@
+from fastapi import FastAPI, BackgroundTasks, Depends
+from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine
+from sqlalchemy.orm import sessionmaker, declarative_base
+from sqlalchemy import Column, Integer, String, DateTime
+import aiohttp
+from bs4 import BeautifulSoup
+from datetime import datetime
+import os
+
+# Récupère les informations des secrets via les variables d'environnement
+DATABASE_URL = os.getenv("DB_URL")
+DATABASE_USERNAME = os.getenv("DB_USERNAME")
+DATABASE_PASSWORD = os.getenv("DB_PASSWORD")
+DATABASE_NAME = os.getenv("DB_NAME")
+
+# Créer l'URL complète pour la connexion à la base de données
+DATABASE_URL_FULL = f"postgresql+asyncpg://{DATABASE_USERNAME}:{DATABASE_PASSWORD}@{DATABASE_URL}/{DATABASE_NAME}"
+
+engine = create_async_engine(DATABASE_URL_FULL, echo=True)
+AsyncSessionLocal = sessionmaker(bind=engine, class_=AsyncSession, expire_on_commit=False)
+Base = declarative_base()
+
+app = FastAPI()
+
+class Loi(Base):
+    __tablename__ = "lois"
+    id = Column(Integer, primary_key=True, index=True)
+    titre = Column(String, index=True)
+    url = Column(String, unique=True)
+    date = Column(DateTime, default=datetime.utcnow)
+
+async def get_db():
+    async with AsyncSessionLocal() as session:
+        yield session
+
+@app.on_event("startup")
+async def startup():
+    async with engine.begin() as conn:
+        await conn.run_sync(Base.metadata.create_all)
+
+async def scrape_legifrance(db: AsyncSession):
+    url = "https://www.legifrance.gouv.fr/jorf/"
+    async with aiohttp.ClientSession() as session:
+        async with session.get(url) as response:
+            html = await response.text()
+            soup = BeautifulSoup(html, "html.parser")
+            lois = []
+            for article in soup.select(".mainListJorf .titleArticle"):
+                titre = article.get_text(strip=True)
+                lien = article.find("a")["href"]
+                full_url = f"https://www.legifrance.gouv.fr{lien}"
+                lois.append((titre, full_url))
+
+            for titre, full_url in lois:
+                existing = await db.execute("SELECT id FROM lois WHERE url = :url", {"url": full_url})
+                if existing.fetchone() is None:
+                    new_loi = Loi(titre=titre, url=full_url)
+                    db.add(new_loi)
+            await db.commit()
+
+@app.get("/scrape")
+async def trigger_scrape(background_tasks: BackgroundTasks, db: AsyncSession = Depends(get_db)):
+    background_tasks.add_task(scrape_legifrance, db)
+    return {"message": "Scraping en cours"}
+
+@app.get("/lois")
+async def list_lois(db: AsyncSession = Depends(get_db)):
+    result = await db.execute("SELECT * FROM lois ORDER BY date DESC LIMIT 10")
+    return result.fetchall()
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..fad7ad1
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+aiohttp
+beautifulsoup4
+sqlalchemy
+asyncpg
+psycopg2-binary