Moncif El-moudenMoncif El-mouden

import httpx
from bs4 import BeautifulSoup
from pathlib import Path
import json

BASE_URL = "https://www.autoritedelaconcurrence.fr/fr/liste-des-decisions"

async def fetch_decisions(page: int = 1) -> list[dict]:
    async with httpx.AsyncClient() as client:
        resp = await client.get(BASE_URL, params={"page": page})
        resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")
    decisions = []

    for card in soup.select(".decision-card"):
        decisions.append({
            "id": card["data-id"],
            "title": card.select_one(".title").get_text(strip=True),
            "date": card.select_one(".date").get_text(strip=True),
            "sector": card.select_one(".sector").get_text(strip=True),
            "url": card.select_one("a")["href"],
        })

    return decisions

async def scrape_all(output: Path = Path("decisions.json")):
    all_decisions = []
    for page in range(1, 50):
        batch = await fetch_decisions(page)
        if not batch:
            break
        all_decisions.extend(batch)
        print(f"Page {page}: {len(batch)} decisions scraped")

    output.write_text(json.dumps(all_decisions, ensure_ascii=False, indent=2))
    print(f"Saved {len(all_decisions)} decisions to {output}")