From d2fe4bf22b2324e2cd2cb88abdf619d991b7211b Mon Sep 17 00:00:00 2001 From: Michael SCHAL Date: Mon, 22 Dec 2025 12:39:01 +0100 Subject: [PATCH] feat: Add Cataloguemate.fr scraper using BrowserlessService to replace the Tiendeo scraper. --- app/services/cataloguemate_scraper.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/app/services/cataloguemate_scraper.py b/app/services/cataloguemate_scraper.py index 648c739..7410514 100644 --- a/app/services/cataloguemate_scraper.py +++ b/app/services/cataloguemate_scraper.py @@ -21,6 +21,10 @@ from sqlalchemy.orm import Session from app.models import Enseigne, Catalogue, CataloguePage, ScrapingLog from app.services.browserless_service import browserless_service +logger = logging.getLogger(__name__) + +BASE_URL = "https://www.cataloguemate.fr" + async def _fetch_with_fallback(url: str) -> str: """Fetch content using Browserless first, then fallback to HTTPX.""" # 1. Try Browserless