From 101e5f06567d00c629f7badb0cb0c9ea159ee0e4 Mon Sep 17 00:00:00 2001 From: Michael SCHAL Date: Sun, 30 Nov 2025 02:42:53 +0100 Subject: [PATCH] feat: add Cataloguemate.fr scraper to replace Tiendeo and utilize BrowserlessService for catalog and page scraping --- app/services/cataloguemate_scraper.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/app/services/cataloguemate_scraper.py b/app/services/cataloguemate_scraper.py index 4235afd..083a328 100644 --- a/app/services/cataloguemate_scraper.py +++ b/app/services/cataloguemate_scraper.py @@ -229,14 +229,23 @@ async def scrape_enseigne(enseigne: Enseigne, db: Session) -> ScrapingLog: if not pages: continue +import hashlib + +# ... imports ... + # Create catalog entry + # Generate content hash (URL + Title + Date) + hash_input = f"{cat_info['url']}{cat_info['title']}{datetime.now().date()}".encode('utf-8') + content_hash = hashlib.sha256(hash_input).hexdigest() + new_cat = Catalogue( enseigne_id=enseigne.id, titre=cat_info['title'], catalogue_url=cat_info['url'], date_debut=datetime.now(), # Todo: extract real dates date_fin=datetime.now() + timedelta(days=14), - image_couverture_url=pages[0]['image_url'] + image_couverture_url=pages[0]['image_url'], + content_hash=content_hash ) db.add(new_cat) db.commit()