From cde1f75d3a179bae81c6d6ba4bf74f02c31fea44 Mon Sep 17 00:00:00 2001 From: Michael SCHAL Date: Sun, 30 Nov 2025 02:45:24 +0100 Subject: [PATCH 1/2] feat: Add Cataloguemate.fr scraper service to replace Tiendeo, utilizing BrowserlessService for robust scraping. --- app/services/cataloguemate_scraper.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/app/services/cataloguemate_scraper.py b/app/services/cataloguemate_scraper.py index 083a328..aec0188 100644 --- a/app/services/cataloguemate_scraper.py +++ b/app/services/cataloguemate_scraper.py @@ -9,6 +9,7 @@ Refactored to use BrowserlessService for robust containerized scraping. import asyncio import logging import re +import hashlib from datetime import datetime, timedelta from typing import Any, Optional @@ -229,10 +230,6 @@ 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') From df8fbded929639a35c8565da47eb4c95e7d089a9 Mon Sep 17 00:00:00 2001 From: Michael SCHAL Date: Sun, 30 Nov 2025 02:47:11 +0100 Subject: [PATCH 2/2] feat: add Cataloguemate.fr scraper to replace Tiendeo and utilize BrowserlessService for robust scraping. --- app/services/cataloguemate_scraper.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/services/cataloguemate_scraper.py b/app/services/cataloguemate_scraper.py index aec0188..51828f1 100644 --- a/app/services/cataloguemate_scraper.py +++ b/app/services/cataloguemate_scraper.py @@ -209,7 +209,7 @@ async def scrape_enseigne(enseigne: Enseigne, db: Session) -> ScrapingLog: try: # 0. Test connection (Implicit in get_page_content, but good to log) - logger.info(f"Starting scraping for {enseigne.nom} using Browserless...") + logger.info(f"Starting scraping for {enseigne.nom} using Browserless v2...") # 1. Get list of catalogs catalogs_list = await scrape_catalog_list(enseigne)