From 2429fa2018a9856f8b7252864d46b5704d79e405 Mon Sep 17 00:00:00 2001 From: Michael SCHAL Date: Mon, 1 Dec 2025 13:26:05 +0100 Subject: [PATCH] Revert "fix: Remove homepage redirect to avoid Amazon bot detection" This reverts commit 5d3d181f5eec16ccb08b891f189e75eaa1938bc5. --- app/services/amazon_scraper_service.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/app/services/amazon_scraper_service.py b/app/services/amazon_scraper_service.py index 7fcb7d1..8f5c6f6 100644 --- a/app/services/amazon_scraper_service.py +++ b/app/services/amazon_scraper_service.py @@ -247,8 +247,19 @@ class AmazonScraperService: page = await context.new_page() try: - # Navigate directly to search (Amazon detects homepage-then-search pattern as bot) - logger.info(f"🔍 Navigating directly to search: {search_url}") + # CRITICAL: Load Amazon homepage FIRST in same context to establish session + logger.info("🏠 Loading Amazon homepage to establish session/cookies...") + await page.goto("https://www.amazon.fr", wait_until="domcontentloaded", timeout=30000) + logger.info("✅ Homepage loaded") + + # Handle homepage popups + await cls._handle_popups(page) + + # Small delay + await page.wait_for_timeout(2000) + + # NOW navigate to search in SAME context (cookies preserved) + logger.info(f"🔍 Navigating to search: {search_url}") await page.goto(search_url, wait_until="domcontentloaded", timeout=60000) logger.info("Page loaded (domcontentloaded)")