From 5d3d181f5eec16ccb08b891f189e75eaa1938bc5 Mon Sep 17 00:00:00 2001 From: Michael SCHAL Date: Mon, 1 Dec 2025 13:25:51 +0100 Subject: [PATCH] fix: Remove homepage redirect to avoid Amazon bot detection Amazon detects the homepage-then-search pattern as bot behavior and blocks with 2065 byte pages. Now navigating directly to search URL to appear more natural. This reverts the homepage loading strategy from commit 85b19e7 as Amazon's bot detection has evolved and now flags this pattern. --- app/services/amazon_scraper_service.py | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/app/services/amazon_scraper_service.py b/app/services/amazon_scraper_service.py index 8f5c6f6..7fcb7d1 100644 --- a/app/services/amazon_scraper_service.py +++ b/app/services/amazon_scraper_service.py @@ -247,19 +247,8 @@ class AmazonScraperService: page = await context.new_page() try: - # 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}") + # Navigate directly to search (Amazon detects homepage-then-search pattern as bot) + logger.info(f"🔍 Navigating directly to search: {search_url}") await page.goto(search_url, wait_until="domcontentloaded", timeout=60000) logger.info("Page loaded (domcontentloaded)")