Michael/Priceflow
1
0 Fork 0
mirror of https://github.com/R0m1k3/Priceflow.git synced 2026-10-21 14:18:11 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #161 from R0m1k3/claude/amazon-france-search-page-01KmPqbdPCqxWXxEoFw9jgFo

Browse Source 
test: Try Amazon scraping without proxy
This commit is contained in:
LogiFlow authored and GitHub committed 2025-11-30 11:11:00 +01:00
2 parents dd6e955d02 77bc8ececf
commit e641de52b9
1 file changed
+3 -3
Download Patch File Download Diff File Expand all files Collapse all files
app/services/amazon_scraper_v2.py
+3 -3
View File
@@ -128,11 +128,11 @@ async def scrape_amazon_search(query: str, max_results: int = 20) -> list[Amazon
try: try:
# Use browserless service to get page content # Use browserless service to get page content
# use_proxy=True for Amazon to avoid rate limiting # Try WITHOUT proxy first - some proxies may be banned by Amazon
logger.info("🚀 Fetching page with Browserless...") logger.info("🚀 Fetching page with Browserless (NO PROXY for testing)...")
html_content, _ = await browserless_service.get_page_content( html_content, _ = await browserless_service.get_page_content(
url=search_url, url=search_url,
use_proxy=True, # Use proxy rotation for Amazon use_proxy=False, # Try without proxy first
wait_selector=None, # Let it load naturally wait_selector=None, # Let it load naturally
extract_text=False # We want HTML for parsing extract_text=False # We want HTML for parsing
) )