SilviuMatei's picture
Update app.py
c9b8fea verified
raw
history blame
2.41 kB
from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
from Gradio_UI import GradioUI
from bs4 import BeautifulSoup
@tool
def amazon_product_scraper(search_url: str) -> list:
"""
Scrapes Amazon search results for product titles, prices, delivery fees, and links.
Args:
search_url: The URL of the Amazon search results page containing product listings.
Returns:
A list containing two elements:
- A list of dictionaries, each with keys "Title", "Price", "Delivery", "Link", sorted by price.
- A string containing a recommendation for the best deal.
"""
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36"
}
response = requests.get(search_url, headers=headers)
if response.status_code != 200:
return [], "Failed to retrieve Amazon results. Amazon may be blocking requests."
soup = BeautifulSoup(response.text, 'html.parser')
product_data = []
for item in soup.select("div[data-asin]"):
title_tag = item.select_one("h2 a")
price_tag = item.select_one("span.a-price-whole")
delivery_tag = item.select_one("span.s-align-children-center")
if title_tag and price_tag:
title = title_tag.text.strip()
price = price_tag.text.strip().replace(',', '') # Normalize prices
delivery = delivery_tag.text.strip() if delivery_tag else "Free"
link = "https://www.amazon.com" + title_tag["href"]
product_data.append({
"Title": title,
"Price": float(price) if price.isnumeric() else None,
"Delivery": delivery,
"Link": link
})
# Filter out products with no price and sort by price
product_data = [p for p in product_data if p["Price"] is not None]
product_data.sort(key=lambda x: x["Price"])
# Recommendation logic
best_deal = product_data[0] if product_data else None
recommendation = ""
if best_deal is not None:
recommendation = f"Best deal: {best_deal['Title']} at ${best_deal['Price']} with {best_deal['Delivery']} (Link: {best_deal['Link']})"
return product_data, recommendation