triposat

import asyncio
import os
import random
import time
from dataclasses import dataclass
from typing import List, Optional, Set

import pandas as pd
from bs4 import BeautifulSoup
from curl_cffi import requests

triposat

import asyncio
import os
from curl_cffi import requests
from bs4 import BeautifulSoup
from tenacity import retry, stop_after_attempt, wait_random


class AsinScraper:
    def __init__(self):
        self.session = requests.Session()

triposat

[
    {
        "asin": "B09MRFNDZ6",
        "url": "https://www.amazon.com/X-Box-Gaming-Console-Bundle-Controllers/dp/B09MRFNDZ6/ref=sr_1_1",
        "name": "X-Box Series X Gaming Console Bundle - 1TB SSD Black X-Box Console with Two Wireless Controllers -Black and White -and ahaghug Authorized HDMI Cable X-Box Series X Gaming Console Bundle - 1TB SSD Black X-Box Console with Two Wireless Controllers -Black and White -and ahaghug Authorized HDMI Cable",
        "sponsored": "false",
        "initial_price": 604.49,
        "final_price": 558,
        "currency": "USD",
        "sold": 300,

triposat

import streamlit as st
import pandas as pd
import plotly.express as px
import json
import re
from pathlib import Path

# Setup dark theme dashboard
st.set_page_config(
    page_title="Hotel Analysis Dashboard",

triposat

import asyncio
from datetime import timedelta
from typing import Dict, Optional, Set
from crawlee.playwright_crawler import PlaywrightCrawler
from crawlee.proxy_configuration import ProxyConfiguration
from playwright.async_api import Page, ElementHandle


class GoogleMapsScraper:
    """

triposat

import asyncio
from datetime import timedelta
from typing import Dict, Optional, Set
from crawlee.playwright_crawler import PlaywrightCrawler
from playwright.async_api import Page, ElementHandle


class GoogleMapsScraper:
    """
    Scraper for extracting business listing data from Google Maps.

triposat

from playwright.async_api import async_playwright
from tenacity import retry, stop_after_attempt, wait_fixed
from dataclasses import dataclass
from typing import List, Optional
from datetime import datetime
import asyncio
import json
import os

triposat

[
    {
        "title": "14.1in Windows 11 Pro Laptop, 8GB DDR4, 512GB SSD Computer, Intel Celeron, 1920x1080, 1TB Expansion, Silver",
        "product_url": "https://www.walmart.com/ip/Temlicolo-14-1-Laptop-8GB-RAM-PC-512GB-SSD-Intel-Celeron-N4020C-up-to-2-8GHz-Windows-11-Pro-Webcam-1TB-SSD-Expansion-Silver/1519228026?classType=VARIANT&selectedSellerId=101196098&from=/search",
        "current_price": "Now$22789",
        "previous_price": "$499.99",
        "rating": "4.5",
        "num_reviews": "220",
        "shipping_info": "Free shipping, arrives in 2 days"
    },

triposat

import asyncio
import random
import json
from playwright.async_api import async_playwright


async def scroll_and_extract(page):
    previous_height = await page.evaluate("document.body.scrollHeight")
    while True:
        network_conditions = await page.evaluate(

triposat

import asyncio
import json
import os
import shutil
from aiohttp import ClientSession, ClientTimeout
from urllib.parse import urlparse, urlencode
from playwright.async_api import async_playwright

# Function to extract the domain from a URL
def extract_domain(url):