Comment scraper Amazon sans se faire bannir en 2026

Ce que vous allez apprendre :

• ✓Extraction de prix, titres et avis produits
• ✓Gestion basique des proxies rotatifs
• ✓Headers et User-Agents aléatoires
• ✓Détection des éléments dynamiques

import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import random
import time

class AmazonScraper:
    def __init__(self):
        self.headers = [
            {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
                'Accept-Language': 'fr-FR,fr;q=0.9,en;q=0.8',
                'Accept-Encoding': 'gzip, deflate, br',
                'Connection': 'keep-alive'
            },
            # Ajouter plus de headers...
        ]
        self.proxies = [
            {'http': 'http://proxy1:port', 'https': 'https://proxy1:port'},
            {'http': 'http://proxy2:port', 'https': 'https://proxy2:port'},
            # Liste de proxies...
        ]

    def get_product_info(self, product_url):
        driver = webdriver.Chrome()
        try:
            driver.get(product_url)

            # Attendre le chargement
            wait = WebDriverWait(driver, 10)

            # Extraire les données
            title = wait.until(EC.presence_of_element_located(
                (By.ID, "productTitle")
            )).text

            price = driver.find_element(By.CLASS_NAME, "a-price-whole").text
            rating = driver.find_element(By.CLASS_NAME, "a-icon-alt").get_attribute("textContent")

            return {
                'title': title,
                'price': price,
                'rating': rating
            }

        except Exception as e:
            print(f"Erreur: {e}")
            return None
        finally:
            driver.quit()

    def rotate_proxy(self):
        return random.choice(self.proxies)

    def rotate_headers(self):
        return random.choice(self.headers)

# Utilisation
scraper = AmazonScraper()
product_data = scraper.get_product_info("https://amazon.fr/dp/PRODUCT_ID")