Luxury Brand Scraper Tutorial for Dior, LV, Gucci

Array ( [as_domain] => amazon.com [as_name] => Amazon.com, Inc. [asn] => AS16509 [continent] => North America [continent_code] => NA [country] => United States [country_code] => US )

Start Your Project

from selenium import webdriver from selenium.webdriver.common.by import By from time import sleep import pandas as pd browser = webdriver.Chrome() browser.get("https://www.dior.com/en_gb/beauty/makeup") sleep(4) Scroll for products: for _ in range(6): browser.find_element(By.TAG_NAME, "body").send_keys(Keys.END) sleep(2) Locate product cards: items = browser.find_elements(By.XPATH, '//article[contains(@class,"product-tile")]') Extract details: dior_records = [] for item in items: try: name = item.find_element(By.CLASS_NAME, "product-tile__title").text except: name = "" try: price = item.find_element(By.CLASS_NAME, "price__amount").text except: price = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" dior_records.append({"brand": "Dior", "name": name, "price": price, "url": url})

Open: browser.get("https://www.louisvuitton.com/eng-ae/women/all-handbags") sleep(5) Scroll: for _ in range(10): browser.find_element(By.TAG_NAME, "body").send_keys(Keys.END) sleep(2) Extract: lv_items = browser.find_elements(By.XPATH, '//li[@class="product-item"]') lv_records = [] for item in lv_items: try: title = item.find_element(By.CLASS_NAME, "product-item__title").text except: title = "" try: price = item.find_element(By.CLASS_NAME, "product-item__price").text except: price = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" lv_records.append({"brand": "Louis Vuitton", "name": title, "price": price, "url": url})

Open Gucci UAE: browser.get("https://www.gucci.com/us/en/ca/women/handbags-c-women-handbags") sleep(5) Scroll: for _ in range(8): browser.find_element(By.TAG_NAME, "body").send_keys(Keys.END) sleep(2) Extract: gucci_records = [] products = browser.find_elements(By.XPATH, '//div[contains(@class,"product-tiles-grid-item")]') for p in products: try: title = p.find_element(By.CLASS_NAME, "product-tiles-grid-item__name").text except: title = "" try: price = p.find_element(By.CLASS_NAME, "product-tiles-grid-item__price").text except: price = "" try: url = p.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" gucci_records.append({"brand": "Gucci", "name": title, "price": price, "url": url})

Open Sephora UAE: browser.get("https://www.sephora.ae/en/categories/makeup") sleep(5) Extract: sephora_records = [] items = browser.find_elements(By.XPATH, '//div[contains(@class,"product-grid-item")]') for item in items: try: title = item.find_element(By.CLASS_NAME, "product-item-name").text except: title = "" try: price = item.find_element(By.CLASS_NAME, "price").text except: price = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" sephora_records.append({"brand": "Sephora", "name": title, "price": price, "url": url})

Add regex: import re def extract_size(t): match = re.search(r"(\d+ml|\d+ g|\d+oz)", t.lower()) return match.group(1) if match else None df["size"] = df["name"].apply(extract_size) Extract color variant: def extract_color(t): colors = ["pink","red","brown","black","white","gold","blue","beige"] for c in colors: if c in t.lower(): return c return None df["color"] = df["name"].apply(extract_color)

def classify_category(name): n = name.lower() if "bag" in n or "tote" in n or "wallet" in n: return "Luxury Handbag" if "lipstick" in n or "foundation" in n: return "Luxury Makeup" if "perfume" in n or "eau" in n: return "Luxury Fragrance" return "Other" df["category"] = df["name"].apply(classify_category)

df.to_csv("luxury_brand_data.csv", index=False) Output sample: { "brand": "Gucci", "name": "GG Marmont mini bag black", "price": "$2350", "url": "https://www.gucci.com/...", "size": null, "color": "black", "category": "Luxury Handbag" }

Array ( [as_domain] => amazon.com [as_name] => Amazon.com, Inc. [asn] => AS16509 [continent] => North America [continent_code] => NA [country] => United States [country_code] => US )

Start Your Project

Our Data Drives Impact - Real Client Stories