SHEIN Scraper: Streamline Fashion Product Intelligence Collection

import requests
from bs4 import BeautifulSoup

REQUEST_HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.8"
}

def extract_shein_product(page_url):
    try:
        page = requests.get(page_url, headers=REQUEST_HEADERS, timeout=15)
        page.raise_for_status()
    except requests.RequestException:
        return None

    document = BeautifulSoup(page.text, "html.parser")

    def get_text(selector):
        element = document.select_one(selector)
        return element.get_text(" ", strip=True) if element else "N/A"

    product_record = {
        "Product_Name": get_text("h1"),
        "Product_Price": get_text('[class*="price"]'),
        "Customer_Rating": get_text('[class*="rating"]'),
        "Availability": get_text('[class*="stock"]'),
        "Product_Category": get_text('[class*="category"]')
    }

    return product_record


# Example SHEIN product page
shein_url = "https://www.shein.com/example-product.html"

product_data = extract_shein_product(shein_url)

if product_data:
    print(product_data)
else:
    print("Unable to retrieve product information.")