How to Scrape Shopee Marketplace

"""
KnoxProxy scraper for Shopee item data via the internal v4 item API.
Shop and item IDs are the two numeric segments in a Shopee product URL.
"""
import random
import time

import requests

PROXY_HOST = "proxy.knoxproxy.com"
PROXY_PORT = 10000  # residential rotating
PROXY_USER = "your_username"
PROXY_PASS = "your_password"

HEADERS = {
    "User-Agent": (
        "Mozilla/5.0 (iPhone; CPU iPhone OS 17_5 like Mac OS X) "
        "AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Mobile/15E148 Safari/604.1"
    ),
    "Accept": "application/json",
    "Referer": "https://shopee.sg/",
}


def proxy_dict(country: str = "sg") -> dict:
    user = f"{PROXY_USER}-country-{country}"
    proxy_url = f"http://{user}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}"
    return {"http": proxy_url, "https": proxy_url}


def fetch_shopee_item(shop_id: str, item_id: str, tld: str = "sg", max_retries: int = 3) -> dict:
    url = f"https://shopee.{tld}/api/v4/item/get?itemid={item_id}&shopid={shop_id}"
    proxies = proxy_dict(country=tld)

    for attempt in range(1, max_retries + 1):
        try:
            resp = requests.get(url, headers=HEADERS, proxies=proxies, timeout=20)
            if resp.status_code == 200:
                return parse_shopee_item(resp.json())
            print(f"Attempt {attempt}: Shopee returned status {resp.status_code}")
        except requests.exceptions.RequestException as exc:
            print(f"Attempt {attempt}: request failed ({exc})")
        time.sleep(random.uniform(3, 6))

    raise RuntimeError(f"Failed to fetch Shopee item {item_id} after {max_retries} attempts")


def parse_shopee_item(payload: dict) -> dict:
    item = payload.get("data", {})
    return {
        "item_id": item.get("itemid"),
        "name": item.get("name"),
        "price": item.get("price", 0) / 100000,  # Shopee prices are scaled by 10^5
        "stock": item.get("stock"),
        "rating": item.get("item_rating", {}).get("rating_star"),
    }


if __name__ == "__main__":
    print(fetch_shopee_item(shop_id="123456", item_id="7891011", tld="sg"))

{
  "item_id": 7891011,
  "name": "Portable Mini Fan USB Rechargeable",
  "price": 8.9,
  "stock": 4213,
  "rating": 4.8
}