How to Scrape Etsy: Products, Sellers, and Sales Data

How to Scrape Etsy: Products, Sellers, and Sales Data

Etsy is a goldmine for e-commerce research. Whether you are analyzing trending products, studying pricing strategies, or building a competitive intelligence tool, scraping Etsy gives you the data you need.

What You Can Extract

• Product listings with prices, descriptions, and images
• Seller information and shop statistics
• Review counts and ratings
• Sales estimates and trending items
• Category and tag data

Setup

pip install requests beautifulsoup4 pandas

Product Search Scraper

import requests
from bs4 import BeautifulSoup
import json
import time
import re

class EtsyScraper:
    def __init__(self, proxy_key=None):
        self.session = requests.Session()
        self.proxy_key = proxy_key
        self.base_url = "https://www.etsy.com"
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36",
            "Accept-Language": "en-US,en;q=0.9"
        })

    def fetch(self, url):
        if self.proxy_key:
            api_url = f"http://api.scraperapi.com?api_key={self.proxy_key}&url={url}"
            return self.session.get(api_url, timeout=30)
        return self.session.get(url, timeout=15)

    def search_products(self, query, max_pages=3, sort="most_relevant"):
        all_products = []
        for page in range(1, max_pages + 1):
            url = f"{self.base_url}/search?q={query}&page={page}&order={sort}"
            response = self.fetch(url)

            if response.status_code != 200:
                break

            products = self.parse_search_results(response.text)
            if not products:
                break

            all_products.extend(products)
            time.sleep(2)

        return all_products

    def parse_search_results(self, html):
        soup = BeautifulSoup(html, "html.parser")
        products = []

        listings = soup.select("[data-listing-id]")
        for listing in listings:
            try:
                listing_id = listing.get("data-listing-id", "")
                title_el = listing.select_one(".v2-listing-card__title")
                price_el = listing.select_one(".currency-value")
                shop_el = listing.select_one(".v2-listing-card__shop")

                # Extract rating
                rating_el = listing.select_one(".stars-svg")
                rating = 0
                if rating_el:
                    label = rating_el.get("aria-label", "")
                    match = re.search(r"([0-9.]+)", label)
                    if match:
                        rating = float(match.group(1))

                products.append({
                    "id": listing_id,
                    "title": title_el.text.strip() if title_el else "",
                    "price": self.parse_price(price_el),
                    "shop": shop_el.text.strip() if shop_el else "",
                    "rating": rating,
                    "url": f"{self.base_url}/listing/{listing_id}"
                })
            except (AttributeError, ValueError):
                continue

        return products

    def parse_price(self, el):
        if el:
            try:
                return float(el.text.strip().replace(",", ""))
            except ValueError:
                pass
        return 0.0

Product Detail Scraper

class ProductDetailScraper(EtsyScraper):
    def get_product_details(self, listing_url):
        response = self.fetch(listing_url)
        soup = BeautifulSoup(response.text, "html.parser")

        details = {}

        # Title and description
        title_el = soup.select_one("h1")
        details["title"] = title_el.text.strip() if title_el else ""

        desc_el = soup.select_one("[data-id=description-text]")
        details["description"] = desc_el.text.strip() if desc_el else ""

        # Price
        price_el = soup.select_one(".wt-text-title-03")
        if price_el:
            match = re.search(r"[0-9,.]+", price_el.text)
            details["price"] = float(match.group().replace(",", "")) if match else 0

        # Reviews and sales
        reviews_el = soup.select_one("[data-reviews-total]")
        details["reviews"] = int(reviews_el.get("data-reviews-total", 0)) if reviews_el else 0

        sales_el = soup.select_one(".wt-text-caption")
        if sales_el and "sale" in sales_el.text.lower():
            match = re.search(r"([0-9,]+)", sales_el.text)
            details["sales"] = int(match.group().replace(",", "")) if match else 0

        # Tags
        tags = [tag.text.strip() for tag in soup.select("[data-tag]")]
        details["tags"] = tags

        return details

Shop Analytics

class ShopScraper(EtsyScraper):
    def get_shop_info(self, shop_name):
        url = f"{self.base_url}/shop/{shop_name}"
        response = self.fetch(url)
        soup = BeautifulSoup(response.text, "html.parser")

        info = {"name": shop_name}

        sales_el = soup.select_one(".shop-sales-count")
        if sales_el:
            match = re.search(r"([0-9,]+)", sales_el.text)
            info["total_sales"] = int(match.group().replace(",", "")) if match else 0

        rating_el = soup.select_one(".stars-svg")
        if rating_el:
            match = re.search(r"([0-9.]+)", rating_el.get("aria-label", ""))
            info["rating"] = float(match.group()) if match else 0

        listings = soup.select("[data-listing-id]")
        info["active_listings"] = len(listings)

        return info

Data Analysis

import pandas as pd

scraper = EtsyScraper()
products = scraper.search_products("handmade candles", max_pages=5)
df = pd.DataFrame(products)

print(f"Total products: {len(df)}")
print(f"Price range: ${df['price'].min():.2f} - ${df['price'].max():.2f}")
print(f"Average price: ${df['price'].mean():.2f}")
print(f"Median price: ${df['price'].median():.2f}")
print(f"\nTop shops by listings:")
print(df["shop"].value_counts().head(10))

df.to_csv("etsy_products.csv", index=False)

Handling Anti-Scraping

Etsy uses Cloudflare and other protections:

• ScraperAPI — bypasses Cloudflare, handles CAPTCHAs
• ThorData — residential proxies for consistent access
• ScrapeOps — track success rates and get alerts

Conclusion

Etsy scraping reveals market trends, pricing strategies, and competitive dynamics in the handmade/vintage marketplace. Use this data to find profitable niches or optimize your own shop.

---

Follow for more e-commerce scraping guides!