ebay_sync.py

import requests
from parsel import Selector
from urllib.parse import urlencode, parse_qs, urlparse
import csv
import re

SCRAPERAPI_KEY = "YOUR_SCRAPERAPI_KEY"

TARGET_URL = "https://www.ebay.co.uk/b/bn_7117580375?_sop=10&mag=1&rt=nc"

OUTPUT_FILE = "SAMPLE_UK_PS5_10_Items.csv"


def extract_item_id(url):
    """Extracts eBay item ID from both standard (/itm/) and catalog (/p/?iid=) URLs."""

    if not url:

        return "N/A"

    itm_match = re.search(r"/itm/(\d+)", url)

    if itm_match:

        return itm_match.group(1)

    parsed_url = urlparse(url)

    query_params = parse_qs(parsed_url.query)

    if "iid" in query_params:

        return query_params["iid"][0]

    return "N/A"


def scrape_ebay():

    print("[-->] Fetching search page via ScraperAPI...")

    payload = {"api_key": SCRAPERAPI_KEY, "url": TARGET_URL, "render": "true"}

    response = requests.get("https://api.scraperapi.com/", params=payload)

    if response.status_code != 200:

        print(f"❌ ScraperAPI Request Failed: {response.status_code}")

        return

    selector = Selector(text=response.text)

    items = selector.css(
        "li.brwrvr__item-card, li.bsig__item, ul.b-list__items_nofooter > li, li.s-item"
    )

    print(f"[-->] Found {len(items)} item cards matching layout containers.")

    scraped_data = []

    seen_urls = set()

    for item in items:

        if len(scraped_data) >= 10:

            break

        url = item.css(
            "a.bsig__title__wrapper::attr(href), a.s-item__link::attr(href)"
        ).get()

        if not url or url in seen_urls:

            continue

        title_parts = item.css(
            "h3.bsig__title__text ::text, .s-item__title ::text"
        ).getall()

        full_title = " ".join([t.strip() for t in title_parts if t.strip()])

        clean_title = full_title.replace("New listing", "").strip()

        if not clean_title or "Shop on eBay" in clean_title:

            continue

        condition = item.css(
            ".bsig__listingCondition span::text, .s-item__subtitle ::text"
        ).get()

        clean_condition = condition.strip() if condition else "N/A"

        price = item.css(".bsig__price--displayprice::text, .s-item__price::text").get()

        clean_price = price.strip() if price else "N/A"

        item_id = extract_item_id(url)

        seen_urls.add(url)

        scraped_data.append(
            {
                "ebay_item_number": item_id,
                "title": clean_title,
                "condition": clean_condition,
                "price": clean_price,
                "url": url,
            }
        )

        print(
            f"[{len(scraped_data)}/10] ID: {item_id} | Price: {clean_price} | Cond: {clean_condition} | Title: {clean_title[:30]}..."
        )

    # Export to CSV with UTF-8 BOM encoding for Excel compatibility

    if scraped_data:

        with open(OUTPUT_FILE, "w", newline="", encoding="utf-8-sig") as f:

            writer = csv.DictWriter(f, fieldnames=scraped_data[0].keys())

            writer.writeheader()

            writer.writerows(scraped_data)

        print(f"\n✅ SUCCESS: Clean UTF-8 CSV saved to '{OUTPUT_FILE}'")

    else:

        print("\n❌ No items extracted.")


if __name__ == "__main__":

    scrape_ebay()