eBay Scraper: Listings and Sold Prices

import json, re
from bs4 import BeautifulSoup

CURRENCY = {"£": "GBP", "$": "USD", "US $": "USD", "AU $": "AUD", "C $": "CAD", "EUR": "EUR", "€": "EUR"}

def money(text):
    m = re.search(r"(US \$|AU \$|C \$|EUR|£|€|\$)\s?([\d.,]+)", text or "")
    if not m:
        return None, None
    amount = m.group(2).replace(",", "") if m.group(1) != "EUR" else m.group(2).replace(".", "").replace(",", ".")
    return float(amount), CURRENCY[m.group(1)]

def text(card, sel):
    el = card.select_one(sel)
    return el.get_text(" ", strip=True) if el else None

def parse_results(html):
    """Search and sold-listings pages: one row per listing card."""
    soup = BeautifulSoup(html, "html.parser")
    rows = []
    for card in soup.select("li.s-card, li.s-item"):
        link = card.select_one("a[href*='/itm/']")
        title = text(card, ".s-card__title, .s-item__title")
        item_id = re.search(r"/itm/(\d+)", link["href"]).group(1) if link else None
        if not item_id or not title or title == "Shop on eBay":   # skip the ad card
            continue
        price, currency = money(text(card, ".s-card__price, .s-item__price"))
        all_text = card.get_text(" | ", strip=True)
        sold = re.search(r"Sold\s+([^|]+?)\s*(\||$)", all_text)
        ship = re.search(r"(\+?\S+ (delivery|postage|shipping)|Free (delivery|postage|shipping))", all_text)
        bids = re.search(r"(\d+) bids?\b", all_text)
        qty_sold = re.search(r"([\d,]+)\+? sold\b", all_text)
        watchers = re.search(r"([\d,]+)\+? watch(?:ers|ing)\b", all_text)
        fmt = "auction" if bids else "best_offer" if "Best Offer" in all_text else "buy_it_now"
        seller = re.search(r"(\S+) \(([\d,]+)\) ([\d.]+)%|(\S+) ([\d.]+)% positive \(([\d,]+)\)", all_text)
        row = {"item_id": item_id, "title": title, "price": price, "currency": currency,
               "condition": text(card, ".s-card__subtitle, .SECONDARY_INFO"),
               "format": fmt, "bids": int(bids.group(1)) if bids else None,
               "quantity_sold": int(qty_sold.group(1).replace(",", "")) if qty_sold else None,
               "watchers": int(watchers.group(1).replace(",", "")) if watchers else None,
               "shipping": ship.group(1) if ship else None,
               "sold_date": sold.group(1).strip() if sold else None,
               "url": link["href"].split("?")[0]}
        if seller and seller.group(1):
            row.update(seller=seller.group(1), feedback_score=int(seller.group(2).replace(",", "")),
                       positive_pct=float(seller.group(3)))
        elif seller:
            row.update(seller=seller.group(4), positive_pct=float(seller.group(5)),
                       feedback_score=int(seller.group(6).replace(",", "")))
        rows.append(row)
    return rows

def parse_item(html):
    """Item page: the schema.org Product block, item specifics and the description frame's URL."""
    soup = BeautifulSoup(html, "html.parser")
    product = {}
    for tag in soup.select("script[type='application/ld+json']"):
        data = json.loads(tag.string or "{}")
        if isinstance(data, dict) and data.get("@type") == "Product":
            product = data
            break
    offer = product.get("offers") or {}
    offer = offer[0] if isinstance(offer, list) else offer
    specifics = {}
    for pair in soup.select(".ux-labels-values"):
        label, value = text(pair, ".ux-labels-values__labels"), text(pair, ".ux-labels-values__values")
        if label and value:
            specifics[label.rstrip(":")] = value
    page = soup.get_text(" | ", strip=True)
    qty_sold = re.search(r"([\d,]+)\+? sold\b", page)
    watchers = re.search(r"([\d,]+)\+? watch(?:ers|ing|ed)\b", page)
    frame = soup.select_one("iframe#desc_ifr")
    return {"item_id": (re.search(r"/itm/(\d+)", offer.get("url", "")) or [None, None])[1],
            "title": product.get("name") or text(soup, "h1"),
            "price": float(offer["price"]) if offer.get("price") else None,
            "currency": offer.get("priceCurrency"),
            "condition": (offer.get("itemCondition") or "").rsplit("/", 1)[-1] or None,
            "availability": (offer.get("availability") or "").rsplit("/", 1)[-1] or None,
            "quantity_sold": int(qty_sold.group(1).replace(",", "")) if qty_sold else None,
            "watchers": int(watchers.group(1).replace(",", "")) if watchers else None,
            "brand": (product.get("brand") or {}).get("name"),
            "gtin": product.get("gtin13") or product.get("gtin"),
            "item_specifics": specifics,
            "images": product.get("image") or [],
            "description_url": frame["src"] if frame else None}

def count(value):
    """'1.2K' -> 1200, '3,456' -> 3456"""
    value = value.replace(",", "")
    return int(float(value[:-1]) * 1000) if value.upper().endswith("K") else int(float(value))

def parse_seller(html):
    """Seller's store or feedback page: name, positive %, items sold, followers."""
    soup = BeautifulSoup(html, "html.parser")
    page = soup.get_text(" | ", strip=True)
    positive = re.search(r"([\d.]+)% positive feedback", page)
    sold = re.search(r"([\d.,]+K?) items? sold", page, re.I)
    followers = re.search(r"([\d.,]+K?) followers?", page, re.I)
    return {"store": text(soup, "h1"),
            "positive_pct": float(positive.group(1)) if positive else None,
            "items_sold": count(sold.group(1)) if sold else None,
            "followers": count(followers.group(1)) if followers else None}

# html = the page the Web Scraping API returned, or resp.text from the proxy example below
# print(json.dumps(parse_results(html), indent=2, ensure_ascii=False))   # search or sold-listings page
# print(json.dumps(parse_item(html), indent=2, ensure_ascii=False))      # item page
# print(json.dumps(parse_seller(html), indent=2, ensure_ascii=False))    # seller store or feedback page

{
  "item_id": "115998877665",
  "title": "Ducky One 2 Mini RGB 60% Keyboard",
  "price": 58.99,
  "currency": "USD",
  "condition": "Used",
  "format": "auction",
  "bids": 7,
  "quantity_sold": null,
  "watchers": null,
  "shipping": "Free delivery",
  "sold_date": "Oct 12, 2026",
  "url": "https://www.ebay.com/itm/115998877665",
  "seller": "techresale",
  "feedback_score": 842,
  "positive_pct": 100.0
}

{
  "item_id": "335500011122",
  "title": "Logitech MX Keys Wireless Keyboard",
  "price": 79.99,
  "currency": "USD",
  "condition": "NewCondition",
  "availability": "InStock",
  "quantity_sold": 1204,
  "watchers": 37,
  "brand": "Logitech",
  "gtin": "5099206088962",
  "item_specifics": {"Brand": "Logitech", "Connectivity": "Bluetooth", "Layout": "US"},
  "images": ["https://i.ebayimg.com/images/g/abc/s-l1600.jpg", "https://i.ebayimg.com/images/g/def/s-l1600.jpg"],
  "description_url": "https://itm.ebaydesc.com/itmdesc/335500011122?t=0"
}