Scrape Vinted Listings with Python: Search + Pagination + Clean CSV Export

python3 -m venv .venv
source .venv/bin/activate
pip install requests python-dotenv

PROXIESAPI_KEY="YOUR_PROXIESAPI_KEY"

import os
import time
import urllib.parse
from typing import Any

import requests
from dotenv import load_dotenv

load_dotenv()

PROXIESAPI_KEY = os.getenv("PROXIESAPI_KEY", "")
TIMEOUT = (10, 60)  # connect, read

session = requests.Session()
session.headers.update({
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0 Safari/537.36",
    "Accept": "application/json,text/plain,*/*",
    "Accept-Language": "en-GB,en;q=0.9",
})


def proxiesapi_url(target_url: str) -> str:
    if not PROXIESAPI_KEY:
        raise RuntimeError("Missing PROXIESAPI_KEY env var")
    return "https://api.proxiesapi.com/?" + urllib.parse.urlencode({
        "key": PROXIESAPI_KEY,
        "url": target_url,
    })


def fetch_json(url: str, *, retries: int = 4, backoff: float = 2.0) -> dict[str, Any]:
    last_err: Exception | None = None
    for attempt in range(1, retries + 1):
        try:
            r = session.get(proxiesapi_url(url), timeout=TIMEOUT)
            r.raise_for_status()

            # Vinted blocks often come back as HTML. This keeps failures obvious.
            ct = (r.headers.get("content-type") or "").lower()
            if "application/json" not in ct and r.text.lstrip().startswith("<"):
                raise RuntimeError("Got HTML instead of JSON (likely blocked/challenged)")

            return r.json()
        except Exception as e:
            last_err = e
            sleep_s = backoff ** attempt
            print(f"attempt {attempt}/{retries} failed: {e} -> sleeping {sleep_s:.1f}s")
            time.sleep(sleep_s)
    raise RuntimeError(f"Failed after {retries} retries: {last_err}")

def vinted_search_url(*, query: str, page: int) -> str:
    base = "https://www.vinted.co.uk/api/v2/catalog/items"
    params = {
        "search_text": query,
        "page": str(page),
        "per_page": "24",
    }
    return base + "?" + urllib.parse.urlencode(params)

from typing import Any


def pick_items_payload(data: dict[str, Any]) -> list[dict[str, Any]]:
    # Common shapes we see across internal catalog APIs:
    # - {"items": [...]}
    # - {"catalog_items": [...]}
    # - {"data": {"items": [...]}}
    candidates = []

    if isinstance(data.get("items"), list):
        candidates.append(data["items"])
    if isinstance(data.get("catalog_items"), list):
        candidates.append(data["catalog_items"])
    if isinstance(data.get("data"), dict) and isinstance(data["data"].get("items"), list):
        candidates.append(data["data"]["items"])

    if candidates:
        return candidates[0]

    # Last-resort: find any list of dicts that looks like listings.
    for v in data.values():
        if isinstance(v, list) and v and isinstance(v[0], dict):
            return v
    return []


def to_number(x: Any) -> float | None:
    try:
        return float(x)
    except Exception:
        return None


def parse_listings(data: dict[str, Any]) -> list[dict[str, Any]]:
    items = pick_items_payload(data)
    out: list[dict[str, Any]] = []

    for it in items:
        item_id = it.get("id") or it.get("item_id")
        title = it.get("title") or it.get("name")

        brand = None
        if isinstance(it.get("brand"), dict):
            brand = it["brand"].get("title") or it["brand"].get("name")
        brand = brand or it.get("brand_title") or it.get("brand_name")

        size = None
        if isinstance(it.get("size"), dict):
            size = it["size"].get("title") or it["size"].get("name")
        size = size or it.get("size_title") or it.get("size")

        price = None
        currency = None
        if isinstance(it.get("price"), dict):
            price = to_number(it["price"].get("amount") or it["price"].get("value"))
            currency = it["price"].get("currency_code") or it["price"].get("currency")
        price = price if price is not None else to_number(it.get("price_numeric") or it.get("price"))

        url = it.get("url") or it.get("item_url")

        photo_url = None
        if isinstance(it.get("photo"), dict):
            photo_url = it["photo"].get("url")
        if not photo_url and isinstance(it.get("photos"), list) and it["photos"]:
            first = it["photos"][0]
            if isinstance(first, dict):
                photo_url = first.get("url")
        photo_url = photo_url or it.get("photo_url") or it.get("image_url")

        out.append({
            "id": item_id,
            "title": title,
            "brand": brand,
            "size": size,
            "price": price,
            "currency": currency,
            "url": url,
            "photo_url": photo_url,
        })

    return out

import csv


def crawl_search(query: str, *, max_pages: int = 10) -> list[dict[str, Any]]:
    all_rows: list[dict[str, Any]] = []
    for page in range(1, max_pages + 1):
        url = vinted_search_url(query=query, page=page)
        data = fetch_json(url)
        rows = parse_listings(data)

        print(f"page {page}: {len(rows)} listings")
        if not rows:
            break

        all_rows.extend(rows)
        time.sleep(0.8)  # be polite; adjust for your needs

    return all_rows


def write_csv(path: str, rows: list[dict[str, Any]]) -> None:
    if not rows:
        raise RuntimeError("No rows to write")
    cols = ["id", "title", "brand", "size", "price", "currency", "url", "photo_url"]
    with open(path, "w", newline="", encoding="utf-8") as f:
        w = csv.DictWriter(f, fieldnames=cols)
        w.writeheader()
        for r in rows:
            w.writerow({k: r.get(k) for k in cols})


if __name__ == "__main__":
    rows = crawl_search("nike dunk", max_pages=5)
    write_csv("vinted_listings.csv", rows)
    print("wrote vinted_listings.csv", len(rows))