Shopping Product

Retrieve detailed Google Shopping product data including pricing, reviews, specifications, and variants using Web Scraper API.

The google_shopping_product source retrieves detailed product information (title, description, pricing, sellers, related items, reviews, etc.) from Google Shopping using a product token acquired from google_shopping_search (here) or google_search.

Request samples

In the code example below, we make a request to retrieve the product page for a Google Shopping product using a valid token.

cURL

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
       "source": "google_shopping_product",
       "query": "<PRODUCT_TOKEN>",
       "render": "html",
       "parse": true
    }'

Python

import requests
from pprint import pprint


# Structure payload.
payload = {
    "source": "google_shopping_product",
    "query": "[product_token_string]",
    "render": "html",
    "parse": True
}

# Get response.
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload,
)

# Print prettified response to stdout.
pprint(response.json())

Node.js

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "google_shopping_product",
    query: "[product_token_string]",
    render: "html",
    parse: true
};

const options = {
    hostname: "realtime.oxylabs.io",
    path: "/v1/queries",
    method: "POST",
    headers: {
        "Content-Type": "application/json",
        Authorization:
            "Basic " + Buffer.from(`${username}:${password}`).toString("base64"),
    },
};

const request = https.request(options, (response) => {
    let data = "";

    response.on("data", (chunk) => {
        data += chunk;
    });

    response.on("end", () => {
        const responseData = JSON.parse(data);
        console.log(JSON.stringify(responseData, null, 2));
    });
});

request.on("error", (error) => {
    console.error("Error:", error);
});

request.write(JSON.stringify(body));
request.end();

HTTP

https://realtime.oxylabs.io/v1/queries?source=google_shopping_product&query=[product_token_string]&parse=true&access_token=12345abcde

PHP

<?php

$params = array(
    'source' => 'google_shopping_product',
    'query' => '[product_token_string]',
    'render' => 'html',
    'parse' => true
);

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, "https://realtime.oxylabs.io/v1/queries");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($params));
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_USERPWD, "USERNAME" . ":" . "PASSWORD");

$headers = array();
$headers[] = "Content-Type: application/json";
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

$result = curl_exec($ch);
echo $result;

if (curl_errno($ch)) {
    echo 'Error:' . curl_error($ch);
}
curl_close($ch);

Golang

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io/ioutil"
	"net/http"
)

func main() {
	const Username = "USERNAME"
	const Password = "PASSWORD"

	payload := map[string]interface{}{
		"source": "google_shopping_product",
		"query": "[product_token_string]",
		"render": "html",
		"parse": true,
	}

	jsonValue, _ := json.Marshal(payload)

	client := &http.Client{}
	request, _ := http.NewRequest("POST",
		"https://realtime.oxylabs.io/v1/queries",
		bytes.NewBuffer(jsonValue),
	)

	request.SetBasicAuth(Username, Password)
	response, _ := client.Do(request)

	responseText, _ := ioutil.ReadAll(response.Body)
	fmt.Println(string(responseText))
}

C#

using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Net.Http.Json;
using System.Threading.Tasks;

namespace OxyApi
{
    class Program
    {
        static async Task Main()
        {
            const string Username = "USERNAME";
            const string Password = "PASSWORD";

            var parameters = new {
                source = "google_shopping_product",
                query = "[product_token_string]",
                render = "html",
                parse = true
            };

            var client = new HttpClient();

            Uri baseUri = new Uri("https://realtime.oxylabs.io");
            client.BaseAddress = baseUri;

            var requestMessage = new HttpRequestMessage(HttpMethod.Post, "/v1/queries");
            requestMessage.Content = JsonContent.Create(parameters);

            var authenticationString = $"{Username}:{Password}";
            var base64EncodedAuthenticationString = Convert.ToBase64String(System.Text.ASCIIEncoding.UTF8.GetBytes(authenticationString));
            requestMessage.Headers.Add("Authorization", "Basic " + base64EncodedAuthenticationString);

            var response = await client.SendAsync(requestMessage);
            var contents = await response.Content.ReadAsStringAsync();

            Console.WriteLine(contents);
        }
    }
}

Java

package org.example;

import okhttp3.*;
import org.json.JSONObject;
import java.util.concurrent.TimeUnit;

public class Main implements Runnable {
    private static final String AUTHORIZATION_HEADER = "Authorization";
    public static final String USERNAME = "USERNAME";
    public static final String PASSWORD = "PASSWORD";

    public void run() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "google_shopping_product");
        jsonObject.put("query", "[product_token_string]");
        jsonObject.put("render", "html");
        jsonObject.put("parse", true);

        Authenticator authenticator = (route, response) -> {
            String credential = Credentials.basic(USERNAME, PASSWORD);
            return response
                    .request()
                    .newBuilder()
                    .header(AUTHORIZATION_HEADER, credential)
                    .build();
        };

        var client = new OkHttpClient.Builder()
                .authenticator(authenticator)
                .readTimeout(180, TimeUnit.SECONDS)
                .build();

        var mediaType = MediaType.parse("application/json; charset=utf-8");
        var body = RequestBody.create(jsonObject.toString(), mediaType);
        var request = new Request.Builder()
                .url("https://realtime.oxylabs.io/v1/queries")
                .post(body)
                .build();

        try (var response = client.newCall(request).execute()) {
            if (response.body() != null) {
                try (var responseBody = response.body()) {
                    System.out.println(responseBody.string());
                }
            }
        } catch (Exception exception) {
            System.out.println("Error: " + exception.getMessage());
        }

        System.exit(0);
    }

    public static void main(String[] args) {
        new Thread(new Main()).start();
    }
}

JSON

{
    "source": "google_shopping_product",
    "query": "[product_token_string]",
    "render": "html",
    "parse": true
}

Important: The query parameter must contain a valid token generated through the google_shopping_search source.

We use synchronous Realtime integration method in our examples. If you would like to use Proxy Endpoint or asynchronous Push-Pull integration, refer to the integration methods section.

Request parameter values

Generic

Basic setup and customization options for scraping Google Shopping product pages.

Parameter	Description	Default Value
source	Sets the scraper.	google_shopping_product
query	The product token from google_shopping_search or google_search	-
render	Enables JavaScript rendering when set to html. Required to receive additional pricing results from "More stores" section. More info.	-
parse	Returns parsed data when set to true. Explore output data dictionary.	false
callback_url	URL to your callback endpoint. More info	-
user_agent_type	Device type and browser. The full list can be found here.	desktop

- mandatory parameter

Localization

Adapt results to specific geographical locations, domains, and languages.

Note: Localization parameters (gl and hl) are now embedded into the product token. To retrieve google_shopping_products data matching the original search result, we recommend leaving these fields empty unless overrides are intentionally needed.

Parameter	Description	Default Value
geo_location	The geographical location that the result should be adapted for. Using this parameter correctly is extremely important to get the right data. For more information, read about our suggested geo_location parameter structures here.	-
locale	Accept-Language header value for interface language changes. More info.	-

Structured data

Below you can find a structured output example for google_shopping_product.

google_shopping_product-output.json

19KB

Open

Output data dictionary

HTML sample

JSON structure

The table below presents a detailed list of each product page element we parse, along with its description and data type. The table also includes some metadata.

Key	Description	Type
url	The URL to the Google Shopping product page.	string
title (optional)	The title of the product listing.	string
description	A detailed description of the product.	string
images	An object containing images of the product.	object
images.full_size	An array of URLs for full-sized images of the product.	array
images.thumbnails	An array of URLs for thumbnail images of the product.	array
pricing	An array containing all online pricing information.	array
reviews	An object containing review information. (US only)	object
variants	An array of objects containing product variants. (colors, sizes, etc.)	array
related_items	An array of objects containing related items.	array
specifications	An array of objects containing product specifications.	array
parse_status_code	The status code of the parsing job. You can see the parser status codes described here.	integer
created_at	The timestamp when the scraping job was created.	timestamp
updated_at	The timestamp when the scraping job was finished.	timestamp
status_code	The status code of the scraping job. You can see the scraper status codes described here.	integer
job_id	The ID of the job associated with the scraping job.	string

In the following sections, parsed JSON code snippets are shortened where more than one item for the result type is available.

Pricing

An object containing pricing information for the product.

...
   "pricing": {
    "online": [
        {
          "price": 559,
          "seller": "Walmart - Seller",
          "details": "Pny GeForce RTX 4070 GPU 12gb Xlr8 Gaming Verto Epic-x RGB Triple Fan Dlss 3 Graphics Card",
          "currency": "USD",
          "condition": "New",
          "seller_link": "https://www.walmart.com/ip/PNY-GeForce-RTX-4070-GPU-12GB-XLR8-Gaming-VERTO-EPIC-X-RGB-Triple-Fan-DLSS-3-Graphics-Card/1396859462?wmlspartner=wlpa&selectedSellerId=101035116&selectedOfferId=159733DADC653E1891C050148D16D747&conditionGroupCode=1",
          "price_shipping": 22.05
        },
...
    ]
},
...

Key (pricing[])	Description	Type
online	An array of objects containing details of pricing for the product.	array
online.price	The price of the product in the specified currency.	float
online.seller	The name of the seller or merchant offering the product.	string
online.details	Additional details about the product, purchase, such as delivery and return policies.	string
online.currency	The currency code for the product price.	string
online.condition	The condition of the product.	string
online.seller_link	The URL to the seller's page for the product.	string
online.price_shipping	The shipping cost for the product.	float

Reviews

An object containing reviews and ratings information for the product.

At the moment, reviews are only available in the US locale.

...       
       "reviews": {
    "rating": 4.7,
    "top_review": {
        "text": "My computer is a Dell Optiplex 9020, i7-4770, 32mb, 500gb SSD. The 3 fan card is a long, and the hard drive cage had to be removed to fit in the Optiplex case. The power supply was upgraded to 750 watts which required an adapter for the Dell motherboard. With those modifications out of the way, installation of the card was drama free, but you have use Google to find the driver in the Nvidia website. I am using this GPU for 3D animation in Blender. I am very pleased with the speed of the rendering with ray tracing in EEVEE and Cycles. As this is an old computer, the computer's CPU never runs at 100%, and I haven't been able to max out this card's capacity yet. I don't hear the fans running but I have never put a high load enough on it yet, I guess. It does have a little electronic buzz when it is rendering.\u00a0Less",
        "author": "walmart.com Shopper",
        "rating": 5,
        "source": "Reviewed on walmart.com"
      },
      "rating_stars": 4.7,
      "reviews_count": 51,
      "review_count_by_stars": {
        "1": {
          "reviews_count": 2
        },
        "2": {
          "reviews_count": 0
        },
        "3": {
          "reviews_count": 2
        },
        "4": {
          "reviews_count": 3
        },
        "5": {
          "reviews_count": 44
        }
    },
},
...

Key(reviews[])	Description	Type
rating	The average rating of the product, typically out of 5.	float
top_review (optional)	An object containing details of the top review for the product.	object
top_review.text (optional)	The text content of the top review	string
top_review.title (optional)	The title of the top review.	string
top_review.author (optional)	The author of the top review.	string
top_review.rating (optional)	The rating given by the top review's author, typically out of 5.	float
top_review.source (optional)	The source or website where the top review was posted.	string
rating_stars	The average rating of the product, typically out of 5 stars.	float
reviews_count (optional)	The total number of reviews for the product.	integer
review_count_by_stars	An object containing the count of reviews for each star rating.	object
review_count_by_stars.url (optional)	An object containing details of X-star reviews.	string
review_count_by_stars.reviews_count	The count of X-star reviews.	integer

Related Items (More options)

An array of objects containing related items for the target product.

...             
   "related_items": [
      {
        "items": [
          {
            "url": "/search?ibp=oshop&prds=catalogid:1368129371371338580,gpcid:14975392695437189622,headlineOfferDocid:2388507960063782588,imageDocid:1618178582933849531,productid:7780474142858650836,pvo:2,pvt:hg,rds:PC_14975392695437189622%7CPROD_PC_14975392695437189622&q=nvidia+rtx&gl=us&hl=en&pvorigin=2",
            "image": "https://encrypted-tbn3.gstatic.com/shopping?q=tbn:ANd9GcScO-LIdlqj1WjcLznMECFXNo4qbZ1TRbkfHdDsDPoIYxx7S9TjKhnQX7Ah6QsKI-zPBKFrC54H0wGZC60Q_NdRebesvYUXwRhQFuZRwvtWmx4_0xoxbylM",
            "price": 639.99,
            "title": "NVIDIA GeForce RTX 5070 12GB GDDR7 Graphics Card",
            "currency": "USD",
            "reviews_count": 228
          },
...
        ],
        "title": "More options"
     }
],
...

Key(related_items[])	Description	Type
items	An array of objects containing details of each related item.	array
items.url	The URL to the related product page.	string
items.image	The URL of the related product's image.	string
items.price	The price of the related product in the specified currency.	float
items.title (optional)	The title of the related product listing.	string
items.rating (optional)	The average user rating of the related product, typically out of 5.	integer
items.store (optional)	The name of the store or merchant offering the related product.	string
items.currency	The currency code for the product price.	string
items.reviews_count	The total number of reviews for the related product.	integer
title	The title or heading for the related items section	string

Specifications

An array of objects containing specification details for the product.

...
"specifications": [
    {
        "items": [
          {
            "title": "Manufacturer",
            "value": "PNY"
          },
          {
            "title": "Output",
            "value": "HDMI, DisplayPort"
          },
          {
            "title": "Interface",
            "value": "PCI Express"
          },
          {
            "title": "Brand",
            "value": "PNY"
          },
...
        ],
        "section_title": "attributes"
      }
],
...

Key (specifications[])	Description	Type
items.title	The title of the specification.	string
items.value	The value of the specification.	string