Scrape Google Product Page with Python

What will be scraped

wwbs-google-shopping-product-page

Using Google Product Page API from SerpApi

This section is to show the comparison between the DIY solution and our solution.

The main difference is that it's a quicker approach. Google Product Page API will bypass blocks from search engines and you don't have to create the parser from scratch and maintain it.

First, we need to install google-search-results:

pip install google-search-results

Import the necessary libraries for work:

from serpapi import GoogleSearch
import json

Next, we write a search query and the necessary parameters for making a request:

params = {
    'api_key': '...',                       # https://serpapi.com/manage-api-key
    'engine': 'google_product',             # SerpApi search engine	
    'product_id': '16230039729797264158',   # product id
    'hl': 'en',                             # language
    'gl': 'us'                              # country of the search, US -> USA
}

We then create a search object where the data is retrieved from the SerpApi backend. In the results dictionary we get data from JSON:

search = GoogleSearch(params)   # where data extraction happens on the SerpApi backend
results = search.get_dict()     # JSON -> Python dict

The data is retrieved quite simply, we just need to turn to the 'product_results' key.

product_results = results['product_results']

Example code to integrate:

from serpapi import GoogleSearch
import os, json

params = {
    'api_key': '...',                       # https://serpapi.com/manage-api-key
    'engine': 'google_product',             # SerpApi search engine	
    'product_id': '16230039729797264158',   # product id
    'hl': 'en',                             # language
    'gl': 'us'                              # country of the search, US -> USA
}

    
search = GoogleSearch(params)               # where data extraction happens on the SerpApi backend
results = search.get_dict()                 # JSON -> Python dict

product_results = results['product_results']

print(json.dumps(product_results, indent=2, ensure_ascii=False))

Output:

{
  "product_id": 16230039729797264158,
  "title": "Sony PlayStation 5 - Standard",
  "prices": [
    "$499.99",
    "$499.00",
    "$700.00"
  ],
  "conditions": [
    "New",
    "New",
    "New"
  ],
  "typical_prices": {
    "low": "$499.00",
    "high": "$719.75",
    "shown_price": "$499.99 at Gamestop"
  },
  "reviews": 63413,
  "rating": 4.7,
  "extensions": [
    "Blu-ray Compatible",
    "4K Capable",
    "Backward Compatible",
    "Standard Edition",
    "With Motion Control",
    "Bluetooth",
    "Wi-Fi"
  ],
  "description": "Experience lightning-fast loading with an ultra-high-speed SSD, deeper immersion with support for haptic feedback, adaptive triggers and 3D audio, and a next generation of incredible PlayStation games.",
  "media": [
    {
      "type": "image",
      "link": "https://encrypted-tbn3.gstatic.com/shopping?q=tbn:ANd9GcRoN7Gg6r9ZxPZGkfTEbukowBuBvalGRrJG44Dwnw8_PAmLUNjt&usqp=CAY"
    },
    {
      "type": "image",
      "link": "https://encrypted-tbn1.gstatic.com/shopping?q=tbn:ANd9GcQOuj8omxssTbuSixiKmldKmSOCllkb1jLSqYHbThqgR3l78gjS&usqp=CAY"
    },
    {
      "type": "image",
      "link": "https://encrypted-tbn2.gstatic.com/shopping?q=tbn:ANd9GcQmw7DOYYmm5nQSQoEhAaE78a5IyNW3tHoCE1VRI2cxTHn9QGg&usqp=CAY"
    },
    {
      "type": "image",
      "link": "https://encrypted-tbn3.gstatic.com/shopping?q=tbn:ANd9GcRsejj3qFlCeXGkvHMG7yGdM6gR_AbzoT_fWZUcYrhS3QKxpHI&usqp=CAY"
    }
  ],
  "highlights": [
    "Integrated I/O: Marvel at incredible graphics and experience new PS5 features.",
    "Ultra-high speed SSD: Maximize your play sessions with near-instant load times for installed PS5 games.",
    "HDR technology: With an HDR TV, supported PS5 games display an unbelievably vibrant and lifelike range of colors.",
    "8K output: PS5 consoles support an 8K output, so you can play games on your 4320p resolution display.",
    "4K TV gaming: Play your favorite PS5 games on your stunning 4K TV. Up to 120 fps with 120Hz output"
  ]
}

DIY Code

If you don't need an explanation, have a look at the full code example in the online IDE.

import requests, json
from parsel import Selector


def get_product_page_results(url, params, headers):
	html = requests.get(url, params=params, headers=headers)
	selector = Selector(html.text)
	
	title = selector.css('.sh-t__title::text').get()
	prices = [price.css('::text').get() for price in selector.css('.MLYgAb .g9WBQb')]
	low_price = selector.css('.KaGvqb .qYlANb::text').get()
	high_price = selector.css('.xyYTQb .qYlANb::text').get()
	shown_price = selector.css('.FYiaub').xpath('normalize-space()').get()
	reviews = int(selector.css('.YVQvvd .HiT7Id span::text').get()[1:-1].replace(',', ''))
	rating = float(selector.css('.uYNZm::text').get())
	extensions = [extension.css('::text').get() for extension in selector.css('.OA4wid')]
	description = selector.css('.sh-ds__trunc-txt::text').get()
	media = [image.css('::attr(src)').get() for image in selector.css('.sh-div__image')]
	highlights = [highlight.css('::text').get() for highlight in selector.css('.KgL16d span')]
	
	data = {
		'title': title,
		'prices': prices,
		'typical_prices': {
			'low': low_price,
			'high': high_price,
			'shown_price': shown_price
		},
		'reviews': reviews,
		'rating': rating,
		'extensions': extensions,
		'description': description,
		'media': media,
		'highlights': highlights
	}
	
	return data


def main():
	# https://docs.python-requests.org/en/master/user/quickstart/#passing-parameters-in-urls
	params = {
		'product_id': '16230039729797264158',	# product id
		'hl': 'en',     						# language
		'gl': 'us'	     						# country of the search, US -> USA
	}

	# https://docs.python-requests.org/en/master/user/quickstart/#custom-headers
	headers = {
	    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'
	}

	URL = f'https://www.google.com/shopping/product/{params["product_id"]}?hl={params["hl"]}&gl={params["gl"]}'
	
	product_page_results = get_product_page_results(URL, params, headers)
	
	print(json.dumps(product_page_results, indent=2, ensure_ascii=False))


if __name__ == "__main__":
    main()

Preparation

Install libraries:

pip install requests parsel

Reduce the chance of being blocked

Make sure you're using request headers user-agent to act as a "real" user visit. Because default requests user-agent is python-requests and websites understand that it's most likely a script that sends a request. Check what's your user-agent.

There's a how to reduce the chance of being blocked while web scraping blog post that can get you familiar with basic and more advanced approaches.

Code Explanation

Import libraries:

import requests, json
from parsel import Selector

Library	Purpose
`requests`	to make a request to the website.
`json`	to convert extracted data to a JSON object.
`Selector`	XML/HTML parser that have full XPath and CSS selectors support.

At the beginning of the main() function, parameters and headers are defined for generating the URL. If you want to pass other parameters or headers to the URL, you can do so using the params and headers dictionaries:

def main():
	# https://docs.python-requests.org/en/master/user/quickstart/#passing-parameters-in-urls
	params = {
		'product_id': '16230039729797264158',	# product id
		'hl': 'en',     						# language
		'gl': 'us'	     						# country of the search, US -> USA
	}

	# https://docs.python-requests.org/en/master/user/quickstart/#custom-headers
	headers = {
	    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'
	}

	URL = f'https://www.google.com/shopping/product/{params["product_id"]}?hl={params["hl"]}&gl={params["gl"]}'

Next, the URL, params and headers is passed to the get_product_page_results(URL, params, headers) function to get all data. The product_page_results dictionary holds the retrieved data that this function returns. At the end of the function, the data is printed out in JSON format:

product_page_results = get_product_page_results(URL, params, headers)

print(json.dumps(product_page_results, indent=2, ensure_ascii=False))

This code uses the generally accepted rule of using the __name__ == "__main__" construct:

if __name__ == "__main__":
    main()

This check will only be performed if the user has run this file. If the user imports this file into another, then the check will not work. You can watch the video Python Tutorial: if name == 'main' for more details.

Let's take a look at the get_product_page_results(url, params, headers) function mentioned earlier.

This function takes url, params and headers parameters to create a request. Now we need to parse the HTML from the Parsel package, into which we pass the HTML structure that was received after the request. This is necessary for successful data extraction:

def get_product_page_results(url, params, headers):
	html = requests.get(url, params=params, headers=headers)
	selector = Selector(html.text)

Data like title, low_price, high_price and description are pretty easy to retrieve. You need to find the selector and get the value:

title = selector.css('.sh-t__title::text').get()
low_price = selector.css('.KaGvqb .qYlANb::text').get()
high_price = selector.css('.xyYTQb .qYlANb::text').get()
description = selector.css('.sh-ds__trunc-txt::text').get()

Code	Explanation
`css()`	to access elements by the passed selector.
`::text` or `::attr(<attribute>)`	to extract textual or attribute data from the node.
`get()`	to actually extract the textual data.

Extracting show_price differs from the previous ones in that you need to extract the text not only from this selector, but also from those nested in it:

shown_price = selector.css('.FYiaub').xpath('normalize-space()').get()

Data such as reviews and rating must be converted to the numeric data type. I want to draw your attention to the fact that reviews are retrieved in this format: (63,413). To convert to a number, you need to remove the brackets and the comma:

reviews = int(selector.css('.YVQvvd .HiT7Id span::text').get()[1:-1].replace(',', ''))
rating = float(selector.css('.uYNZm::text').get())

The prices, extensions, media and highlights lists contain multiple elements in their selector, so they are extracted using list comprehensions:

prices = [price.css('::text').get() for price in selector.css('.MLYgAb .g9WBQb')]
extensions = [extension.css('::text').get() for extension in selector.css('.OA4wid')]
media = [image.css('::attr(src)').get() for image in selector.css('.sh-div__image')]
highlights = [highlight.css('::text').get() for highlight in selector.css('.KgL16d span')]

After extracting all the data, the data dictionary is formed:

data = {
    'title': title,
    'prices': prices,
    'typical_prices': {
        'low': low_price,
        'high': high_price,
        'shown_price': shown_price
    },
    'reviews': reviews,
    'rating': rating,
    'extensions': extensions,
    'description': description,
    'media': media,
    'highlights': highlights
}

At the end of the function, the data dictionary is returned.

return data

Output:

{
  "title": "Sony PlayStation 5 - Standard",
  "prices": [
    "$499.00",
    "$700.00",
    "$729.00"
  ],
  "typical_prices": {
    "low": "$499.00",
    "high": "$719.75",
    "shown_price": "$499.00 at EvQ"
  },
  "reviews": 63413,
  "rating": 4.7,
  "extensions": [
    "Blu-ray Compatible",
    "4K Capable",
    "Backward Compatible",
    "Standard Edition",
    "With Motion Control",
    "Bluetooth",
    "Wi-Fi"
  ],
  "description": "Experience lightning-fast loading with an ultra-high-speed SSD, deeper immersion with support for haptic feedback, adaptive triggers and 3D audio, and a next generation of incredible PlayStation games.",
  "media": [
    "https://encrypted-tbn3.gstatic.com/shopping?q=tbn:ANd9GcSbKnqqdMH6hYKh8mzk9kje2m3KI-bRktHWihZ_LYAHQF0BNIXyfzjjusW0XMVpuUk13pFiHLVztP7Rk7GDgxBUnC6hFY84sQ&usqp=CAY",
    "https://encrypted-tbn1.gstatic.com/shopping?q=tbn:ANd9GcTa0aWvl4ZCffiyfM3sBvdYLk1K8SkMIo6ZkmN3ASkW7GPgVmB_XMOFCBgmW-AMOspQ9KFLJjKN9uPZbj0ScCVOizsmX8Fegg&usqp=CAY",
    "https://encrypted-tbn2.gstatic.com/shopping?q=tbn:ANd9GcRJRtfshsdgf4JJGzS-QzvYXjzOy4NKV-y_0yQn-W6n109ziyqOzTvDcX-YXNmr3rPu4cHKpo7OVV2fkDzodE7LK6Pxh63l&usqp=CAY",
    "https://encrypted-tbn3.gstatic.com/shopping?q=tbn:ANd9GcS6lCLgdUU42DbmP2Y8o5MPMHF_j1LFpMvdBHNTPLIfBOn8bnpC-xPBYl14wDMiPK7lQ1YL_BEeOm5vqVmfJpBLnOomYoXy&usqp=CAY"
  ],
  "highlights": [
    "Integrated I/O: Marvel at incredible graphics and experience new PS5 features.",
    "Ultra-high speed SSD: Maximize your play sessions with near-instant load times for installed PS5 games.",
    "HDR technology: With an HDR TV, supported PS5 games display an unbelievably vibrant and lifelike range of colors.",
    "8K output: PS5 consoles support an 8K output, so you can play games on your 4320p resolution display.",
    "4K TV gaming: Play your favorite PS5 games on your stunning 4K TV. Up to 120 fps with 120Hz output"
  ]
}

Links

Join us on Twitter | YouTube

Add a Feature Request💫 or a Bug🐞

Scrape Google Product Page with Python

Artur Chukhrai, Dmitriy Zub

What will be scraped

Using Google Product Page API from SerpApi

DIY Code

Preparation

Code Explanation

Links

Free Plan · 100 searches / month

APIs

Easy Integrations

Features

Use Cases

What will be scraped

Using Google Product Page API from SerpApi

DIY Code

Preparation

Code Explanation

Links

Free Plan · 100 searches / month